CN111340691A - Image processing method, device, electronic device and storage medium - Google Patents
Image processing method, device, electronic device and storage mediumDownload PDFInfo
- Publication number
- CN111340691A CN111340691ACN202010229712.6ACN202010229712ACN111340691ACN 111340691 ACN111340691 ACN 111340691ACN 202010229712 ACN202010229712 ACN 202010229712ACN 111340691 ACN111340691 ACN 111340691A
- Authority
- CN
- China
- Prior art keywords
- image
- displayed
- area
- target
- target object
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/18—Image warping, e.g. rearranging pixels individually
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本公开涉及图像处理技术，尤其涉及一种图像处理方法、装置、电子设备及存储介质。The present disclosure relates to image processing technologies, and in particular, to an image processing method, apparatus, electronic device, and storage medium.
背景技术Background technique
随着图像处理技术的发展，出现了对图像进行液化变形处理的技术，该技术可以将待处理图像当中包含的如脸部、手臂等目标对象进行液化变形处理，以达到对图像的目标对象进行优化显示的效果。With the development of image processing technology, the technology of liquefying and deforming images has appeared. This technology can perform liquefaction and deformation processing on target objects such as faces and arms contained in the images to be processed, so as to achieve the target object of the image. Optimize the display effect.
相关技术中，对图像中的如人脸等目标对象进行液化变形处理后，通常会将液化变形处理得到的图像直接显示在终端的显示界面上，然而这种技术会导致在显示界面的边缘位置处显示出拉伸变形的条纹，降低了对目标对象的液化变形处理效果，存在图像显示效果差的问题。In the related art, after liquefying and deforming target objects such as faces in the image, the image obtained by the liquefaction and deformation process is usually displayed directly on the display interface of the terminal. There are stretched and deformed stripes at the place, which reduces the liquefaction deformation processing effect on the target object, and there is a problem that the image display effect is poor.
发明内容SUMMARY OF THE INVENTION
本公开提供一种图像处理方法、装置、电子设备及存储介质，以至少解决相关技术中存在的图像显示效果差的问题。本公开的技术方案如下：The present disclosure provides an image processing method, apparatus, electronic device and storage medium, so as to at least solve the problem of poor image display effect existing in the related art. The technical solutions of the present disclosure are as follows:
根据本公开实施例的第一方面，提供一种图像处理方法，包括：According to a first aspect of the embodiments of the present disclosure, an image processing method is provided, including:
获取对原始图像中的目标对象进行液化变形处理后得到的待显示图像；Obtaining an image to be displayed obtained by liquefying and deforming the target object in the original image;
当识别到所述目标对象被所述待显示图像的图像边缘切割时，确定目标图像区域；其中，所述目标图像区域包括所述待显示图像的，除异常变形区域之外的图像区域；所述异常变形区域为所述目标对象被所述待显示图像的图像边缘切割时所产生的；When it is recognized that the target object is cut by the image edge of the image to be displayed, a target image area is determined; wherein, the target image area includes the image area of the to-be-displayed image except the abnormally deformed area; the The abnormal deformation area is generated when the target object is cut by the image edge of the to-be-displayed image;
将与所述目标图像区域对应的图像进行显示。An image corresponding to the target image area is displayed.
在一示例性实施例中，所述确定目标图像区域之前，还包括：当所述目标对象对应的至少一个标准关键点位于所述待显示图像之外时，识别所述目标对象被所述图像边缘切割。In an exemplary embodiment, before determining the target image area, the method further includes: when at least one standard key point corresponding to the target object is located outside the to-be-displayed image, recognizing that the target object is covered by the image. Edge cut.
在一示例性实施例中，所述当所述目标对象对应的至少一个标准关键点位于所述待显示图像之外时，识别所述目标对象被所述图像边缘切割之前，还包括：基于所述目标对象的标准对象模型，确定所述目标对象对应的标准关键点集；获取所述待显示图像上，对应于所述标准关键点集中各标准关键点的位置信息；根据所述位置信息，识别所述各标准关键点是否位于所述待显示图像内。In an exemplary embodiment, when the at least one standard key point corresponding to the target object is located outside the to-be-displayed image, recognizing that the target object is cut by the edge of the image further includes: based on the The standard object model of the target object is determined, and the standard key point set corresponding to the target object is determined; the position information corresponding to each standard key point in the standard key point set on the to-be-displayed image is obtained; according to the position information, Identify whether the standard key points are located in the to-be-displayed image.
在一示例性实施例中，所述当识别到所述目标对象被所述待显示图像的图像边缘切割时，确定目标图像区域，包括：获取待显示图像的图像尺寸；放大所述待显示图像，以使放大后的待显示图像中存在与所述图像尺寸相同的且不包括所述异常变形区域的图像区域，作为所述目标图像区域。In an exemplary embodiment, determining the target image area when it is recognized that the target object is cut by an image edge of the image to be displayed includes: acquiring an image size of the image to be displayed; enlarging the image to be displayed , so that an image area that is the same size as the image and does not include the abnormal deformation area exists in the enlarged image to be displayed as the target image area.
在一示例性实施例中，所述将与所述目标图像区域对应的图像进行显示，包括：将所述放大后的待显示图像中，与所述目标图像区域对应的图像进行显示。In an exemplary embodiment, the displaying the image corresponding to the target image area includes: displaying the image corresponding to the target image area in the enlarged image to be displayed.
在一示例性实施例中，所述放大所述待显示图像，包括：获取第一图像放大比例；所述第一图像放大比例，与所述异常变形区域的异常变形程度呈正相关关系；基于所述第一图像放大比例，放大所述待显示图像。In an exemplary embodiment, the enlarging the image to be displayed includes: acquiring a first image enlargement ratio; the first image enlargement ratio has a positive correlation with the abnormal deformation degree of the abnormal deformation area; The first image enlargement ratio is used to enlarge the to-be-displayed image.
在一示例性实施例中，所述异常变形程度，与所述目标对象的液化变形等级和/或所述目标对象的被切割程度，呈正相关关系；其中，所述目标对象的被切割程度，为所述目标对象被所述待显示图像的图像边缘切割的程度。In an exemplary embodiment, the abnormal deformation degree is positively correlated with the liquefaction deformation level of the target object and/or the cutting degree of the target object; wherein, the cutting degree of the target object, is the degree to which the target object is cut by the image edge of the to-be-displayed image.
在一示例性实施例中，所述目标对象的被切割程度是根据图外关键点占比得到的；其中，所述图外关键点占比为位于所述待显示图像之外的标准关键点的数量，与所述目标对象对应的标准关键点集所包含的标准关键点的总数之间的比值。In an exemplary embodiment, the cut degree of the target object is obtained according to the ratio of key points outside the figure; wherein, the ratio of key points outside the figure is a standard key point located outside the to-be-displayed image. , the ratio between the total number of standard key points included in the standard key point set corresponding to the target object.
在一示例性实施例中，所述基于所述第一图像放大比例，放大所述待显示图像，包括：当所述第一图像放大比例大于设定的第一比例阈值时，按照所述第一比例阈值放大所述待显示图像。In an exemplary embodiment, the enlarging the to-be-displayed image based on the first image enlargement ratio includes: when the first image enlargement ratio is greater than a set first ratio threshold, according to the first image enlargement ratio A proportional threshold magnifies the to-be-displayed image.
在一示例性实施例中，所述将与所述目标图像区域对应的图像进行显示，包括：将所述待显示图像中，与所述目标图像区域对应的图像进行放大后显示。In an exemplary embodiment, the displaying the image corresponding to the target image area includes: in the to-be-displayed image, the image corresponding to the target image area is enlarged and displayed.
在一示例性实施例中，所述将所述待显示图像中，与所述目标图像区域对应的图像进行放大后显示，包括：获取第二图像放大比例；所述第二图像放大比例，与所述异常变形区域的异常变形程度呈正相关关系；当所述第二图像放大比例大于设定的第二比例阈值时，按照所述第二比例阈值，将所述待显示图像中，与所述目标图像区域对应的图像进行放大后显示。In an exemplary embodiment, the displaying after enlarging the image corresponding to the target image area in the image to be displayed includes: acquiring a second image enlargement ratio; the second image enlargement ratio is the same as The abnormal deformation degree of the abnormal deformation area is positively correlated; when the magnification ratio of the second image is greater than the set second ratio threshold, according to the second ratio threshold, the to-be-displayed image is compared with the The image corresponding to the target image area is enlarged and displayed.
根据本公开实施例的第二方面，提供一种图像处理装置，包括：According to a second aspect of the embodiments of the present disclosure, there is provided an image processing apparatus, including:
图像获取模块，被配置为执行获取对原始图像中的目标对象进行液化变形处理后得到的待显示图像；an image acquisition module, configured to perform acquisition of the to-be-displayed image obtained by liquefying and deforming the target object in the original image;
区域确定模块，被配置为执行当识别到所述目标对象被所述待显示图像的图像边缘切割时，确定目标图像区域；其中，所述目标图像区域包括所述待显示图像的，除异常变形区域之外的图像区域；所述异常变形区域为所述目标对象被所述待显示图像的图像边缘切割时所产生的；an area determination module configured to determine a target image area when it is recognized that the target object is cut by an image edge of the to-be-displayed image; wherein, the target image area includes the to-be-displayed image, except for abnormal deformation The image area outside the area; the abnormal deformation area is generated when the target object is cut by the image edge of the to-be-displayed image;
图像显示模块，被配置为执行将与所述目标图像区域对应的图像进行显示。The image display module is configured to display the image corresponding to the target image area.
在一示例性实施例中，图像处理装置，还包括：In an exemplary embodiment, the image processing apparatus further includes:
切割识别模块，被配置为执行当所述目标对象对应的至少一个标准关键点位于所述待显示图像之外时，识别所述目标对象被所述图像边缘切割。A cutting recognition module configured to perform, when at least one standard key point corresponding to the target object is located outside the to-be-displayed image, recognize that the target object is cut by the edge of the image.
在一示例性实施例中，图像处理装置，还包括：In an exemplary embodiment, the image processing apparatus further includes:
关键点识别模块，被配置为执行基于所述目标对象的标准对象模型，确定所述目标对象对应的标准关键点集；获取所述待显示图像上，对应于所述标准关键点集中各标准关键点的位置信息；根据所述位置信息，识别所述各标准关键点是否位于所述待显示图像内。The key point identification module is configured to execute a standard object model based on the target object, and determine the standard key point set corresponding to the target object; acquire the image to be displayed, corresponding to each standard key point set in the standard key point set position information of the point; according to the position information, identify whether the standard key points are located in the to-be-displayed image.
