CN106295672B - A kind of face identification method and device - Google Patents
A kind of face identification method and device Download PDFInfo
- Publication number
- CN106295672B CN106295672B CN201510323032.XA CN201510323032A CN106295672B CN 106295672 B CN106295672 B CN 106295672B CN 201510323032 A CN201510323032 A CN 201510323032A CN 106295672 B CN106295672 B CN 106295672B
- Authority
- CN
- China
- Prior art keywords
- face information
- face
- recognized
- preset threshold
- distance value
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/169—Holistic features and representations, i.e. based on the facial image taken as a whole
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
Abstract
本发明公开了一种人脸识别方法及装置，其方法包括：获取视频流中当前帧的待识别人脸信息与存储于人脸特征库中的参考人脸信息的特征距离值；根据特征距离值与预设阈值的关系，判断待识别人脸信息与参考人脸信息是否匹配；若待识别人脸信息与参考人脸信息匹配，则提高预设阈值的值作为新的预设阈值。本发明通过采用与前一帧的待识别人脸信息的匹配结果相关的动态阈值，避免了因周边环境变化而影响待识别人脸信息与参考人脸信息的特征距离值，进而导致误识别的现象，提高了人脸识别的识别成功率。
The invention discloses a face recognition method and device, the method comprising: obtaining the feature distance value between the face information to be recognized in the current frame of the video stream and the reference face information stored in the face feature database; The relationship between the value and the preset threshold is used to determine whether the face information to be recognized matches the reference face information; if the face information to be recognized matches the reference face information, the value of the preset threshold is increased as a new preset threshold. In the present invention, by adopting a dynamic threshold related to the matching result of the face information to be recognized in the previous frame, it avoids the influence of the surrounding environment changes on the characteristic distance value between the face information to be recognized and the reference face information, thereby causing misidentification. This phenomenon improves the recognition success rate of face recognition.
Description
技术领域technical field
本发明涉及信息安全及身份认证领域，尤其涉及一种人脸识别方法及装置。The invention relates to the fields of information security and identity authentication, in particular to a face recognition method and device.
背景技术Background technique
视频人脸识别由于具有易于操作、稳定性好等特点潜藏巨大的商业价值，成为近年的研究热点，在海关、公安部门、公司门禁等各个领域都得到了很好的应用。相信如果将视频人脸识别应用到营业厅的身份认证，取代原有的手机号和密码认证方式，会大大减少营业厅的身份认证时长。Video face recognition has become a research hotspot in recent years due to its characteristics of easy operation and good stability and potential huge commercial value. It has been well applied in various fields such as customs, public security departments, and company access control. It is believed that if the video face recognition is applied to the identity authentication of the business hall to replace the original mobile phone number and password authentication method, the identity authentication time of the business hall will be greatly reduced.
目前人脸识别的成功率很大程度上依赖于从开始就设定好的阈值是否适用，不同的光照、姿态、角度、表情的变化，都会使识别成功率急剧下降。如此一来，当某一个人在被识别时，如果某些帧的图像识别的效果不好，会导致识别失败或是误识别为其他人，从而造成识别的断档。At present, the success rate of face recognition depends largely on whether the threshold value set from the beginning is applicable. Different lighting, posture, angle, and expression changes will cause the recognition success rate to drop sharply. In this way, when a person is being recognized, if the image recognition effect of some frames is not good, the recognition will fail or be mistakenly recognized as another person, resulting in a gap in recognition.
发明内容Contents of the invention
为了解决上述技术问题，本发明提供了一种人脸识别方法及装置，解决了现有人脸识别技术中使用固定的预设阈值，识别成功率低的问题。In order to solve the above technical problems, the present invention provides a face recognition method and device, which solves the problem of low recognition success rate due to the use of fixed preset thresholds in the existing face recognition technology.
依据本发明的一个方面，提供了一种人脸识别方法，包括：According to one aspect of the present invention, a face recognition method is provided, including:
获取视频流中当前帧的待识别人脸信息与存储于人脸特征库中对应的参考人脸信息的特征距离值；Obtain the feature distance value of the face information to be recognized in the current frame of the video stream and the corresponding reference face information stored in the face feature database;
根据特征距离值与预设阈值的关系，判断待识别人脸信息与参考人脸信息是否匹配；According to the relationship between the feature distance value and the preset threshold, it is judged whether the face information to be recognized matches the reference face information;
若待识别人脸信息与参考人脸信息匹配，则提高预设阈值的值作为新的预设阈值。If the face information to be recognized matches the reference face information, the value of the preset threshold is increased as a new preset threshold.
其中，获取视频流中当前帧的待识别人脸信息与存储于人脸特征库中对应的参考人脸信息的特征距离值的步骤包括：Wherein, the step of obtaining the feature distance value of the face information to be recognized in the current frame of the video stream and the corresponding reference face information stored in the face feature database includes:
提取待识别人脸信息中的待识别人脸特征，并对待识别人脸特征进行降维处理；Extract the face features to be recognized in the face information to be recognized, and perform dimensionality reduction processing on the face features to be recognized;
计算降维处理后的待识别人脸特征与人脸特征库中所有参考人脸特征之间的距离值，并选取距离值的最小值作为特征距离值。Calculate the distance value between the face feature to be recognized after dimensionality reduction processing and all reference face features in the face feature database, and select the minimum value of the distance value as the feature distance value.
其中，根据特征距离值与预设阈值的关系，判断待识别人脸信息与参考人脸信息是否匹配的步骤包括：Wherein, according to the relationship between the feature distance value and the preset threshold, the step of judging whether the face information to be recognized matches the reference face information includes:
若特征距离值小于或等于预设阈值，则待识别人脸信息与参考人脸信息匹配；If the feature distance value is less than or equal to the preset threshold, the face information to be recognized matches the reference face information;
若特征距离值大于预设阈值，则待识别人脸信息与参考人脸信息不匹配。If the feature distance value is greater than the preset threshold, the face information to be recognized does not match the reference face information.
其中，根据特征距离值与预设阈值的关系，判断待识别人脸信息与参考人脸信息是否匹配的步骤之后，还包括：Wherein, after the step of judging whether the face information to be recognized matches the reference face information according to the relationship between the feature distance value and the preset threshold value, it also includes:
若待识别人脸信息与参考人脸信息不匹配，则读取视频流中间隔预设时间后的一帧的待识别人脸信息再次进行匹配。If the face information to be recognized does not match the reference face information, the face information to be recognized in a frame after a preset time interval in the video stream is read and matched again.
