技术领域technical field
本发明涉及人脸识别技术领域，尤其涉及一种人脸的活体检测方法及装置。The present invention relates to the technical field of face recognition, in particular to a method and device for live body detection of a face.
背景技术Background technique
目前，生物特征识别技术广泛地应用于安全领域，是认证用户身份的主要手段之一。生物特征识别技术，尤其是人脸识别技术，已被广泛应用于各个领域，比如金融支付领域、门禁安全领域等。鉴于人脸识别技术具有方便易用、用户友好性、非接触式等有点，近年来取得了突飞猛进的发展。At present, biometric identification technology is widely used in the security field and is one of the main means of authenticating user identities. Biometric recognition technology, especially face recognition technology, has been widely used in various fields, such as financial payment field, access control security field and so on. In view of the advantages of convenience, user-friendliness, and non-contact, face recognition technology has achieved rapid development in recent years.
然而，传统的人脸识别技术通常只针对摄像机拍摄到的图像进行处理，并不考虑所拍摄到的图像是否为真人，从而导致照片人脸、面具人脸等伪造的人脸模型能够通过人脸识别系统的检测，进而，容易导致人脸识别的安全性受到影响。However, the traditional face recognition technology usually only processes the images captured by the camera, without considering whether the captured images are real people, resulting in forged face models such as photo faces, mask faces, etc. The detection of the recognition system, in turn, is likely to affect the security of face recognition.
基于此，目前亟需一种人脸的活体检测方法，用于解决现有技术中人脸识别技术无法识别伪造的人脸模型，从而影响人脸识别的安全性的问题。Based on this, there is an urgent need for a human face liveness detection method, which is used to solve the problem that the face recognition technology in the prior art cannot identify a fake face model, thereby affecting the security of face recognition.
发明内容Contents of the invention
本发明实施例提供一种人脸的活体检测方法及装置，以解决现有技术中人脸识别技术无法识别伪造的人脸模型，从而影响人脸识别的安全性的技术问题。Embodiments of the present invention provide a face detection method and device to solve the technical problem that the face recognition technology in the prior art cannot identify fake face models, thereby affecting the security of face recognition.
本发明实施例提供一种人脸的活体检测方法，所述方法包括：An embodiment of the present invention provides a method for liveness detection of a human face, the method comprising:
获取待检测人脸在不同时刻对应的特征向量；Obtain the feature vectors corresponding to the faces to be detected at different moments;
获取所述待检测人脸中预设关键点在所述不同时刻对应的位置信息，所述位置信息为所述预设关键点在所述待检测人脸中的位置；所述预设关键点为能表征人脸表情的区域；Obtaining the position information corresponding to the preset key points in the human face to be detected at the different moments, the position information being the position of the preset key points in the human face to be detected; the preset key points is an area that can represent facial expressions;
根据所述不同时刻对应的特征向量及所述不同时刻对应的位置信息，确定所述待检测人脸的人脸变化度；According to the feature vectors corresponding to the different moments and the position information corresponding to the different moments, determine the face change degree of the face to be detected;
若所述待检测人脸的人脸变化度大于预设阈值，则确定所述待检测人脸通过活体检测。If the face change degree of the face to be detected is greater than a preset threshold, it is determined that the face to be detected has passed the living body detection.
如此，可以通过判断待检测人脸中的预设关键点在不同时刻是否存在位置上的变化，可以确定待检测人脸是否为活体。采用这种方法，由于不法分子伪造的人脸模型是静态的，因此，本发明实施例提供的活体检测方法能够有效识别出伪造的人脸模型，从而提高人脸识别的安全性，进而提高人脸识别系统的可靠性。In this way, it can be determined whether the face to be detected is a living body by judging whether the preset key points in the face to be detected have position changes at different times. With this method, since the face models forged by criminals are static, the living body detection method provided by the embodiment of the present invention can effectively identify the forged face models, thereby improving the security of face recognition, and further improving the human body detection method. Reliability of facial recognition systems.
在一种可能的实现方式中，根据所述不同时刻对应的特征向量及所述不同时刻对应的位置信息，确定所述待检测人脸的人脸变化度，包括：In a possible implementation manner, determining the face change degree of the face to be detected according to the feature vectors corresponding to the different moments and the position information corresponding to the different moments includes:
根据所述不同时刻对应的特征向量，确定特征相似度；determining feature similarity according to the feature vectors corresponding to the different moments;
根据所述不同时刻对应的位置信息，确定位置变化度；Determine the degree of change in position according to the position information corresponding to the different moments;
根据所述特征相似度和所述位置变化度，确定所述待检测人脸的人脸变化度。According to the feature similarity and the position change degree, determine the face change degree of the face to be detected.
在一种可能的实现方式中，获取待检测人脸在不同时刻对应的特征向量，包括：In a possible implementation, the feature vectors corresponding to the faces to be detected at different moments are obtained, including:
获取所述待检测人脸的各分割区域在所述不同时刻对应的特征向量；所述各分割区域是根据人脸的五官位置确定的；Acquiring feature vectors corresponding to each segmented area of the human face to be detected at the different moments; each segmented area is determined according to the facial features of the face;
根据所述不同时刻对应的特征向量，确定特征相似度，包括：According to the feature vectors corresponding to the different moments, the feature similarity is determined, including:
根据每个分割区域在所述不同时刻对应的特征向量，确定每个分割区域的特征相似度；Determine the feature similarity of each segmented area according to the feature vectors corresponding to each segmented area at the different moments;
根据所述特征相似度和所述位置变化度，确定所述待检测人脸的人脸变化度，包括：According to the feature similarity and the position change degree, determining the face change degree of the human face to be detected includes:
根据每个分割区域的特征相似度和所述位置变化度，确定所述待检测人脸的人脸变化度。According to the feature similarity of each segmented area and the position change degree, determine the face change degree of the face to be detected.
通过对待检测人脸进行分割，能够综合考虑各分割区域的表情敏感度，从而提高活体检测的准确率。By segmenting the face to be detected, the expression sensitivity of each segmented area can be considered comprehensively, thereby improving the accuracy of live body detection.
在一种可能的实现方式中，根据每个分割区域的特征相似度和所述位置变化度，确定所述待检测人脸的人脸变化度，包括：In a possible implementation manner, according to the feature similarity of each segmented area and the position change degree, determining the face change degree of the face to be detected includes:
针对任一预设关键点，确定所述预设关键点所属的分割区域；For any preset key point, determine the segmented area to which the preset key point belongs;
根据所属的分割区域的特征相似度及所述预设关键点的位置变化度，确定所述分割区域的人脸变化度；According to the feature similarity of the segmented area to which it belongs and the positional change degree of the preset key point, determine the face change degree of the segmented area;
根据各分割区域的人脸变化度，确定所述待检测人脸的人脸变化度。Determine the face change degree of the face to be detected according to the face change degree of each segmented area.
在一种可能的实现方式中，所述分割区域包括嘴巴区域、鼻子区域、脸颊区域、眉毛区域、眼睛区域和前额区域。In a possible implementation manner, the segmented regions include a mouth region, a nose region, a cheek region, an eyebrow region, an eye region, and a forehead region.
