技术领域technical field
本发明涉及照片管理领域，尤其涉及一种照片分类管理方法、服务器、装置及系统。The present invention relates to the field of photo management, in particular to a photo classification management method, server, device and system.
背景技术Background technique
随着科技的进步和人们生活水平的提高，照相机，具有拍照功能的手机、掌上电脑等电子设备走进了千家万户。越来越多的用户热衷于拍照，获取到大量的照片。目前，对于拍照得到的照片，用户只能通过手动的方式对这些照片进行标记分类，以实现对这些照片的管理，例如：对照片手动标记后，将其存储到某一分类文件目录下。现有技术进行手工标记的操作比较麻烦，用户对拍摄的每张照片进行标记分类也比较耗时，如果不进行标记又不能很好地对照片进行分类管理，这对用户造成使用负担。With the advancement of science and technology and the improvement of people's living standards, electronic devices such as cameras, mobile phones with camera functions, and handheld computers have entered thousands of households. More and more users are keen on taking pictures and have obtained a large number of photos. At present, for the photos obtained by taking pictures, the user can only manually mark and classify these photos to realize the management of these photos, for example: after manually marking the photos, store them in a certain classification file directory. In the prior art, the operation of manually marking is cumbersome, and it is time-consuming for the user to mark and classify each photo taken. If no marking is performed, the photos cannot be well classified and managed, which will cause a burden to the user.
发明内容Contents of the invention
本发明实施例所要解决的技术问题在于，提供一种照片分类管理方法、服务器、装置及系统，可对通过拍摄等方式获取到的照片自动进行分类管理。The technical problem to be solved by the embodiments of the present invention is to provide a photo classification management method, server, device and system, which can automatically classify and manage photos obtained by shooting or other means.
为了解决上述技术问题，本发明实施例提供了一种照片分类管理方法，包括：In order to solve the above technical problems, an embodiment of the present invention provides a photo classification management method, including:
服务器获取待分类照片的图像内容特征；The server obtains the image content characteristics of the photos to be classified;
所述服务器根据所述待分类照片的图像内容特征确定所述待分类照片的照片类别；The server determines the photo category of the photo to be classified according to the image content characteristics of the photo to be classified;
所述服务器将确定的所述待分类照片的照片类别发送给用户终端，以使用户终端根据所述确定的照片类别，对所述待分类照片进行分类管理。The server sends the determined photo category of the photo to be classified to the user terminal, so that the user terminal classifies and manages the photo to be classified according to the determined photo category.
相应地，本发明实施例还提供了一种服务器，包括：Correspondingly, an embodiment of the present invention also provides a server, including:
获取模块，用于获取待分类照片的图像内容特征；An acquisition module, configured to acquire image content features of photos to be classified;
分类模块，用于根据所述获取模块获取到的待分类照片的图像内容特征确定所述待分类照片的类别；A classification module, configured to determine the category of the photos to be classified according to the image content characteristics of the photos to be classified acquired by the acquisition module;
通信模块，用于将所述分类模块确定的所述待分类照片的类别发送给用户终端，以使用户终端根据所述确定的待分类照片的类别，对所述待分类照片进行分类管理。A communication module, configured to send the category of the photo to be classified determined by the classification module to a user terminal, so that the user terminal performs classification management on the photo to be classified according to the determined category of the photo to be classified.
相应地，本发明实施例还提供了一种照片分类管理装置，包括：Correspondingly, an embodiment of the present invention also provides a photo classification management device, including:
照片获取模块，用于获取待分类照片；The photo acquisition module is used to obtain photos to be classified;
通信模块，用于将所述照片获取模块获取的待分类照片或者所述待分类照片的缩略图发送给服务器，并用于接收由服务器确定的所述待分类照片的照片类别；A communication module, configured to send the photos to be classified or the thumbnails of the photos to be classified acquired by the photo acquisition module to a server, and to receive the photo category of the photos to be classified determined by the server;
分类管理模块，用于根据所述通信模块接收到的待分类照片的照片类别，对所述待分类照片进行分类管理；A classification management module, configured to perform classification management on the photos to be classified according to the photo categories of the photos to be classified received by the communication module;
其中，所述服务器根据获取所述待分类照片的图像内容特征确定出所述待分类照片的照片类别。Wherein, the server determines the photo category of the photo to be classified according to the acquired image content characteristics of the photo to be classified.
相应地，本发明实施例还提供了一种照片分类管理系统，包括：照片分类管理装置和服务器，其中，Correspondingly, an embodiment of the present invention also provides a photo classification management system, including: a photo classification management device and a server, wherein,
所述照片分类管理装置，用于获取待分类照片，并将所述待分类照片或者所述待分类照片的缩略图发送给所述服务器；The photo classification management device is used to obtain the photos to be classified, and send the photos to be classified or the thumbnails of the photos to be classified to the server;
所述服务器，用于根据所述待分类照片或者所述待分类照片的缩略图获取待分类照片的图像内容特征，根据所述待分类照片的图像内容特征确定所述待分类照片的照片类别，并将确定的所述待分类照片的照片类别发送给所述照片分类管理装置；The server is configured to acquire the image content characteristics of the photos to be classified according to the photos to be classified or the thumbnails of the photos to be classified, and determine the photo category of the photos to be classified according to the image content characteristics of the photos to be classified, and sending the determined photo categories of the photos to be classified to the photo classification management device;
所述照片分类管理装置还用于接收由服务器确定的所述待分类照片的照片类别，并根据照片类别，对所述待分类照片进行分类管理。The photo classification management device is further configured to receive the photo category of the photo to be classified determined by the server, and perform classification management on the photo to be classified according to the photo category.
实施本发明实施例，具有如下有益效果：Implementing the embodiment of the present invention has the following beneficial effects:
本发明可对用户通过拍照等方式获取到的照片进行特征的识别以及对照片的分类，使得用户不需要对照片进行手动标记或者手动分类，实现了对照片内容的自动化分类操作，较好地实现了依照照片的内容的类别来对照片的组织和分类管理，极大地方便了用户。The present invention can identify the features and classify the photos obtained by the user by taking pictures, etc., so that the user does not need to manually mark or classify the photos, realizes the automatic classification operation of the photo content, and better realizes In order to organize and classify photos according to the category of the content of the photos, it greatly facilitates the user.
附图说明Description of drawings
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.
图1是本发明实施例的照片分类管理系统的结构组成示意图；Fig. 1 is a schematic diagram of the structural composition of a photo classification management system according to an embodiment of the present invention;
图2是图1中的照片分类管理装置的结构组成示意图；Fig. 2 is a schematic diagram of the structural composition of the photo classification management device in Fig. 1;
图3是图1中的服务器的结构组成示意图；FIG. 3 is a schematic diagram of the structural composition of the server in FIG. 1;
图4是本发明的照片分类管理方法的第一实施例流程示意图；Fig. 4 is a schematic flow chart of the first embodiment of the photo classification management method of the present invention;
图5是本发明的照片分类管理方法的第二实施例流程示意图。Fig. 5 is a schematic flowchart of the second embodiment of the photo classification management method of the present invention.
具体实施方式Detailed ways
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
请参见图1，是本发明实施例的照片分类管理系统的结构组成示意图，本实施例中，所述照片分类管理系统包括：照片分类管理装置1和服务器2。所述照片分类管理装置1和所述服务器2可通过有线或者无线的方式相连接，进行数据传递。Please refer to FIG. 1 , which is a schematic structural diagram of a photo classification management system according to an embodiment of the present invention. In this embodiment, the photo classification management system includes: a photo classification management device 1 and a server 2 . The photo classification management device 1 and the server 2 can be connected by wire or wirelessly for data transmission.
所述照片分类管理装置1包括用户终端，用于获取待分类照片，并将所述待分类照片或者所述待分类照片的缩略图发送给所述服务器2。The photo classification management apparatus 1 includes a user terminal, configured to acquire photos to be classified, and send the photos to be classified or thumbnails of the photos to be classified to the server 2 .
所述服务器2用于根据所述待分类照片或者所述待分类照片的缩略图获取待分类照片的图像内容特征，根据所述待分类照片的图像内容特征确定所述待分类照片的照片类别，并将确定的所述待分类照片的照片类别发送给所述照片分类管理装置1。The server 2 is used to obtain the image content characteristics of the photos to be classified according to the photos to be classified or the thumbnails of the photos to be classified, and determine the photo category of the photos to be classified according to the image content characteristics of the photos to be classified, And send the determined photo categories of the photos to be classified to the photo classification management device 1 .
所述照片分类管理装置1还用于接收由服务器2确定的所述待分类照片的照片类别，并根据照片类别对所述待分类照片进行分类管理。The photo classification management apparatus 1 is further configured to receive the photo category of the photo to be classified determined by the server 2, and perform classification management on the photo to be classified according to the photo category.
所述照片分类管理装置1可以是具有通信功能的照相机、具有拍照功能的手机/电脑、用户通过拍照、拷贝、传输等方式获取到待分类照片后，通过所述照片分类管理装置1向所述服务器2发送所述待分类照片，或者仅发送所述待分类照片的缩略图。The photo classification management device 1 can be a camera with a communication function, a mobile phone/computer with a camera function, after the user obtains the photos to be classified by taking pictures, copying, transmitting, etc., the photo classification management device 1 sends the photo to the The server 2 sends the photos to be classified, or only sends thumbnails of the photos to be classified.
所述服务器2确定所述待分类照片的照片类别后，将该待分类照片的照片类别发送给所述照片分类管理装置1，由该照片分类管理装置1对所述待分类照片进行管理，例如，所述照片分类管理装置1根据该待分类照片的类别，将该待分类照片存储到相应类别的目录下，并分类显示。After the server 2 determines the photo category of the photos to be classified, it sends the photo category of the photos to be classified to the photo classification management device 1, and the photo classification management device 1 manages the photos to be classified, for example According to the category of the photo to be classified, the photo classification management device 1 stores the photo to be classified in a directory of the corresponding category, and displays the photo by category.
另外，所述服务器2在对待分类照片进行分类确定后，还可将该待分类照片及其照片类别发送到由所述照片分类管理装置1指定的照片服务器中，如发送到用户指定的一用户照片空间服务器中，以使所述用户照片空间服务器按照照片类别将所述待分类照片存储到相应存储器中，当用户需要时可随时在该用户的空间中(如QQ空间)按照照片类别显示所述待分类照片。In addition, after the server 2 determines the classification of the photos to be classified, it can also send the photos to be classified and their photo categories to the photo server designated by the photo classification management device 1, such as sending to a user designated by the user. In the photo space server, the photo space server of the user stores the photos to be classified in the corresponding memory according to the photo category, and can display the photos according to the photo category in the user's space (such as QQ space) at any time when the user needs. Describe the photos to be categorized.