其中，根据特征距离值与预设阈值的关系，判断待识别人脸信息与参考人脸信息是否匹配的步骤之后，还包括：Wherein, after the step of judging whether the face information to be recognized matches the reference face information according to the relationship between the feature distance value and the preset threshold value, it also includes:
若待识别人脸信息与参考人脸信息匹配，则判断特征距离值是否小于预设置信度值；If the face information to be recognized matches the reference face information, it is judged whether the feature distance value is less than a preset reliability value;
若小于，则读取视频流中下一帧的待识别人脸信息，并提高预设阈值的值作为新的预设阈值。If it is less, read the face information to be recognized in the next frame of the video stream, and increase the value of the preset threshold as a new preset threshold.
其中，在根据特征距离值与预设阈值的关系，判断待识别人脸信息与参考人脸信息是否匹配的步骤之后，还包括：Wherein, after the step of judging whether the face information to be recognized matches the reference face information according to the relationship between the feature distance value and the preset threshold value, it also includes:
检测匹配次数是否超过预定次数；若超过，则待识别人脸信息识别成功，否则识别失败。Detect whether the number of matching times exceeds the predetermined number; if it exceeds, the recognition of the face information to be recognized is successful, otherwise the recognition fails.
其中，在待识别人脸信息识别失败的步骤之后，还包括：Among them, after the step of failing to recognize the face information to be recognized, it also includes:
提示对待识别人脸信息进行注册。Prompt to register the face information to be recognized.
其中，计算视频流中当前帧的待识别人脸信息与存储于人脸特征库中的参考人脸信息的特征距离值的步骤之前，还包括：Wherein, before the step of calculating the feature distance value of the face information to be recognized in the current frame of the video stream and the reference face information stored in the face feature database, it also includes:
对获取到的人脸信息进行注册处理；Register and process the acquired face information;
将处理注册后的人脸信息存储于人脸特征库中。Store the processed and registered face information in the face feature database.
其中，对获取到的人脸信息进行注册处理的步骤包括：Wherein, the steps of registering the obtained face information include:
对人脸信息进行归一化处理；Normalize face information;
对归一化处理后的人脸信息进行特征提取，并采用子空间计算对人脸信息进行降维处理。Feature extraction is performed on the face information after normalization processing, and the dimensionality reduction processing is performed on the face information by subspace calculation.
依据本发明的另一个方面，还提供了一种人脸识别装置，包括：According to another aspect of the present invention, a face recognition device is also provided, including:
获取模块，用于获取视频流中当前帧的待识别人脸信息与存储于人脸特征库中对应的参考人脸信息的特征距离值；Obtaining module, for acquiring the face information to be recognized of the current frame in the video stream and the feature distance value of the corresponding reference face information stored in the face feature database;
匹配模块，用于根据特征距离值与预设阈值的关系，判断待识别人脸信息与参考人脸信息是否匹配；The matching module is used to determine whether the face information to be recognized matches the reference face information according to the relationship between the feature distance value and the preset threshold;
调整模块，用于当待识别人脸信息与参考人脸信息匹配时，提高预设阈值的值作为新的预设阈值。An adjustment module, configured to increase the value of the preset threshold as a new preset threshold when the face information to be recognized matches the reference face information.
其中，获取模块包括：Among them, the acquisition module includes:
提取单元，用于提取待识别人脸信息中的待识别人脸特征，并对待识别人脸特征进行降维处理；The extraction unit is used to extract the face features to be recognized in the face information to be recognized, and perform dimensionality reduction processing on the face features to be recognized;
计算单元，用于计算降维处理后的待识别人脸特征与人脸特征库中所有参考人脸特征之间的距离值，并选取距离值的最小值作为特征距离值。The calculation unit is used to calculate the distance value between the face feature to be recognized after dimension reduction processing and all reference face features in the face feature database, and select the minimum value of the distance value as the feature distance value.
其中，匹配模块包括：Among them, the matching module includes:
第一匹配单元，用于当特征距离值小于或等于预设阈值时，确定待识别人脸信息与参考人脸信息匹配；The first matching unit is used to determine that the face information to be recognized matches the reference face information when the feature distance value is less than or equal to a preset threshold;
第二匹配单元，用于当特征距离值大于预设阈值时，确定待识别人脸信息与参考人脸信息不匹配。The second matching unit is configured to determine that the face information to be recognized does not match the reference face information when the feature distance value is greater than a preset threshold.
其中，该人脸识别装置还包括：Among them, the face recognition device also includes:
第一处理模块，用于当待识别人脸信息与参考人脸信息不匹配时，读取视频流中间隔预设时间后的一帧的待识别人脸信息再次进行匹配。The first processing module is used to read the face information of a frame to be recognized after a preset time interval in the video stream and perform matching again when the face information to be recognized does not match the reference face information.
其中，该人脸识别装置还包括：Among them, the face recognition device also includes:
判断模块，用于当待识别人脸信息与参考人脸信息匹配时，判断特征距离值是否小于预设置信度值；Judging module, used for judging whether the feature distance value is less than a preset reliability value when the face information to be recognized matches the reference face information;
第二处理模块，用于当特征距离值小于预设置信度值时，读取视频流中下一帧的待识别人脸信息，并提高预设阈值的值作为新的预设阈值。The second processing module is used to read the face information to be recognized in the next frame in the video stream when the feature distance value is less than the preset reliability value, and increase the value of the preset threshold as a new preset threshold.
其中，该人脸识别装置还包括：识别模块，用于检测匹配次数是否超过预定次数；若超过，则待识别人脸信息识别成功，否则识别失败。Wherein, the face recognition device further includes: a recognition module, which is used to detect whether the number of matching times exceeds a predetermined number; if it exceeds, the recognition of the face information to be recognized succeeds, otherwise the recognition fails.
其中，该人脸识别装置还包括：Among them, the face recognition device also includes:
提示模块，用于当确定待识别人脸信息识别失败后，提示对待识别人脸信息进行注册。The prompt module is configured to prompt the registration of the face information to be recognized after it is determined that the recognition of the face information to be recognized fails.