在一种可能的实现方式中，获取所述待检测人脸中预设关键点在所述不同时刻对应的位置信息，包括：In a possible implementation manner, obtaining position information corresponding to preset key points in the face to be detected at the different moments includes:
采用飞行时间TOF技术获取所述待检测人脸中预设关键点在所述不同时刻对应的位置信息；Obtaining the position information corresponding to the preset key points in the face to be detected at the different moments by using time-of-flight TOF technology;
或or
采用3D人脸重建技术获取所述待检测人脸中预设关键点在所述不同时刻对应的位置信息。Using a 3D face reconstruction technology to obtain position information corresponding to preset key points in the face to be detected at the different moments.
采用TOF技术获取人脸的相关数据，可以在用户无感知的情况下，获取用户人脸的相关数据，对用户的配合度要求较低，用户的体验更佳。The use of TOF technology to obtain face-related data can obtain user-related face data without the user's perception, which requires less cooperation from the user and provides a better user experience.
在一种可能的实现方式中，在确定所述待检测人脸通过活体检测之后，还包括：In a possible implementation, after it is determined that the face to be detected has passed the liveness detection, it further includes:
根据所述第一特征向量和所述第二特征向量，确定所述待检测人脸对应的特征向量；determining a feature vector corresponding to the face to be detected according to the first feature vector and the second feature vector;
根据所述待检测人脸对应的特征向量以及预先存储的至少一个已检测人脸对应的特征向量，若确定所述至少一个已检测人脸中存在所述待检测人脸的相似人脸，则确定所述待检测人脸通过身份认证。According to the feature vector corresponding to the face to be detected and the pre-stored feature vector corresponding to at least one detected face, if it is determined that there is a similar face to the face to be detected in the at least one detected face, then It is determined that the face to be detected has passed identity authentication.
本发明实施例提供一种人脸的活体检测装置，所述装置包括：An embodiment of the present invention provides a human face biopsy detection device, the device comprising:
获取单元，用于获取待检测人脸在不同时刻对应的特征向量；以及获取所述待检测人脸中预设关键点在所述不同时刻对应的位置信息，所述位置信息为所述预设关键点在所述待检测人脸中的位置；所述预设关键点为能表征人脸表情的区域；An acquisition unit, configured to acquire feature vectors corresponding to the faces to be detected at different times; and acquire position information corresponding to preset key points in the faces to be detected at different times, the position information being the preset The position of the key point in the human face to be detected; the preset key point is an area that can represent facial expressions;
处理单元，用于根据所述不同时刻对应的特征向量及所述不同时刻对应的位置信息，确定所述待检测人脸的人脸变化度；若所述待检测人脸的人脸变化度大于预设阈值，则确定所述待检测人脸通过活体检测。A processing unit, configured to determine the face change degree of the face to be detected according to the feature vectors corresponding to the different moments and the position information corresponding to the different moments; if the face change degree of the face to be detected is greater than If the preset threshold is determined, it is determined that the face to be detected has passed the liveness detection.
在一种可能的实现方式中，所述处理单元具体用于：In a possible implementation manner, the processing unit is specifically configured to:
根据所述不同时刻对应的特征向量，确定特征相似度；并根据所述不同时刻对应的位置信息，确定位置变化度；以及根据所述特征相似度和所述位置变化度，确定所述待检测人脸的人脸变化度。Determine the feature similarity according to the feature vectors corresponding to the different moments; and determine the position change degree according to the position information corresponding to the different moments; and determine the to-be-detected according to the feature similarity and the position change degree The degree of facial variation of the face.
在一种可能的实现方式中，所述获取单元具体用于：In a possible implementation manner, the acquiring unit is specifically configured to:
获取所述待检测人脸的各分割区域在所述不同时刻对应的特征向量；所述各分割区域是根据人脸的五官位置确定的；Acquiring feature vectors corresponding to each segmented area of the human face to be detected at the different moments; each segmented area is determined according to the facial features of the face;
所述处理单元具体用于：The processing unit is specifically used for:
根据每个分割区域在所述不同时刻对应的特征向量，确定每个分割区域的特征相似度；Determine the feature similarity of each segmented area according to the feature vectors corresponding to each segmented area at the different moments;
以及根据每个分割区域的特征相似度和所述位置变化度，确定所述待检测人脸的人脸变化度。And according to the feature similarity of each segmented area and the position change degree, determine the face change degree of the face to be detected.
在一种可能的实现方式中，所述处理单元具体用于：In a possible implementation manner, the processing unit is specifically configured to:
针对任一预设关键点，确定所述预设关键点所属的分割区域；并根据所属的分割区域的特征相似度及所述预设关键点的位置变化度，确定所述分割区域的人脸变化度；以及根据各分割区域的人脸变化度，确定所述待检测人脸的人脸变化度。For any preset key point, determine the segmented area to which the preset key point belongs; and determine the face of the segmented area according to the feature similarity of the segmented area to which it belongs and the position change degree of the preset key point degree of change; and determining the degree of change of the face of the face to be detected according to the degree of change of the face of each segmented area.
在一种可能的实现方式中，所述分割区域包括嘴巴区域、鼻子区域、脸颊区域、眉毛区域、眼睛区域和前额区域。In a possible implementation manner, the segmented regions include a mouth region, a nose region, a cheek region, an eyebrow region, an eye region, and a forehead region.
在一种可能的实现方式中，所述获取单元具体用于：In a possible implementation manner, the acquiring unit is specifically configured to:
采用飞行时间TOF技术获取所述待检测人脸中预设关键点在所述不同时刻对应的位置信息；Obtaining the position information corresponding to the preset key points in the face to be detected at the different moments by using time-of-flight TOF technology;
或or
采用3D人脸重建技术获取所述待检测人脸中预设关键点在所述不同时刻对应的位置信息。Using a 3D face reconstruction technology to obtain position information corresponding to preset key points in the face to be detected at the different moments.
在一种可能的实现方式中，所述处理单元在确定所述待检测人脸通过活体检测之后，还用于：In a possible implementation manner, after determining that the face to be detected has passed the liveness detection, the processing unit is further configured to:
根据所述第一特征向量和所述第二特征向量，确定所述待检测人脸对应的特征向量；以及根据所述待检测人脸对应的特征向量以及预先存储的至少一个已检测人脸对应的特征向量，若确定所述至少一个已检测人脸中存在所述待检测人脸的相似人脸，则确定所述待检测人脸通过身份认证。According to the first feature vector and the second feature vector, determine the feature vector corresponding to the face to be detected; and according to the feature vector corresponding to the face to be detected and at least one pre-stored detected face corresponding If it is determined that there is a similar face to the face to be detected in the at least one detected face, it is determined that the face to be detected has passed the identity authentication.
本申请实施例的还提供一种装置，该装置具有实现上文所描述的人脸的活体检测方法的功能。该功能可以通过硬件执行相应的软件实现，在一种可能的设计中，该装置包括：处理器、收发器、存储器；该存储器用于存储计算机执行指令，该收发器用于实现该装置与其他通信实体进行通信，该处理器与该存储器通过该总线连接，当该装置运行时，该处理器执行该存储器存储的该计算机执行指令，以使该装置执行上文所描述的人脸的活体检测方法。An embodiment of the present application also provides a device, which has the function of implementing the method for detecting human face life as described above. This function can be implemented by hardware executing corresponding software. In a possible design, the device includes: a processor, a transceiver, and a memory; the memory is used to store computer-executed instructions, and the transceiver is used to realize the communication between the device and other The entity communicates, the processor and the memory are connected through the bus, and when the device is running, the processor executes the computer-executed instructions stored in the memory, so that the device executes the human face biopsy detection method described above .