需要说明的是，所述照片分类管理装置1在获取到待分类照片后，根据需要也可由其自身进行照片的分类识别，并进行管理操作，即所述照片分类管理装置1获取所述待分类照片的图像内容特征，根据所述待分类照片的图像内容特征确定所述待分类照片的照片类别，并根据照片类别，对所述待分类照片进行分类管理。It should be noted that, after the photo classification management device 1 acquires the photos to be classified, it can also classify and identify the photos by itself according to needs, and perform management operations, that is, the photo classification management device 1 obtains the photos to be classified According to the image content characteristics of the photos, the photo categories of the photos to be classified are determined according to the image content characteristics of the photos to be classified, and the photos to be classified are classified and managed according to the photo categories.
进一步的，请参见图2，是图1中的照片分类管理装置1的结构组成示意图，所述照片分类管理装置1可以包括：照片获取模块11、通信模块12以及分类管理模块13。Further, please refer to FIG. 2 , which is a schematic structural diagram of the photo classification management device 1 in FIG. 1 . The photo classification management device 1 may include a photo acquisition module 11 , a communication module 12 and a classification management module 13 .
所述照片获取模块11，用于获取待分类照片。The photo acquisition module 11 is configured to acquire photos to be classified.
所述照片获取模块11可以通过拍照的方式获取到照片，当然，也可通过数据传输的方式从其他设备中获取到照片，所述照片获取模块11在获取到待分类的照片后，还能够根据需要提取所述待分类照片的缩略图。The photo acquisition module 11 can obtain the photos by taking pictures, and of course, can also obtain the photos from other devices by means of data transmission. After the photo acquisition module 11 obtains the photos to be classified, it can The thumbnails of the photos to be classified need to be extracted.
所述通信模块12，用于将所述照片获取模块11获取到的待分类照片或者所述待分类照片的缩略图发送给服务器2，并用于接收由服务器2确定的所述待分类照片的照片类别。The communication module 12 is configured to send the photos to be classified obtained by the photo acquisition module 11 or the thumbnails of the photos to be classified to the server 2, and to receive the photos of the photos to be classified determined by the server 2 category.
具体的，所述通信模块12的发送方式可由用户根据通信速度、流量费用等情况和需要确定，例如：当通信承载在有线网络或WIFI等速度快的无线网络上，用户不关注流量产生费用且希望对所有照片及时管理时，在获取到待分类照片的同时，即将待分类照片发送给服务器2；而当通信承载在速度一般的无线网络上，且用户关注流量产生费用但希望对当前拍摄照片及时管理时，可以在获取到待分类照片时，将其缩略图发送给服务器2；当用户仅需要对部分照片进行管理，且管理需求及时性不强时，可采用手动发送方式，在获取到待分类照片后，由用户手动决定是否上传给所述服务器2。Specifically, the sending method of the communication module 12 can be determined by the user according to the communication speed, traffic charges, etc. When it is desired to manage all photos in a timely manner, when the photos to be classified are obtained, the photos to be classified are sent to the server 2; and when the communication is carried on a wireless network with a normal speed, and the user pays attention to traffic charges but wishes to update the photos currently taken When managing in time, you can send its thumbnails to the server 2 when you get the photos to be classified; when the user only needs to manage some photos, and the management requirements are not timely, you can use manual sending. After the photos to be classified, the user manually decides whether to upload them to the server 2.
所述通信模块12在发送所述待分类照片或者其缩略图的同时，还可发送该待分类照片的名称标识，以便于所述服务器2返回相应待分类照片的名称标识及其照片类别，从而使得所述照片分类管理装置1能够对名称标识所对应的待分类照片按照其照片类别进行分类管理。照片分类管理装置1和服务器2通过消息携带名称标识来保证类别和待分类照片的对应，从而可以支持多消息并发请求。When the communication module 12 sends the photo to be classified or its thumbnail, it can also send the name identification of the photo to be classified, so that the server 2 returns the name identification and photo category of the corresponding photo to be classified, so that This enables the photo classification management device 1 to classify and manage the photos to be classified corresponding to the name identifiers according to their photo categories. The photo classification management device 1 and the server 2 ensure the correspondence between the categories and the photos to be classified by carrying name identifiers in the messages, so that multiple concurrent requests for messages can be supported.
所述分类管理模块13，用于根据所述通信模块12接收到的待分类照片的照片类别，对所述待分类照片进行管理。分类管理可以包括分类存储管理、分类显示管理等。The classification management module 13 is configured to manage the photos to be classified according to the photo categories of the photos to be classified received by the communication module 12 . Category management may include category storage management, category display management, and the like.
进一步的，所述通信模块12还用于向所述服务器发送照片类别设置请求，以便所述服务器2依据所述照片类别设置请求携带的照片类别对所述待分类照片或者所述待分类照片的缩略图分类。Further, the communication module 12 is also configured to send a photo category setting request to the server, so that the server 2 can make a comparison of the photos to be classified or the photos to be classified according to the photo category carried in the photo category setting request. Thumbnail categories.
具体的，用户可以通过所述通信模块12向服务器2发送待分类照片或者待分类照片缩略图的同时，发送单独的照片类别设置请求，用于请求所述服务器2依据该单独的照片类别设置请求中携带的照片类别对所述待分类照片或者待分类照片的缩略图分类；Specifically, the user can send a photo to be classified or a thumbnail of a photo to be classified to the server 2 through the communication module 12, and at the same time send a separate photo category setting request, which is used to request the server 2 to set the request according to the separate photo category. Classify the photos to be classified or the thumbnails of the photos to be classified by the category of photos carried in ;
也可以在向所述服务器2发送携带待分类照片或待分类照片的缩略图的消息中携带照片类别设置请求，以请求所述服务器2依据所述照片类别设置请求携带的照片类别对所述待分类照片进行分类。It is also possible to send a photo category setting request to the server 2 in a message carrying photos to be classified or thumbnails of photos to be classified, so as to request the server 2 to set the photo category according to the photo category that is carried in the photo category setting request. Classify photos into categories.
进一步的，所述照片分类管理装置1还可以包括：提取模块14。Further, the photo classification management device 1 may further include: an extraction module 14 .
所述提取模块14，用于对所述照片获取模块11获取的待分类照片进行人脸检测，并提取得到人脸图像；The extraction module 14 is configured to perform face detection on the photos to be classified acquired by the photo acquisition module 11, and extract a face image;
所述通信模块12还用于向所述服务器2发送所述人脸图像，供所述服务器2对该人脸图像进行分类。The communication module 12 is also configured to send the face image to the server 2 for the server 2 to classify the face image.
具体的，用户需要对照片按人脸聚类分类时，例如将同一个人的所有照片归在一类时，用户可通过所述提取模块14对照片执行人脸检测操作，提取照片中的人脸图像，并通过所述通信模块12发送给所述服务器2。Concretely, when the user needs to classify photos according to face clustering, for example, when all photos of the same person are classified into one category, the user can perform a face detection operation on the photos through the extraction module 14 to extract the faces in the photos image, and send it to the server 2 through the communication module 12.
另外，所述通信模块12在发送所述人脸图像的同时，还可向所述服务器2发送人脸识别请求以便于所述服务器2根据该请求提取所述人脸图像中的人脸图像特征，并按照人脸图像特征来对所述待分类照片进行分类。用户可在所述通信模块12向服务器2发送的携带人脸图像的消息中，用该消息中具体的字段值指示人脸识别请求；也可以通过通信模块12向服务器发送单独的指示消息指示需要对人脸图像进行人脸识别。这样使得服务器2能够按照用户需要进行人脸照片类别的识别，而不会进行其他的如室内室外等照片类型的识别。而对于专用于进行人脸照片类别的识别的人脸识别聚类服务器，可以不需要在额外的消息中指示人脸识别请求。In addition, when the communication module 12 sends the face image, it can also send a face recognition request to the server 2 so that the server 2 can extract the face image features in the face image according to the request. , and classify the photos to be classified according to the face image features. The user can use the specific field value in the message to indicate the face recognition request in the message carrying the face image sent by the communication module 12 to the server 2; it is also possible to send a separate indication message to the server through the communication module 12 to indicate the need Perform face recognition on face images. In this way, the server 2 can identify the type of face photo according to the needs of the user, instead of identifying other photo types such as indoor and outdoor. However, for a face recognition clustering server dedicated to identifying the category of face photos, it is not necessary to indicate the face recognition request in an additional message.
进一步的，所述通信模块12在发送所述待分类照片或者其缩略图，或者人脸图像时，还可同时发送该待分类照片的名称标识，使得所述服务器2返回相应待分类照片的名称标识以及类别，从而使得所述分类管理模块13能够对名称标识所对应的待分类照片按照其类别进行管理。这里通过消息携带名称标识来保证类别和待分类照片的对应，从而可以支持多消息并发分类请求。Further, when the communication module 12 sends the photo to be classified or its thumbnail, or the face image, it can also send the name identification of the photo to be classified at the same time, so that the server 2 returns the name of the corresponding photo to be classified IDs and categories, so that the classification management module 13 can manage the photos to be classified corresponding to the name IDs according to their categories. Here, the name identifier carried in the message is used to ensure the correspondence between the category and the photos to be classified, so that multiple messages concurrent classification requests can be supported.
所述分类管理模块13可直接根据照片类别将所述待分类照片放到其所属类别的照片组中进行组织和管理，包括：根据所述确定的照片类别，对所述待分类照片进行分类存储以便进行分类显示，该情况下，所述分类管理模块13可包括一分类显示单元，用于根据所述确定的照片类别，对所述待分类照片进行分类显示；在手机上建立文件夹(类别组)，把照片硬拷贝或者软拷贝放到对应的文件夹下；建立类别组和照片的逻辑关联，如：为类别组维护一个文档，包括所有属于该类别的照片。The classification management module 13 can directly organize and manage the photos to be classified into photo groups of the category to which they belong according to the photo category, including: classifying and storing the photos to be classified according to the determined photo category In order to classify and display, in this case, the classification management module 13 may include a classification display unit for classifying and displaying the photos to be classified according to the determined photo category; Group), put the hard copy or soft copy of the photo into the corresponding folder; establish a logical association between the category group and the photo, such as: maintain a document for the category group, including all photos belonging to the category.
