CN112889062B

CN112889062B - Face recognition data processing method, device, mobile equipment and computer readable storage medium

Info

Publication number: CN112889062B
Application number: CN201880098811.6A
Authority: CN
Inventors: 梁俊豪
Original assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd; Shenzhen Huantai Technology Co Ltd
Current assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd; Shenzhen Huantai Technology Co Ltd
Priority date: 2018-12-07
Filing date: 2018-12-07
Publication date: 2024-09-20
Anticipated expiration: 2038-12-07
Also published as: CN112889062A; WO2020113571A1

Abstract

A face recognition data processing method, comprising: the mobile equipment receives the human face identification error feedback information, and adjusts a corresponding identification control threshold value in the current human face identification algorithm according to the human face identification error feedback information; and carrying out face recognition according to the current face recognition algorithm after the recognition control threshold is adjusted.

Description

Face recognition data processing method, device, mobile equipment and computer readable storage medium

Technical Field

The present application relates to the field of image recognition, and in particular, to a face recognition data processing method, apparatus, mobile device, and non-volatile computer readable storage medium.

Background

With the development of image recognition technology, more and more mobile devices use face recognition to finish authentication, such as unlocking, payment verification and the like, so that convenience is brought to life of people. Face recognition is affected by the environment and the face state, such as light, hair shielding, etc., and there may be cases of false recognition.

The traditional system does not process the misidentification, and the next time the same user uses face recognition authentication in the same scene, the misidentification phenomenon is likely to occur.

Disclosure of Invention

The embodiment of the application provides a face recognition data processing method, a device, mobile equipment and a nonvolatile computer readable storage medium, which can automatically adjust a face recognition algorithm control threshold value through feedback information and improve the face recognition accuracy.

A face recognition data processing method, comprising:

the mobile equipment receives the human face identification error feedback information;

Adjusting a corresponding recognition control threshold value in a current face recognition algorithm according to the face recognition error feedback information; and

And carrying out face recognition according to the current face recognition algorithm after the recognition control threshold is adjusted.

A face recognition data processing apparatus comprising:

the receiving module is used for receiving the human face recognition error feedback information through the mobile equipment;

The adjusting module is used for adjusting the corresponding recognition control threshold value in the current face recognition algorithm according to the face recognition error feedback information;

And the recognition module is used for recognizing the face according to the current face recognition algorithm after the recognition control threshold is adjusted.

A mobile device comprising a memory and a processor, the memory having stored therein computer readable instructions that, when executed by the processor, cause the processor to perform the steps of:

receiving human face identification error feedback information through mobile equipment;

A non-transitory computer readable storage medium having stored thereon computer readable instructions that, when executed by a processor, cause the processor to perform the steps of:

According to the face recognition data processing method, the device, the mobile equipment and the nonvolatile computer readable storage medium, the mobile equipment receives the face recognition error feedback information, the corresponding recognition control threshold value in the current face recognition algorithm is adjusted according to the face recognition error feedback information, the face recognition is carried out according to the current face recognition algorithm after the recognition control threshold value is adjusted, and when the face recognition is wrong, the face recognition algorithm control threshold value is automatically and intelligently adjusted through the face recognition feedback information, so that the next false recognition phenomenon is reduced, and the face recognition accuracy is improved.

Drawings

For a better description and illustration of embodiments and/or examples of those applications disclosed herein, reference may be made to one or more of the accompanying drawings. Additional details or examples used to describe the drawings should not be construed as limiting the scope of any of the disclosed invention, the presently described embodiments and/or examples, and the presently understood best mode of carrying out any of these applications.

Fig. 1 is a schematic view of an application environment of a face recognition data processing method in an embodiment.

Fig. 2 is a flowchart of a face recognition data processing method in one embodiment.

FIG. 3 is a schematic diagram of a lock screen interface in one embodiment.

FIG. 4 is a schematic diagram of a desktop after successful unlocking in one embodiment.

Fig. 5 is a flowchart of a face recognition data processing method in one embodiment.

Fig. 6 is a flow chart of face recognition in one embodiment.

FIG. 7 is a flow chart of adjusting an identification control threshold in one embodiment.

Fig. 8 is a flowchart of a face recognition data processing method in a specific embodiment.

Fig. 9 is a block diagram of a face recognition data processing apparatus in one embodiment.

Fig. 10 is a schematic diagram of an internal structure of a mobile device in one embodiment.

Fig. 11 is a block diagram of a part of the structure of a mobile device related to this embodiment in one embodiment.

Detailed Description

The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

It will be understood that the terms "first," "second," and the like, as used in embodiments of the application, may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish one element from another element. For example, a first control may be referred to as a second control, both of which are controls, but which are not the same control, without departing from the scope of the application.