其中，该人脸识别装置还包括：Among them, the face recognition device also includes:
注册模块，用于对获取到的人脸信息进行注册处理；A registration module, configured to perform registration processing on the acquired face information;
存储模块，用于将处理注册后的人脸信息存储于人脸特征库中。The storage module is used for storing the processed and registered face information in the face feature database.
其中，注册模块包括：Among them, the registration module includes:
第一处理单元，用于对人脸信息进行归一化处理；a first processing unit, configured to perform normalization processing on face information;
第二处理单元，用于对归一化处理后的人脸信息进行特征提取，并采用子空间计算对人脸信息进行降维处理。The second processing unit is used to perform feature extraction on the normalized face information, and perform dimensionality reduction processing on the face information by using subspace calculation.
本发明的实施例的有益效果是：一种人脸识别方法及装置，通过获取待识别人脸信息与参考人脸信息的特征距离值，并检测该特征距离值是否小于当前的预设阈值，以判断待识别人脸信息与参考人脸信息的匹配情况；其中，当前预设阈值与前一帧待识别人脸信息的匹配结果相关，当前一帧的待识别人脸信息匹配结果很理想的时候，会适当提高下一帧的预设阈值，降低匹配难度，这样就在一定程度上避免了周边环境变化而影响特征距离值，进而导致误识别的现象，提高了人脸识别的识别成功率。The beneficial effect of the embodiment of the present invention is: a face recognition method and device, by acquiring the characteristic distance value between the face information to be recognized and the reference face information, and detecting whether the characteristic distance value is smaller than the current preset threshold value, To judge the matching situation between the face information to be recognized and the reference face information; wherein, the current preset threshold is related to the matching result of the face information to be recognized in the previous frame, and the matching result of the face information to be recognized in the current frame is ideal At this time, the preset threshold of the next frame will be appropriately increased to reduce the difficulty of matching, so that to a certain extent, the change of the surrounding environment will be avoided and the feature distance value will be affected, which will lead to the phenomenon of false recognition and improve the recognition success rate of face recognition. .
附图说明Description of drawings
图1表示本发明的人脸识别方法的流程示意简图一；Fig. 1 shows the schematic flow chart one of face recognition method of the present invention;
图2表示本发明实施例中步骤10的流程示意图；Fig. 2 shows the schematic flow chart of step 10 in the embodiment of the present invention;
图3表示本发明实施例中步骤20的流程示意图；Fig. 3 shows the schematic flow chart of step 20 in the embodiment of the present invention;
图4表示本发明的人脸识别方法的流程示意简图二；Fig. 4 shows the schematic flow diagram two of the face recognition method of the present invention;
图5表示本发明实施例中优选方案的流程示意简图；Fig. 5 shows the schematic flow diagram of the preferred solution in the embodiment of the present invention;
图6表示本发明实施例中具体实现的代码示意图；Fig. 6 shows the code schematic diagram of concrete realization in the embodiment of the present invention;
图7表示本发明的人脸识别装置的结构示意图。FIG. 7 shows a schematic structural diagram of the face recognition device of the present invention.
其中图中：101、获取模块，201、匹配模块，301、调整模块。In the figure: 101, acquisition module, 201, matching module, 301, adjustment module.
具体实施方式Detailed ways
下面将参照附图更详细地描述本发明的示例性实施例。虽然附图中显示了本发明的示例性实施例，然而应当理解，可以以各种形式实现本发明而不应被这里阐述的实施例所限制。相反，提供这些实施例是为了能够更透彻地理解本发明，并且能够将本发明的范围完整的传达给本领域的技术人员。Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.
实施例Example
视频人脸识别由于具有易操作性、稳定性好且认证流程简单的特点，被普遍应用于海关、公安部分、银行、公司门禁等领域。但现有的人脸识别技术中，特征匹配的预设阈值不可动态调整，易造成的误识别或识别成功率低的问题。为了解决上述问题，如图1所示，本发明的实施例提供了一种人脸识别方法，具体包括以下步骤：Video face recognition is widely used in customs, public security departments, banks, company access control and other fields due to its easy operability, good stability and simple authentication process. However, in the existing face recognition technology, the preset threshold for feature matching cannot be adjusted dynamically, which may easily cause misidentification or low recognition success rate. In order to solve the above problems, as shown in Figure 1, an embodiment of the present invention provides a face recognition method, which specifically includes the following steps:
步骤10：获取视频流中当前帧的待识别人脸信息与存储于人脸特征库中的参考人脸信息的特征距离值。Step 10: Obtain the feature distance value between the face information to be recognized in the current frame of the video stream and the reference face information stored in the face feature database.
以营业厅的身份认证为例，当某用户在营业厅办理业务，柜台摄像机将持续为该用户拍摄实时视频，基于该视频对用户进行身份认证。认证时，获取视频流中的当前帧所提供的待识别人脸信息，并计算该待识别人脸信息与对应的参考人脸信息的特征距离值，其中，所有的参考人脸信息均存储于认证系统的人脸特征库中。Taking the identity authentication of the business hall as an example, when a user handles business in the business hall, the counter camera will continue to shoot real-time video for the user, and authenticate the user based on the video. During authentication, the face information to be recognized provided by the current frame in the video stream is obtained, and the feature distance value between the face information to be recognized and the corresponding reference face information is calculated, wherein all reference face information is stored in In the face feature database of the authentication system.
步骤20：根据特征距离值与预设阈值的关系，判断待识别人脸信息与参考人脸信息是否匹配。Step 20: According to the relationship between the feature distance value and the preset threshold, determine whether the face information to be recognized matches the reference face information.
其中，这里所说的预设阈值并不是一定值，而是受前一帧待识别人脸信息与参考人脸信息之间的特征距离值影响而动态变化的。若前一帧待识别人脸信息与参考人脸信息之间的特征距离值接近，也就是说匹配效果理想，则当前的预设阈值小于前一帧对应的预设阈值。这样就可在一定程度上避免因光线、角度或表情姿势等，而影响匹配效果的问题。Wherein, the preset threshold mentioned here is not a certain value, but is dynamically changed by the influence of the characteristic distance value between the face information to be recognized in the previous frame and the reference face information. If the feature distance value between the face information to be recognized in the previous frame and the reference face information is close, that is to say, the matching effect is ideal, then the current preset threshold is smaller than the corresponding preset threshold in the previous frame. In this way, the problem of affecting the matching effect due to light, angle or expression posture can be avoided to a certain extent.