也可以进一步将类别标识添加在照片上如添加到元数据中，以保证分类结果的持续有效，即使软件重装或系统重装后仍可以根据照片的类别标识确定该照片的照片类别。此种情况下，所述分类管理模块13可以包括：标记单元和管理单元。It is also possible to further add the category identification to the photo, such as adding it to the metadata, to ensure the continuous validity of the classification result. Even after the software is reinstalled or the system is reinstalled, the photo category of the photo can still be determined according to the category identification of the photo. In this case, the classification management module 13 may include: a marking unit and a management unit.
所述标记单元，用于根据所述通信模块12接收到的待分类照片的照片类别，为所述待分类照片添加该照片类别的类别标识。The marking unit is configured to, according to the photo category of the photo to be classified received by the communication module 12, add a category identification of the photo category to the photo to be classified.
所述管理单元，用于对添加了类别标识的所述待分类照片进行管理。The management unit is configured to manage the photos to be classified to which category identifiers have been added.
进一步的，所述照片分类管理装置1还可用于根据所述分类管理模块13对照片的组织和管理来展示照片。如：用户打开某个类别组对应的文件夹，则呈现该文件夹下面照片的缩略图；又如，用户选中某一类别，则读取其对应的文档，根据文档所列照片提取其缩略图来展示。若将类别标识标记在了照片上，所述照片分类管理装置1还可根据用户要展示的所属类别的需求，直接读取照片的类别标识，将该类别的照片找到并展示照片。Further, the photo classification management device 1 can also be used to display photos according to the organization and management of photos by the classification management module 13 . For example, if the user opens a folder corresponding to a category group, the thumbnails of the photos under the folder will be displayed; for another example, if the user selects a category, the corresponding document will be read, and the thumbnails will be extracted according to the photos listed in the document to show. If the category identification is marked on the photo, the photo classification management device 1 can also directly read the category identification of the photo according to the requirements of the category to be displayed by the user, find and display the photos of the category.
再请参见图3，是图1中的服务器2的结构组成示意图。所述服务器2具体包括：获取模块21，分类模块22以及通信模块23。Please refer to FIG. 3 again, which is a schematic diagram of the structural composition of the server 2 in FIG. 1 . The server 2 specifically includes: an acquisition module 21 , a classification module 22 and a communication module 23 .
所述获取模块21，用于获取待分类照片的图像内容特征。The acquiring module 21 is configured to acquire image content features of photos to be classified.
所述分类模块22，用于根据所述获取模块21获取到的待分类照片的图像内容特征确定所述待分类照片的照片类别。The classification module 22 is configured to determine the photo category of the photo to be classified according to the image content characteristics of the photo to be classified obtained by the acquisition module 21 .
在通过主动请求、被动接收等方式获取到所述照片分类管理装置1上传的待分类照片或者待分类照片的缩略图后，所述获取模块21根据待分类照片或者待分类照片的缩略图，获得待分类照片的图像内容特征。After obtaining the photo to be classified or the thumbnail of the photo to be classified uploaded by the photo classification management device 1 through active request, passive reception, etc., the acquisition module 21 obtains the photo according to the photo to be classified or the thumbnail of the photo to be classified Image content features of photos to be classified.
所述获取模块21可根据图像识别技术，对接收到的待分类照片或者待分类照片的缩略图进行图像识别，读取其中的图像内容信息(主景信息和/或背景信息)作为图像内容特征、或图像内容信息(主景信息和/或背景信息)和元数据信息作为图像内容特征。然后由所述分类模块22进行分类。例如，识别出待分类照片中的主景信息为单人或者多人的头像特征，则可以确定为人物照类别；如识别出主景信息为一朵花的特写的特征，则可以确定为植物照类别；如识别出背景信息为室外特征，则确定为室外照类别；若识别出背景信息为大海的特征，则确定为海洋照类别。若识别出包括单人或者多人的头像特征，且背景信息为海洋特征，则可确定为海洋人物类别。具体的识别是通过待分类照片和照片类别的相似度计算。所述服务器2具体可以由单一的分类服务器承载，也可以由分类服务器云(多个分类服务器构成的云)来承载，以保证满足多种类别的分类需求和多分类请求的快速响应。The acquisition module 21 can perform image recognition on the received photo to be classified or the thumbnail of the photo to be classified according to the image recognition technology, and read the image content information (main scene information and/or background information) therein as the image content feature , or image content information (main scene information and/or background information) and metadata information as image content features. Classification is then performed by the classification module 22 . For example, if it is recognized that the main scene information in the photo to be classified is a head portrait feature of a single person or multiple people, it can be determined as a portrait category; if it is recognized that the main scene information is a feature of a close-up of a flower, it can be determined as a plant If the background information is recognized as an outdoor feature, it is determined as an outdoor photo category; if the background information is recognized as a feature of the sea, it is determined as an ocean photo category. If the avatar features of a single person or multiple people are identified, and the background information is a marine feature, it can be determined as a marine character category. The specific identification is calculated by the similarity between the photo to be classified and the photo category. Specifically, the server 2 may be carried by a single classification server, or may be carried by a classification server cloud (a cloud composed of multiple classification servers), so as to ensure that the classification requirements of various categories and the rapid response of multi-classification requests are met.
所述通信模块23，用于将所述分类模块22确定的所述待分类照片的类别发送给用户终端，以使用户终端根据所述确定的待分类照片的类别，对所述待分类照片进行管理。The communication module 23 is configured to send the category of the photo to be classified determined by the classification module 22 to the user terminal, so that the user terminal performs the processing on the photo to be classified according to the determined category of the photo to be classified. manage.
其中，所述用户终端即为上述的照片分类管理装置1，所述通信模块23可通过现有的有线/无线通信网络等将所述待分类照片的照片类别发送给所述照片分类管理装置1。Wherein, the user terminal is the above-mentioned photo classification management device 1, and the communication module 23 can send the photo categories of the photos to be classified to the photo classification management device 1 through an existing wired/wireless communication network, etc. .
进一步的，请参见图3，所述服务器2还可包括：设置模块24。Further, referring to FIG. 3 , the server 2 may further include: a setting module 24 .
所述设置模块24，用于对预置的照片库中存储的照片进行分类训练，根据图像内容特征得到一个或者多个照片类别及该照片类别下的图像特征。The setting module 24 is used to perform classification training on the photos stored in the preset photo library, and obtain one or more photo categories and image features under the photo categories according to the image content characteristics.
所述服务器2通过设置模块24对内置或者外设的包括大量照片的照片库中的照片进行分类训练，根据图像内容特征得到一个或多个照片类别及该照片类别下的图像特征并保存，以供所述获取模块21和分类模块22完成待分类照片的分类。Said server 2 classifies and trains the photos in the built-in or peripheral photo library comprising a large number of photos through the setting module 24, and obtains one or more photo categories and the image features under the photo category according to the image content characteristics and saves them to For the acquisition module 21 and the classification module 22 to complete the classification of the photos to be classified.
具体的，如图3所示，所述获取模块21可以包括：Specifically, as shown in Figure 3, the acquisition module 21 may include:
第一接收单元211，用于接收所述待分类照片或者所述待分类照片的缩略图。The first receiving unit 211 is configured to receive the photo to be classified or a thumbnail of the photo to be classified.
第一特征获取单元212，用于读取所述待分类照片或者所述待分类照片的缩略图的图像内容特征，其中，将图像内容信息(主景信息和/或背景信息)、或图像内容信息(主景信息和/或背景信息)和元数据信息作为所述待分类照片的图像内容特征。The first feature acquisition unit 212 is configured to read the image content features of the photo to be classified or the thumbnail of the photo to be classified, wherein the image content information (main scene information and/or background information), or image content Information (main scene information and/or background information) and metadata information are used as image content features of the photos to be classified.
具体的，如图3所示，所述分类模块22可以包括：Specifically, as shown in Figure 3, the classification module 22 may include:
第一计算单元，用于计算所述待分类照片的图像内容特征与各照片类别下的图像特征的相似度；如基于分块最优匹配的图像相似度计算方法(首先对图像进行分块处理，并利用最优匹配在一对一匹配的前提下，计算两幅图像的全部分块所能达到的最大相似度)。The first calculation unit is used to calculate the similarity between the image content feature of the photo to be classified and the image feature under each photo category; such as an image similarity calculation method based on block optimal matching (first image is processed by block) , and use the optimal matching to calculate the maximum similarity that can be achieved by all the blocks of the two images under the premise of one-to-one matching).
第一确定单元，用于根据所述第一计算单元计算得到的所述待分类照片的图像内容特征与各照片类别下的图像特征的相似度，将相似度最高且相似度高于阈值的照片类别作为所述待分类照片的照片类别。The first determination unit is configured to select the photos with the highest similarity and higher than the threshold according to the similarity between the image content features of the photos to be classified and the image features under each photo category calculated by the first calculation unit The category is used as the photo category of the photo to be classified.
进一步的，如图3所示，所述服务器2还可包括：Further, as shown in Figure 3, the server 2 may also include:
判断模块25，用于在接收到用户发送的照片类别设置请求时，判断本端是否支持对所请求的照片类别的识别；Judging module 25, configured to determine whether the local end supports identification of the requested photo category when receiving a photo category setting request sent by the user;
所述设置模块24则还用于在所述判断模块25的判断结果为支持时，为用户设置所请求的照片类别，以便所述分类模块22依据所设置的照片类别对待分类照片分类；若判断结果为不支持，收集所请求的照片类别所对应的照片，并对收集到的照片进行分类训练，得到所述手机到照片的图像内容特征并创建所请求的照片类别及其图像特征。The setting module 24 is also used to set the requested photo category for the user when the judgment result of the judging module 25 is support, so that the classification module 22 classifies the photos to be classified according to the set photo category; The result is not supported, collect photos corresponding to the requested photo category, and perform classification training on the collected photos, obtain the image content characteristics of the mobile phone to the photos and create the requested photo category and its image features.