本发明实施例还提供一种计算机存储介质，所述存储介质中存储软件程序，该软件程序在被一个或多个处理器读取并执行时实现上述各种可能的实现方式中所描述的人脸的活体检测方法。An embodiment of the present invention also provides a computer storage medium, where a software program is stored in the storage medium, and when the software program is read and executed by one or more processors, the above-mentioned various possible implementations are implemented. Face liveness detection method.
本发明实施例还提供一种包含指令的计算机程序产品，当其在计算机上运行时，使得计算机执行上述各种可能的实现方式中所描述的人脸的活体检测方法。An embodiment of the present invention also provides a computer program product containing instructions, which, when run on a computer, cause the computer to execute the human face biopsy detection method described in the various possible implementation manners above.
附图说明Description of drawings
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简要介绍。In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings that need to be used in the description of the embodiments.
图1为本发明实施例提供的一种人脸的活体检测方法所对应的流程示意图；FIG. 1 is a schematic flowchart corresponding to a human face liveness detection method provided by an embodiment of the present invention;
图2为本发明实施例提供的一种人脸的分割区域的示意图；FIG. 2 is a schematic diagram of a segmented region of a human face provided by an embodiment of the present invention;
图3a为眼睛对应的预设关键点的一种示意图；Fig. 3a is a schematic diagram of preset key points corresponding to eyes;
图3b为嘴巴对应的预设关键点的一种示意图；Fig. 3b is a schematic diagram of the preset key points corresponding to the mouth;
图4为预设关键点与分割区域的所属关系的示意图；FIG. 4 is a schematic diagram of the affiliation relationship between preset key points and segmented regions;
图5为本发明实施例中所涉及到的人脸的活体检测的整体性流程示意图；FIG. 5 is a schematic diagram of the overall flow of human face biopsy detection involved in the embodiment of the present invention;
图6为本发明实施例中所涉及到的采用活体检测技术进行身份认证流程示意图；FIG. 6 is a schematic diagram of an identity authentication process using a biopsy detection technology involved in an embodiment of the present invention;
图7为本发明实施例提供的一种人脸的活体检测装置的结构示意图。FIG. 7 is a schematic structural diagram of a human face biopsy detection device provided by an embodiment of the present invention.
具体实施方式Detailed ways
下面结合说明书附图对本申请进行具体说明，方法实施例中的具体操作方法也可以应用于装置实施例中。The present application will be described in detail below in conjunction with the accompanying drawings, and the specific operation methods in the method embodiments can also be applied to the device embodiments.
图1示例性示出了本发明实施例提供的一种人脸的活体检测方法所对应的流程示意图，如图1所示，包括如下步骤：Fig. 1 exemplarily shows a schematic flow chart corresponding to a human face liveness detection method provided by an embodiment of the present invention, as shown in Fig. 1 , including the following steps:
步骤101，获取待检测人脸在不同时刻对应的特征向量。Step 101, acquiring feature vectors corresponding to faces to be detected at different times.
步骤102，获取待检测人脸中预设关键点在不同时刻对应的位置信息。Step 102, acquiring position information corresponding to preset key points in the face to be detected at different times.
步骤103，根据不同时刻对应的特征向量及不同时刻对应的位置信息，确定待检测人脸的人脸变化度；Step 103, according to the eigenvectors corresponding to different moments and the position information corresponding to different moments, determine the face change degree of the face to be detected;
步骤104，若待检测人脸的人脸变化度大于预设阈值，则确定待检测人脸通过活体检测。Step 104, if the face change degree of the face to be detected is greater than a preset threshold, it is determined that the face to be detected passes the living body detection.
如此，可以通过判断待检测人脸中的预设关键点在不同时刻是否存在位置上的变化，可以确定待检测人脸是否为活体。采用这种方法，由于不法分子伪造的人脸模型是静态的，因此，本发明实施例提供的活体检测方法能够有效识别出伪造的人脸模型，从而提高人脸识别的安全性，进而提高人脸识别系统的可靠性。In this way, it can be determined whether the face to be detected is a living body by judging whether the preset key points in the face to be detected have position changes at different times. With this method, since the face models forged by criminals are static, the living body detection method provided by the embodiment of the present invention can effectively identify the forged face models, thereby improving the security of face recognition, and further improving the human body detection method. Reliability of facial recognition systems.
具体来说，步骤101和步骤102中，不同时刻可以是指两个不同时刻，或者也可以是指三个不同的时刻，或者还可以是指N个不同的时刻(N为大于1的整数)。为了便于描述，以下以两个不同时刻为例进行描述，即在步骤101中，获取待检测人脸在第一时刻和第二时刻分别对应的特征向量；在步骤102中，获取待检测人脸中预设关键点在第一时刻和第二时刻分别对应的位置信息，其中，第一时刻和第二时刻为两个不同的时刻。Specifically, in step 101 and step 102, different moments may refer to two different moments, or may also refer to three different moments, or may also refer to N different moments (N is an integer greater than 1) . For the convenience of description, two different moments are taken as examples below, that is, in step 101, the eigenvectors corresponding to the faces to be detected at the first moment and the second moment are obtained respectively; in step 102, the faces to be detected are obtained Position information corresponding to the preset key points at the first moment and the second moment respectively, wherein the first moment and the second moment are two different moments.
基于上述对不同时刻的解释，步骤101中，可以通过预设的神经网络模型对任一时刻的待检测人脸的人脸数据对应的特征进行提取，并根据提取到的特征获取待认证人脸在任一时刻对应的特征向量。Based on the above explanations at different times, in step 101, the features corresponding to the face data of the face to be detected at any time can be extracted through the preset neural network model, and the face to be authenticated can be obtained according to the extracted features The corresponding eigenvectors at any moment in time.
进一步地，预设的神经网络模型可以为多种类型的神经网络模型，比如，可以是2D深度神经网络模型，或者也可以是3D深度神经网络模型，具体不做限定。Further, the preset neural network model can be various types of neural network models, for example, it can be a 2D deep neural network model, or it can also be a 3D deep neural network model, which is not specifically limited.