步骤30：若待识别人脸信息与参考人脸信息匹配，则提高预设阈值的值作为新的预设阈值。Step 30: If the face information to be recognized matches the reference face information, increase the value of the preset threshold as a new preset threshold.
这里是说，在当前帧的待识别人脸信息与参考人脸信息匹配成功后，会提高匹配的预设阈值，这样，在进行下一帧的匹配时，会使下一帧更易匹配成功。This means that after the face information to be recognized in the current frame is successfully matched with the reference face information, the preset threshold for matching will be increased, so that when the next frame is matched, the next frame will be easier to match successfully.
通过获取待识别人脸信息与参考人脸信息的特征距离值，并检测该特征距离值是否小于当前的预设阈值，以判断待识别人脸信息与参考人脸信息的匹配情况，当匹配次数超过预定次数时识别成功；其中，当前预设阈值与前一帧待识别人脸信息的匹配结果相关，当前一帧的待识别人脸信息匹配结果很理想的时候，会适当提高下一帧的预设阈值，降低匹配难度，这样就在一定程度上避免了周边环境变化而影响特征距离值，进而导致误识别的现象，提高了人脸识别的识别成功率。By obtaining the feature distance value between the face information to be recognized and the reference face information, and detecting whether the feature distance value is smaller than the current preset threshold, to judge the matching situation between the face information to be recognized and the reference face information, when the matching times The recognition is successful when the predetermined number of times is exceeded; among them, the current preset threshold is related to the matching result of the face information to be recognized in the previous frame, and when the matching result of the face information to be recognized in the current frame is ideal, it will appropriately increase the Preset the threshold to reduce the difficulty of matching, so that to a certain extent, it avoids the change of the surrounding environment and affects the feature distance value, which leads to the phenomenon of false recognition, and improves the recognition success rate of face recognition.
以上简述了本发明实施例的核心方案及流程，下面将结合附图对步骤10和步骤20进行进一步详细说明。The core solutions and processes of the embodiments of the present invention have been briefly described above, and step 10 and step 20 will be further described in detail below in conjunction with the accompanying drawings.
如图2所示，步骤10具体包括：As shown in Figure 2, step 10 specifically includes:
步骤11：提取待识别人脸信息中的待识别人脸特征，并对待识别人脸特征进行降维处理。Step 11: Extract the face features to be recognized from the face information to be recognized, and perform dimensionality reduction processing on the face features to be recognized.
步骤12：计算降维处理后的待识别人脸特征与人脸特征库中所有参考人脸特征之间的距离值，并选取距离值的最小值作为特征距离值。Step 12: Calculate the distance value between the face feature to be recognized after dimensionality reduction processing and all reference face features in the face feature database, and select the minimum value of the distance value as the feature distance value.
简单来说，人脸识别即是将人脸图片/视频进行特征提取和降维，并存储于人脸特征库中，识别时将待识别的图片/视频同样进行特征提取和降维，并将降维后的人脸特征与数据库中的人脸特征一一比较，寻找与其特征值最接近的人脸图片，根据设定好的阈值判定是否匹配成功。To put it simply, face recognition is to perform feature extraction and dimensionality reduction on face pictures/videos, and store them in the face feature library. The face features after dimensionality reduction are compared with the face features in the database one by one to find the face picture closest to its feature value, and judge whether the matching is successful according to the set threshold.
也就是说，人脸特征库中存储有所有注册过的参考人脸特征，即人脸特征向量值，当需要识别时，对待识别人脸信息(人脸照片或图像)进行特征提取，得到待识别人脸最原始高维向量，一般为7万多维，为了简化计算，还需将原始人脸特征进行降维处理，得到待识别人脸信息的特征向量值。That is to say, all registered reference face features, that is, face feature vector values, are stored in the face feature library. The most original high-dimensional vector for face recognition is generally more than 70,000 dimensions. In order to simplify the calculation, it is necessary to reduce the dimensionality of the original face features to obtain the feature vector value of the face information to be recognized.
为了进一步简化匹配过程，由于在注册人脸信息时，会采集对应用户的身份信息，如姓名、性别或身份证号码等基本信息，在人脸特征库中查找对应的参考人脸信息时，可通过检索身份信息相同的参考人脸信息的集合，缩小匹配对比对象的范围，以降低计算量，提高匹配效率。但对于没有采集对应用户身份信息的情况可采用逐一匹配对比的过程。In order to further simplify the matching process, since the identity information of the corresponding user is collected when registering the face information, such as basic information such as name, gender or ID card number, when looking for the corresponding reference face information in the face feature database, you can By retrieving a collection of reference face information with the same identity information, the range of matching and comparison objects is narrowed down to reduce the amount of calculation and improve matching efficiency. However, for the case where the corresponding user identity information is not collected, a process of matching and comparing one by one can be adopted.
如图3所示，步骤20具体包括以下几种情况：As shown in Figure 3, step 20 specifically includes the following situations:
步骤21：若特征距离值小于或等于预设阈值，则待识别人脸信息与参考人脸信息匹配。Step 21: If the feature distance value is less than or equal to the preset threshold, the face information to be recognized matches the reference face information.
步骤22：若特征距离值大于预设阈值，则待识别人脸信息与参考人脸信息不匹配。Step 22: If the feature distance value is greater than the preset threshold, the face information to be recognized does not match the reference face information.
这里说的是，如果特征距离值小于当前的预设阈值，则表示待识别人脸信息与对应的参考人脸信息相匹配，否则不匹配。What is said here is that if the feature distance value is smaller than the current preset threshold, it means that the face information to be recognized matches the corresponding reference face information, otherwise it does not match.
在步骤20得到匹配结果的步骤之后，还包括判断匹配次数以结束匹配过程的步骤，具体可参照以下步骤实现：After the step of obtaining the matching result in step 20, it also includes the step of judging the number of matches to end the matching process, which can be realized with reference to the following steps:
步骤40：若匹配次数超过预定次数，则待识别人脸信息识别成功，否则待识别人脸信息识别失败。Step 40: If the number of matching times exceeds the predetermined number, the recognition of the face information to be recognized is successful; otherwise, the recognition of the face information to be recognized fails.