在所述获取模块21的所述第一接收单元211接收到所述待分类照片或者所述待分类照片的缩略图时，所述判断模块25同时判断是否接收到与所述待分类照片或者所述待分类照片的缩略图同步发送的照片类别设置请求，若接收到，所述判断模块25判断所述服务器2中是否保存有该照片类别设置请求携带的照片类别，以及该照片类别对应的图像内容特征，若存在，所述设置模块24则直接为该用户设置其所请求的照片类别，并以该设置的照片类别作为待分类照片的照片类别；若不存在，所述设置模块24则对收集到的该请求的照片类别所对应的照片进行训练，创建该照片类别设置请求携带的照片类别及其图像内容特征，以供所述分类模块22确定待分类照片的照片类别。例如，当用户要求雪山照类别时，若服务器2通过判断模块25判断未保存雪山照类别及其图像内容特征，则可以雪山等词作为关键字在互联网上进行搜索，将搜索到的图片存入照片库中，并通过所述设置模块24对照片库中收集的该照片分类类别所对应的照片进行训练，创建该照片类别及其图像特征。When the first receiving unit 211 of the acquisition module 21 receives the photo to be classified or the thumbnail of the photo to be classified, the judging module 25 simultaneously judges whether a The photo category setting request synchronously sent by the thumbnails of the photos to be classified, if received, the judging module 25 judges whether the photo category carried in the photo category setting request is stored in the server 2, and the image corresponding to the photo category Content feature, if exist, then described setting module 24 then directly sets the photo category that it requests for this user, and with the photo category of this setting as the photo category of photo to be classified; If not exist, described setting module 24 then to The collected photos corresponding to the requested photo category are trained, and the photo category setting request carries the photo category and its image content characteristics for the classification module 22 to determine the photo category of the photo to be classified. For example, when the user requests the category of snow-capped photos, if the server 2 judges through the judging module 25 that the categories and image content features of the photos of snow-capped mountains are not preserved, then words such as snow-capped mountains can be used as keywords to search on the Internet, and the searched pictures can be stored in the In the photo library, the photos corresponding to the photo classification category collected in the photo library are trained by the setting module 24, and the photo category and its image features are created.
具体的，对于人脸照片的识别，所述服务器2的所述设置模块24还可以用于对预置的照片库中存储的照片进行人脸检测、人脸识别、人脸聚类训练，根据人脸图像特征得到一个或者多个照片类别及该照片类别下的人脸特征和人脸图像(保存对应的人脸图像，可用于后续根据该照片类别的新人脸图像和所有之前的人脸图像一起更新该照片类别的人脸特征)以供后续进行人脸类别的照片识别。Specifically, for the recognition of face photos, the setting module 24 of the server 2 can also be used to perform face detection, face recognition, and face clustering training on photos stored in a preset photo library, according to Face image features Get one or more photo categories and the face features and face images under the photo category (save the corresponding face image, which can be used for subsequent new face images and all previous face images based on the photo category Update the face features of this photo category together) for subsequent photo recognition of the face category.
用户需要按照人脸进行分类时，可根据自身需要和网络请求，通过所述照片分类管理装置1向服务器2发送人脸图像，所述服务器2的获取模块21还可以包括：When the user needs to classify according to the face, he can send the face image to the server 2 through the photo classification management device 1 according to his own needs and network requests, and the acquisition module 21 of the server 2 can also include:
第二接收单元213，用于接收人脸图像；The second receiving unit 213 is configured to receive a face image;
第二特征获取单元214，用于提取所述第二接收单元213接收到的人脸图像中的人脸图像特征，并将所述人脸图像特征记为所述待分类照片的图像内容特征；其中，所述人脸图像是由所述用户终端即所述照片分类管理装置1对所述待分类照片进行人脸检测并提取得到的。The second feature acquisition unit 214 is used to extract the face image features in the face image received by the second receiving unit 213, and record the face image features as the image content features of the photo to be classified; Wherein, the face image is obtained by detecting and extracting faces from the photos to be classified by the user terminal, that is, the photo classification management device 1 .
具体的，用户需要按照人脸进行分类时，也可根据自身需要和网络请求，通过所述照片分类管理装置1向服务器2直接发送待分类照片，所述获取模块21还可以包括：Specifically, when the user needs to classify according to the face, he can also send the photos to be classified directly to the server 2 through the photo classification management device 1 according to his own needs and network requests, and the acquisition module 21 can also include:
第三接收单元215，用于接收待分类照片；The third receiving unit 215 is configured to receive photos to be classified;
第三特征获取单元216，用于对所述待分类照片进行人脸检测，提取人脸图像，并提取人脸图像中的人脸图像特征，将所述人脸图像特征记为所述待分类照片的图像内容特征。The third feature acquisition unit 216 is configured to perform face detection on the photo to be classified, extract the face image, and extract the face image features in the face image, and record the face image feature as the to-be-classified photo. The image content characteristics of a photo.
对于上述进行的人脸图像的图像内容特征的获取，所述分类模块22具体可以包括以下单元进行分类识别：For the above-mentioned acquisition of the image content feature of the face image, the classification module 22 may specifically include the following units for classification and recognition:
第二计算单元，用于计算所述待分类照片的人脸图像特征与本端存储的各照片类别中的人脸特征的相似度；The second calculation unit is used to calculate the similarity between the face image features of the photo to be classified and the face features in each photo category stored at the local end;
第二确定单元，用于根据所述第二计算单元计算得到的相似度，将相似度最高且高于阈值的照片类别判定为所述待分类照片的照片类别；The second determination unit is configured to determine, according to the similarity calculated by the second calculation unit, the photo category with the highest similarity and higher than a threshold as the photo category of the photos to be classified;
所述设置模块24则还用于将该人脸图像关联于已判定为所述待分类照片的照片类别，并根据该人脸图像更新其关联的照片类别的人脸特征，若不存在相似度高于阈值的照片类别，根据该人脸图像特征创建新的照片类别并将该人脸图像关联于该照片类别。The setting module 24 is also used to associate the face image with the photo category that has been determined as the photo to be classified, and update the face features of the associated photo category according to the face image, if there is no similarity If the photo category is higher than the threshold, a new photo category is created according to the features of the face image and the face image is associated with the photo category.
其中，所述第二计算单元223具体是将所述人脸图像特征与本端存储的各照片类别中的人脸特征进行比对，计算相似度，如：基于改进Ha u s d o r f f距离的人脸相似度匹配的方法(首先将人脸划分为脸型、双眼、鼻、嘴等几个特征点集，分别计算各部分的改进Ha u s d o r f f距离，然后进行加权计算相似度)。若存在与所述接收到的人脸图像特征匹配的人脸图像，即相似度最高且高于阈值的照片类别，则将该人脸图像所在的照片类别记为所述待分类照片的照片类别，之后，根据该人脸图像更新其关联的照片类别的人脸图像特征，方便后续该类别的人脸照片的识别；若不存在相似度高于阈值的照片类别时，则所述设置模块24还用于根据该人脸图像特征创建新的照片类别并将该人脸图像关联于该照片类别。具体可以重新生成照片类别的全部人脸图像特征，也可以根据相似度计算的差异度更新部分人脸图像特征。Wherein, the second calculation unit 223 specifically compares the face image features with the face features in each photo category stored locally to calculate the similarity, such as: face similarity based on improved Hausdorff distance Degree matching method (first divide the face into several feature point sets such as face shape, eyes, nose, mouth, etc., respectively calculate the improved Hausdorff distance of each part, and then perform weighted calculation of similarity). If there is a face image matched with the received face image feature, that is, the photo category with the highest similarity and higher than the threshold, the photo category where the face image is located is recorded as the photo category of the photo to be classified , after that, update the face image features of its associated photo category according to the face image, so as to facilitate the recognition of the face photos of this category; if there is no photo category with similarity higher than the threshold, then the setting module 24 It is also used to create a new photo category according to the feature of the face image and associate the face image with the photo category. Specifically, all face image features of the photo category can be regenerated, and some face image features can also be updated according to the degree of difference calculated by similarity.
进一步的，对于上述的人脸照片的识别，所述服务器2还可以包括：Further, for the recognition of the above-mentioned face photos, the server 2 may also include:
通知模块26，用于在接收到所述用户终端即所述照片分类管理装置1发送的人脸识别请求时，通知所述获取模块21提取人脸图像中的人脸图像特征，以使所述分类模块22按照人脸图像特征来对所述待分类照片进行分类。The notification module 26 is configured to notify the acquisition module 21 to extract the face image features in the face image when receiving the face recognition request sent by the user terminal, that is, the photo classification management device 1, so that the The classification module 22 classifies the photos to be classified according to the facial image features.
也就是说，在所述通知模块26确定接收到所述照片分类管理装置1在发送了待分类照片或者人脸图像的同时，还接收到用户指示的人脸识别请求时，即确定用户对该次上传的待分类照片或者人脸图像需要进行人脸类型的识别，通知所述获取模块21再进行人脸图像特征提取，以及使所述分类模块22进行待分类照片或者人脸图像的识别分类操作。That is to say, when the notification module 26 determines that the photo classification management device 1 has also received a face recognition request indicated by the user while sending the photos or face images to be classified, it is determined that the user The photo to be classified or the face image uploaded for the first time need to carry out the identification of the face type, and the acquisition module 21 is notified to perform the feature extraction of the face image, and the classification module 22 is made to carry out the recognition and classification of the photo to be classified or the face image operate.
在具体实施时，所述获取模块21也可以根据用户对待分类照片的照片类别设置请求来获取待分类照片的图像内容特征。例如：During specific implementation, the acquisition module 21 may also acquire the image content features of the photos to be classified according to the user's photo category setting request of the photos to be classified. E.g:
用户通过所述照片分类管理装置1在携带待分类照片、待分类照片缩略图或者人脸图像的消息中，用该消息中的某一字段值指示服务器2需要依照何种照片类别对待分类照片、待分类照片缩略图或者人脸图像进行分类；或者，用户在发送携带待分类照片、待分类照片缩略图或者人脸图像的消息的同时，发送一指示消息，并在该指示消息的某一字段值中指示按人脸分类、指示按照室内、风景、单人等类别来分类，所述获取模块21通过相应的单元或单元组合获取待分类照片、缩略图或者人脸图像中的图像内容特征以进行后续的判断识别。The user uses the photo classification management device 1 to indicate to the server 2 according to which photo category to treat the classified photos, Thumbnails of photos to be classified or face images for classification; or, the user sends an instruction message while sending a message carrying photos to be classified, thumbnails of photos to be classified or face images, and in a certain field of the instruction message In the value, the indication is classified by face, and the indication is classified by categories such as indoor, landscape, single person, etc., and the acquisition module 21 acquires the image content features in the photos to be classified, thumbnails, or human face images through corresponding units or unit combinations. Make subsequent judgments and identifications.
而对于专用于进行人脸照片类别的识别的人脸识别聚类服务器，可以不需要在额外的消息中指示人脸识别请求。However, for a face recognition clustering server dedicated to identifying the category of face photos, it is not necessary to indicate the face recognition request in an additional message.