在一示例性实施例中，所述区域确定模块，进一步被配置为执行获取待显示图像的图像尺寸；放大所述待显示图像，以使放大后的待显示图像中存在与所述图像尺寸相同的且不包括所述异常变形区域的图像区域，作为所述目标图像区域。In an exemplary embodiment, the area determination module is further configured to perform acquiring the image size of the image to be displayed; and enlarging the image to be displayed, so that the enlarged image to be displayed has the same size as the image. The image area that does not include the abnormal deformation area is used as the target image area.
在一示例性实施例中，所述图像显示模块，被配置为执行将所述放大后的待显示图像中，与所述目标图像区域对应的图像进行显示。In an exemplary embodiment, the image display module is configured to display an image corresponding to the target image area in the enlarged image to be displayed.
在一示例性实施例中，所述区域确定模块，进一步被配置为执行获取第一图像放大比例；所述第一图像放大比例，与所述异常变形区域的异常变形程度呈正相关关系；基于所述第一图像放大比例，放大所述待显示图像。In an exemplary embodiment, the region determination module is further configured to perform acquiring a first image magnification ratio; the first image magnification ratio is positively correlated with the abnormal deformation degree of the abnormal deformation region; The first image enlargement ratio is used to enlarge the to-be-displayed image.
在一示例性实施例中，所述异常变形程度，与所述目标对象的液化变形等级和/或所述目标对象的被切割程度，呈正相关关系；其中，所述目标对象的被切割程度，为所述目标对象被所述待显示图像的图像边缘切割的程度。In an exemplary embodiment, the abnormal deformation degree is positively correlated with the liquefaction deformation level of the target object and/or the cutting degree of the target object; wherein, the cutting degree of the target object, is the degree to which the target object is cut by the image edge of the to-be-displayed image.
在一示例性实施例中，所述目标对象的被切割程度是根据图外关键点占比得到的；其中，所述图外关键点占比为位于所述待显示图像之外的标准关键点的数量，与所述目标对象对应的标准关键点集所包含的标准关键点的总数之间的比值。In an exemplary embodiment, the cut degree of the target object is obtained according to the ratio of key points outside the figure; wherein, the ratio of key points outside the figure is a standard key point located outside the to-be-displayed image. , the ratio between the total number of standard key points included in the standard key point set corresponding to the target object.
在一示例性实施例中，所述区域确定模块，进一步被配置为执行当所述第一图像放大比例大于设定的第一比例阈值时，按照所述第一比例阈值放大所述待显示图像。In an exemplary embodiment, the region determination module is further configured to perform, when the first image enlargement ratio is greater than a set first ratio threshold, enlarge the to-be-displayed image according to the first ratio threshold .
在一示例性实施例中，所述图像显示模块，进一步被配置为执行将所述待显示图像中，与所述目标图像区域对应的图像进行放大后显示。In an exemplary embodiment, the image display module is further configured to perform an enlarged display of an image corresponding to the target image area in the to-be-displayed image.
在一示例性实施例中，所述图像显示模块，进一步被配置为执行获取第二图像放大比例；所述第二图像放大比例，与所述异常变形区域的异常变形程度呈正相关关系；当所述第二图像放大比例大于设定的第二比例阈值时，按照所述第二比例阈值，将所述待显示图像中，与所述目标图像区域对应的图像进行放大后显示。In an exemplary embodiment, the image display module is further configured to obtain a second image magnification ratio; the second image magnification ratio is positively correlated with the abnormal deformation degree of the abnormal deformation area; When the enlargement ratio of the second image is greater than the set second ratio threshold, the image corresponding to the target image area in the to-be-displayed image is enlarged and displayed according to the second ratio threshold.
根据本公开实施例的第三方面，提供一种电子设备，包括：处理器；用于存储所述处理器可执行指令的存储器；其中，所述处理器被配置为执行所述指令，以实现如上所述的图像处理方法。According to a third aspect of embodiments of the present disclosure, there is provided an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to achieve Image processing method as described above.
根据本公开实施例的第四方面，提供一种存储介质，当所述存储介质中的指令由电子设备的处理器执行时，使得电子设备能够执行如上所述的图像处理方法。According to a fourth aspect of the embodiments of the present disclosure, a storage medium is provided, when instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute the image processing method as described above.
根据本公开实施例的第五方面，提供一种计算机程序产品，所述程序产品包括计算机程序，所述计算机程序存储在可读存储介质中，设备的至少一个处理器从所述可读存储介质读取并执行所述计算机程序，使得设备执行第一方面的任一项实施例中所述的图像处理方法。According to a fifth aspect of the embodiments of the present disclosure, there is provided a computer program product, the program product comprising a computer program, the computer program being stored in a readable storage medium, and at least one processor of a device from the readable storage medium The computer program is read and executed, so that the device executes the image processing method described in any one of the embodiments of the first aspect.
本公开的实施例提供的技术方案至少带来以下有益效果：The technical solutions provided by the embodiments of the present disclosure bring at least the following beneficial effects:
获取对原始图像中的目标对象进行液化变形处理后得到的待显示图像后，可识别出目标对象是否被待显示图像的图像边缘切割，当目标对象被图像边缘切割时，可将该待显示图像的，除异常变形区域之外的图像区域确定为目标图像区域，该异常变形区域为目标对象被待显示图像的图像边缘切割时所产生的，然后可以将与目标图像区域的对应的图像显示在终端的显示界面上。本公开的技术方案，能够在目标对象被图像边缘切割时，可先自适应地从待显示图像中确定出不包含异常变形区域的目标显示区域，再将该目标显示区域所对应的图像显示在终端的显示界面上，由此可以避免在显示界面的边缘位置处显示具有拉伸条纹的图像，优化图像显示效果。After acquiring the to-be-displayed image obtained by liquefying and deforming the target object in the original image, it can be identified whether the target object is cut by the image edge of the to-be-displayed image, and when the target object is cut by the image edge, the to-be-displayed image can be , the image area other than the abnormally deformed area is determined as the target image area, and the abnormally deformed area is generated when the target object is cut by the image edge of the image to be displayed, and then the image corresponding to the target image area can be displayed in the on the display interface of the terminal. According to the technical solution of the present disclosure, when the target object is cut by the edge of the image, the target display area that does not contain the abnormal deformation area can be adaptively determined from the to-be-displayed image, and then the image corresponding to the target display area can be displayed on the On the display interface of the terminal, an image with stretched stripes can be avoided to be displayed at the edge position of the display interface, and the image display effect is optimized.
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.
附图说明Description of drawings
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理，并不构成对本公开的不当限定。The accompanying drawings, which are incorporated into and constitute a part of this specification, illustrate embodiments consistent with the present disclosure, and together with the description, serve to explain the principles of the present disclosure and do not unduly limit the present disclosure.
图1是根据一示例性实施例示出的一种图像处理方法的应用环境图。FIG. 1 is an application environment diagram of an image processing method according to an exemplary embodiment.
图2是根据一示例性实施例示出的一种图像处理方法的流程图。Fig. 2 is a flowchart of an image processing method according to an exemplary embodiment.
图3是根据一示例性实施例示出的一种图像处理方法的原理图。Fig. 3 is a schematic diagram of an image processing method according to an exemplary embodiment.
图4是根据一示例性实施例示出的识别标准关键点是否在图像内的方法的流程图。FIG. 4 is a flowchart illustrating a method for identifying whether a standard key point is in an image according to an exemplary embodiment.
图5是根据一示例性实施例示出的标准关键点的示意图。FIG. 5 is a schematic diagram of standard key points according to an exemplary embodiment.
图6是根据一示例性实施例示出的标准关键点的示意图。FIG. 6 is a schematic diagram of standard key points according to an exemplary embodiment.
图7是根据一示例性实施例示出的一种处理图像的方法的示意图。Fig. 7 is a schematic diagram showing a method for processing an image according to an exemplary embodiment.
图8是根据一示例性实施例示出的另一种处理图像的方法的示意图。FIG. 8 is a schematic diagram illustrating another method for processing an image according to an exemplary embodiment.
图9是根据一示例性实施例示出的一种图像处理方法的流程图。Fig. 9 is a flowchart of an image processing method according to an exemplary embodiment.
图10是根据一示例性实施例示出的图像处理方法的一种应用场景图。Fig. 10 is a diagram showing an application scenario of the image processing method according to an exemplary embodiment.
图11是根据一示例性实施例示出的图像处理方法的另一种应用场景图。Fig. 11 is a diagram showing another application scenario of the image processing method according to an exemplary embodiment.
图12是根据一示例性实施例示出的一种图像处理装置的框图。Fig. 12 is a block diagram of an image processing apparatus according to an exemplary embodiment.
图13是根据一示例性实施例示出的一种电子设备的内部结构图。Fig. 13 is an internal structure diagram of an electronic device according to an exemplary embodiment.
具体实施方式Detailed ways
为了使本领域普通人员更好地理解本公开的技术方案，下面将结合附图，对本公开实施例中的技术方案进行清楚、完整地描述。In order to make those skilled in the art better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
需要说明的是，本公开的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本公开的实施例能够以除了在这里图示或描述的那些以外的顺序实施。以下示例性实施例中所描述的实施方式并不代表与本公开相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本公开的一些方面相一致的装置和方法的例子。It should be noted that the terms "first", "second" and the like in the description and claims of the present disclosure and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence. It is to be understood that the data so used may be interchanged under appropriate circumstances such that the embodiments of the disclosure described herein can be practiced in sequences other than those illustrated or described herein. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with this disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as recited in the appended claims.
本公开所提供的图像处理方法，可以应用于如图1所示的应用环境中，图1是根据一示例性实施例示出的一种图像处理方法的应用环境图，该应用环境中可以包括终端100，该终端100可以但不限于是各种个人计算机、笔记本电脑、智能手机、平板电脑和便携式可穿戴设备。The image processing method provided by the present disclosure can be applied to the application environment shown in FIG. 1 . FIG. 1 is an application environment diagram of an image processing method according to an exemplary embodiment, and the application environment may include a terminal 100, the terminal 100 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices.