Fig. 1 is an application environment diagram of a face recognition data processing method in one embodiment. As shown in fig. 1, the application environment includes a mobile device 110. The mobile device 110 is provided with a camera, face images can be acquired, face recognition is carried out on the acquired face images, the mobile device 110 is provided with a feedback information receiving key, which can be an entity key or a virtual key, the feedback information receiving key is used for receiving face recognition error feedback information, a corresponding recognition control threshold value in a current face recognition algorithm is adjusted according to the face recognition error feedback information, and face recognition is carried out according to the current face recognition algorithm after the recognition control threshold value is adjusted. The mobile device 110 may be a smart phone, tablet, wearable device, personal digital assistant, or the like.

Fig. 2 is a flowchart of a face recognition data processing method in one embodiment. As shown in fig. 2, a face recognition data processing method is described by taking an example of application to the mobile device in fig. 1, and specifically includes:

In operation 202, the mobile device receives face recognition error feedback information.

The human face recognition error feedback information is feedback information for describing human face recognition errors, and the human face recognition errors comprise various types of errors, such as false acceptance recognition and false rejection recognition. The false acceptance identification refers to that the false face is identified as a preset face image after being subjected to algorithm identification, for example, the preset face image recorded in the mobile equipment is a face image of a user A, and when the acquired face image is a face image of a user B, the algorithm erroneously identifies the face image of the user B as the face image of the user A, so that the face verification is erroneously successful. The false rejection recognition refers to that the correct face is recognized as a non-preset face image after algorithm recognition, for example, the preset face image recorded in the mobile equipment is a face image of a user A, and when the acquired face image is the face image of the user A, the algorithm erroneously recognizes the face image of the user A as the face image of other users, so that the face verification is unsuccessful.

Specifically, the human face recognition error feedback information is received through an operation acting on the mobile device, wherein the operation can be an operation directly or indirectly acting on the mobile device, and the operation directly acting on the mobile device can be an operation performed on an entity key or a virtual key of a screen. The operation indirectly acting on the mobile device may be a gesture operation, an eyeball operation, or the like. Different types of human face recognition error feedback information can be fed back through different keys, or different types of human face recognition error feedback information can be fed back through different gestures and eyeball movements. The human face recognition error feedback information can be notified to the system layer through the UI interface.

And operation 204, adjusting a corresponding recognition control threshold value in the current face recognition algorithm according to the face recognition error feedback information.

The recognition control threshold is a threshold for controlling the accuracy of face recognition, and different types of recognition control thresholds corresponding to different face recognition algorithms. As with 2D face recognition algorithms, the recognition control threshold may include an alignment threshold, a prosthetic threshold, etc. In one embodiment, when the face recognition algorithm is a network model algorithm, the recognition control threshold may be a parameter of the network model. The recognition control threshold may be a recognition control threshold in a 2D face recognition algorithm or a 3D face recognition algorithm.

Aiming at different face recognition error feedback information, the recognition control threshold value needs to be adjusted in different adjustment modes, and a specific adjustment algorithm can be determined according to the content of the face recognition error feedback information and the meaning of the recognition control threshold value. The adjustment principle is that when the human face recognition error feedback information is the error acceptance recognition feedback information, the human face recognition algorithm is required to be more strict, and the human faces of other users are prevented from being recognized as the human faces of preset users. When the human face identification error feedback information is the error rejection identification feedback information, the human face identification algorithm needs to be made more loose, and the problem that the correct human face of the preset user cannot be successfully identified under the influence of the environment or other factors, so that the human face cannot be successfully verified is avoided.

And operation 206, performing face recognition according to the current face recognition algorithm after the recognition control threshold is adjusted.

The system confirms that the face recognition is misidentification according to the face recognition error feedback information, so that the threshold is adjusted to reduce the next or subsequent misacceptance identification and/or misrejection identification. The face recognition result can be used for unlocking, paying, starting or closing an application program, setting permission and other operations requiring face recognition verification, and the face recognition is performed according to the current face recognition algorithm after the recognition control threshold is adjusted, so that the accuracy of face recognition is improved, and the effectiveness of the permission of each operation performed according to the face recognition result is ensured.

According to the face recognition data processing method, the mobile device receives the face recognition error feedback information, the corresponding recognition control threshold value in the current face recognition algorithm is adjusted according to the face recognition error feedback information, face recognition is performed according to the current face recognition algorithm after the recognition control threshold value is adjusted, dynamic intelligent automatic adjustment can be performed on the face recognition algorithm when the face recognition is wrong, next continuous error recognition can be avoided, and the face recognition accuracy is improved.