具体的，上述的第一接收单元211、第二接收单元213以及第三接收单元215可以为一个接收单元实现，所述第一特征获取单元212、第二特征获取单元213以及第三特征获取单元216可以为一个特征获取单元实现。Specifically, the above-mentioned first receiving unit 211, second receiving unit 213, and third receiving unit 215 can be implemented as one receiving unit, and the first feature acquiring unit 212, the second feature acquiring unit 213, and the third feature acquiring unit 216 can be implemented as a feature acquisition unit.
通过上述实施例的描述可知，本发明的实施例具有以下优点：It can be seen from the description of the above embodiments that the embodiments of the present invention have the following advantages:
本发明的实施例可对用户通过拍照、传输等方式获取到的照片进行图像内容特征的识别以及对照片的分类，使得用户不需要对照片进行手动标记或者手动分类，实现了对照片图像内容的自动化分类操作，较好地实现了依照照片的图像内容的类别来对照片的组织和管理，极大地方便了用户。特别是可以自动依据人脸特征来实现对照片的组织和管理，将同一人的照片组织在一起，方便用户对同一人不同时间不同地点不同装扮的照片的查看。此外还支持新照片类别及新人脸的创建，能有效地扩充。The embodiment of the present invention can identify the characteristics of the image content and classify the photos obtained by the user through photographing, transmission, etc., so that the user does not need to manually mark or classify the photos, and realizes the image content of the photos. The automatic classification operation better realizes the organization and management of the photos according to the categories of the image content of the photos, which greatly facilitates the users. In particular, it can automatically realize the organization and management of photos based on facial features, organize photos of the same person together, and facilitate users to view photos of the same person in different times, different places, and different outfits. In addition, it also supports the creation of new photo categories and new faces, which can be effectively expanded.
下面对本发明的一种照片分类管理方法进行详细描述。A photo classification management method of the present invention will be described in detail below.
请参见图4，是本发明的照片分类管理方法的第一实施例流程示意图，本实施例中，所述照片分类管理方法包括：Please refer to FIG. 4 , which is a schematic flow chart of the first embodiment of the photo classification management method of the present invention. In this embodiment, the photo classification management method includes:
S101：服务器获取待分类照片的图像内容特征。S101: The server acquires image content features of the photos to be classified.
服务器在通过接收等方式获取到所述照片分类管理装置上传的待分类照片或者待分类照片的缩略图后，所述S101根据待分类照片或者待分类照片的缩略图，获得待分类照片的图像内容特征。After the server obtains the photos to be classified or the thumbnails of the photos to be classified uploaded by the photo classification management device by means of receiving, etc., the S101 obtains the image content of the photos to be classified according to the photos to be classified or the thumbnails of the photos to be classified feature.
所述S101可根据图像识别技术，对接收到的待分类照片或者待分类照片的缩略图进行图像识别，读取其中的图像内容信息(主景信息和/或背景信息)作为图像内容特征，或读取其中的图像内容信息(主景信息和/或别进信息)和元数据信息作为图像内容特征。The S101 can perform image recognition on the received photo to be classified or the thumbnail of the photo to be classified according to the image recognition technology, and read the image content information (main scene information and/or background information) therein as the image content feature, or The image content information (main scene information and/or clip information) and metadata information therein are read as image content features.
用户需要对如人物照等特定照片进行分类时，用户端的照片分类管理装置可根据用户需要对特定照片执行人脸检测操作，提取照片中的人脸图像，并发送给所述服务器，所述S101将该人脸图像作为所述需要分类的特定照片即待分类照片的图像内容特征，或者用户端的照片分类管理装置也可以直接向服务器发送需要分类的如人物照等特定照片给服务器，由所述服务器进行照片的人脸检测提取人脸图像，并提取照片中的人脸图像特征，所述S101将该人脸图像特征作为所述需要分类的特定照片即待分类照片的图像内容特征。When the user needs to classify specific photos such as photos of people, the photo classification management device at the user end can perform face detection operations on specific photos according to user needs, extract face images in the photos, and send them to the server, the S101 The face image is used as the image content feature of the specific photo that needs to be classified, that is, the photo to be classified, or the photo classification management device at the user end can also directly send specific photos that need to be classified, such as portrait photos, etc. to the server, and the The server detects the face of the photo to extract the face image, and extracts the face image feature in the photo, and the S101 uses the face image feature as the image content feature of the specific photo that needs to be classified, that is, the photo to be classified.
S102：服务器根据所述待分类照片的图像内容特征确定所述待分类照片的照片类别。S102: The server determines the photo category of the photo to be classified according to the image content characteristics of the photo to be classified.
具体的，所述S102识别出待分类照片中的主景信息为单人或者多人的头像特征，则可以确定为人物照类别；如识别出主景信息为一朵花的特写的特征，则可以确定为植物照类别；如识别出背景信息为室外特征，则确定为室外照类别；若识别出背景信息为大海的特征，则确定为海洋照类别。若识别出包括单人或者多人的头像特征，且背景信息为海洋特征，则可确定为海洋人物类别。具体的识别是通过待分类照片和照片类别的相似度计算。分类的服务器具体可以由单一的分类服务器承载，也可以由分类服务器云(多个分类服务器构成的云)来承载，以保证满足多种类别的分类需求和多分类请求的快速响应。Specifically, if the S102 recognizes that the main scene information in the photo to be classified is a head portrait feature of a single person or multiple people, then it can be determined as a portrait category; if the main scene information is identified as a feature of a close-up of a flower, then It can be determined as a plant photo category; if the background information is identified as an outdoor feature, then it is determined as an outdoor photo category; if the background information is recognized as a feature of the sea, it is determined as an ocean photo category. If the avatar features of a single person or multiple people are identified, and the background information is a marine feature, it can be determined as a marine character category. The specific identification is calculated by the similarity between the photo to be classified and the photo category. Specifically, the classification server can be hosted by a single classification server, or it can be carried by a classification server cloud (a cloud composed of multiple classification servers), so as to ensure that the classification requirements of various categories are met and the rapid response to multi-classification requests is met.
S103：服务器将确定的所述待分类照片的照片类别发送给用户终端。S103: The server sends the determined photo category of the photo to be classified to the user terminal.
用户终端和服务器之间可通过现有的通信网络进行数据传输。Data transmission can be performed between the user terminal and the server through the existing communication network.
另外，所述服务器还可通过S103将该待分类照片及其照片类别发送到由用户指定的照片服务器中，如发送到用户指定的一用户照片空间服务器中，以使所述用户照片空间服务器按照照片类别将所述待分类照片存储到相应存储器中，当用户需要时可随时在该用户的空间中(如QQ空间)按照照片类别显示所述待分类照片。In addition, the server can also send the photo to be classified and its photo category to a photo server designated by the user through S103, for example, to a user photo space server designated by the user, so that the user photo space server can follow the The photo category stores the photos to be classified in the corresponding memory, and when the user needs, the photos to be classified can be displayed in the user's space (such as QQ space) according to the photo category at any time.
S104：用户终端根据所述确定的照片类别，对所述待分类照片进行分类管理。所述S104具体包括：所述用户终端根据所述确定的照片类别，对所述待分类照片进行分类显示；或者包括：根据所述确定得到的待分类照片的照片类别，所述用户终端为所述待分类照片添加该类别的类别标识，并对添加了类别标识的所述待分类照片进行分类管理。S104: The user terminal classifies and manages the photos to be classified according to the determined photo category. The S104 specifically includes: the user terminal classifies and displays the photos to be classified according to the determined photo category; or includes: according to the determined photo category of the photos to be classified, the user terminal is the The category identification of the category is added to the photos to be classified, and the classification management is performed on the photos to be classified to which the category identification is added.
所述S104可直接根据照片类别将所述待分类照片放到其所属类别的照片组中进行组织和管理，包括：在手机上建立文件夹(类别组)，把照片硬拷贝或者软拷贝放到对应的文件夹下；建立类别组和照片的逻辑关联，如：为类别组维护一个文档，包括所有属于该类别的照片。The S104 can directly organize and manage the photos to be classified into photo groups of the category to which they belong according to the category of the photos, including: creating a folder (category group) on the mobile phone, and putting the hard copy or soft copy of the photo into the corresponding photo group. Under the folder; establish a logical association between category groups and photos, such as: maintain a document for category groups, including all photos belonging to this category.
也可以进一步将照片类别标识在照片上(添加到元数据中)，以保证分类结果的持续有效，即使软件重装或系统重装后仍可以根据照片的类别标识确定该照片的照片类别。It is also possible to further identify the photo category on the photo (add it to the metadata) to ensure the continuous validity of the classification result. Even after the software is reinstalled or the system is reinstalled, the photo category of the photo can still be determined according to the category identification of the photo.
进一步的，所述用户终端还可通过对照片的组织和管理来展示照片。如：用户打开某个类别组对应的文件夹，则呈现该文件夹下面照片的缩略图；又如，用户选中某一类别，则读取其对应的文档，根据文档所列照片提取其缩略图来展示。若将类别标识标记在了照片上，所述用户终端还可根据用户要展示的所属类别的需求，直接读取照片的类别标识，将该类别的照片找到并展示照片。Further, the user terminal can also display photos by organizing and managing photos. For example, if the user opens a folder corresponding to a category group, the thumbnails of the photos under the folder will be displayed; for another example, if the user selects a category, the corresponding document will be read, and the thumbnails will be extracted according to the photos listed in the document to show. If the category identifier is marked on the photo, the user terminal can also directly read the category identifier of the photo according to the requirements of the category to be displayed by the user, find and display photos of the category.
通过上述实施例的描述可知，本发明的实施例具有以下优点：It can be seen from the description of the above embodiments that the embodiments of the present invention have the following advantages:
本发明的实施例可对用户通过拍照、传输等方式获取到的照片进行图像内容特征的识别以及对照片的分类，使得用户不需要对照片进行手动标记或者手动分类，实现了对照片图像内容的自动化分类操作，较好地实现了依照照片的图像内容的类别来对照片的组织和管理，极大地方便了用户。特别是可以自动依据人脸特征来实现对照片的组织和管理，将同一人的照片组织在一起，方便用户对同一人不同时间不同地点不同装扮的照片的查看。此外还支持新照片类别及新人脸的创建，能有效地扩充。The embodiment of the present invention can identify the characteristics of the image content and classify the photos obtained by the user through photographing, transmission, etc., so that the user does not need to manually mark or classify the photos, and realizes the image content of the photos. The automatic classification operation better realizes the organization and management of the photos according to the categories of the image content of the photos, which greatly facilitates the users. In particular, it can automatically realize the organization and management of photos based on facial features, organize photos of the same person together, and facilitate users to view photos of the same person in different times, different places, and different outfits. In addition, it also supports the creation of new photo categories and new faces, which can be effectively expanded.