终端100可以通过其上配置的摄像头采集的用户10的图像，基于该图像对用户10的脸部11进行液化变形处理，例如可以以采集的图像中的人脸关键点为基础，对用户10的脸部11对应的图像进行液化瘦脸处理，以使得终端100在屏幕的显示界面110上展示出经过美颜瘦脸的图像。The terminal 100 may collect the image of the
具体的，终端100采集用户10的原始图像111，并对该原始图像111进行液化变形处理，如箭头110所指示的虚线框示意出终端100对原始图像111的图像处理过程，该过程可以由终端100上安装的具有美颜功能的应用程序来完成。其中，终端100所采集的图像111当中，可以包括用户10的人脸对应的人脸图像12，在此可将人脸图像12作为目标对象，可以理解，如果需要对用户10的其他部位如手臂、眼睛等进行液化处理，则可以相应地将手臂、眼睛作为目标对象。然后，终端100可以利用具有美颜功能的应用程序对原始图像111中的人脸图像12进行液化变形处理，此处的液化变形处理具体是液化瘦脸处理，从而可以得到液化瘦脸图像112，该液化瘦脸图像112当中包括用户10的人脸对应的液化瘦脸后的人脸图像13。接着，终端100可以将液化瘦脸图像112展示在显示界面110上，以使用户10能够在该显示界面110上看到液化瘦脸后的人脸图像14。Specifically, the terminal 100 collects the original image 111 of the
如上为终端100对如人脸等目标对象进行液化变形处理的基本过程，本公开的技术方案，在对原始图像中的目标对象进行液化变形处理后，先不直接将该液化变形处理后得到的待显示图像进行显示，而可以先识别该目标对象是否被待显示图像的图像边缘切割，如果识别到目标对象被待显示图像的图像边缘切割，则确定出目标图像区域；其中，该目标图像区域可以包括待显示图像的，除异常变形区域之外的图像区域，而该异常变形区域是指目标对象被待显示图像的图像边缘切割时所产生的异常变形区域。在确定目标图像区域后，终端100再将与目标图像区域对应的图像在显示界面110上进行展示。此外，如果识别出目标对象没有被待显示图像的图像边缘切割，则终端100可以将该待显示图像展示在显示界面110上。基于此可以避免在显示界面110的边缘位置处显示具有拉伸条纹的图像，优化图像显示效果。The above is the basic process for the terminal 100 to perform liquefaction deformation processing on a target object such as a human face. In the technical solution of the present disclosure, after liquefaction deformation processing is performed on the target object in the original image, it is not directly obtained after the liquefaction deformation processing. The image to be displayed is displayed, and it can be first identified whether the target object is cut by the image edge of the image to be displayed, and if it is identified that the target object is cut by the image edge of the image to be displayed, the target image area is determined; wherein, the target image area It can include the image area to be displayed except the abnormal deformation area, and the abnormal deformation area refers to the abnormal deformation area generated when the target object is cut by the image edge of the image to be displayed. After determining the target image area, the terminal 100 displays the image corresponding to the target image area on the
图2是根据一示例性实施例示出的一种图像处理方法的流程图，如图2所示，图像处理方法可应用于如图1所示的终端100中，该图像处理方法可以包括以下步骤：Fig. 2 is a flowchart showing an image processing method according to an exemplary embodiment. As shown in Fig. 2, the image processing method can be applied to the terminal 100 shown in Fig. 1, and the image processing method can include the following steps :
步骤S201，获取对原始图像中的目标对象进行液化变形处理后得到的待显示图像。Step S201 , acquiring an image to be displayed obtained by performing liquefaction deformation processing on the target object in the original image.
本步骤中，原始图像可以是需要由终端100进行液化处理的图像，该原始图像中可以包含有液化处理对象，该液化处理对象称为目标对象。其中，该原始图像可以是终端100其上配置的摄像头实时采集的图像，也可以是电子相册当中存储的图像。而该原始图像可以是单独一张图像，也可以是多帧视频图像。对于多帧视频图像，终端100可以依次将视频中的每一帧图像作为原始图像，并对其包含的目标对象进行液化变形处理。示例性的，该原始图像可以是包含用户的人脸的图像，而该目标对象可以是该用户的脸部。In this step, the original image may be an image that needs to be liquefied by the terminal 100, and the original image may contain a liquefaction process object, and the liquefaction process object is called a target object. The original image may be an image captured in real time by a camera configured on the terminal 100, or may be an image stored in an electronic album. The original image may be a single image or multiple frames of video images. For multiple frames of video images, the terminal 100 may sequentially regard each frame of images in the video as an original image, and perform liquefaction and deformation processing on the target objects contained in the images. Exemplarily, the original image may be an image containing the user's face, and the target object may be the user's face.
终端100可以对原始图像进行液化变形处理，并将液化变形处理后得到的图像作为待显示图像。示例性的，终端100可以对原始图像111中的人脸图像12进行液化变形处理，得到具有液化瘦脸图像112，该液化瘦脸图像112当中包括用户10的人脸11对应的液化瘦脸后的人脸图像13，对用户10的人脸11对应的图像具有液化瘦脸效果，而终端100可以将该液化瘦脸图像112作为待显示图像。The terminal 100 may perform liquefaction deformation processing on the original image, and use the image obtained after the liquefaction deformation process as the image to be displayed. Exemplarily, the terminal 100 may perform liquefaction and deformation processing on the
步骤S202，当识别到目标对象被待显示图像的图像边缘切割时，确定目标图像区域。Step S202, when it is recognized that the target object is cut by the image edge of the image to be displayed, determine the target image area.
本步骤中，终端100在将待显示图像在其显示界面上进行显示之前，需要先判断该目标对象是否被待显示图像的图像边缘切割。以人脸作为目标对象为例，如图1和图3所示，首先参考图1，在图1当中，人脸被完整地拍摄并显示在待显示图像之内，终端100可判断该目标对象没有被待显示图像的图像边缘切割。而在图3当中，终端100对原始图像310的人脸图像31进行液化变形处理后得到待显示图像320，在将待显示图像320进行显示之前，终端100可判断该目标对象即人脸图像32被待显示图像320的图像边缘切割，如示意框3100示出了人脸被图像边缘切割的部分，该被切割的部分没有在待显示图像当中进行显示，而在液化变形处理的过程当中，由于目标对象位于图像的边缘位置，在对目标对象进行液化变形处理时，由于图像边缘像素信息较少，而图像边缘的像素被拉伸到图像中间以后，图像边缘的像素没有更边缘的信息可以填充过来，此时就会出现空白并且被拉伸出条纹，即当目标图像被图像边缘切割时，图像边缘液化完之后会在图像边缘位置出现条纹的拉伸，该出现条纹拉伸的区域称为异常变形区域，该异常变形区域是该目标对象被图像边缘切割时产生的，如图3所示，人脸图像32被待显示图像320的图像边缘切割时，在待显示图像320的图像边缘会产生异常变形区域3200，而如果直接将该待显示图像320在终端100的显示界面上进行显示，则用户会发现显示图像上的人脸靠近图像边缘位置处会有拉伸变形的条纹，使得用户的美颜效果露怯，特别是当液化半径比较大，瘦脸力度比较大的时候，拉伸纹路会更加明显，从而降低图像显示效果。In this step, before the terminal 100 displays the to-be-displayed image on its display interface, it needs to first determine whether the target object is cut by the image edge of the to-be-displayed image. Taking the human face as the target object as an example, as shown in FIG. 1 and FIG. 3 , referring to FIG. 1 first, in FIG. 1 , the human face is completely photographed and displayed in the image to be displayed, and the terminal 100 can determine the target object Not cut by the image edges of the image to be displayed. In FIG. 3 , the terminal 100 performs liquefaction and deformation processing on the face image 31 of the
基于此，终端100在识别到目标对象被待显示图像的图像边缘切割时，需要确定出目标图像区域，该目标图像区域可以包括待显示图像的，除异常变形区域之外的图像区域。参考图3，在终端100确定目标图像区域的过程中，可以将待显示图像320中，除异常变形区域3200所在的边缘图像区域322以外的图像区域作为目标图像区域321，使得该目标图像区域321中不包含异常变形区域3200。Based on this, when the terminal 100 recognizes that the target object is cut by the image edge of the image to be displayed, it needs to determine the target image area, and the target image area may include the image area to be displayed except the abnormal deformation area. Referring to FIG. 3 , in the process of determining the target image area by the terminal 100, an image area other than the
步骤S203，将与目标图像区域对应的图像进行显示。Step S203, displaying the image corresponding to the target image area.
如图3所示，终端100可以将不包含异常变形区域3200的目标图像区域321，在待显示图像320中对应的图像330显示在该终端100的显示界面上，以使得在该显示界面上展示的图像中，即使被液化处理的目标对象被图像边缘切割，也不会在该图像边缘处显示出被拉伸的条纹，提高图像显示效果，而具体到对人脸进行美颜而言，终端100不会在显示界面上显示出脸部皮肤被拉伸出条纹，具有更好的人脸美颜效果，优化用户体验。As shown in FIG. 3 , the terminal 100 may display the
上述图像处理方法中，获取对原始图像中的目标对象进行液化变形处理后得到的待显示图像后，可识别出目标对象是否被待显示图像的图像边缘切割，当目标对象被图像边缘切割时，可将该待显示图像的，除异常变形区域之外的图像区域确定为目标图像区域，该异常变形区域为目标对象被待显示图像的图像边缘切割时所产生的，然后可以将与目标图像区域的对应的图像显示在终端的显示界面上。该技术方案能够在目标对象被图像边缘切割时，可先自适应地从待显示图像中确定出不包含异常变形区域的目标显示区域，再将该目标显示区域所对应的图像显示在终端的显示界面上，由此可以避免在显示界面的边缘位置处显示具有拉伸条纹的图像，优化图像显示效果。In the above-mentioned image processing method, after obtaining the to-be-displayed image obtained by liquefying and deforming the target object in the original image, it can be identified whether the target object is cut by the image edge of the to-be-displayed image, and when the target object is cut by the image edge, The image area of the image to be displayed except the abnormal deformation area can be determined as the target image area, and the abnormal deformation area is generated when the target object is cut by the image edge of the image to be displayed, and then it can be combined with the target image area. The corresponding image is displayed on the display interface of the terminal. According to the technical solution, when the target object is cut by the edge of the image, the target display area that does not contain the abnormal deformation area can be adaptively determined from the image to be displayed, and then the image corresponding to the target display area can be displayed on the display of the terminal. On the interface, the image with stretched stripes can be avoided to be displayed at the edge position of the display interface, and the image display effect can be optimized.
在一示例性实施例中，可以根据目标对象对应的标准关键点是否均位于待显示图像内来识别目标对象是否被图像边缘所切割。如图4所示，可以在确定目标图像区域之前，通过如下步骤判断标准关键点是否均位于待显示图像当中，具体步骤包括：In an exemplary embodiment, whether the target object is cut by the edge of the image may be identified according to whether the standard key points corresponding to the target object are all located in the image to be displayed. As shown in FIG. 4 , before determining the target image area, the following steps can be used to determine whether the standard key points are all located in the image to be displayed. The specific steps include:
步骤S401，基于目标对象的标准对象模型，确定目标对象对应的标准关键点集。Step S401 , based on the standard object model of the target object, determine a standard key point set corresponding to the target object.