考虑到待检测人脸的不同区域对面部表情的敏感程度是不同的，比如眼睛、嘴巴等区域的敏感程度相对较高，而脸颊、额头等区域对应的敏感程度相对较低，因此，本发明实施例可以将待检测人脸划分成多个分割区域，从而提高活体检测的准确率。其中，各分割区域可以是根据人脸的五官位置确定的。如图2所示，为本发明实施例提供的一种人脸的分割区域的示意图。如图2所示，可以将人脸分割成多个分割区域，比如分割区域可以是嘴巴区域，或者也可以是鼻子区域，或者也可以是脸颊区域，或者也可以是眉毛区域，或者也可以是眼睛区域，或者也可以是前额区域，具体不做限定。Considering that different areas of the human face to be detected have different sensitivities to facial expressions, for example, the sensitivities of areas such as eyes and mouth are relatively high, while the corresponding sensitivities of areas such as cheeks and forehead are relatively low. Therefore, the present invention In this embodiment, the human face to be detected can be divided into multiple segmentation regions, thereby improving the accuracy of living body detection. Wherein, each segmented area may be determined according to the facial features of the human face. As shown in FIG. 2 , it is a schematic diagram of a segmented region of a human face provided by an embodiment of the present invention. As shown in Figure 2, the human face can be divided into multiple segmentation regions, for example, the segmentation region can be the mouth region, or the nose region, or the cheek region, or the eyebrow region, or the The eye area, or also the forehead area, is not specifically limited.
基于图2所示的人脸的分割区域的示意，本发明实施例中，也可以获取待检测人脸的各分割区域在任一时刻对应的特征向量。具体来说，可以通过预设的神经网络模型对任一时刻的待检测人脸的某个分割区域的人脸数据对应的特征进行提取，并根据提取到的特征获取待认证人脸的某个分割区域在任一时刻对应的特征向量。Based on the schematic diagram of the segmented regions of the human face shown in FIG. 2 , in the embodiment of the present invention, the feature vector corresponding to each segmented region of the human face to be detected at any moment may also be obtained. Specifically, the features corresponding to the face data of a segmented area of the face to be detected at any time can be extracted through the preset neural network model, and a certain face of the face to be authenticated can be obtained according to the extracted features. The feature vector corresponding to the segmented area at any moment.
步骤102中，预设关键点可以是指能表征人脸表情的区域，比如，人在笑的时候，眼睛通常会弯起，那么，眼睛可以对应多个预设关键点，如图3a所示，为眼睛对应的预设关键点的一种示例，可以将眼角、眼尾、上眼睑的中心点、下眼睑的中心点以及眼球中心作为眼睛对应的预设关键点；再比如，人在哭的时候，嘴巴通常会抿住，那么，嘴巴也可以对应多个预设关键点，如图3b所示，为嘴巴对应的预设关键点的一种示例，可以将嘴角、上嘴唇的中心点、下嘴唇的中心点、门牙作为嘴巴对应的预设关键点。In step 102, the preset key points may refer to areas that can represent human facial expressions. For example, when a person smiles, the eyes are usually curved. Then, the eyes may correspond to multiple preset key points, as shown in FIG. 3a , is an example of the preset key points corresponding to the eyes. You can use the corners of the eyes, the end of the eyes, the center point of the upper eyelid, the center point of the lower eyelid, and the center of the eyeball as the preset key points corresponding to the eyes; another example is that a person is crying When , the mouth is usually closed, so the mouth can also correspond to multiple preset key points, as shown in Figure 3b, which is an example of the preset key points corresponding to the mouth. The corners of the mouth and the center point of the upper lip can be , the center point of the lower lip, and the front teeth are used as the preset key points corresponding to the mouth.
本发明实施例中，获取待检测人脸中预设关键点在任一时刻对应的位置信息的方式有多种，一种可能的实现方式为，可以采用飞行时间(Time Of Flight，TOF)技术获取待检测人脸中预设关键点在任一时刻对应的位置信息。具体来说，TOF技术可以通过向目标连续发送光脉冲，然后用传感器接收从物体返回的光，通过探测这些发射和接收光脉冲的飞行(往返)时间来得到目标物距离。本发明实施例中，可以将TOF技术应用到摄像头上，从而获取待检测人脸中预设关键点在任一时刻对应的位置信息(比如坐标数据)。采用TOF技术获取人脸的相关数据，可以在用户无感知的情况下，获取用户人脸的相关数据，对用户的配合度要求较低，用户的体验更佳。In the embodiment of the present invention, there are many ways to obtain the position information corresponding to the preset key points in the face to be detected at any time, and one possible implementation method is that Time Of Flight (TOF) technology can be used to obtain The position information corresponding to the preset key points in the face to be detected at any moment. Specifically, TOF technology can continuously send light pulses to the target, and then use the sensor to receive the light returned from the object, and obtain the target object distance by detecting the flight (round-trip) time of these emitted and received light pulses. In the embodiment of the present invention, the TOF technology can be applied to the camera, so as to obtain the position information (such as coordinate data) corresponding to the preset key points in the face to be detected at any moment. The use of TOF technology to obtain face-related data can obtain user-related face data without the user's perception, which requires less cooperation from the user and provides a better user experience.
另一种可能的实现发送中，可以采用人脸重建技术获取待检测人脸中预设关键点在任一时刻对应的位置信息。具体来说，对于采集到的人脸图像(比如监控视频中每一帧的人脸图像)，可以采用基于级联回归(Cascaded Regression，CR)方法，生成一个由多个弱回归级联组成的强回归，再结合深度学习算法，实现端到端的重建，如此，输入一张人脸图像，可以直接输出人脸的3D模型，进而，根据该人脸的3D模型可以确定待检测人脸中预设关键点在任一时刻对应的位置信息(比如坐标数据)。In another possible implementation of sending, the face reconstruction technology can be used to obtain the position information corresponding to the preset key points in the face to be detected at any time. Specifically, for the collected face images (such as the face images of each frame in the surveillance video), a cascaded regression (Cascaded Regression, CR) method can be used to generate a cascade of multiple weak regressions. Strong regression, combined with deep learning algorithms, realizes end-to-end reconstruction. In this way, inputting a face image can directly output the 3D model of the face, and then, according to the 3D model of the face, the predicted Set the position information (such as coordinate data) corresponding to the key point at any time.
在其它可能的实现方式中，也采用其它方法获取待检测人脸中预设关键点在任一时刻对应的位置信息，比如通过待认证用户手动输入的方式获取待检测人脸中预设关键点在任一时刻对应的位置信息，具体不做限定。In other possible implementations, other methods are also used to obtain the position information corresponding to the preset key points in the face to be detected at any time, such as obtaining the preset key points in the face to be detected at any time through manual input by the user to be authenticated. The location information corresponding to a moment is not specifically limited.
同样考虑到待检测人脸的不同区域对面部表情的敏感程度的不同，在图2示出的人脸的各分割区域的基础上，本发明实施例中，在获取到预设关键点在任一时刻对应的位置信息之后，还可以各分割区域对应的位置，进一步确定每个预设关键点所属的分割区域。举个例子，如图4所示，为预设关键点与分割区域的所属关系的示意图，假设待检测人脸具有图4中示出的编号为1～30的30个预设关键点，并且，待检测人脸具有图4中虚线框出的前额区域、眉毛区域、眼睛区域、鼻子区域、嘴巴区域和脸颊区域共6个分割区域，结合各预设关键点的位置信息以及各分割区域的位置，可以确定出各预设关键点所属的分割区域。Considering the sensitivity of facial expressions in different areas of the human face to be detected, on the basis of each segmented area of the human face shown in FIG. After the location information corresponding to the time, the location corresponding to each segmented area can also be used to further determine the segmented area to which each preset key point belongs. For example, as shown in Figure 4, it is a schematic diagram of the relationship between the preset key points and the segmented area, assuming that the face to be detected has 30 preset key points numbered 1 to 30 shown in Figure 4, and , the face to be detected has 6 segmentation areas, including the forehead area, eyebrow area, eye area, nose area, mouth area, and cheek area, which are framed by dotted lines in Figure 4. Combining the position information of each preset key point and the position, the segmented area to which each preset key point belongs can be determined.