再请参见图5，是本发明的照片分类管理方法的第二实施例流程示意图，本实施例的所述方法包括：Please refer to FIG. 5 again, which is a schematic flow chart of the second embodiment of the photo classification management method of the present invention. The method of this embodiment includes:
S201：服务器对预置的照片库中存储的照片进行分类训练，确定照片类别及其对应的图像特征。S201: The server performs classification training on photos stored in a preset photo library, and determines photo categories and corresponding image features.
其中，所述照片库中包括收集到的多张照片。所述服务器通过S201对照片库中收集到的大量的照片进行分类训练，根据图像内容特征得到一个或者多个照片类别及该照片类别下的图像特征。Wherein, the photo library includes a plurality of collected photos. The server performs classification training on a large number of photos collected in the photo library through S201, and obtains one or more photo categories and image features under the photo category according to image content characteristics.
另外的，服务器对预置的照片库中存储的照片进行人脸检测、人脸识别、人脸聚类训练，根据各照片的人脸图像特征得到一个或者多个照片类别及该照片类别下的人脸特征和人脸图像(保存对应的人脸图像，可用于后续根据该照片类别的新人脸图像和所有之前的人脸图像一起更新该照片类别的人脸特征)。In addition, the server performs face detection, face recognition, and face clustering training on the photos stored in the preset photo library, and obtains one or more photo categories and the photo categories under the photo category according to the face image features of each photo. Face features and face images (save the corresponding face images, which can be used to update the face features of the photo category according to the new face images of the photo category and all previous face images).
S202：服务器获取待分类照片的图像内容特征。S202: The server acquires image content features of the photos to be classified.
具体的，所述S202可通过以下方式获取到待分类照片的图像内容特征：Specifically, the S202 can obtain the image content features of the photos to be classified in the following ways:
方式一：method one:
所述服务器接收待分类照片或者所述待分类照片的缩略图，其中，所述待分类照片的缩略图是由照片获取装置对其获取的照片执行缩略图提取操作后得到的；The server receives the photos to be classified or the thumbnails of the photos to be classified, wherein the thumbnails of the photos to be classified are obtained by the photo acquisition device after performing a thumbnail extraction operation on the photos acquired;
所述服务器读取所述待分类照片或者所述待分类照片的缩略图的图像内容特征，其中，将图像内容信息(主景信息和/或背景信息)、或图像内容信息(主景信息和/或背景信息)和元数据信息作为所述待分类照片的图像内容特征。The server reads the image content characteristics of the photo to be classified or the thumbnail of the photo to be classified, wherein the image content information (main scene information and/or background information), or image content information (main scene information and /or background information) and metadata information as the image content features of the photos to be classified.
方式二：Method 2:
所述服务器接收人脸图像，提取人脸图像中的人脸图像特征，并将所述人脸图像特征记为所述待分类照片的图像内容特征；The server receives the face image, extracts the face image feature in the face image, and records the face image feature as the image content feature of the photo to be classified;
其中，所述人脸图像是由所述用户终端对所述待分类照片进行人脸检测并提取得到的。Wherein, the face image is obtained by the user terminal performing face detection and extraction on the photo to be classified.
方式三：Method 3:
所述服务器接收由所述用户终端发送的待分类照片；The server receives the photos to be classified sent by the user terminal;
所述服务器对所述待分类照片进行人脸检测提取人脸图像，并提取人脸图像中的人脸图像特征，将所述人脸图像特征记为所述待分类照片的图像内容特征。The server performs face detection on the photo to be classified to extract a face image, and extracts features of the face image in the face image, and records the feature of the face image as an image content feature of the photo to be classified.
进一步的，对于普通的待分类照片或者待分类照片的缩略图，在所述S202之前，还包括步骤：Further, for ordinary photos to be classified or thumbnails of photos to be classified, before the S202, further steps are included:
所述服务器判断在接收到用户终端在发送待分类照片或者待分类照片的缩略图的同时，是否接收到用户关于此次发送的待分类照片或者待分类照片的缩略图的照片类别设置请求。该照片类别设置请求可以是一个单独的指示消息，也可以是在携带所述待分类照片或者待分类照片的缩略图的消息中的某个字段指示的内容。The server judges whether it receives a photo category setting request from the user about the photo to be classified or the thumbnail of the photo to be classified sent this time while receiving the user terminal sending the photo to be classified or the thumbnail of the photo to be classified. The photo category setting request may be a separate indication message, or may be the content indicated by a certain field in the message carrying the photo to be classified or the thumbnail of the photo to be classified.
若所述服务器接收到用户终端发送的照片类别设置请求，则进一步判断本端是否支持对所请求的照片类别的识别确定；If the server receives the photo category setting request sent by the user terminal, it further judges whether the local end supports identification and determination of the requested photo category;
若支持，所述服务器为用户设置所请求的照片类别，并执行所述S202；If supported, the server sets the requested photo category for the user, and executes S202;
若不支持，所述服务器收集所请求的照片类别所对应的照片，并对收集到的照片进行分类训练，得到所述收集到的照片的图像内容特征，并根据所述收集到的照片的图像内容特征创建所请求的照片类别及该照片类别下的图像特征。例如，当用户要求雪山照类别时，若服务器通过判断确定未保存雪山照类别及其图像内容特征，则可通过以雪山等词作为关键字进行搜索，将搜索到的图片存入照片库中，并通过所述S304对照片库中收集的该照片分类类别所对应的照片进行分类训练，得到所请求的照片类别的图像内容特征并创建该照片类别。If not supported, the server collects the photos corresponding to the requested photo category, and performs classification training on the collected photos, obtains the image content characteristics of the collected photos, and based on the images of the collected photos The content feature creates the requested photo category and image features under the photo category. For example, when the user requests the category of snow mountain photos, if the server determines through judgment that the category of snow mountain photos and its image content features are not saved, the searched pictures can be stored in the photo library by using words such as snow mountains as keywords to search. And carry out classification training on the photos corresponding to the photo classification category collected in the photo library through the S304, obtain the image content characteristics of the requested photo category and create the photo category.
而对于需要进行人脸识别的待分类照片或者人脸图像，在所述S202之前，还包括步骤：And for the photos to be classified or face images that need face recognition, before the S202, also include steps:
所述服务器判断在接收到用户终端在发送待分类照片或者人脸图像的同时，是否接收到用户终端发送的人脸识别请求；The server judges whether the face recognition request sent by the user terminal is received while receiving the user terminal sending the photo to be classified or the face image;
若是，则执行所述S202。If yes, execute S202.
具体可以根据用户的照片类别设置请求，选择相应的方式进行图像内容特征的获取。比如：用户请求对待分类照片按人脸分类，则提取人脸图像特征，用户请求将待分类照片风景来分类，则提取背景中的内容作为图像内容特征。Specifically, according to the user's photo category setting request, a corresponding method may be selected to acquire the image content features. For example, if the user requests to classify the photo to be classified by face, then extract the face image features, and if the user requests to classify the landscape of the photo to be classified, then extract the content in the background as the image content feature.
S203：服务器根据所述待分类照片的图像内容特征确定所述待分类照片的照片类别。S203: The server determines the photo category of the photo to be classified according to the image content feature of the photo to be classified.
具体的，对于所述S202中的方式一中获取的图像内容特征，所述S203可通过：计算所述待分类照片的图像内容特征与各照片类别下的图像特征的相似度；根据计算得到的相似度，将相似度最高且相似度高于阈值的照片类别作为所述待分类照片的照片类别Specifically, for the image content features acquired in the first way in S202, the S203 can be: calculating the similarity between the image content features of the photos to be classified and the image features under each photo category; Similarity, using the photo category with the highest similarity and a similarity higher than the threshold as the photo category of the photo to be classified
对于所述S202中方式二或者方式三中获取的图像内容特征，所述S203将计算所述待分类照片的人脸图像特征与本端存储的各照片类别中的人脸特征的相似度；将相似度最高且高于阈值的照片类别判定为所述待分类照片的照片类别，并将该人脸图像关联于该已判定为所述待分类照片的照片类别，并根据该人脸图像更新其关联的照片类别的人脸图像特征；若不存在相似度高于阈值的照片类别，所述服务器根据该人脸图像特征创建新的照片类别并将该人脸图像关联于该照片类别。For the image content features obtained in the method two or three in the S202, the S203 will calculate the similarity between the face image features of the photo to be classified and the face features in each photo category stored at the end; The photo category with the highest similarity and higher than the threshold is determined as the photo category of the photo to be classified, and the face image is associated with the photo category that has been determined to be the photo to be classified, and the face image is updated according to the photo category of the photo to be classified. The face image feature of the associated photo category; if there is no photo category with a similarity higher than the threshold, the server creates a new photo category according to the face image feature and associates the face image with the photo category.
S204：服务器将确定的所述待分类照片的照片类别发送给用户终端。S204: The server sends the determined photo category of the photo to be classified to the user terminal.
S205：所述用户终端根据所述确定的照片类别，对所述待分类照片进行分类管理。S205: The user terminal classifies and manages the photos to be classified according to the determined photo category.
具体可包括：所述用户终端根据所述确定的照片类别，对所述待分类照片进行分类显示。或者可包括：用户终端根据所述确定得到的待分类照片的照片类别，为所述待分类照片添加该类别的类别标识，具体可将类别标识标记在照片上，例如：添加到元数据中，以保证分类结果的持续有效，即使软件重装或系统重装后仍可以根据照片的类别标识确定该照片的照片类别。然后对添加了类别标识的所述待分类照片进行分类管理，具体可直接根据照片类别将所述待分类照片放到其所属类别的照片组中进行组织和管理，包括：在手机上建立文件夹(类别组)，把照片硬拷贝或者软拷贝放到对应的文件夹下；建立类别组和照片的逻辑关联，如：为类别组维护一个文档，包括所有属于该类别的照片。Specifically, it may include: the user terminal classifies and displays the photos to be classified according to the determined photo category. Or it may include: the user terminal adds a category identifier of the category to the photo to be classified according to the determined photo category of the photo to be classified, specifically, the category identifier may be marked on the photo, for example: added to the metadata, In order to ensure the continuous effectiveness of the classification results, the photo category of the photo can still be determined according to the category identification of the photo even after the software or system is reinstalled. Then classify and manage the photos to be classified with the added category identification, specifically, put the photos to be classified into photo groups of their category directly according to the photo category for organization and management, including: establishing folders on the mobile phone (category group), put the hard copy or soft copy of the photo into the corresponding folder; establish a logical association between the category group and the photo, such as: maintain a document for the category group, including all photos belonging to the category.