In one embodiment, a mobile device receives face recognition error feedback information, comprising: the face recognition error feedback information is received through a control displayed on a screen of the mobile device, and different controls transmit different face recognition error feedback information.

Specifically, when the face recognition is wrong, the control of the mobile device screen receives the operation of the user, different controls correspond to different trigger events, for example, the trigger event corresponding to the first control is to transmit the wrong acceptance recognition feedback information, and the trigger event corresponding to the second control is to transmit the wrong rejection recognition feedback information. The display positions of the controls can be different, for example, the control for transmitting the false rejection identification feedback information such as unlocking failure can be displayed on a screen locking interface, so that the control can be operated to transmit the false rejection identification feedback information under the condition of unlocking failure. The control for transmitting the error acceptance identification feedback information, namely the successful error unlocking, can be displayed on an interface after the successful unlocking, so that the control can be conveniently and rapidly operated under the condition of the successful error unlocking, and the error acceptance identification feedback information is transmitted.

As shown in fig. 3, a schematic diagram of a first control displayed on the screen lock interface in one embodiment is provided, where the first control 208 is configured to transmit false rejection identification feedback information to the face recognition algorithm module when the unlocking of the person fails. As shown in fig. 4, a schematic diagram of a second control displayed on the desktop after successful unlocking in one embodiment, where the second control 210 is used to transmit false acceptance identification feedback information to the face recognition algorithm module when the unlocking is successful. In one embodiment, the second control is in a hidden state, and the display of the second control may be triggered by a pull-down operation on the desktop.

In this embodiment, different face recognition error feedback information is transmitted to the system through different controls displayed on the UI interface, and the face recognition error feedback information is fed back rapidly through the operations acting on the controls, so that convenience and timeliness of the face recognition error feedback information feedback are improved.

In one embodiment, receiving face recognition error feedback information via a control displayed on a screen of a mobile device includes: and responding to the operation of the first control displayed on the screen of the mobile device, generating error acceptance identification feedback information, taking the error acceptance identification feedback information as face recognition error feedback information, and receiving the error acceptance identification feedback information transmitted by the first control.

The operation on the first control displayed on the screen of the mobile device may be any user-defined operation such as clicking, touch duration exceeding a preset threshold, sliding operation, etc. The first control may be a control specially used for feeding back the error acceptance identification feedback information, or may be a control with other functions. When the first control has multiple functions, the error acceptance identification feedback information is triggered and generated through a preset operation corresponding to the received face identification error feedback information. If the first control is slid leftwards to indicate that the face false acceptance identification occurs, generating false acceptance identification feedback information when the first control identifies the operation of sliding leftwards.

The first control corresponds to a preset feedback value, the preset feedback value represents error acceptance identification feedback information, if the transmission value is 1, the first control generates a feedback value with the value of 1 when recognizing preset operation, the feedback value is transmitted to the face recognition system, and the face recognition system judges the adjustment direction of the identification control threshold value according to the size of the feedback value.

In one embodiment, generating false acceptance identification feedback information in response to an operation on a first control displayed on a screen of the mobile device includes: the mobile device acquires a current face image, when the current face image is not actually matched with a preset unlocking face image, the current face image is mistakenly identified as the preset unlocking face by a current face identification algorithm, and when the screen of the mobile device is triggered to be successfully unlocked, erroneous acceptance identification feedback information is generated in response to the operation acted on the first control.

Specifically, the current face recognition algorithm recognizes the current face image as a preset unlocking face by mistake, and the screen of the mobile device is triggered to be successfully unlocked, which indicates that the unlocking is caused by the fact that the face recognition algorithm misrecognizes the face recognition of other users as the preset unlocking face input by the mobile device, if the face of the user A is input, the mobile phone is unlocked by the user B. The user a may operate the first control, which generates false acceptance identification feedback information according to the operation of the user a.

In this embodiment, when the unlocking error is successful, the identification feedback information can be quickly fed back by the first control. It can be understood that the application scenario may not be limited to unlocking, and if other application scenarios, such as face payment, face entering into an application, etc., may respectively correspond to different control quick feedback error acceptance identification feedback information matched with the application scenario.

In one embodiment, receiving face recognition error feedback information through a control displayed on a screen of the mobile device includes: and responding to the operation of the second control displayed on the screen of the mobile device, generating false rejection identification feedback information, taking the false rejection identification feedback information as human face identification false feedback information, and receiving the false rejection identification feedback information transmitted by the second control.