步骤103中，待检测人脸的人脸变化度可以根据不同时刻对应的特征向量及不同时刻预设关键点对应的位置信息来确定。具体的确定方式有多种，一种可能的实现方式为，根据待检测人脸在不同时刻对应的特征向量，确定特征相似度，并根据待检测人脸在中预设关键点在不同时刻对应的位置信息，确定位置变化度，以及根据特征相似度和位置变化度，确定待检测人脸的人脸变化度。In step 103, the face change degree of the face to be detected can be determined according to the feature vectors corresponding to different moments and the position information corresponding to preset key points at different moments. There are many specific determination methods. One possible implementation method is to determine the feature similarity according to the feature vectors corresponding to the faces to be detected at different times, and to preset key points corresponding to the faces at different times according to the faces to be detected. position information, determine the position change degree, and determine the face change degree of the face to be detected according to the feature similarity and the position change degree.
即，待检测人脸的人脸变化度可以根据公式(1)确定：That is, the face change degree of the face to be detected can be determined according to formula (1):
Δ＝λ1·S-λ2·D 公式(1)Δ＝λ1 ·S-λ2 ·D Formula (1)
公式(1)中，Δ为待检测人脸的人脸变化度；S为特征变化度；D位置变化度；λ1为特征变化度对应的权重；λ2为位置变化度对应的权重。In the formula (1), Δ is the degree of change of the face of the face to be detected; S is the degree of change of the feature; D the degree of position change;λ1 is the weight corresponding to the degree of feature change;λ2 is the weight corresponding to the degree of position change.
考虑到本发明实施例中可以采用对待检测人脸进行分割的方式，获取待检测人脸的各分割区域在不同时刻对应的特征向量。基于此，若获取到的是待检测人脸的各分割区域在不同时刻对应的特征向量，则可以根据每个分割区域在不同时刻对应的特征向量，确定每个分割区域的特征相似度；且可以根据每个分割区域中包括的预设关键点的位置变化度，确定每个分割区域的位置变化度；进而，可以根据每个分割区域的特征相似度和位置变化度，确定每个分割区域的人脸变化度，进而确定待检测人脸的人脸变化度。Considering that in the embodiment of the present invention, the face to be detected can be segmented, and the feature vectors corresponding to each segmented area of the face to be detected at different moments are obtained. Based on this, if the feature vectors corresponding to each segmented area of the face to be detected are obtained at different times, the feature similarity of each segmented area can be determined according to the feature vectors corresponding to each segmented area at different times; and The position change degree of each segmented region can be determined according to the position change degree of preset key points included in each segmented region; furthermore, the position change degree of each segmented region can be determined according to the feature similarity and position change degree of each segmented region. The face change degree of the face, and then determine the face change degree of the face to be detected.
更进一步地，每个分割区域的位置变化度可以根据公式(2)确定：Furthermore, the position change degree of each segmented area can be determined according to formula (2):
公式(2)中，Di为第i个分割区域的位置变化度，1≤i≤M，M为待检测人脸中的分割区域的数量，M为大于1的整数；dij为不同时刻下第i个分割区域中的第j个预设关键点的欧式距离，1≤j≤n，n为第i个分割区域中的预设关键点的数量，n为大于1的整数。In formula (2), Di is the degree of position change of the i-th segmented area, 1≤i≤M, M is the number of segmented areas in the face to be detected, and M is an integer greater than 1; dij is different moments The Euclidean distance of the j-th preset key point in the next i-th segmented area, 1≤j≤n, n is the number of preset key points in the i-th segmented area, and n is an integer greater than 1.
需要说明的是，公式(2)仅为一种示例，本领域技术人员也可以采用其它方式来计算每个分割区域的位置变化度，比如采用向量的方式来计算，具体不做限定。It should be noted that the formula (2) is only an example, and those skilled in the art may also use other methods to calculate the position change degree of each segmented region, such as using a vector method to calculate, which is not specifically limited.
进而，根据每个分割区域的特征变化度和每个分割区域的位置变化度，可以确定每个分割区域的人脸变化度。每个分割区域的人脸变化度可以根据公式(3)确定：Furthermore, according to the feature variation degree of each segmented region and the positional variation degree of each segmented region, the face variation degree of each segmented region can be determined. The face change degree of each segmented area can be determined according to formula (3):
公式(3)中，δi为第i个分割区域的人脸变化度，1≤i≤M，M为待检测人脸中的分割区域的数量，M为大于1的整数；Si为第i个分割区域的特征变化度；Di为第i个分割区域的位置变化度；λ1为特征变化度对应的权重；λ2为位置变化度对应的权重。In the formula (3), δi is the face change degree of the i-th segmented area, 1≤i≤M, M is the number of segmented areas in the face to be detected, and M is an integer greater than 1; Si is the The feature change degree of the i segmented area; Di is the position change degree of the i-th segmented area; λ1 is the weight corresponding to the feature change degree; λ2 is the weight corresponding to the position change degree.
进而，待检测人脸的人脸变化度可以根据公式(4)确定：Furthermore, the face change degree of the face to be detected can be determined according to formula (4):
公式(4)中，Δ为待检测人脸的人脸变化度；δi为第i个分割区域的人脸变化度，1≤i≤M，M为待检测人脸中的分割区域的数量，M为大于1的整数；ωi为第i个分割区域对应的权重。In formula (4), Δ is the face change degree of the face to be detected; δi is the face change degree of the i-th segmented area, 1≤i≤M, and M is the number of segmented areas in the face to be detected , M is an integer greater than 1; ωi is the weight corresponding to the i-th segmented region.
需要说明的是，公式(4)仅为一种示例，本领域技术人员在得到每个分割区域的人脸变化度的基础上，还可以采用其它的方式来确定待检测人脸的人脸变化度。例如，如公式(5)所示，为另一种待检测人脸的人脸变化度的确定方式。It should be noted that formula (4) is only an example, and those skilled in the art can also use other methods to determine the face change of the face to be detected on the basis of obtaining the face change degree of each segmented area. Spend. For example, as shown in formula (5), it is another way of determining the degree of face change of the face to be detected.
公式(5)中，Δ为待检测人脸的人脸变化度；如果δi≤Thri，则(Thri-δi)+＝1；否则，(Thri-δi)+＝0。In formula (5), Δ is the face change degree of the face to be detected; if δi ≤ Thri , then (Thri −δi )+ =1; otherwise, (Thri −δi )+ =0.
需要说明的是，公式(5)中，根据不同分割区域对表情变化的敏感度，为每个分割区域设定不同的阈值(即Thri)，敏感度越高，人脸变化越显著，相似度越小，因此设置的阈值越小。换言之，如果某一分割区域的相似度δi≤Thri，那么代表该分割区域的表情发生变化；否则，代表该分割区域的表情未发生变化。It should be noted that in formula (5), different thresholds (ie Thri ) are set for each segmented area according to the sensitivity of different segmented areas to expression changes. The higher the sensitivity, the more significant the face change, similar to The smaller the degree is, the smaller the threshold is set. In other words, if the similarity δi ≤ Thri of a segmented region, it means that the expression of the segmented region has changed; otherwise, it means that the expression of the segmented region has not changed.