为了避免误识别，通常人脸识别都设置多次匹配过程，在预定匹配过程中若匹配次数达到预定次数，则表示识别成功，否则表示识别失败。例如：若设置匹配过程为5次，识别成功的预定次数为3次，若在5次匹配过程中匹配次数达到3次及以上，则匹配成功，否则匹配失败。In order to avoid misidentification, face recognition usually sets multiple matching processes. If the number of matching times reaches the predetermined number during the predetermined matching process, it means that the recognition is successful, otherwise it means that the recognition fails. For example: if the matching process is set to 5 times, the predetermined number of successful recognition is 3 times, if the number of matching times reaches 3 times or more in the 5 matching processes, the matching is successful, otherwise the matching fails.
进一步地，以上提及当待识别人脸信息与参考人脸信息匹配时可动态调整预设阈值，但当待识别人脸信息与参考人脸信息不匹配时，可执行以下步骤：Further, as mentioned above, when the face information to be recognized matches the reference face information, the preset threshold can be dynamically adjusted, but when the face information to be recognized does not match the reference face information, the following steps can be performed:
若待识别人脸信息与参考人脸信息不匹配，则读取视频流中间隔预设时间后的一帧的待识别人脸信息再次进行匹配。If the face information to be recognized does not match the reference face information, the face information to be recognized in a frame after a preset time interval in the video stream is read and matched again.
若当前帧的待识别人脸信息与参考人脸信息匹配不成功，为了排除是光照、角度、表情或姿势等外界因素的影响，认证系统会读取视频流中与当前帧间隔预设时间(如300ms或500ms)后的一帧作为待识别人脸信息，然后进行再一次的匹配过程。If the face information to be recognized in the current frame fails to match the reference face information, in order to eliminate the influence of external factors such as illumination, angle, expression or posture, the authentication system will read the preset time interval between the current frame and the video stream ( For example, a frame after 300ms or 500ms) is used as the face information to be recognized, and then the matching process is performed again.
为了保证人脸识别的正确率，在步骤20匹配成功之后，还包括：In order to ensure the correct rate of face recognition, after the successful matching in step 20, it also includes:
若待识别人脸信息与参考人脸信息匹配，则判断特征距离值是否小于预设置信度值。If the face information to be recognized matches the reference face information, it is judged whether the feature distance value is less than a preset reliability value.
在视频人脸识别时，由于光照、表情、姿态等因素均不可控，因此在系统识别出被识别者，如果前面有置信度较高的帧，在后续的识别中可将匹配的预设阈值适当放宽。其中，这里所说的预设置信度值要高于匹配的预设阈值。也就是说当匹配成功后，为了保证后续匹配的正确率，还要进行一次置信度的判断，只有置信度高的时候，才能表示匹配的正确率较高。In video face recognition, because factors such as illumination, expression, and posture are uncontrollable, the system recognizes the person to be recognized. If there is a frame with high confidence in front, the matching preset threshold can be used in subsequent recognition. Appropriate relaxation. Wherein, the preset reliability value mentioned here is higher than the matching preset threshold. That is to say, after the matching is successful, in order to ensure the correct rate of subsequent matching, a confidence level judgment is required. Only when the confidence level is high, can the matching correct rate be high.
若小于，则读取视频流中下一帧的待识别人脸信息，并提高预设阈值的值作为新的预设阈值。If it is less, read the face information to be recognized in the next frame of the video stream, and increase the value of the preset threshold as a new preset threshold.
这里说的是，待识别人脸信息的置信度高，在后续匹配过程中才可提高预设阈值的值，放宽匹配条件，提高匹配成功率。What is said here is that the confidence of the face information to be recognized is high, and the value of the preset threshold can be increased in the subsequent matching process to relax the matching conditions and improve the matching success rate.
在经上述过程后，待识别人脸信息识别失败，表示人脸特征库中没有对应的参考人脸信息，如图4所示，在步骤40识别失败后，还包括：After the above process, if the recognition of the face information to be recognized fails, it means that there is no corresponding reference face information in the face feature database, as shown in Figure 4, after the recognition failure in step 40, it also includes:
步骤50：若待识别人脸信息识别失败，则提示对待识别人脸信息进行注册。Step 50: If the recognition of the face information to be recognized fails, prompting to register the face information to be recognized.
这里所说的注册入库，与步骤10之前预先创建人脸特征库的注册入库相似，以下将具体介绍步骤10之前的注册入库过程。The registration and warehousing mentioned here is similar to the registration and warehousing of the pre-created face feature database before step 10. The registration and warehousing process before step 10 will be introduced in detail below.
对获取到的人脸信息进行注册处理；Register and process the acquired face information;
将处理注册后的人脸信息存储于人脸特征库中。Store the processed and registered face information in the face feature database.
在视频人脸识别过程中，最初的准备工作即是人脸信息注册入库，具体地，对获取到的人脸信息进行注册处理的步骤如下：In the video face recognition process, the initial preparatory work is to register the face information into the database. Specifically, the steps to register the acquired face information are as follows:
对人脸信息进行归一化处理。对通过视频或图像输入的至少一张图片信息进行人脸检测，检测是否包含人脸，对包含人脸的图片信息作为待处理的人脸信息。对人脸信息进行归一化处理，即将人脸统一剪成固定像素的图片，再执行光照归一化，将光照的影响减到最弱。Normalize face information. Face detection is performed on at least one piece of picture information input through video or image to detect whether it contains a human face, and the picture information containing a human face is used as the face information to be processed. Normalize the face information, that is, cut the face into a fixed-pixel picture, and then perform light normalization to minimize the impact of light.
对归一化处理后的人脸信息进行特征提取，并采用子空间计算对人脸信息进行降维处理。提取的归一化处理后的人脸信息的初始人脸特征，即人脸最原始的高维向量维数过高，一般为7万多维，直接计算十分复杂。为了降低计算难度，需要对其进行降维处理，得到一个特征向量值，降维方式一般采用子空间计算的方式实现。将降维处理后的特征向量值存储至人脸特征库中作为参考人脸特征。The feature extraction is performed on the normalized face information, and the dimensionality reduction processing is performed on the face information by subspace calculation. The initial face features of the extracted normalized face information, that is, the most primitive high-dimensional vector of the face has too high a dimension, generally more than 70,000 dimensions, and direct calculation is very complicated. In order to reduce the difficulty of calculation, it is necessary to perform dimension reduction processing to obtain an eigenvector value. The dimension reduction method is generally realized by subspace calculation. Store the feature vector value after dimensionality reduction in the face feature library as the reference face feature.