其中，各目标对象可分别对应至少一种标准对象模型，标准对象模型可以包括相应目标对象的标准关键点集，而标准对象模型可通过标准关键点集对目标对象上的各标准关键点进行标记，还可进一步为各标准关键点设置相应的序号。以人脸作为目标对象为例，目标移动端拍摄或者直播的美颜瘦脸，通常是基于人脸的标准关键点进行液化变形处理，终端100可以先针对视频或者直播取帧，通过标准人脸模型对每帧图像进行人脸的标准关键点的识别标记，对标准关键点所在图像区域进行液化变形以达到瘦脸、大眼、小脸或瘦下巴等美颜美型的效果，如图5所示，液化变形前人脸图像51和液化变形后人脸图像52的标准关键点是一一对应的，如液化变形前人脸图像51的标准关键点K1对应液化变形后人脸图像52的标准关键点K2，在液化变形处理过程中，终端100可以通过对液化变形前人脸图像51的标准关键点K1的位置进行移动，得到液化变形后人脸图像52的标准关键点K2。本步骤中，终端100可以预先获取标准对象模型，根据该标准对象模型确定出该目标对象所对应的标准关键点集。Wherein, each target object may correspond to at least one standard object model, the standard object model may include a standard key point set of the corresponding target object, and the standard object model may mark each standard key point on the target object through the standard key point set , you can further set the corresponding serial number for each standard key point. Taking the face as the target object as an example, the beauty and face-lifting that is captured by the target mobile terminal or live broadcast is usually liquefied and deformed based on the standard key points of the face. The standard key points of the face are identified and marked for each frame of image, and the image area where the standard key points are located is liquefied and deformed to achieve the effect of face reduction, big eyes, small face or chin, as shown in Figure 5. , the standard key points of the
步骤S402，获取待显示图像上，对应于标准关键点集中各标准关键点的位置信息。In step S402, the position information corresponding to each standard key point in the standard key point set on the image to be displayed is acquired.
本步骤，终端100可以根据标准关键点集，在待显示图像上确定出标准关键点集中的各标准关键点，在该待显示图像上的位置信息，例如各标准关键点在该待显示图像上对应的像素坐标。In this step, the terminal 100 may determine each standard key point in the standard key point set on the image to be displayed according to the standard key point set, and the position information on the to-be-displayed image, for example, each standard key point on the to-be-displayed image the corresponding pixel coordinates.
步骤S403，根据位置信息，识别各标准关键点是否位于待显示图像内。Step S403, according to the location information, identify whether each standard key point is located in the image to be displayed.
其中，目标对象所对应的标准关键点集中的各标准关键点并不一定都位于该待显示图像当中，而终端100可以通过步骤S402所得到的各标准关键点的位置信息，识别该目标对象的各标准关键点是否位于该待显示图像内，一般而言，如果能获取到某个标准关键点在该待显示图像上的位置信息，则可以认为该标准关键点位于该待显示图像内，而如果无法获取到某个标准关键点的位置信息，则可以判断该标准关键点不在该待显示图像内。Wherein, each standard key point in the standard key point set corresponding to the target object is not necessarily located in the to-be-displayed image, and the terminal 100 can identify the target object through the position information of each standard key point obtained in step S402. Whether each standard key point is located in the to-be-displayed image, generally speaking, if the position information of a certain standard key point on the to-be-displayed image can be obtained, it can be considered that the standard key point is located in the to-be-displayed image, and If the position information of a certain standard key point cannot be obtained, it can be determined that the standard key point is not in the to-be-displayed image.
上述实施例，可以基于对图像的目标对象进行液化变形的原理，根据标准关键点在的位置信息识别各标准关键点是否位于待显示图像之内，而标准关键点的数量通常比较少，因此终端100可快速地识别出目标对象所对应的各标准关键点是否位于待显示图像内，提高图像处理效率。In the above embodiment, based on the principle of liquefying and deforming the target object of the image, whether each standard key point is located in the to-be-displayed image can be identified according to the position information of the standard key point, and the number of standard key points is usually relatively small, so the terminal 100 can quickly identify whether each standard key point corresponding to the target object is located in the to-be-displayed image, thereby improving image processing efficiency.
进一步的，在一示例性实施例当中，当目标对象对应的至少一个标准关键点位于待显示图像之外时，终端100可识别该目标对象被图像边缘切割。具体的，以人脸作为目标对象为例进行说明，如图6所示，人脸图像62对应多个标准关键点，图外关键点示意框620示出的是该人脸图像62对应三个标准关键点位于待显示图像620之外，从而终端100可以判断人脸图像62被该待显示图像620的图像边缘切割，当一个标准关键点位于待显示图像之外时，终端100即可快速地判断出目标对象被图像边缘进行切割，而对该被边缘切割的目标对象进行液化处理后，产生了影响目标对象液化处理效果的拉伸条纹等异常变形区域，一般而言，位于待显示图像之外的标准关键点的数量越多，对目标对象液化处理效果的影响越大，例如表现为图像边缘位置处的拉伸条纹越长，由此本实施例可根据位于待显示图像之外的标准关键点的数量快速判断目标对象是否被图像边缘切割，还可以进一步根据该位于待显示图像之外的标准关键点的数量及时在待显示图像上确定出合适的目标图像区域，提高图像处理效率和图像显示效果。Further, in an exemplary embodiment, when at least one standard key point corresponding to the target object is located outside the to-be-displayed image, the terminal 100 may recognize that the target object is cut by the edge of the image. Specifically, taking the face as the target object for illustration, as shown in FIG. 6 , the
在一示例性实施例中，步骤S202中的当识别到目标对象被待显示图像的图像边缘切割时，确定目标图像区域，具体可以通过如下步骤实现：In an exemplary embodiment, in step S202, when it is recognized that the target object is cut by the image edge of the image to be displayed, the target image area is determined, which can be specifically implemented by the following steps:
获取待显示图像的图像尺寸；放大待显示图像，以使放大后的待显示图像中存在与图像尺寸相同的且不包括异常变形区域的图像区域，作为目标图像区域。The image size of the image to be displayed is acquired; the image to be displayed is enlarged, so that an image area with the same size as the image and excluding abnormal deformation area exists in the enlarged image to be displayed as the target image area.
本实施例中，终端100在确定目标图像区域的过程中，可以先将待显示图像进行放大，从放大的待显示图像中确定出目标图像区域。具体而言，待显示图像具有一定的图像尺寸(简称为原始图像尺寸)，在将待显示图像进行放大时，终端100可以将该待显示图像从其原始图像尺寸开始逐渐放大，随着该待显示图像被逐渐放大，该待显示图像中的各图像区域也被相应放大，当放大后的待显示图像中存在与原始图像尺寸相同，且不包括异常变形区域的图像区域时，将该放大后的待显示图像中存在的与原始图像尺寸相同且不包括异常变形区域的图像区域，确定为目标图像区域。In this embodiment, in the process of determining the target image area, the terminal 100 may first enlarge the image to be displayed, and determine the target image area from the enlarged image to be displayed. Specifically, the to-be-displayed image has a certain image size (referred to as the original image size for short). When enlarging the to-be-displayed image, the terminal 100 may gradually enlarge the to-be-displayed image from its original image size. The displayed image is gradually enlarged, and each image area in the to-be-displayed image is also enlarged accordingly. When there is an image area in the enlarged to-be-displayed image that is the same size as the original image and does not include abnormally deformed areas, the enlarged The image area that exists in the to-be-displayed image with the same size as the original image and does not include abnormal deformation area is determined as the target image area.
通过本实施例所确定的目标图像区域具有至少两个特点，即不包括异常变形区域，并与待显示图像的图像尺寸一致。由此，进一步的，步骤S203中的将与目标图像区域对应的图像进行显示，具体可以包括：The target image area determined by this embodiment has at least two characteristics, that is, it does not include abnormal deformation areas, and is consistent with the image size of the image to be displayed. Therefore, further, displaying the image corresponding to the target image area in step S203 may specifically include:
将放大后的待显示图像中，与目标图像区域对应的图像进行显示。In the enlarged image to be displayed, the image corresponding to the target image area is displayed.
本实施例中，终端100可以在确定出与原始图像尺寸相同且不包括异常变形区域的目标图像区域后，可以将放大后的待显示图像中，与该目标区域对应的图像进行显示，从而使得在终端100上能以待显示图像的图像尺寸显示出目标图像区域对应的图像，避免显示出与待显示图像的图像尺寸不同的图像所带来的图像尺寸突变等问题，进一步优化图像显示效果。In this embodiment, after determining the target image area that is the same size as the original image and does not include the abnormal deformation area, the terminal 100 may display the image corresponding to the target area in the enlarged image to be displayed, so that the The image corresponding to the target image area can be displayed on the terminal 100 with the image size of the image to be displayed, so as to avoid problems such as sudden change in image size caused by displaying an image with a different image size from the image to be displayed, and further optimize the image display effect.
在一示例性实施例中，进一步的，上述放大待显示图像的步骤，可以包括：In an exemplary embodiment, further, the above-mentioned step of enlarging the image to be displayed may include:
获取第一图像放大比例；第一图像放大比例，与异常变形区域的异常变形程度呈正相关关系；基于第一图像放大比例，放大待显示图像。A first image magnification ratio is acquired; the first image magnification ratio is positively correlated with the abnormal deformation degree of the abnormal deformation area; based on the first image magnification ratio, the image to be displayed is enlarged.
本实施例中，终端100可以根据异常变形区域的异常变形程度确定出第一图像放大比例。具体的，异常变形区域的异常变形程度与该第一图像放大比例呈正相关关系，即异常变形程度越大，该待显示图像所对应的图像放大比例也越大，终端100在将待显示图像进行放大之前，可以先根据异常变形程度获取相应的第一图像放大比例，根据该第一图像放大比例对待显示图像进行放大处理。In this embodiment, the terminal 100 may determine the first image magnification ratio according to the abnormal deformation degree of the abnormal deformation area. Specifically, the abnormal deformation degree of the abnormal deformation area has a positive correlation with the magnification ratio of the first image, that is, the larger the abnormal deformation degree is, the larger the image magnification ratio corresponding to the image to be displayed is. Before enlarging, a corresponding first image enlargement ratio may be obtained according to the abnormal deformation degree, and the to-be-displayed image may be enlarged according to the first image enlargement ratio.
具体的，在待显示图像进行放大处理时，终端100可以设置一定的图像放大比例作为第一图像放大比例，该第一图像放大比例可根据异常变形区域的异常变形程度来确定，如果该异常变形区域的异常变形程度越大，则在该待显示图像中，包含有该异常变形区域的图像边缘区域也会越大，那么在将待显示图像进行放大处理时，为了获得更好的显示效果，需要将该包含有异常变形区域的图像边缘区域排除在图像的显示范围之外，因而对于异常变形程度越大的待显示图像，需要采用更大的图像放大比例才可将该包含有异常变形区域的图像边缘区域排除在图像的显示范围之外。Specifically, when the image to be displayed is enlarged, the terminal 100 may set a certain image enlargement ratio as the first image enlargement ratio, and the first image enlargement ratio may be determined according to the abnormal deformation degree of the abnormal deformation area. The greater the abnormal deformation degree of the area, the larger the image edge area including the abnormal deformation area in the to-be-displayed image. Then, when the to-be-displayed image is enlarged, in order to obtain a better display effect, It is necessary to exclude the edge area of the image containing the abnormal deformation area from the display range of the image. Therefore, for the image to be displayed with a larger degree of abnormal deformation, a larger image magnification ratio is required to include the abnormal deformation area. The edge area of the image is excluded from the display range of the image.