在其它可能的实现方式中，也可以将待检测人脸在不同时刻对应的特征向量和预设关键点在不同时刻对应的位置信息输入预先训练好的相似度模型，从而确定待检测人脸的人脸变化度，具体不做限定。In other possible implementations, the feature vectors corresponding to the faces to be detected at different times and the position information corresponding to the preset key points at different times can also be input into the pre-trained similarity model, so as to determine the The degree of face change is not limited.
步骤104中，可以通过判断待检测人脸的人脸变化度是否大于预设阈值来确定待检测人脸是否通过活体检测，若大于，则可以确定待检测人脸通过活体检测；否则，可以确定待检测人脸未通过活体检测。其中，预设阈值可以是本领域技术人员根据经验和实际情况确定的，具体不做限定。In step 104, it can be determined whether the face to be detected has passed the liveness detection by judging whether the degree of change of the face to be detected is greater than a preset threshold, if greater, it can be determined that the face to be detected has passed the liveness detection; otherwise, it can be determined The face to be detected failed the liveness detection. Wherein, the preset threshold may be determined by those skilled in the art based on experience and actual conditions, and is not specifically limited.
举个例子，以采用公式(4)计算得到的待检测人脸的人脸变化度为例，如果该待检测人脸的人脸变化度Δ大于预设阈值，则确定待检测人脸在不同时刻发生变化，认为面部表情变化捕捉成功，从而确定待检测人员通过活体检测；否则，确定待检测人脸在不同时刻未发生变化，认为面部表情变化捕捉失败，从而确定待检测人员未通过活体检测。For example, take the face change degree of the face to be detected calculated by formula (4) as an example, if the face change degree Δ of the face to be detected is greater than the preset threshold, it is determined that the face to be detected is in different If the time changes, it is considered that the facial expression change capture is successful, so as to determine that the person to be detected has passed the liveness detection; otherwise, it is determined that the face to be detected has not changed at different times, and it is considered that the facial expression change capture has failed, so as to determine that the person to be detected has not passed the liveness detection .
再举个例子，以采用公式(5)计算得到的待检测人脸的人脸变化度为例，如果Δ≥M/2，即表示待检测人脸中在不同时刻发生变化的分割区域的数量超过半数，则认为面部表情变化捕捉成功，从而确定待检测人员通过活体检测；否则，表示待检测人脸中在不同时刻发生变化的分割区域的数量未超过半数，则认为面部表情变化捕捉失败，从而确定待检测人员未通过活体检测。For another example, take the face change degree of the face to be detected calculated by formula (5) as an example, if Δ≥M/2, it means the number of segmented regions in the face to be detected that change at different times If more than half, it is considered that the facial expression change capture is successful, so as to determine that the person to be detected has passed the liveness detection; otherwise, it means that the number of segmented regions that change at different times in the face to be detected is not more than half, then it is considered that the facial expression change capture has failed, Therefore, it is determined that the person to be tested has not passed the liveness test.
为了更清楚地介绍上述人脸的活体检测方法，下面结合图5，对本发明实施例中所涉及到的人脸的活体检测流程进行整体性说明。具体可参加图5示出的内容，此处不再详细介绍。In order to more clearly introduce the above-mentioned liveness detection method of a human face, the flow of liveness detection of a human face involved in the embodiment of the present invention will be described as a whole below with reference to FIG. 5 . Specifically, reference may be made to the content shown in FIG. 5 , which will not be described in detail here.
本发明实施例中，在执行步骤104之后，还可以进行人脸识别，从而确定待检测人脸是否通过身份认证。具体来说，人脸识别的方式可以是根据第一特征向量和第二特征向量，确定待检测人脸对应的特征向量；进而，可以根据待检测人脸对应的特征向量以及预先存储的至少一个已检测人脸对应的特征向量，若确定至少一个已检测人脸中存在待检测人脸的相似人脸，则可以确定待检测人脸通过身份认证。In the embodiment of the present invention, after step 104 is executed, face recognition may also be performed, so as to determine whether the face to be detected has passed identity authentication. Specifically, the way of face recognition can be to determine the feature vector corresponding to the face to be detected according to the first feature vector and the second feature vector; furthermore, it can be based on the feature vector corresponding to the face to be detected and at least one pre-stored For the feature vectors corresponding to the detected faces, if it is determined that there is a similar face to the face to be detected in at least one of the detected faces, it can be determined that the face to be detected has passed the identity authentication.
在其它可能是实现方式中，人脸识别的方式也可以是采用现有的基于深度神经网络模型对待检测人脸进行识别，具体不做限定。In other possible implementation manners, the manner of face recognition may also be to use an existing deep neural network model to recognize the face to be detected, which is not specifically limited.
下面以活体检测技术进行身份认证为例，结合图6，对本发明实施例中所涉及到的采用活体检测技术进行身份认证流程做整体性说明。具体可参加图6示出的内容，此处不再详细介绍。In the following, identity authentication using the living body detection technology is taken as an example, and with reference to FIG. 6 , an overall description of the identity authentication process using the living body detection technology involved in the embodiment of the present invention is given. Specifically, reference may be made to the content shown in FIG. 6 , which will not be described in detail here.
基于同样的发明构思，图7示例性示出了本发明实施例提供的一种人脸的活体检测装置的结构示意图，如图7所示，该装置包括获取单元201和处理单元202；其中，Based on the same inventive concept, FIG. 7 exemplarily shows a schematic structural diagram of a human face biopsy detection device provided by an embodiment of the present invention. As shown in FIG. 7 , the device includes an acquisition unit 201 and a processing unit 202; wherein,
获取单元201，用于获取待检测人脸在不同时刻对应的特征向量；以及获取所述待检测人脸中预设关键点在所述不同时刻对应的位置信息，所述位置信息为所述预设关键点在所述待检测人脸中的位置；所述预设关键点为能表征人脸表情的区域；The acquiring unit 201 is configured to acquire feature vectors corresponding to the faces to be detected at different times; and acquire position information corresponding to preset key points in the faces to be detected at different times, the position information being the preset Set the position of the key point in the described human face to be detected; the preset key point is an area that can represent facial expressions;
处理单元202，用于根据所述不同时刻对应的特征向量及所述不同时刻对应的位置信息，确定所述待检测人脸的人脸变化度；若所述待检测人脸的人脸变化度大于预设阈值，则确定所述待检测人脸通过活体检测。The processing unit 202 is configured to determine the degree of change of the face of the face to be detected according to the feature vectors corresponding to the different moments and the position information corresponding to the different moments; if the degree of change of the face of the face to be detected is If it is greater than the preset threshold, it is determined that the face to be detected has passed the liveness detection.