以上分别就人脸识别的每个步骤做出了详细解释说明，下面将结合具体应用场景(以营业厅为例)对人脸识别方法的整体流程进行进一步的说明。Each step of face recognition has been explained in detail above, and the overall flow of the face recognition method will be further explained below in conjunction with specific application scenarios (taking a business hall as an example).
如图5所示，当某用户去营业厅办理业务时，首先需要对其进行身份认证，在身份认证时采用人脸识别的方式进行认证。As shown in Figure 5, when a user goes to the business hall to handle business, he first needs to be authenticated, and face recognition is used for authentication during identity authentication.
首先获取视频流中当前帧的待识别人脸信息与存储于人脸特征库有中对应的参考人脸信息的特征距离值。这里，通过柜台的摄像机将采集到该用户的视频信息输入至识别系统，将当前帧的待识别人脸信息的人脸特征与人脸特征库中所存储的所有参考人脸信息的人脸特征进行比较，计算出多个距离值，在多个距离值中选取最小值作为特征距离值，并将最小距离值对应的参考人脸信息作为该用户对应的参考人脸信息。First, obtain the feature distance value between the face information to be recognized in the current frame of the video stream and the corresponding reference face information stored in the face feature database. Here, the video information of the user collected by the camera at the counter is input to the recognition system, and the face features of the face information to be recognized in the current frame are combined with the face features of all reference face information stored in the face feature library. Comparing, calculating multiple distance values, selecting the minimum value among the multiple distance values as the characteristic distance value, and using the reference face information corresponding to the minimum distance value as the reference face information corresponding to the user.
判断特征距离值是否小于预设阈值。将上述得到的特征距离值与当前的预设阈值做比较，若小于，则表示匹配成功，若未小于，则获取视频流中的下一帧作为当前帧。It is judged whether the feature distance value is smaller than a preset threshold. Compare the feature distance value obtained above with the current preset threshold, if it is less than, it means that the matching is successful, if not, then get the next frame in the video stream as the current frame.
匹配成功后，判断特征距离值是否小于预设置信度值，若小于，则进行下一步，若未小于，则获取视频流中的下一帧作为当前帧。After the matching is successful, it is judged whether the feature distance value is less than the preset reliability value, if it is less than, proceed to the next step, if not, then obtain the next frame in the video stream as the current frame.
若特征距离值小于预设置信度值，则读取视频流中另一帧的待识别人脸信息，并提高预设阈值的值作为新的预设阈值。If the feature distance value is less than the preset reliability value, read the face information to be recognized in another frame in the video stream, and increase the value of the preset threshold as a new preset threshold.
获取待识别人脸信息与对应的参考人脸信息的特征距离值；其中，这是所说的对应的参考人脸信息与之前确定的对应的参考人脸信息是相同的。Acquire the feature distance value between the face information to be recognized and the corresponding reference face information; wherein, the corresponding reference face information is the same as the previously determined corresponding reference face information.
继续判断特征距离值是否小于新的预设阈值，如果未小于，则读取视频流中的另一帧作为当前帧；如果小于，则进行下一步。Continue to judge whether the feature distance value is smaller than the new preset threshold, if not, read another frame in the video stream as the current frame; if it is smaller, go to the next step.
判断匹配过程是否达到预设次数，如果未达到，则继续读取视频流中的另一帧作为当前帧；若果达到，则进行下一步。Determine whether the matching process reaches the preset number of times, if not, continue to read another frame in the video stream as the current frame; if it does, go to the next step.
判断匹配次数是否达到预定次数，如果达到，则表示该用户识别成功；如果未达到，则表示该用户识别失败，并提示对待识别人脸信息进行注册，即提示对该用户进行人脸特征的注册。Judging whether the number of matches reaches the predetermined number, if it does, it means that the user has been recognized successfully; if not, it means that the user has failed to be recognized, and prompts to register the face information to be recognized, that is, prompts to register the user's face features .
本发明实施例提供的人脸识别方法，具体实现时可参照如图6所示的代码进行实现，通过获取待识别人脸信息与参考人脸信息的特征距离值，并检测该特征距离值是否小于当前的预设阈值，以判断待识别人脸信息与参考人脸信息的匹配情况，当匹配次数小于预定次数时识别成功；其中，当前预设阈值与前一帧待识别人脸信息的匹配结果相关，当前一帧的待识别人脸信息匹配结果很理想的时候，会适当提高下一帧的预设阈值，降低匹配难度，这样就在一定程度上避免了周边环境变化而影响特征距离值，进而导致误识别的现象，提高了人脸识别的识别成功率。The face recognition method provided by the embodiment of the present invention can be implemented with reference to the code shown in Figure 6 during specific implementation, by obtaining the characteristic distance value between the face information to be recognized and the reference face information, and detecting whether the characteristic distance value is less than the current preset threshold to determine the matching between the face information to be recognized and the reference face information, and the recognition is successful when the number of matches is less than the predetermined number of times; where the current preset threshold matches the face information to be recognized in the previous frame The results are related. When the matching result of the face information to be recognized in the previous frame is ideal, the preset threshold of the next frame will be appropriately increased to reduce the matching difficulty, so as to avoid the surrounding environment changes from affecting the feature distance value to a certain extent. , which in turn leads to the phenomenon of misidentification, and improves the recognition success rate of face recognition.
以上是对本发明实施例中人脸识别方法的示例进行的简单说明，下面将结合如图7对上述方法对应的装置进行简单介绍，该人脸识别装置，包括：The above is a brief description of an example of the face recognition method in the embodiment of the present invention. The device corresponding to the above method will be briefly introduced below in conjunction with FIG. 7. The face recognition device includes:
获取模块101，用于获取视频流中当前帧的待识别人脸信息与存储于人脸特征库中对应的参考人脸信息的特征距离值；Obtaining module 101, for acquiring the face information to be identified of the current frame in the video stream and the feature distance value of the corresponding reference face information stored in the face feature database;
匹配模块201，用于根据特征距离值与预设阈值的关系，判断待识别人脸信息与参考人脸信息是否匹配；The matching module 201 is used to determine whether the face information to be recognized matches the reference face information according to the relationship between the feature distance value and the preset threshold;
调整模块301，用于当待识别人脸信息与参考人脸信息匹配时，提高预设阈值的值作为新的预设阈值。The adjustment module 301 is configured to increase the value of the preset threshold as a new preset threshold when the face information to be recognized matches the reference face information.