在一示例性实施例中，异常变形程度，与目标对象的液化变形等级和/或目标对象的被切割程度，呈正相关关系。In an exemplary embodiment, the abnormal deformation degree has a positive correlation with the liquefaction deformation level of the target object and/or the cut degree of the target object.
其中，目标对象的被切割程度，是指目标对象被待显示图像的图像边缘切割的程度。而液化变形等级可以对应于对目标对象进行液化变形处理的液化变形程度，等级越高液化变形程度则越大。本实施例中，终端100可以将目标对象的液化变形等级或者被切割程度中的至少一种作为异常变形程度的影响因素，当液化变形等级越大时，终端100可认为异常变形程度越大，而被切割程度越大时，也可以认为异常变形程度越大。Wherein, the cut degree of the target object refers to the degree to which the target object is cut by the image edge of the image to be displayed. The liquefaction deformation level may correspond to the liquefaction deformation degree of the liquefaction deformation process on the target object, and the higher the level, the greater the liquefaction deformation degree. In this embodiment, the terminal 100 may use at least one of the liquefaction deformation level or the cutting degree of the target object as an influencing factor of the abnormal deformation degree. The greater the degree of cutting, the greater the degree of abnormal deformation.
在其中一些实施例当中，目标对象的被切割程度是根据图外关键点占比得到的。In some of the embodiments, the cut degree of the target object is obtained according to the proportion of key points outside the graph.
其中，图外关键点占比是指位于待显示图像之外的标准关键点的数量，与目标对象对应的标准关键点集所包含的标准关键点的总数之间的比值。举例来说，当标准关键点集所包含的标准关键点为81个，而位于待显示图像之外的标准关键点的数量为1个，则图外关键点占比为1/81。本实施例中，终端100可以根据图外关键点占比量化目标对象的被切割程度，图外关键点占比越大时，可以认为目标对象的被切割程度越大。The ratio of off-image key points refers to the ratio between the number of standard key points located outside the image to be displayed and the total number of standard key points included in the standard key point set corresponding to the target object. For example, when the standard keypoint set includes 81 standard keypoints, and the number of standard keypoints located outside the image to be displayed is one, the ratio of off-image keypoints is 1/81. In this embodiment, the terminal 100 can quantify the cut degree of the target object according to the proportion of key points outside the graph. When the proportion of key points outside the graph is larger, it can be considered that the cut degree of the target object is greater.
基于此，上述实施例中的获取第一图像放大比例的步骤，具体可以包括：Based on this, the step of obtaining the first image magnification ratio in the above embodiment may specifically include:
根据液化变形等级和/或图外关键点占比，确定第一图像放大比例。The first image magnification ratio is determined according to the liquefaction deformation level and/or the ratio of key points outside the image.
其中，可以将图外关键点占比和液化变形等级进行量化，如上实施例所述，图外关键点占比可以通过位于待显示图像之外的标准关键点的数量与标准关键点集所包含的标准关键点的总数之间的比值来表示，而液化变形等级可以用1、2、3、4和5等进行表示，在确定第一图像放大比例时，终端100可以根据量化后的图外关键点占比和液化变形等级的乘积来进行计算。Among them, the proportion of key points outside the image and the level of liquefaction deformation can be quantified. As described in the above embodiment, the proportion of key points outside the image can be determined by the number of standard key points located outside the image to be displayed and the standard key point set. It is represented by the ratio between the total number of standard key points of Calculated as the product of the key point ratio and the liquefaction deformation level.
示例性的，终端100基于图外关键点占比和液化变形等级计算图像放大比例的方式可以采用：A1＝h*BC+1，其中，A1表示第一图像放大比例，h表示调节因子，可以设为0.5，B表示图外关键点占比，C表示液化变形等级，取值可以是1、2、3、4和5等。Exemplarily, the manner in which the terminal 100 calculates the image enlargement ratio based on the ratio of the key points outside the image and the liquefaction deformation level may adopt: A1=h*BC+1, where A1 represents the first image enlargement ratio, and h represents the adjustment factor, which can be Set to 0.5, B represents the proportion of key points outside the figure, C represents the liquefaction deformation level, and the value can be 1, 2, 3, 4, and 5.
本实施例可以根据各张待显示图像的液化变形等级和/或图外关键点占比灵活且准确地设置相应的图像放大比例，提供更好的显示效果。In this embodiment, the corresponding image magnification ratio can be flexibly and accurately set according to the liquefaction deformation level of each image to be displayed and/or the proportion of key points outside the image, thereby providing a better display effect.
在一示例性实施例中，终端100可以对第一图像放大比例进行限制，因为如果图像放大比例过大，在终端100的显示界面上所显示的图像将会很大，会影响图像显示效果，例如对于人脸图像，如果图像放大比例过大，则在终端100上显示的人脸会被过度放大，从而影响人脸显示效果。在一示例性实施例中，上述基于第一图像放大比例，放大待显示图像的步骤，具体可以包括：In an exemplary embodiment, the terminal 100 may limit the first image magnification ratio, because if the image magnification ratio is too large, the image displayed on the display interface of the terminal 100 will be very large, which will affect the image display effect. For example, for a human face image, if the image magnification ratio is too large, the human face displayed on the terminal 100 will be excessively enlarged, thereby affecting the display effect of the human face. In an exemplary embodiment, the above-mentioned step of enlarging the image to be displayed based on the first image enlarging ratio may specifically include:
当第一图像放大比例大于设定的第一比例阈值时，按照第一比例阈值放大待显示图像。When the enlargement ratio of the first image is greater than the set first ratio threshold, the image to be displayed is enlarged according to the first ratio threshold.
本实施例中，终端100可以设置第一比例阈值，当终端100判断待显示图像的图像放大比例大于设定的第一比例阈值时，按照该第一比例阈值放大待显示图像；而当待显示图像的图像放大比例小于该第一比例阈值时，可按照第一图像放大比例放大待显示图像。In this embodiment, the terminal 100 may set a first scale threshold. When the terminal 100 determines that the image enlargement scale of the image to be displayed is greater than the set first scale threshold, the terminal 100 enlarges the to-be-displayed image according to the first scale threshold; When the image enlargement ratio of the image is smaller than the first ratio threshold, the image to be displayed may be enlarged according to the first image enlargement ratio.
在具体实现中，可以采用A1＝h*BC+1来计算第一图像放大比例，而终端100可以根据该第一图像放大比例，将该待显示图像的实际焦距参数调节为原始焦距参数的A1倍，即可达到将该待显示图像进行放大显示的效果，而本实施例按照该方式计算第一图像放大比例时，可设置一最大取值(即第一比例阈值)，例如可以将最大取值设为1.15，即按照A1＝h*BC+1计算第一图像放大比例时，当计算得到的第一图像放大比例A1大于1.15，可以使得A1＝1.15，按照第一图像放大比例A1＝1.15来放大待显示图像。这样，一方面可以使得在终端100上显示的图像在整体衔接自然，液化处理效果自然细致，也不易察觉焦距拉近、脸被放大，并且也解决了屏幕边缘被拉伸出条纹模糊的问题。In a specific implementation, A1=h*BC+1 can be used to calculate the first image enlargement ratio, and the terminal 100 can adjust the actual focal length parameter of the to-be-displayed image to A1 of the original focal length parameter according to the first image enlargement ratio times, the effect of magnifying and displaying the image to be displayed can be achieved, and when calculating the magnification ratio of the first image in this way, a maximum value (ie, the first ratio threshold) can be set, for example, the maximum value can be set The value is set to 1.15, that is, when the first image enlargement ratio is calculated according to A1=h*BC+1, when the calculated first image enlargement ratio A1 is greater than 1.15, A1=1.15 can be set, and A1=1.15 according to the first image enlargement ratio to zoom in on the image to be displayed. In this way, on the one hand, the images displayed on the terminal 100 can be connected naturally as a whole, the liquefaction processing effect is natural and detailed, and it is not easy to notice that the focal length is zoomed in and the face is enlarged, and the problem of stretched stripes on the edge of the screen is also solved.
在一示例性实施例中，步骤S203中的将与目标图像区域对应的图像进行显示，可以包括：In an exemplary embodiment, displaying the image corresponding to the target image area in step S203 may include:
将待显示图像中，与目标图像区域对应的图像进行放大后显示。In the image to be displayed, the image corresponding to the target image area is enlarged and displayed.
本实施例中，终端100可以从待显示图像中先提取出目标图像区域对应的图像，将该提取出的目标图像区域对应的图像进行放大后再显示。一般而言，终端100可直接将待显示图像中与目标图像区域对应的图像进行显示。参考图7，可以将待显示图像720中截取出除包含有异常变形区域7200的边缘图像区域722之外的图像区域，作为目标图像区域，然后将该目标图像区域对应的图像730直接在终端100的显示界面上进行显示。而本实施例提供的方案，可以将待显示图像中与目标图像区域对应的图像进行放大后显示，能获得更好的显示效果。In this embodiment, the terminal 100 may first extract an image corresponding to the target image area from the image to be displayed, and then display the image corresponding to the extracted target image area after enlarging. Generally speaking, the terminal 100 can directly display the image corresponding to the target image area in the image to be displayed. Referring to FIG. 7 , an image area other than the
示例性的，如图8所示，可以从待显示图像820中选取出与目标图像区域对应的图像821，也可以从待显示图像820中截取掉包含有异常变形区域8200的第一图像边缘区域822，从而得到与目标图像区域对应的图像821，可以理解，该与目标图像区域对应的图像821的纵向图像尺寸与待显示图像820的纵向图像尺寸相同，而横向图像尺寸不一致，为了进一步得到更好的图像显示效果，可以将该与目标图像区域对应的图像821进行放大，以使得放大后的与目标图像区域对应的图像830，的横向图像尺寸与待显示图像820的横向图像尺寸一致，然而，放大后的与目标图像区域对应的图像830的纵向图像尺寸将会大于待显示图像820的纵向图像尺寸，为了获得更好的图像显示效果，可以根据待显示图像820的纵向图像尺寸在图像830当中进一步截取掉第二图像边缘区域832，以使得图像830中剩余的图像区域831的横向和纵向尺寸都与待显示图像820的横向和纵向尺寸一致，由此终端100可以将图像830中与该剩余的图像区域831对应的图像840进行显示。这样，终端100可以方便地按照待显示图像820的显示方式将图像840显示在其显示界面上，不会由于图像横纵尺寸不一致而产生额外的图像拉伸变形的问题。因此，本实施例的方案可以适当将与目标图像区域对应的图像进行放大，再从放大后的与目标图像区域对应的图像中选取出与待显示图像的横纵尺寸相同的图像进行显示，可灵活调节图像的放大比例，选出合适尺寸的图像在终端上进行显示，进一步优化图像显示效果。Exemplarily, as shown in FIG. 8 , an
在一示例性实施例中，进一步的，上述将待显示图像中，与目标图像区域对应的图像进行放大后显示的步骤，可以进一步包括：In an exemplary embodiment, further, the above-mentioned step of enlarging and displaying the image corresponding to the target image area in the image to be displayed may further include:
获取第二图像放大比例；其中，该第二图像放大比例，与异常变形区域的异常变形程度呈正相关关系；当第二图像放大比例大于设定的第二比例阈值时，按照第二比例阈值，将待显示图像中，与目标图像区域对应的图像进行放大后显示。Obtain a second image enlargement ratio; wherein, the second image enlargement ratio has a positive correlation with the abnormal deformation degree of the abnormal deformation area; when the second image enlargement ratio is greater than the set second ratio threshold, according to the second ratio threshold, In the image to be displayed, the image corresponding to the target image area is enlarged and displayed.