在一种可能的实现方式中，所述处理单元202具体用于：In a possible implementation manner, the processing unit 202 is specifically configured to:
根据所述不同时刻对应的特征向量，确定特征相似度；并根据所述不同时刻对应的位置信息，确定位置变化度；以及根据所述特征相似度和所述位置变化度，确定所述待检测人脸的人脸变化度。Determine the feature similarity according to the feature vectors corresponding to the different moments; and determine the position change degree according to the position information corresponding to the different moments; and determine the to-be-detected according to the feature similarity and the position change degree The degree of facial variation of the face.
在一种可能的实现方式中，所述获取单元201具体用于：In a possible implementation manner, the acquiring unit 201 is specifically configured to:
获取所述待检测人脸的各分割区域在所述不同时刻对应的特征向量；所述各分割区域是根据人脸的五官位置确定的；Acquiring feature vectors corresponding to each segmented area of the human face to be detected at the different moments; each segmented area is determined according to the facial features of the face;
所述处理单元202具体用于：The processing unit 202 is specifically used for:
根据每个分割区域在所述不同时刻对应的特征向量，确定每个分割区域的特征相似度；Determine the feature similarity of each segmented area according to the feature vectors corresponding to each segmented area at the different moments;
以及根据每个分割区域的特征相似度和所述位置变化度，确定所述待检测人脸的人脸变化度。And according to the feature similarity of each segmented area and the position change degree, determine the face change degree of the face to be detected.
在一种可能的实现方式中，所述处理单元202具体用于：In a possible implementation manner, the processing unit 202 is specifically configured to:
针对任一预设关键点，确定所述预设关键点所属的分割区域；并根据所属的分割区域的特征相似度及所述预设关键点的位置变化度，确定所述分割区域的人脸变化度；以及根据各分割区域的人脸变化度，确定所述待检测人脸的人脸变化度。For any preset key point, determine the segmented area to which the preset key point belongs; and determine the face of the segmented area according to the feature similarity of the segmented area to which it belongs and the position change degree of the preset key point degree of change; and determining the degree of change of the face of the face to be detected according to the degree of change of the face of each segmented area.
在一种可能的实现方式中，所述分割区域包括嘴巴区域、鼻子区域、脸颊区域、眉毛区域、眼睛区域和前额区域。In a possible implementation manner, the segmented regions include a mouth region, a nose region, a cheek region, an eyebrow region, an eye region, and a forehead region.
在一种可能的实现方式中，所述获取单元201具体用于：In a possible implementation manner, the acquiring unit 201 is specifically configured to:
采用飞行时间TOF技术获取所述待检测人脸中预设关键点在所述不同时刻对应的位置信息；Obtaining the position information corresponding to the preset key points in the face to be detected at the different moments by using time-of-flight TOF technology;
或or
采用3D人脸重建技术获取所述待检测人脸中预设关键点在所述不同时刻对应的位置信息。Using a 3D face reconstruction technology to obtain position information corresponding to preset key points in the face to be detected at the different moments.
在一种可能的实现方式中，所述处理单元202在确定所述待检测人脸通过活体检测之后，还用于：In a possible implementation manner, after the processing unit 202 determines that the face to be detected has passed the liveness detection, it is further configured to:
根据所述第一特征向量和所述第二特征向量，确定所述待检测人脸对应的特征向量；以及根据所述待检测人脸对应的特征向量以及预先存储的至少一个已检测人脸对应的特征向量，若确定所述至少一个已检测人脸中存在所述待检测人脸的相似人脸，则确定所述待检测人脸通过身份认证。According to the first feature vector and the second feature vector, determine the feature vector corresponding to the face to be detected; and according to the feature vector corresponding to the face to be detected and at least one pre-stored detected face corresponding If it is determined that there is a similar face to the face to be detected in the at least one detected face, it is determined that the face to be detected has passed the identity authentication.
本申请实施例的还提供一种装置，该装置具有实现上文所描述的人脸的活体检测方法的功能。该功能可以通过硬件执行相应的软件实现，在一种可能的设计中，该装置包括：处理器、收发器、存储器；该存储器用于存储计算机执行指令，该收发器用于实现该装置与其他通信实体进行通信，该处理器与该存储器通过该总线连接，当该装置运行时，该处理器执行该存储器存储的该计算机执行指令，以使该装置执行上文所描述的人脸的活体检测方法。An embodiment of the present application also provides a device, which has the function of implementing the method for detecting human face life as described above. This function can be implemented by hardware executing corresponding software. In a possible design, the device includes: a processor, a transceiver, and a memory; the memory is used to store computer-executed instructions, and the transceiver is used to realize the communication between the device and other The entity communicates, the processor and the memory are connected through the bus, and when the device is running, the processor executes the computer-executed instructions stored in the memory, so that the device executes the human face biopsy detection method described above .
本发明实施例还提供一种计算机存储介质，所述存储介质中存储软件程序，该软件程序在被一个或多个处理器读取并执行时实现上述各种可能的实现方式中所描述的人脸的活体检测方法。An embodiment of the present invention also provides a computer storage medium, where a software program is stored in the storage medium, and when the software program is read and executed by one or more processors, the above-mentioned various possible implementations are implemented. Face liveness detection method.
本发明实施例还提供一种包含指令的计算机程序产品，当其在计算机上运行时，使得计算机执行上述各种可能的实现方式中所描述的人脸的活体检测方法。An embodiment of the present invention also provides a computer program product containing instructions, which, when run on a computer, cause the computer to execute the human face biopsy detection method described in the various possible implementation manners above.
本领域内的技术人员应明白，本发明的实施例可提供为方法、系统、或计算机程序产品。因此，本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, systems, or computer program products. Accordingly, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart or blocks of the flowchart and/or the block or blocks of the block diagrams.
尽管已描述了本发明的优选实施例，但本领域内的技术人员一旦得知了基本创造性概念，则可对这些实施例作出另外的变更和修改。所以，所附权利要求意欲解释为包括优选实施例以及落入本发明范围的所有变更和修改。While preferred embodiments of the invention have been described, additional changes and modifications to these embodiments can be made by those skilled in the art once the basic inventive concept is appreciated. Therefore, it is intended that the appended claims be construed to cover the preferred embodiment as well as all changes and modifications which fall within the scope of the invention.