通过上述实施例的描述可知，本发明的实施例具有以下优点：It can be seen from the description of the above embodiments that the embodiments of the present invention have the following advantages:
本发明的实施例可对用户通过拍照、传输等方式获取到的照片进行图像内容特征的识别以及对照片的分类，使得用户不需要对照片进行手动标记或者手动分类，实现了对照片图像内容的自动化分类操作，较好地实现了依照照片的图像内容的类别来对照片的组织和管理，极大地方便了用户。特别是可以自动依据人脸特征来实现对照片的组织和管理，将同一人的照片组织在一起，方便用户对同一人不同时间不同地点不同装扮的照片的查看。此外还支持新照片类别及新人脸的创建，能有效地扩充。The embodiment of the present invention can identify the characteristics of the image content and classify the photos obtained by the user through photographing, transmission, etc., so that the user does not need to manually mark or classify the photos, and realizes the image content of the photos. The automatic classification operation better realizes the organization and management of the photos according to the categories of the image content of the photos, which greatly facilitates the users. In particular, it can automatically realize the organization and management of photos based on facial features, organize photos of the same person together, and facilitate users to view photos of the same person in different times, different places, and different outfits. In addition, it also supports the creation of new photo categories and new faces, which can be effectively expanded.
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，所述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory，ROM)或随机存储记忆体(Random AccessMemory，RAM)等。Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented through computer programs to instruct related hardware, and the programs can be stored in a computer-readable storage medium. During execution, it may include the processes of the embodiments of the above-mentioned methods. Wherein, the storage medium may be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM) or a random access memory (Random Access Memory, RAM) and the like.
以上所揭露的仅为本发明较佳实施例而已，当然不能以此来限定本发明之权利范围，因此依本发明权利要求所作的等同变化，仍属本发明所涵盖的范围。The above disclosures are only preferred embodiments of the present invention, and certainly cannot limit the scope of rights of the present invention. Therefore, equivalent changes made according to the claims of the present invention still fall within the scope of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711384927.XACN108073948A (en) | 2012-01-17 | 2012-01-17 | A kind of photo sort management, server, apparatus and system |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210013824.3ACN103207870B (en) | 2012-01-17 | 2012-01-17 | Photo classification management method, server, device and system |
| CN201711384927.XACN108073948A (en) | 2012-01-17 | 2012-01-17 | A kind of photo sort management, server, apparatus and system |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210013824.3ADivisionCN103207870B (en) | 2012-01-17 | 2012-01-17 | Photo classification management method, server, device and system |
| Publication Number | Publication Date |
|---|---|
| CN108073948Atrue CN108073948A (en) | 2018-05-25 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711384927.XAPendingCN108073948A (en) | 2012-01-17 | 2012-01-17 | A kind of photo sort management, server, apparatus and system |
| CN201210013824.3AActiveCN103207870B (en) | 2012-01-17 | 2012-01-17 | Photo classification management method, server, device and system |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210013824.3AActiveCN103207870B (en) | 2012-01-17 | 2012-01-17 | Photo classification management method, server, device and system |
| Country | Link |
|---|---|
| CN (2) | CN108073948A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109948734A (en)* | 2019-04-02 | 2019-06-28 | 北京旷视科技有限公司 | Image clustering method, device and electronic device |
| WO2020020226A1 (en)* | 2018-07-27 | 2020-01-30 | 中兴通讯股份有限公司 | Photo classification method, device, computer-readable medium, and system |
| WO2020192736A1 (en)* | 2019-03-26 | 2020-10-01 | 华为技术有限公司 | Object recognition method and device |
| CN114897888A (en)* | 2022-06-22 | 2022-08-12 | 中国电信股份有限公司 | Image review method, device and system |
| WO2022193232A1 (en)* | 2021-03-18 | 2022-09-22 | 京东方科技集团股份有限公司 | Face clustering method and apparatus, classification storage method, medium, and electronic device |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103559236A (en)* | 2013-10-25 | 2014-02-05 | 华为终端有限公司 | Image displaying method and terminal |
| CN104750688A (en)* | 2013-12-25 | 2015-07-01 | 鸿富锦精密工业（深圳）有限公司 | Photo management method and system |
| CN103744996A (en)* | 2014-01-23 | 2014-04-23 | 惠州Tcl移动通信有限公司 | Mobile terminal album classifying method and system |
| CN104915344B (en)* | 2014-03-10 | 2019-04-26 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
| WO2015139204A1 (en)* | 2014-03-18 | 2015-09-24 | 华为终端有限公司 | Picture management method and device |
| CN104951426A (en)* | 2014-03-26 | 2015-09-30 | 联想移动通信软件（武汉）有限公司 | Taken photo classified processing method and device and terminal equipment |
| CN104980641B (en)* | 2014-04-04 | 2019-01-08 | 宏碁股份有限公司 | Electronic device and image viewing method thereof |
| CN103995889B (en)* | 2014-06-03 | 2017-11-03 | 广东欧珀移动通信有限公司 | Picture classification method and device |
| US20180107660A1 (en)* | 2014-06-27 | 2018-04-19 | Amazon Technologies, Inc. | System, method and apparatus for organizing photographs stored on a mobile computing device |
| US9479672B2 (en)* | 2014-07-18 | 2016-10-25 | Sony Mobile Communications Inc. | Method and system for efficient transfer of digital images captured by a lifelog camera |
| CN104168378B (en)* | 2014-08-19 | 2018-06-05 | 上海卓易科技股份有限公司 | A kind of picture group technology and device based on recognition of face |
| CN104216976B (en)* | 2014-09-01 | 2018-09-04 | 广东欧珀移动通信有限公司 | A kind of mobile terminal picture grouping inspection method and system |
| CN105654101B (en)* | 2014-11-11 | 2019-04-26 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
| CN104408428B (en)* | 2014-11-28 | 2018-05-15 | 东莞宇龙通信科技有限公司 | Method and device for processing photos in same scene |
| CN104572905B (en)* | 2014-12-26 | 2018-09-04 | 小米科技有限责任公司 | Print reference creation method, photo searching method and device |
| WO2016134506A1 (en)* | 2015-02-26 | 2016-09-01 | 刘一佳 | Method for feature reminder when screening photographs and mobile terminal |
| WO2016149943A1 (en)* | 2015-03-26 | 2016-09-29 | 北京旷视科技有限公司 | Image management method and image synchronization method |
| CN104731979A (en)* | 2015-04-16 | 2015-06-24 | 广东欧珀移动通信有限公司 | A method and device for saving all exclusive information resources of a specific person |
| CN106156247B (en)* | 2015-04-28 | 2020-09-15 | 中兴通讯股份有限公司 | Image management method and device |
| CN104933102A (en)* | 2015-05-29 | 2015-09-23 | 努比亚技术有限公司 | Picturing storage method and device |
| CN106412213A (en)* | 2015-07-27 | 2017-02-15 | 中兴通讯股份有限公司 | Contact person information processing method and device and mobile terminal |
| CN105205093B (en)* | 2015-07-28 | 2019-04-23 | 小米科技有限责任公司 | Method and device for processing pictures in gallery |
| CN105243098B (en)* | 2015-09-16 | 2018-10-26 | 小米科技有限责任公司 | The clustering method and device of facial image |
| CN105824862A (en)* | 2015-10-20 | 2016-08-03 | 维沃移动通信有限公司 | Image classification method based on electronic equipment and electronic equipment |
| EP3361423B1 (en)* | 2015-10-30 | 2022-12-14 | Morpho, Inc. | Learning system, learning device, learning method, learning program, teacher data creation device, teacher data creation method, teacher data creation program, terminal device, and threshold value changing device |
| CN105426515B (en)* | 2015-12-01 | 2018-12-18 | 小米科技有限责任公司 | video classifying method and device |
| CN105512255A (en)* | 2015-12-01 | 2016-04-20 | 上海斐讯数据通信技术有限公司 | Picture screening method and device and mobile terminal |
| CN105554340A (en)* | 2015-12-09 | 2016-05-04 | 深圳市华德安科技有限公司 | Image processing method and device based on law enforcement recorder |
| CN105574155A (en)* | 2015-12-16 | 2016-05-11 | 广东欧珀移动通信有限公司 | A photo search method and device |
| CN105608425B (en)* | 2015-12-17 | 2019-02-15 | 小米科技有限责任公司 | The method and device of classification storage is carried out to photo |
| CN105653152A (en)* | 2015-12-23 | 2016-06-08 | 北京金山安全软件有限公司 | Picture processing method and device and electronic equipment |
| CN105608189B (en)* | 2015-12-23 | 2019-10-11 | 北京金山安全软件有限公司 | Picture classification method and device and electronic equipment |
| CN106919604A (en)* | 2015-12-25 | 2017-07-04 | 北京奇虎科技有限公司 | Electron album management method and device |
| CN105740379A (en)* | 2016-01-27 | 2016-07-06 | 北京汇图科技有限责任公司 | Photo classification management method and apparatus |
| WO2017128266A1 (en)* | 2016-01-28 | 2017-08-03 | 杨钰 | Method of sorting images and mobile terminal |
| WO2017128264A1 (en)* | 2016-01-28 | 2017-08-03 | 杨钰 | Method of acquiring data relating to using image sorting technology on the basis of facial recognition and mobile terminal |
| WO2017128265A1 (en)* | 2016-01-28 | 2017-08-03 | 杨钰 | Method of notifying information when sorting images and a mobile terminal |
| CN107133629B (en)* | 2016-02-29 | 2020-09-04 | 百度在线网络技术（北京）有限公司 | Picture classification method and device and mobile terminal |
| CN105740850A (en)* | 2016-03-04 | 2016-07-06 | 北京小米移动软件有限公司 | Method and device for classifying photos |
| CN105912590A (en)* | 2016-04-01 | 2016-08-31 | 乐视控股（北京）有限公司 | Classified storage method and device for pictures and mobile terminal |
| CN106407369A (en)* | 2016-09-09 | 2017-02-15 | 华南理工大学 | Photo management method and system based on deep learning face recognition |
| CN106385502B (en)* | 2016-09-19 | 2020-07-17 | 珠海大横琴科技发展有限公司 | Photo arrangement method and mobile terminal |
| CN106446955A (en)* | 2016-09-29 | 2017-02-22 | 宇龙计算机通信科技(深圳)有限公司 | Picture processing method and apparatus |