其中，获取模块101包括：Wherein, the acquisition module 101 includes:
提取单元，用于提取待识别人脸信息中的待识别人脸特征，并对待识别人脸特征进行降维处理；The extraction unit is used to extract the face features to be recognized in the face information to be recognized, and perform dimensionality reduction processing on the face features to be recognized;
计算单元，用于计算降维处理后的待识别人脸特征与人脸特征库中所有参考人脸特征之间的距离值，并选取距离值的最小值作为特征距离值。The calculation unit is used to calculate the distance value between the face feature to be recognized after dimension reduction processing and all reference face features in the face feature database, and select the minimum value of the distance value as the feature distance value.
其中，匹配模块201包括：Wherein, the matching module 201 includes:
第一匹配单元，用于当特征距离值小于或等于预设阈值时，确定待识别人脸信息与参考人脸信息匹配；The first matching unit is used to determine that the face information to be recognized matches the reference face information when the feature distance value is less than or equal to a preset threshold;
第二匹配单元，用于当特征距离值大于预设阈值时，确定待识别人脸信息与参考人脸信息不匹配。The second matching unit is configured to determine that the face information to be recognized does not match the reference face information when the feature distance value is greater than a preset threshold.
其中，该人脸识别装置还包括：Among them, the face recognition device also includes:
第一处理模块，用于当待识别人脸信息与参考人脸信息不匹配时，读取视频流中间隔预设时间后的一帧的待识别人脸信息再次进行匹配。The first processing module is used to read the face information of a frame to be recognized after a preset time interval in the video stream and perform matching again when the face information to be recognized does not match the reference face information.
其中，该人脸识别装置还包括：Among them, the face recognition device also includes:
判断模块，用于当待识别人脸信息与参考人脸信息匹配时，判断特征距离值是否小于预设置信度值；Judging module, used for judging whether the feature distance value is less than a preset reliability value when the face information to be recognized matches the reference face information;
第二处理模块，用于当特征距离值小于预设置信度值时，读取视频流中下一帧的待识别人脸信息，并提高预设阈值的值作为新的预设阈值。The second processing module is used to read the face information to be recognized in the next frame in the video stream when the feature distance value is less than the preset reliability value, and increase the value of the preset threshold as a new preset threshold.
其中，该人脸识别装置还包括：识别模块，用于检测匹配次数是否超过预定次数；若超过，则待识别人脸信息识别成功，否则识别失败。Wherein, the face recognition device further includes: a recognition module, which is used to detect whether the number of matching times exceeds a predetermined number; if it exceeds, the recognition of the face information to be recognized succeeds, otherwise the recognition fails.
其中，该人脸识别装置还包括：Among them, the face recognition device also includes:
提示模块，用于当确定待识别人脸信息识别失败后，提示对待识别人脸信息进行注册。The prompt module is configured to prompt the registration of the face information to be recognized after it is determined that the recognition of the face information to be recognized fails.
其中，该人脸识别装置还包括：Among them, the face recognition device also includes:
注册模块，用于对获取到的人脸信息进行注册处理；A registration module, configured to perform registration processing on the acquired face information;
存储模块，用于将处理注册后的人脸信息存储于人脸特征库中。The storage module is used for storing the processed and registered face information in the face feature database.
其中，注册模块包括：Among them, the registration module includes:
第一处理单元，用于对人脸信息进行归一化处理；a first processing unit, configured to perform normalization processing on face information;
第二处理单元，用于对归一化处理后的人脸信息进行特征提取，并采用子空间计算对人脸信息进行降维处理。The second processing unit is used to perform feature extraction on the normalized face information, and perform dimensionality reduction processing on the face information by using subspace calculation.
需要说明的是，该装置是与上述人脸识别方法对应的装置，上述方法实施例中所有实现方式均适用于该装置的实施例中，也能达到相同的技术效果。It should be noted that this device is a device corresponding to the above-mentioned face recognition method, and all the implementation methods in the above-mentioned method embodiments are applicable to the embodiments of the device, and can also achieve the same technical effect.
以上所述的是本发明的优选实施方式，应当指出对于本技术领域的普通人员来说，在不脱离本发明所述的原理前提下还可以作出若干改进和润饰，这些改进和润饰也在本发明的保护范围内。What has been described above is a preferred embodiment of the present invention. It should be pointed out that for those skilled in the art, some improvements and modifications can also be made without departing from the principles described in the present invention. within the scope of protection of the invention.