显然，本领域的技术人员可以对本发明进行各种改动和变型而不脱离本发明的精神和范围。这样，倘若本发明的这些修改和变型属于本发明权利要求及其等同技术的范围之内，则本发明也意图包含这些改动和变型在内。Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these modifications and variations.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811572285.0ACN109766785B (en) | 2018-12-21 | 2018-12-21 | Method and device for liveness detection of human face |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811572285.0ACN109766785B (en) | 2018-12-21 | 2018-12-21 | Method and device for liveness detection of human face |
| Publication Number | Publication Date |
|---|---|
| CN109766785A CN109766785A (en) | 2019-05-17 |
| CN109766785Btrue CN109766785B (en) | 2023-09-01 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811572285.0AActiveCN109766785B (en) | 2018-12-21 | 2018-12-21 | Method and device for liveness detection of human face |
| Country | Link |
|---|---|
| CN (1) | CN109766785B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112132996A (en)* | 2019-06-05 | 2020-12-25 | Tcl集团股份有限公司 | Door lock control method, mobile terminal, door control terminal and storage medium |
| CN112395902A (en)* | 2019-08-12 | 2021-02-23 | 北京旷视科技有限公司 | Face living body detection method, image classification method, device, equipment and medium |
| CN110458098B (en)* | 2019-08-12 | 2023-06-16 | 上海天诚比集科技有限公司 | Face comparison method for face angle measurement |
| CN110728215A (en)* | 2019-09-26 | 2020-01-24 | 杭州艾芯智能科技有限公司 | Face living body detection method and device based on infrared image |
| CN111274879B (en)* | 2020-01-10 | 2023-04-25 | 北京百度网讯科技有限公司 | Method and device for detecting reliability of biopsy model |
| CN111783644B (en)* | 2020-06-30 | 2023-07-14 | 百度在线网络技术（北京）有限公司 | Detection method, detection device, detection equipment and computer storage medium |
| CN112927382B (en)* | 2021-02-03 | 2023-01-10 | 广东共德信息科技有限公司 | Face recognition attendance system and method based on GIS service |
| CN112819986A (en)* | 2021-02-03 | 2021-05-18 | 广东共德信息科技有限公司 | Attendance system and method |
| CN112927383B (en)* | 2021-02-03 | 2022-12-02 | 广东共德信息科技有限公司 | Cross-regional labor worker face recognition system and method based on building industry |
| CN116758643A (en)* | 2023-05-26 | 2023-09-15 | 支付宝(杭州)信息技术有限公司 | Method and device for detecting deeply forged face image |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104348778A (en)* | 2013-07-25 | 2015-02-11 | 信帧电子技术（北京）有限公司 | Remote identity authentication system, terminal and method carrying out initial face identification at handset terminal |
| CN104361326A (en)* | 2014-11-18 | 2015-02-18 | 新开普电子股份有限公司 | Method for distinguishing living human face |
| CN105389554A (en)* | 2015-11-06 | 2016-03-09 | 北京汉王智远科技有限公司 | Live body discrimination method and device based on face recognition |
| CN105447432A (en)* | 2014-08-27 | 2016-03-30 | 北京千搜科技有限公司 | Face anti-fake method based on local motion pattern |
| CN106850648A (en)* | 2015-02-13 | 2017-06-13 | 腾讯科技（深圳）有限公司 | Auth method, client and service platform |
| CN107220590A (en)* | 2017-04-24 | 2017-09-29 | 广东数相智能科技有限公司 | A kind of anti-cheating network research method based on In vivo detection, apparatus and system |
| CN107330914A (en)* | 2017-06-02 | 2017-11-07 | 广州视源电子科技股份有限公司 | Human face part motion detection method and device and living body identification method and system |
| CN107346422A (en)* | 2017-06-30 | 2017-11-14 | 成都大学 | A kind of living body faces recognition methods based on blink detection |
| CN107886070A (en)* | 2017-11-10 | 2018-04-06 | 北京小米移动软件有限公司 | Verification method, device and the equipment of facial image |
| CN107992842A (en)* | 2017-12-13 | 2018-05-04 | 深圳云天励飞技术有限公司 | Biopsy method, computer installation and computer-readable recording medium |
| CN108805047A (en)* | 2018-05-25 | 2018-11-13 | 北京旷视科技有限公司 | A kind of biopsy method, device, electronic equipment and computer-readable medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107451510B (en)* | 2016-05-30 | 2023-07-21 | 北京旷视科技有限公司 | Living body detection method and living body detection system |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104348778A (en)* | 2013-07-25 | 2015-02-11 | 信帧电子技术（北京）有限公司 | Remote identity authentication system, terminal and method carrying out initial face identification at handset terminal |
| CN105447432A (en)* | 2014-08-27 | 2016-03-30 | 北京千搜科技有限公司 | Face anti-fake method based on local motion pattern |
| CN104361326A (en)* | 2014-11-18 | 2015-02-18 | 新开普电子股份有限公司 | Method for distinguishing living human face |
| CN106850648A (en)* | 2015-02-13 | 2017-06-13 | 腾讯科技（深圳）有限公司 | Auth method, client and service platform |
| CN105389554A (en)* | 2015-11-06 | 2016-03-09 | 北京汉王智远科技有限公司 | Live body discrimination method and device based on face recognition |
| CN107220590A (en)* | 2017-04-24 | 2017-09-29 | 广东数相智能科技有限公司 | A kind of anti-cheating network research method based on In vivo detection, apparatus and system |
| CN107330914A (en)* | 2017-06-02 | 2017-11-07 | 广州视源电子科技股份有限公司 | Human face part motion detection method and device and living body identification method and system |
| CN107346422A (en)* | 2017-06-30 | 2017-11-14 | 成都大学 | A kind of living body faces recognition methods based on blink detection |
| CN107886070A (en)* | 2017-11-10 | 2018-04-06 | 北京小米移动软件有限公司 | Verification method, device and the equipment of facial image |
| CN107992842A (en)* | 2017-12-13 | 2018-05-04 | 深圳云天励飞技术有限公司 | Biopsy method, computer installation and computer-readable recording medium |
| CN108805047A (en)* | 2018-05-25 | 2018-11-13 | 北京旷视科技有限公司 | A kind of biopsy method, device, electronic equipment and computer-readable medium |
| Publication number | Publication date |
|---|---|
| CN109766785A (en) | 2019-05-17 |
| Publication | Publication Date | Title |
|---|---|---|
| CN109766785B (en) | Method and device for liveness detection of human face | |
| KR102483642B1 (en) | Method and apparatus for liveness test | |
| US11790494B2 (en) | Facial verification method and apparatus based on three-dimensional (3D) image | |
| US20240161539A1 (en) | Facial verification method and apparatus | |
| CN105612533B (en) | Living body detection method, living body detection system, and computer program product | |
| CN106897658B (en) | Method and device for identifying living body of human face | |
| KR102357340B1 (en) | Method and apparatus for face recognition | |
| CN106557723B (en) | A face identity authentication system with interactive liveness detection and method thereof | |
| WO2015165365A1 (en) | Facial recognition method and system | |
| EP3825905A1 (en) | Method and apparatus with liveness test and/or biometric authentication, computer program therefore and medium storing the same | |
| US12014578B2 (en) | Authentication device, authentication method, and recording medium | |
| US20180075291A1 (en) | Biometrics authentication based on a normalized image of an object | |
| CN106663157A (en) | User authentication method, device for executing same, and recording medium for storing same | |
| US10360441B2 (en) | Image processing method and apparatus | |
| US11048926B2 (en) | Adaptive hand tracking and gesture recognition using face-shoulder feature coordinate transforms | |
| CN108229493A (en) | Object verification method and device and electronic equipment | |
| WO2020195732A1 (en) | Image processing device, image processing method, and recording medium in which program is stored | |
| US11568681B2 (en) | Iris authentication device, iris authentication method and recording medium | |
| Mehta et al. | Regenerating vital facial keypoints for impostor identification from disguised images using CNN | |
| KR20210050649A (en) | Face verifying method of mobile device | |
| CN111652019A (en) | Face living body detection method and device | |
| Hemalatha et al. | A study of liveness detection in face biometric systems | |
| Dixit et al. | SIFRS: Spoof Invariant Facial Recognition System (A Helping Hand for Visual Impaired People) | |
| CN115116146A (en) | Liveness detection method, device, equipment and system |
| 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 |