| CN106528094A (en)* | 2016-10-20 | 2017-03-22 | 惠州Tcl移动通信有限公司 | A similarity-based application icon classifying method and system |
| CN106874918A (en)* | 2017-02-23 | 2017-06-20 | 上海与德信息技术有限公司 | A kind of photo store method and device |
| CN106980658A (en)* | 2017-03-15 | 2017-07-25 | 北京旷视科技有限公司 | Video labeling method and device |
| CN108805148B (en)* | 2017-04-28 | 2022-01-11 | 富士通株式会社 | Method of processing image and apparatus for processing image |
| CN107292749A (en)* | 2017-08-04 | 2017-10-24 | 平安科技（深圳）有限公司 | Car damages sorting technique, system and the readable storage medium storing program for executing of certificate photograph |
| CN107832765A (en)* | 2017-09-13 | 2018-03-23 | 百度在线网络技术（北京）有限公司 | Picture recognition to including word content and picture material |
| WO2019051795A1 (en)* | 2017-09-15 | 2019-03-21 | 广东欧珀移动通信有限公司 | Image processing method and device, terminal, server, and computer-readable storage medium |
| CN107679532B (en)* | 2017-09-15 | 2019-12-03 | Oppo广东移动通信有限公司 | Data transmission method and device, mobile terminal and computer readable storage medium |
| CN107679563A (en)* | 2017-09-15 | 2018-02-09 | 广东欧珀移动通信有限公司 | Image processing method and device, system, computer equipment |
| CN107679561A (en)* | 2017-09-15 | 2018-02-09 | 广东欧珀移动通信有限公司 | Image processing method and device, system, computer equipment |
| CN107679560B (en)* | 2017-09-15 | 2021-07-09 | Oppo广东移动通信有限公司 | Data transmission method, device, mobile terminal and computer-readable storage medium |
| WO2019051801A1 (en)* | 2017-09-15 | 2019-03-21 | 广东欧珀移动通信有限公司 | Image processing method and apparatus, computer device, and non-volatile readable storage medium |
| WO2019051797A1 (en)* | 2017-09-15 | 2019-03-21 | 广东欧珀移动通信有限公司 | Image processing method and apparatus, computer device, and computer-readable storage medium |
| CN107679559B (en)* | 2017-09-15 | 2020-01-10 | Oppo广东移动通信有限公司 | Image processing method, image processing device, computer-readable storage medium and mobile terminal |
| CN107729815B (en)* | 2017-09-15 | 2020-01-14 | Oppo广东移动通信有限公司 | Image processing method, image processing device, mobile terminal and computer readable storage medium |
| CN107729384A (en)* | 2017-09-18 | 2018-02-23 | 维沃移动通信有限公司 | Image ranking method and mobile terminal |
| CN108121762A (en)* | 2017-11-24 | 2018-06-05 | 努比亚技术有限公司 | A kind of image processing method, mobile terminal and computer storage media |
| CN107992822B (en) | 2017-11-30 | 2020-04-10 | Oppo广东移动通信有限公司 | Image processing method and apparatus, computer device, computer-readable storage medium |
| CN107958069B (en)* | 2017-12-05 | 2020-05-26 | Oppo广东移动通信有限公司 | Image processing method and device, electronic equipment and computer readable storage medium |
| CN108304882B (en)* | 2018-02-07 | 2022-03-04 | 腾讯科技（深圳）有限公司 | Image classification method and device, server, user terminal and storage medium |
| CN110489594A (en)* | 2018-05-14 | 2019-11-22 | 北京松果电子有限公司 | Image vision mask method, device, storage medium and equipment |
| CN108830235B (en)* | 2018-06-21 | 2020-11-24 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating information |
| CN109934214A (en)* | 2019-02-22 | 2019-06-25 | 深兰科技（上海）有限公司 | A kind of training of object type, detection method and device |
| CN110598032B (en)* | 2019-09-25 | 2022-06-14 | 京东方艺云(杭州)科技有限公司 | An image label generation method, server and terminal device |
| CN110703972B (en)* | 2019-09-29 | 2021-04-06 | 维沃移动通信有限公司 | File control method and electronic equipment |
| CN110956680A (en)* | 2019-10-28 | 2020-04-03 | 恒大智慧科技有限公司 | Postcard making method and device and storage medium |
| CN110909368B (en)* | 2019-11-07 | 2023-09-05 | 腾讯科技（深圳）有限公司 | Data encryption method, device and computer readable storage medium |
| CN110874420A (en)* | 2019-11-09 | 2020-03-10 | 上海光数信息科技有限公司 | Picture information processing system and method |
| CN111666441A (en)* | 2020-04-24 | 2020-09-15 | 北京旷视科技有限公司 | Method, device and electronic system for determining personnel identity type |
| CN111666262B (en)* | 2020-05-28 | 2021-06-22 | 重庆中联信息产业有限责任公司 | Working method for extracting feature points of massive medical images in network attached storage NAS state |
| CN111857478B (en)* | 2020-07-17 | 2022-02-11 | 北京百度网讯科技有限公司 | An image layout method, device, electronic device and storage medium |
| CN114693957A (en)* | 2020-12-30 | 2022-07-01 | 顺丰科技有限公司 | Package sorting method, device, electronic device and storage medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050271352A1 (en)* | 2002-09-26 | 2005-12-08 | Kouji Yokouchi | Apparatus and program for image classification |
| CN101510205A (en)* | 2009-03-16 | 2009-08-19 | 广州市有福数码科技有限公司 | Method for implementing automatically clustering photographs, apparatus and system |
| CN101894147A (en)* | 2010-06-29 | 2010-11-24 | 深圳桑菲消费通信有限公司 | Electronic photo album clustering management method |
| CN101990667A (en)* | 2008-04-02 | 2011-03-23 | 谷歌公司 | Method and apparatus to incorporate automatic face recognition in digital image collections |
| CN102129451A (en)* | 2011-02-17 | 2011-07-20 | 上海交通大学 | Method for clustering data in image retrieval system |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9075808B2 (en)* | 2007-03-29 | 2015-07-07 | Sony Corporation | Digital photograph content information service |
| US8254684B2 (en)* | 2008-01-02 | 2012-08-28 | Yahoo! Inc. | Method and system for managing digital photos |
| US9639780B2 (en)* | 2008-12-22 | 2017-05-02 | Excalibur Ip, Llc | System and method for improved classification |
| CN102033958B (en)* | 2010-12-28 | 2013-04-17 | Tcl商用信息科技（惠州）股份有限公司 | Photo sort management system and method |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050271352A1 (en)* | 2002-09-26 | 2005-12-08 | Kouji Yokouchi | Apparatus and program for image classification |
| CN101990667A (en)* | 2008-04-02 | 2011-03-23 | 谷歌公司 | Method and apparatus to incorporate automatic face recognition in digital image collections |
| CN101510205A (en)* | 2009-03-16 | 2009-08-19 | 广州市有福数码科技有限公司 | Method for implementing automatically clustering photographs, apparatus and system |
| CN101894147A (en)* | 2010-06-29 | 2010-11-24 | 深圳桑菲消费通信有限公司 | Electronic photo album clustering management method |
| CN102129451A (en)* | 2011-02-17 | 2011-07-20 | 上海交通大学 | Method for clustering data in image retrieval system |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020020226A1 (en)* | 2018-07-27 | 2020-01-30 | 中兴通讯股份有限公司 | Photo classification method, device, computer-readable medium, and system |
| WO2020192736A1 (en)* | 2019-03-26 | 2020-10-01 | 华为技术有限公司 | Object recognition method and device |
| US12314342B2 (en) | 2019-03-26 | 2025-05-27 | Huawei Technologies Co., Ltd. | Object recognition method and apparatus |
| CN109948734A (en)* | 2019-04-02 | 2019-06-28 | 北京旷视科技有限公司 | Image clustering method, device and electronic device |
| WO2022193232A1 (en)* | 2021-03-18 | 2022-09-22 | 京东方科技集团股份有限公司 | Face clustering method and apparatus, classification storage method, medium, and electronic device |
| US12223690B2 (en)* | 2021-03-18 | 2025-02-11 | Boe Technology Group Co., Ltd. | Face clustering method and apparatus, classification storage method, medium and electronic device |
| CN114897888A (en)* | 2022-06-22 | 2022-08-12 | 中国电信股份有限公司 | Image review method, device and system |
| Publication number | Publication date |
|---|---|
| CN103207870A (en) | 2013-07-17 |
| CN103207870B (en) | 2020-06-02 |
| Publication | Publication Date | Title |
|---|---|---|
| CN108073948A (en) | A kind of photo sort management, server, apparatus and system | |
| CN110602554B (en) | Cover image determination method, device and device | |
| CN106716393B (en) | Method and apparatus for identifying and matching objects depicted in images | |
| CN103155477B (en) | Data syn-chronization in DCE | |
| CN102906790B (en) | Image information processing device | |
| US20140293069A1 (en) | Real-time image classification and automated image content curation | |
| JP5524219B2 (en) | Interactive image selection method | |
| US20150103097A1 (en) | Method and Device for Implementing Augmented Reality Application | |
| WO2019127832A1 (en) | Intelligent search method and apparatus, terminal, server, and storage medium | |
| CN105630915A (en) | Method and device for classifying and storing pictures in mobile terminals | |
| CN103995889A (en) | Method and device for classifying pictures | |
| CN105243084A (en) | Photographed image file storage method and system and photographed image file search method and system | |
| CN104850848A (en) | Photo Classification Method and Device | |
| CN103348315B (en) | Content storage management in camera | |
| CN109446946A (en) | A kind of multi-cam real-time detection method based on multithreading | |
| WO2016145844A1 (en) | Picture sorting method and corresponding picture storage and display device | |
| WO2017067485A1 (en) | Picture management method and device, and terminal | |
| CN105159959A (en) | Image file processing method and system | |
| CN108563651A (en) | A kind of Target Searching Method, device and the equipment of more videos | |
| JP2006079458A (en) | Image transmission system, method, and program | |
| JP2006236218A (en) | Electronic album display system, electronic album display method, and electronic album display program | |
| CN107666573A (en) | The method for recording of object video and device, computing device under camera scene | |
| CN105843827A (en) | Picture classification method and device for mobile terminal | |
| KR100827845B1 (en) | Apparatus and method for providing people tag | |
| CN105592221A (en) | Multimedia-sending method and communication terminal |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20180525 |