本实施例中，终端100可以基于与异常变形区域的异常变形程度呈正相关关系的第二图像放大比例，将待显示图像中，与目标图像区域对应的图像进行放大后显示。其中，终端100可根据异常变形区域的异常变形程度确定出第二图像放大比例。In this embodiment, the terminal 100 may enlarge and display the image corresponding to the target image area in the image to be displayed based on the second image enlargement ratio that is positively correlated with the abnormal deformation degree of the abnormal deformation area. The terminal 100 may determine the second image enlargement ratio according to the abnormal deformation degree of the abnormal deformation area.
具体的，异常变形区域的异常变形程度与第二图像放大比例呈正相关关系，即异常变形程度越大，该待显示图像中，与目标图像区域对应的图像所对应的第二图像放大比例也越大，终端100在将该与目标图像区域对应的图像进行放大之前，可以先根据异常变形程度获取第二图像放大比例，根据该第二图像放大比例对该与目标图像区域对应的图像进行放大处理。其中，如果该异常变形区域的异常变形程度越大，则包含该异常变形区域的图像边缘区域也会越大，那么不包含有异常变形区域的目标图像区域则会越小，为了获得更好的显示效果，需要将目标图像区域对应的图像进行适当放大，而对于异常变形程度越大的情况，可采用越大的图像放大比例。Specifically, the abnormal deformation degree of the abnormal deformation area is positively correlated with the magnification ratio of the second image, that is, the greater the abnormal deformation degree, the higher the magnification ratio of the second image corresponding to the image corresponding to the target image area in the image to be displayed. is large, before enlarging the image corresponding to the target image area, the terminal 100 may first obtain a second image enlargement ratio according to the degree of abnormal deformation, and perform enlargement processing on the image corresponding to the target image area according to the second image enlargement ratio . Among them, if the abnormal deformation degree of the abnormal deformation area is larger, the image edge area including the abnormal deformation area will also be larger, and the target image area that does not contain the abnormal deformation area will be smaller. To display the effect, it is necessary to appropriately enlarge the image corresponding to the target image area, and in the case of a larger degree of abnormal deformation, a larger image enlargement ratio can be used.
终端100可以对该与目标图像区域对应的图像的第二图像放大比例进行限制，因为如果图像放大比例过大，在终端100的显示界面上所显示的图像将会很大，会影响图像显示效果，例如对于人脸图像，如果图像放大比例过大，则在终端100上显示的人脸会被过度放大，从而影响人脸显示效果。The terminal 100 may limit the second image magnification ratio of the image corresponding to the target image area, because if the image magnification ratio is too large, the image displayed on the display interface of the terminal 100 will be very large, which will affect the image display effect For example, for a face image, if the magnification ratio of the image is too large, the face displayed on the terminal 100 will be excessively enlarged, thereby affecting the display effect of the face.
因此，终端100可以设置第二比例阈值，当终端100判断第二图像放大比例大于该第二比例阈值时，可按照该第二比例阈值放大上述待显示图像中，与目标图像区域对应的图像；而当第二图像放大比例小于该第二比例阈值时，可按照第二图像放大比例放大与目标图像区域对应的图像。Therefore, the terminal 100 may set a second proportional threshold, and when the terminal 100 determines that the magnification ratio of the second image is greater than the second proportional threshold, the terminal 100 may magnify the image corresponding to the target image area in the above-mentioned to-be-displayed image according to the second proportional threshold; When the second image enlargement ratio is smaller than the second ratio threshold, the image corresponding to the target image area may be enlarged according to the second image enlargement ratio.
在具体实现中，可以采用A2＝h*BC+1来计算第二图像放大比例，而终端100可以根据该第二图像放大比例，将该待显示图像的实际焦距参数调节为原始焦距参数的A2倍，即可达到将与目标图像区域对应的图像进行放大显示的效果，而本实施例按照该方式计算第二图像放大比例时，可设置一最大取值(即第二比例阈值)，例如可以将最大取值设为1.15，即按照A2＝h*BC+1计算第二图像放大比例时，当计算得到的第二图像放大比例A2大于1.15，可以使得A2＝1.15，按照第二图像放大比例A2＝1.15来放大待显示图像中与目标图像区域对应的图像。这样，一方面可以使得在终端100上显示的图像在整体衔接自然，液化处理效果自然细致，也不易察觉焦距拉近、脸被放大，并且也解决了屏幕边缘被拉伸出条纹模糊的问题。In a specific implementation, A2=h*BC+1 can be used to calculate the second image enlargement ratio, and the terminal 100 can adjust the actual focal length parameter of the to-be-displayed image to A2 of the original focal length parameter according to the second image enlargement ratio times, the effect of magnifying and displaying the image corresponding to the target image area can be achieved, and when calculating the magnification ratio of the second image in this way, a maximum value (ie, the second ratio threshold) can be set, for example, you can The maximum value is set to 1.15, that is, when the second image enlargement ratio is calculated according to A2=h*BC+1, when the calculated second image enlargement ratio A2 is greater than 1.15, A2=1.15, according to the second image enlargement ratio A2=1.15 to enlarge the image corresponding to the target image area in the image to be displayed. In this way, on the one hand, the images displayed on the terminal 100 can be connected naturally as a whole, the liquefaction processing effect is natural and detailed, and it is not easy to notice that the focal length is zoomed in and the face is enlarged, and the problem of stretched stripes and blurred edges of the screen is also solved.
在一示例性实施例中，提供了一种图像处理方法，如图9所示，图9是根据一示例性实施例示出的一种图像处理方法的流程图，该图像处理方法可以由如图1所示的终端100来实现，具体步骤包括：In an exemplary embodiment, an image processing method is provided. As shown in FIG. 9 , FIG. 9 is a flowchart of an image processing method shown according to an exemplary embodiment. The terminal 100 shown in 1 is implemented, and the specific steps include:
步骤S901，获取对原始图像中的目标对象进行液化变形处理后得到的待显示图像；Step S901, acquiring an image to be displayed obtained by performing liquefaction deformation processing on the target object in the original image;
步骤S902，当目标对象对应的至少一个标准关键点位于待显示图像之外时，识别目标对象被图像边缘切割；Step S902, when at least one standard key point corresponding to the target object is located outside the to-be-displayed image, identify that the target object is cut by the edge of the image;
步骤S903，获取待显示图像的图像尺寸；Step S903, acquiring the image size of the image to be displayed;
步骤S904，放大待显示图像，以使放大后的待显示图像中存在与图像尺寸相同的且不包括异常变形区域的图像区域，作为目标图像区域；Step S904, enlarging the image to be displayed, so that there is an image area in the enlarged image to be displayed that has the same size as the image and does not include the abnormal deformation area, as the target image area;
步骤S905，将放大后的待显示图像中，与目标图像区域对应的图像进行显示。Step S905: Display the image corresponding to the target image area in the enlarged image to be displayed.
上述实施例提供的图像处理方法，终端100可以在将液化变形处理后得到的待显示图像进行显示之前，先判断目标对象是否被该待显示图像的图像边缘切割，具体的，当目标对象对应的至少一个标准关键点位于待显示图像之外时，终端100可判断该目标对象被图像边缘切割，此时，终端100可确定出不包含异常变形区域的目标图像区域，具体的，终端100可以将待显示图像进行放大，以使放大后的待显示图像中存在与图像尺寸相同的且不包括异常变形区域的图像区域，作为目标图像区域，然后终端100可以将放大后的待显示图像中，与该目标图像区域对应的图像进行显示，解决目标对象被图像边缘切割时产生的拉伸变形问题，以优化图像显示效果，提升用户体验。In the image processing method provided by the above embodiment, the terminal 100 may first determine whether the target object is cut by the image edge of the to-be-displayed image before displaying the to-be-displayed image obtained after the liquefaction deformation process. When at least one standard key point is located outside the image to be displayed, the terminal 100 can determine that the target object is cut by the edge of the image, and at this time, the terminal 100 can determine the target image area that does not contain the abnormal deformation area. Specifically, the terminal 100 can The to-be-displayed image is enlarged, so that there is an image area in the enlarged to-be-displayed image that has the same size as the image and does not include an abnormally deformed area, as the target image area, and then the terminal 100 can use the enlarged image to be displayed with the same size as the image area. The image corresponding to the target image area is displayed, so as to solve the problem of stretching and deformation generated when the target object is cut by the edge of the image, so as to optimize the image display effect and improve the user experience.
本公开的技术方案能应用于移动端拍摄和视频直播的美颜瘦脸处理当中，如图10和图11所示为本公开的技术方案的另外两个示例性的应用场景，先对如图10和11的应用场景做一个简要介绍。The technical solution of the present disclosure can be applied to the beautification and face-lifting processing of mobile terminal shooting and live video. Figure 10 and Figure 11 show two other exemplary application scenarios of the technical solution of the present disclosure. And 11 application scenarios to make a brief introduction.