Claims (16)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510323032.XA CN106295672B (en) | 2015-06-12 | 2015-06-12 | A kind of face identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510323032.XA CN106295672B (en) | 2015-06-12 | 2015-06-12 | A kind of face identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106295672A CN106295672A (en) | 2017-01-04 |
| CN106295672B true CN106295672B (en) | 2019-10-29 |
Family
ID=57650673
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510323032.XA Active CN106295672B (en) | 2015-06-12 | 2015-06-12 | A kind of face identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106295672B (en) |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106952371A (en) * | 2017-03-21 | 2017-07-14 | 北京深度未来科技有限公司 | A kind of face roaming authentication method and system |
| CN107622191B (en) * | 2017-09-08 | 2020-03-10 | Oppo广东移动通信有限公司 | Unlocking control method and related product |
| CN107657161A (en) * | 2017-09-12 | 2018-02-02 | 广东欧珀移动通信有限公司 | Mobile payment method and related products based on face recognition |
| CN108090340B (en) * | 2018-02-09 | 2020-01-10 | Oppo广东移动通信有限公司 | Face recognition processing method, face recognition processing device and intelligent terminal |
| TWI671685B (en) * | 2018-09-19 | 2019-09-11 | 和碩聯合科技股份有限公司 | Face recognition method and electronic device using the same |
| CN109272991B (en) * | 2018-09-29 | 2021-11-02 | 阿波罗智联(北京)科技有限公司 | Voice interaction method, device, equipment and computer-readable storage medium |
| CN109615750B (en) * | 2018-12-29 | 2021-12-28 | 深圳市多度科技有限公司 | Face recognition control method and device for access control machine, access control equipment and storage medium |
| CN109858375B (en) * | 2018-12-29 | 2023-09-26 | 简图创智(深圳)科技有限公司 | Living body face detection method, terminal and computer readable storage medium |
| CN109977765A (en) * | 2019-02-13 | 2019-07-05 | 平安科技（深圳）有限公司 | Facial image recognition method, device and computer equipment |
| CN112241666A (en) * | 2019-07-18 | 2021-01-19 | 佳能株式会社 | Target identification method, device and storage medium |
| CN110597863B (en) * | 2019-09-25 | 2023-01-24 | 上海依图网络科技有限公司 | Retrieval system and method for keeping stable performance in control library through dynamic threshold |
| CN111488562B (en) * | 2020-04-07 | 2023-07-18 | 中国移动通信集团江苏有限公司 | Threshold determination method, device, equipment and medium based on face comparison |
| CN111914668B (en) * | 2020-07-08 | 2024-10-18 | 浙江大华技术股份有限公司 | Pedestrian re-recognition method, device and system based on image enhancement technology |
| CN111898495B (en) * | 2020-07-16 | 2021-04-16 | 云从科技集团股份有限公司 | Dynamic threshold management method, system, device and medium |
| CN115033862A (en) * | 2022-06-06 | 2022-09-09 | 展讯通信(天津)有限公司 | Biological characteristic template updating method, device, chip and equipment |
| CN115607168A (en) * | 2022-10-31 | 2023-01-17 | 脑陆(重庆)智能科技研究院有限公司 | EEG signal-based control method, device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101216884A (en) * | 2007-12-29 | 2008-07-09 | 北京中星微电子有限公司 | A method and system for face authentication |
| CN102111535A (en) * | 2009-12-23 | 2011-06-29 | 华晶科技股份有限公司 | Method for improving human face identification rate |
| CN103235909A (en) * | 2013-04-25 | 2013-08-07 | 广东欧珀移动通信有限公司 | Method and device for resetting password and mobile device |
| CN103824058A (en) * | 2014-02-26 | 2014-05-28 | 杨勇 | Face recognition system and method based on locally distributed linear embedding algorithm |
| CN104573644A (en) * | 2014-12-29 | 2015-04-29 | 天津瑞为拓新科技发展有限公司 | Multi-mode face identification method |
-
2015
- 2015-06-12 CN CN201510323032.XA patent/CN106295672B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101216884A (en) * | 2007-12-29 | 2008-07-09 | 北京中星微电子有限公司 | A method and system for face authentication |
| CN102111535A (en) * | 2009-12-23 | 2011-06-29 | 华晶科技股份有限公司 | Method for improving human face identification rate |
| CN103235909A (en) * | 2013-04-25 | 2013-08-07 | 广东欧珀移动通信有限公司 | Method and device for resetting password and mobile device |
| CN103824058A (en) * | 2014-02-26 | 2014-05-28 | 杨勇 | Face recognition system and method based on locally distributed linear embedding algorithm |
| CN104573644A (en) * | 2014-12-29 | 2015-04-29 | 天津瑞为拓新科技发展有限公司 | Multi-mode face identification method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106295672A (en) | 2017-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106295672B (en) | A kind of face identification method and device | |
| CN106295482B (en) | A kind of update method and device of face database | |
| US20130246270A1 (en) | Method and System for Multi-Modal Identity Recognition | |
| KR102655949B1 (en) | Face verifying method and apparatus based on 3d image | |
| KR102370063B1 (en) | Method and apparatus for verifying face | |
| Fathy et al. | Face-based active authentication on mobile devices | |
| CN105468950B (en) | Identity authentication method, device, terminal and server | |
| US9864756B2 (en) | Method, apparatus for providing a notification on a face recognition environment, and computer-readable recording medium for executing the method | |
| WO2019062080A1 (en) | Identity recognition method, electronic device, and computer readable storage medium | |
| CN110866466A (en) | Face recognition method, face recognition device, storage medium and server | |
| WO2019134246A1 (en) | Facial recognition-based security monitoring method, device, and storage medium | |
| WO2019179036A1 (en) | Deep neural network model, electronic device, identity authentication method, and storage medium | |
| KR101214732B1 (en) | Apparatus and method for recognizing faces using a plurality of face images | |
| CN105005779A (en) | Face verification anti-counterfeit recognition method and system thereof based on interactive action | |
| CN105243370A (en) | A fingerprint identification method, fingerprint identification device and mobile terminal | |
| CN106650646A (en) | Action recognition based living body face recognition method and system | |
| JP2015529365A5 (en) | ||
| WO2014187134A1 (en) | Method and apparatus for protecting browser private information | |
| EP3862895B1 (en) | Biometric authentication device, biometric authentication method, and biometric authentication program | |
| CN110612530A (en) | Method for selecting frames used in face processing | |
| WO2019011072A1 (en) | Iris live detection method and related product | |
| JP7248348B2 (en) | Face authentication device, face authentication method, and program | |
| CN108154070A (en) | Face identification method and device | |
| CN106529243A (en) | Identity authentication method, device and terminal | |
| CN105427480A (en) | A teller machine based on image analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 518048 Shenzhen Riverside Road, Futian District, Shenzhen, Guangdong, 1141 Applicant after: Medium shift information technology Co., Ltd. Address before: 518048 Guangdong province Futian District Shenzhen City Binhe Road, No. 9023, building 11, 41 layers of the country through the Applicant before: China Mobile (Shenzhen) Co., Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200316 Address after: Room 1006, building 16, yard 16, Yingcai North Third Street, future science city, Changping District, Beijing 100000 Co-patentee after: CHINA MOBILE COMMUNICATIONS GROUP Co.,Ltd. Patentee after: China Mobile Information Technology Co., Ltd Address before: 518048 Shenzhen Riverside Road, Futian District, Shenzhen, Guangdong, 1141 Patentee before: CHINA MOBILE INFORMATION TECHNOLOGY Co.,Ltd. |