如图10所示，图10是根据一示例性实施例示出的图像处理方法的一种应用场景图，该应用场景可以包括直播服务器1020，以及与该直播服务器1020通过网络进行连接的主播端1010和观众端1030，其中，主播端1010可以实时采集主播的原始图像，主播端1010可以将对该原始图像进行处理过程交由直播服务器1020进行处理，直播服务器1020从终端1010接收原始图像1001，按照如上实施例所述的图像处理方法，得到与目标图像区域对应的图像称为目标图像1002，并将目标图像1002分别发送到主播端1010和观众端1030上进行显示。As shown in FIG. 10, FIG. 10 is a diagram of an application scenario of the image processing method according to an exemplary embodiment. The application scenario may include a
如图11所示，图11是根据一示例性实施例示出的图像处理方法的另一种应用场景图，该应用场景可以包括直播服务器1120，以及与该直播服务器1120通过网络进行连接的主播端1110和观众端1130，其中，主播端1110可以实时采集主播的原始图像，主播端1110可以直接按照如上实施例所述的图像处理方法，得到与目标图像区域对应的图像称为目标图像1101，并在其显示界面上进行显示，同时还将该目标图像1101发送给直播服务器1120，直播服务器1120可以进一步将该目标图像1101推送到观众端1130进行显示。As shown in FIG. 11 , FIG. 11 is another application scenario diagram of the image processing method according to an exemplary embodiment, and the application scenario may include a
通过上述图像处理方式，在主播端和观众端上显示的图像都是在整体衔接自然，液化处理效果自然细致的图像，而且用户也不易察觉焦距拉近或者主播的脸被放大，并且也解决了屏幕边缘被拉伸出条纹模糊的问题。Through the above-mentioned image processing methods, the images displayed on the host and the audience are naturally connected as a whole, and the liquefaction processing effect is natural and detailed, and it is not easy for the user to notice that the focal length is zoomed in or the host's face is enlarged, and it also solves the problem. The edge of the screen is stretched and the stripes are blurred.
基于如图10和图11的应用场景，本公开的图像处理方法可以具体包括如下步骤：Based on the application scenarios shown in FIGS. 10 and 11 , the image processing method of the present disclosure may specifically include the following steps:
对主播的人脸进行美颜处理过程中，可以先取视频或者直播的各图像帧，然后通过人脸识别人脸关键点的模型对人脸轮廓五官等进行标注，其中，该模型可以是深度学习训练得到的，而模型的深度学习训练的具体流程可以包括：预先收集大量人脸照片，然后大量标注人脸关键点的位置，例如脸部轮廓、眼周、瞳孔、眉毛轮廓、鼻子轮廓、嘴巴轮廓等等，接着进行机器学习即可得到人脸识别的模型，还可以进一步补充数据集再次训练，对模型进行优化。然后，可以基于人脸关键点对人脸轮廓五官进行美颜变形，包含瘦脸大眼等等处理。接着，识别人脸的部分关键点是否不在屏幕内，该识别过程可以基于关键点标注的位置来计算是否有部分关键点的位置不包括在屏幕内的图像中，然后统计不在屏幕内的人脸关键点的数量及其占比B，B＝不在屏幕内的人脸关键点个数/人脸关键点总个数；将该图像的实际焦距参数调节为当前焦距参数的A倍，这样脸部拉伸模糊变形区域则被截取掉，屏幕不会再显示出来，而A的取值与不在屏幕内的人脸关键点个数占比B成正比、与美颜的程度C成正比，A可根据以下方式计算：A＝h*BC+1，h为0.5,0<＝B<＝1，C＝1，2，3，4，5；其中，A的最大取值为1.15，即按照上述公式计算得到A>1.15时，使A＝1.15。In the process of beautifying the host's face, each image frame of the video or live broadcast can be taken first, and then the facial contour and facial features, etc. can be marked through the model of face recognition key points. The model can be deep learning. The specific process of deep learning training of the model can include: collecting a large number of face photos in advance, and then marking the positions of key points of the face, such as face contour, eye circumference, pupil, eyebrow contour, nose contour, mouth Contours, etc., then machine learning can be used to obtain a face recognition model, and the data set can be further supplemented for retraining to optimize the model. Then, based on the key points of the face, the facial contours and facial features can be beautified and deformed, including face-lifting and big-eyed processing. Next, identify whether some key points of the face are not on the screen. The recognition process can calculate whether some key points are not included in the image on the screen based on the positions marked by the key points, and then count the faces that are not on the screen. The number of key points and their proportion B, B = the number of face key points not on the screen/the total number of face key points; adjust the actual focal length parameter of the image to A times the current focal length parameter, so that the face The stretched, blurred and deformed area is intercepted, and the screen will no longer be displayed. The value of A is proportional to the number of key points of the face that are not on the screen, B, and proportional to the degree of beauty C. A can be Calculated according to the following method: A=h*BC+1, h is 0.5, 0<=B<=1, C=1, 2, 3, 4, 5; among them, the maximum value of A is 1.15, that is, according to the above When A>1.15 is obtained from the formula calculation, A=1.15.
上述图像处理过程，可使用人脸关键点为技术基础的液化瘦脸，当识别脸部处于屏幕边缘被切割的状态，也即脸部皮肤被拉伸出条纹时，适当地对焦距参数进行放大，使得皮肤变形区域被切割，图像整体衔接自然，美颜效果自然细致，也难以察觉终端所显示的图像中焦距拉近、脸被放大，并且也解决了屏幕边缘皮肤被拉伸出条纹模糊的问题，还可以支持实时视频场景，对主播进行快速美颜处理，解决美颜边缘露怯问题，得到更好的美颜拍摄体验。The above image processing process can use the liquefaction face-lifting technology based on the key points of the face. When the recognized face is in the state where the edge of the screen is cut, that is, when the facial skin is stretched out of stripes, the focal length parameter is appropriately enlarged. The skin deformation area is cut, the overall image is natural, and the beauty effect is natural and detailed, and it is difficult to detect that the focal length is zoomed in and the face is enlarged in the image displayed by the terminal, and the problem that the skin on the edge of the screen is stretched and blurred is also solved. , it can also support real-time video scenes, perform fast beautification processing on the anchor, solve the problem of beautifying edges, and get a better beauty shooting experience.
应该理解的是，虽然图2至图9的流程图中的各个步骤按照箭头的指示依次显示，但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，这些步骤可以以其它的顺序执行。而且，图2至图9中的至少一部分步骤可以包括多个步骤或者多个阶段，这些步骤或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，这些步骤或者阶段的执行顺序也不必然是依次进行，而是可以与其它步骤或者其它步骤中的步骤或者阶段的至少一部分轮流或者交替地执行。It should be understood that although the steps in the flowcharts of FIG. 2 to FIG. 9 are shown in sequence according to the arrows, these steps are not necessarily executed in the sequence shown by the arrows. Unless explicitly stated herein, the execution of these steps is not strictly limited to the order, and these steps may be performed in other orders. Moreover, at least a part of the steps in FIG. 2 to FIG. 9 may include multiple steps or multiple stages. These steps or stages are not necessarily executed and completed at the same time, but may be executed at different times. The order of execution is also not necessarily sequential, but may be performed alternately or alternately with other steps or at least a portion of the steps or stages within the other steps.
图12是根据一示例性实施例示出的一种图像处理装置1200的框图。参照图12，该装置1200包括图像获取模块1201、区域确定模块1202和图像显示模块1203。FIG. 12 is a block diagram of an image processing apparatus 1200 according to an exemplary embodiment. 12 , the apparatus 1200 includes an
图像获取模块1201，被配置为执行获取对原始图像中的目标对象进行液化变形处理后得到的待显示图像；The
区域确定模块1202，被配置为执行当识别到目标对象被待显示图像的图像边缘切割时，确定目标图像区域；其中，目标图像区域包括待显示图像的，除异常变形区域之外的图像区域；异常变形区域为目标对象被待显示图像的图像边缘切割时所产生的；The
图像显示模块1203，被配置为执行将与目标图像区域对应的图像进行显示。The
在一示例性实施例中，图像处理装置1200，还包括：切割识别模块，被配置为执行当目标对象对应的至少一个标准关键点位于待显示图像之外时，识别目标对象被图像边缘切割。In an exemplary embodiment, the image processing apparatus 1200 further includes: a cutting recognition module configured to perform recognition that the target object is cut by the image edge when at least one standard key point corresponding to the target object is located outside the to-be-displayed image.
在一示例性实施例中，图像处理装置1200，还包括：关键点识别模块，被配置为执行基于目标对象的标准对象模型，确定目标对象对应的标准关键点集；获取待显示图像上，对应于标准关键点集中各标准关键点的位置信息；根据位置信息，识别各标准关键点是否位于待显示图像内。In an exemplary embodiment, the image processing apparatus 1200 further includes: a key point identification module, configured to execute a standard object model based on the target object, and determine a standard key point set corresponding to the target object; The position information of each standard key point in the standard key point set; according to the position information, it is identified whether each standard key point is located in the image to be displayed.
在一示例性实施例中，区域确定模块1202，进一步被配置为执行获取待显示图像的图像尺寸；放大待显示图像，以使放大后的待显示图像中存在与图像尺寸相同的且不包括异常变形区域的图像区域，作为目标图像区域。In an exemplary embodiment, the
在一示例性实施例中，图像显示模块1203，被配置为执行将放大后的待显示图像中，与目标图像区域对应的图像进行显示。In an exemplary embodiment, the
在一示例性实施例中，区域确定模块1202，进一步被配置为执行获取第一图像放大比例；第一图像放大比例，与异常变形区域的异常变形程度呈正相关关系；基于第一图像放大比例，放大待显示图像。In an exemplary embodiment, the
在一示例性实施例中，异常变形程度，与目标对象的液化变形等级和/或目标对象的被切割程度，呈正相关关系；其中，目标对象的被切割程度，为目标对象被待显示图像的图像边缘切割的程度。In an exemplary embodiment, the abnormal deformation degree has a positive correlation with the liquefaction deformation level of the target object and/or the cut degree of the target object; wherein, the cut degree of the target object is the amount of the image to be displayed of the target object. The degree to which the edges of the image are cut.
在一示例性实施例中，目标对象的被切割程度是根据图外关键点占比得到的；其中，图外关键点占比为位于待显示图像之外的标准关键点的数量，与目标对象对应的标准关键点集所包含的标准关键点的总数之间的比值。In an exemplary embodiment, the cut degree of the target object is obtained according to the ratio of key points outside the image; wherein, the ratio of key points outside the image is the number of standard key points located outside the image to be displayed, which is different from that of the target object. The ratio between the total number of standard keypoints contained in the corresponding standard keypoint set.
在一示例性实施例中，区域确定模块1202，进一步被配置为执行当第一图像放大比例大于设定的第一比例阈值时，按照第一比例阈值放大待显示图像。In an exemplary embodiment, the
在一示例性实施例中，图像显示模块1203，进一步被配置为执行将待显示图像中，与目标图像区域对应的图像进行放大后显示。In an exemplary embodiment, the
在一示例性实施例中，图像显示模块1203，进一步被配置为执行获取第二图像放大比例；第二图像放大比例，与异常变形区域的异常变形程度呈正相关关系；当第二图像放大比例大于设定的第二比例阈值时，按照第二比例阈值，将待显示图像中，与目标图像区域对应的图像进行放大后显示。In an exemplary embodiment, the
关于上述实施例中的装置，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。Regarding the apparatus in the above-mentioned embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be described in detail here.
图13是根据一示例性实施例示出的一种电子设备的内部结构图。例如，设备1300可以是移动电话、计算机、数字广播终端、消息收发设备、游戏控制台、平板设备、医疗设备、健身设备、个人数字助理等。Fig. 13 is an internal structure diagram of an electronic device according to an exemplary embodiment. For example,
参照图13，设备1300可以包括以下一个或多个组件：处理组件1302、存储器1304、电力组件1306、多媒体组件1308、音频组件1310、输入/输出(I/O)的接口1312、传感器组件1314以及通信组件1316。13, a
处理组件1302通常控制设备1300的整体操作，诸如与显示、电话呼叫、数据通信、相机操作和记录操作相关联的操作。处理组件1302可以包括一个或多个处理器1320来执行指令，以完成上述的方法的全部或部分步骤。此外，处理组件1302可以包括一个或多个模块，便于处理组件1302和其他组件之间的交互。例如，处理组件1302可以包括多媒体模块，以方便多媒体组件1308和处理组件1302之间的交互。The
存储器1304被配置为存储各种类型的数据以支持在设备1300的操作。这些数据的示例包括用于在设备1300上操作的任何应用程序或方法的指令、联系人数据、电话簿数据、消息、图片、视频等。存储器1304可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)、电可擦除可编程只读存储器(EEPROM)、可擦除可编程只读存储器(EPROM)、可编程只读存储器(PROM)、只读存储器(ROM)、磁存储器、快闪存储器、磁盘或光盘。
电源组件1306为设备1300的各种组件提供电力。电源组件1306可以包括电源管理系统，一个或多个电源，及其他与为设备1300生成、管理和分配电力相关联的组件。
多媒体组件1308包括在所述设备1300和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件1308包括一个前置摄像头和/或后置摄像头。当设备1300处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件1310被配置为输出和/或输入音频信号。例如，音频组件1310包括一个麦克风(MIC)，当设备1300处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器1304或经由通信组件1316发送。在一些实施例中，音频组件1310还包括一个扬声器，用于输出音频信号。
I/O接口1312为处理组件1302和外围接口模块之间提供接口，上述外围接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。The I/
传感器组件1314包括一个或多个传感器，用于为设备1300提供各个方面的状态评估。例如，传感器组件1314可以检测到设备1300的打开/关闭状态，组件的相对定位，例如所述组件为设备1300的显示器和小键盘，传感器组件1314还可以检测设备1300或设备1300一个组件的位置改变，用户与设备1300接触的存在或不存在，设备1300方位或加速/减速和设备1300的温度变化。传感器组件1314可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件1314还可以包括光传感器，如CMOS或CCD图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件1314还可以包括加速度传感器、陀螺仪传感器、磁传感器、压力传感器或温度传感器。
通信组件1316被配置为便于设备1300和其他设备之间有线或无线方式的通信。设备1300可以接入基于通信标准的无线网络，如WiFi，运营商网络(如2G、3G、4G或5G)，或它们的组合。在一个示例性实施例中，通信组件1316经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信组件1316还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
在示例性实施例中，设备1300可以被一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述图像处理方法。In an exemplary embodiment,
在示例性实施例中，还提供了一种包括指令的非临时性计算机可读存储介质，例如包括指令的存储器1304，上述指令可由设备1300的处理器1320执行以完成上述图像处理方法。例如，所述非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。In an exemplary embodiment, there is also provided a non-transitory computer-readable storage medium including instructions, such as a
在一示例性实施例中，还提供了一种计算机程序产品，所述程序产品包括计算机程序，所述计算机程序存储在可读存储介质中，设备的至少一个处理器从所述可读存储介质读取并执行所述计算机程序，使得设备执行如上实施例所述的图像处理方法。In an exemplary embodiment, there is also provided a computer program product comprising a computer program stored in a readable storage medium from which at least one processor of the device The computer program is read and executed, so that the apparatus executes the image processing method described in the above embodiment.
本领域技术人员在考虑说明书及实践这里公开的发明后，将容易想到本公开的其它实施方案。本申请旨在涵盖本公开的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本公开的真正范围和精神由下面的权利要求指出。Other embodiments of the present disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or techniques in the technical field not disclosed by the present disclosure . The specification and examples are to be regarded as exemplary only, with the true scope and spirit of the disclosure being indicated by the following claims.
应当理解的是，本公开并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利要求来限制。It is to be understood that the present disclosure is not limited to the precise structures described above and illustrated in the accompanying drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010229712.6ACN111340691B (en) | 2020-03-27 | 2020-03-27 | Image processing method, device, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010229712.6ACN111340691B (en) | 2020-03-27 | 2020-03-27 | Image processing method, device, electronic device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111340691Atrue CN111340691A (en) | 2020-06-26 |
| CN111340691B CN111340691B (en) | 2024-06-04 |
Family
ID=71187400
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010229712.6AActiveCN111340691B (en) | 2020-03-27 | 2020-03-27 | Image processing method, device, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111340691B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111784604A (en)* | 2020-06-29 | 2020-10-16 | 北京字节跳动网络技术有限公司 | Image processing method, device, equipment and computer readable storage medium |
| CN113034351A (en)* | 2021-03-25 | 2021-06-25 | 联想(北京)有限公司 | Image processing method and device |
| CN114255175A (en)* | 2020-09-25 | 2022-03-29 | 广州虎牙科技有限公司 | Facial beautification method, device, electronic device and storage medium |
| WO2022187997A1 (en)* | 2021-03-08 | 2022-09-15 | 深圳市大疆创新科技有限公司 | Video processing method, electronic device, and storage medium |
| CN116016988A (en)* | 2022-12-05 | 2023-04-25 | 广州方硅信息技术有限公司 | Live image processing method, device, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018040613A1 (en)* | 2016-08-31 | 2018-03-08 | 中兴通讯股份有限公司 | Method and device for displaying icon on terminal interface |
| CN108053377A (en)* | 2017-12-11 | 2018-05-18 | 北京小米移动软件有限公司 | Image processing method and equipment |
| CN108259765A (en)* | 2018-03-27 | 2018-07-06 | 努比亚技术有限公司 | A kind of image pickup method, terminal and computer readable storage medium |
| CN108898043A (en)* | 2018-02-09 | 2018-11-27 | 迈格威科技有限公司 | Image processing method, image processing apparatus and storage medium |
| CN109658406A (en)* | 2018-12-25 | 2019-04-19 | 广州天鹏计算机科技有限公司 | Recognition methods, device, computer equipment and the storage medium of blood-vessel image |
| CN110298785A (en)* | 2019-06-29 | 2019-10-01 | 北京字节跳动网络技术有限公司 | Image beautification method, device and electronic equipment |
| CN110675420A (en)* | 2019-08-22 | 2020-01-10 | 华为技术有限公司 | Image processing method and electronic equipment |
- 2020
- 2020-03-27CNCN202010229712.6Apatent/CN111340691B/enactiveActive
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018040613A1 (en)* | 2016-08-31 | 2018-03-08 | 中兴通讯股份有限公司 | Method and device for displaying icon on terminal interface |
| CN108053377A (en)* | 2017-12-11 | 2018-05-18 | 北京小米移动软件有限公司 | Image processing method and equipment |
| CN108898043A (en)* | 2018-02-09 | 2018-11-27 | 迈格威科技有限公司 | Image processing method, image processing apparatus and storage medium |
| CN108259765A (en)* | 2018-03-27 | 2018-07-06 | 努比亚技术有限公司 | A kind of image pickup method, terminal and computer readable storage medium |
| CN109658406A (en)* | 2018-12-25 | 2019-04-19 | 广州天鹏计算机科技有限公司 | Recognition methods, device, computer equipment and the storage medium of blood-vessel image |
| CN110298785A (en)* | 2019-06-29 | 2019-10-01 | 北京字节跳动网络技术有限公司 | Image beautification method, device and electronic equipment |
| CN110675420A (en)* | 2019-08-22 | 2020-01-10 | 华为技术有限公司 | Image processing method and electronic equipment |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111784604A (en)* | 2020-06-29 | 2020-10-16 | 北京字节跳动网络技术有限公司 | Image processing method, device, equipment and computer readable storage medium |
| CN114255175A (en)* | 2020-09-25 | 2022-03-29 | 广州虎牙科技有限公司 | Facial beautification method, device, electronic device and storage medium |
| WO2022187997A1 (en)* | 2021-03-08 | 2022-09-15 | 深圳市大疆创新科技有限公司 | Video processing method, electronic device, and storage medium |
| CN113034351A (en)* | 2021-03-25 | 2021-06-25 | 联想(北京)有限公司 | Image processing method and device |
| CN116016988A (en)* | 2022-12-05 | 2023-04-25 | 广州方硅信息技术有限公司 | Live image processing method, device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111340691B (en) | 2024-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111340691B (en) | Image processing method, device, electronic device and storage medium | |
| US11308692B2 (en) | Method and device for processing image, and storage medium | |
| US11030733B2 (en) | Method, electronic device and storage medium for processing image | |
| CN106651955B (en) | Method and device for positioning target object in picture | |
| CN106570110B (en) | Image duplicate removal method and device | |
| CN106339680B (en) | Face key independent positioning method and device | |
| JP6357589B2 (en) | Image display method, apparatus, program, and recording medium | |
| CN106295566A (en) | Facial expression recognizing method and device | |
| JP2016531362A (en) | Skin color adjustment method, skin color adjustment device, program, and recording medium | |
| CN107944367B (en) | Face key point detection method and device | |
| CN110909654A (en) | Training image generation method and device, electronic equipment and storage medium | |
| CN106528879A (en) | Picture processing method and device | |
| CN110717452B (en) | Image recognition method, device, terminal and computer readable storage medium | |
| CN107424130B (en) | Picture beautifying method and device | |
| CN106778531A (en) | Face detection method and device | |
| CN110807769B (en) | Image display control method and device | |
| WO2022121577A1 (en) | Image processing method and apparatus | |
| CN108898591A (en) | Methods of marking and device, electronic equipment, the readable storage medium storing program for executing of picture quality | |
| CN107958223A (en) | Face identification method and device, mobile equipment, computer-readable recording medium | |
| CN104077563A (en) | Human face recognition method and device | |
| CN107992811A (en) | Face identification method and device | |
| CN112099639A (en) | Display attribute adjusting method and device, display equipment and storage medium | |
| CN111340690B (en) | Image processing method, device, electronic equipment and storage medium | |
| CN108010009A (en) | A kind of method and device for removing interference figure picture | |
| CN107463373A (en) | The management method and device of picture U.S. face method, good friend's face value |
Legal Events
| 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TG01 | Patent term adjustment | ||
| TG01 | Patent term adjustment |