Specifically, the operation on the second control displayed on the screen of the mobile device may be any user-defined operation such as clicking, touching for a period of time exceeding a preset threshold, sliding operation, and the like. The second control may be a control specially used for feeding back the false reject identification feedback information, or may be a control with other functions. When the second control has multiple functions, the false rejection identification feedback information is triggered and generated through a preset operation corresponding to the received false rejection identification feedback information of the face identification. If the right sliding on the second control indicates that the face false rejection identification occurs, false rejection identification feedback information is generated when the second control identifies the right sliding operation.

In one embodiment, the control that feeds back the false reject identification feedback information and the false accept identification feedback information is the same control, and different types of information are fed back by different operations on this control. If the user slides leftwards, the identification feedback information is received by the feedback error, and if the user slides rightwards, the identification feedback information is refused by the feedback error. By integrating the controls, the generation of the controls can be saved, and resources can be saved.

The second control corresponds to a preset feedback value, the preset feedback value represents false rejection identification feedback information, if the transmission value is 2, the first control generates a feedback value with the value of 2 when recognizing the preset operation, the feedback value is transmitted to the face recognition system, and the face recognition system judges the adjustment direction of the identification control threshold value according to the magnitude of the feedback value.

In one embodiment, generating false rejection identification feedback information in response to an operation on a second control displayed on a screen of a mobile device includes: the mobile device acquires a current face image, and when the current face image is actually matched with a preset unlocking face image, the current face image is mistakenly identified as a non-preset unlocking face by a current face identification algorithm, so that the screen unlocking of the mobile device fails, wrong rejection identification feedback information is generated in response to the operation acting on the second control.

Specifically, the current face recognition algorithm erroneously recognizes the current face image as a non-preset unlocking face, so that the screen of the mobile device fails to unlock, which means that the unlocking is failed due to the fact that the face recognition algorithm cannot recognize the preset unlocking face input by the mobile device, if the face input by the user A is the face input by the user A, the user A cannot unlock. The user a may operate a second control that generates false acceptance rejection feedback information according to the operation of the user a.

In this embodiment, when the correct face fails to be unlocked, the identification feedback information can be quickly fed back by the second control. It can be understood that the application scenario may not be limited to unlocking, and if other application scenarios, such as face payment, face entering into an application, etc., may respectively correspond to different control quick feedback false rejection identification feedback information matched with the application scenario.

In one embodiment, when the current face image is actually matched with the preset unlocking face image, the time length for the current face image to be identified as the preset unlocking face by the current face recognition algorithm is obtained, a target control is determined according to the time length, and false rejection recognition feedback information is generated in response to the operation acting on the target control.

Specifically, when the current face image is actually matched with the preset unlocking face image, if the face of the user A is input, the current face image is the face of the user A, the current face recognition algorithm recognizes the current face image as a non-preset unlocking face in a first time period, and the current face recognition algorithm cannot recognize the face of the user A in the first time period, and recognizes the current face image as a preset unlocking face in a second time period, the difference value between the second time period and the starting time period is the time period when the current face image is recognized as the preset unlocking face by the current face recognition algorithm. The shorter the duration, the more sensitive the current face recognition algorithm is, and the higher the recognition degree is. And determining target controls according to the identification time length, wherein different target controls are used for indicating the current face recognition algorithm to adjust the identification control threshold value in different magnitudes.

In this embodiment, the recognition control threshold is adjusted differently by recognizing the duration, so that accuracy of adjustment of the recognition control threshold is further improved.

In one embodiment, identifying the control threshold includes at least one of an alignment threshold, a prosthesis threshold; operation 204 comprises: and when the human face recognition error feedback information is the error acceptance recognition feedback information, the comparison threshold value is increased and/or the prosthesis threshold value is reduced.

Specifically, the 2D face recognition algorithm mainly includes two thresholds, a comparison threshold and a prosthesis threshold. The threshold is compared to control the similarity threshold of the recorded face and the face tried to be verified, and the lower the threshold is, the easier the verification is successful, if the face is verified to be unlocked, the lower the threshold is, the easier the unlocking is. When the human face recognition error feedback information is the error acceptance recognition feedback information, the current human face recognition algorithm is easy to use other human faces as preset human faces, the similarity threshold is low, and the comparison threshold needs to be improved. The comparison threshold is used as a threshold for determining the authenticity of the face to be unlocked, and the higher the threshold is, the easier the fake face is to be identified as the genuine face. When the false feedback information of the face recognition is the false acceptance feedback information, the current face recognition algorithm is easy to recognize the false face as the true face, the threshold for explaining the true and false degrees is high, and the threshold of the prosthesis needs to be reduced. It will be appreciated that the increasing of the alignment threshold and the decreasing of the prosthesis threshold may alternatively or simultaneously be adjusted, the magnitude of which may be matched or custom-defined with the current face recognition algorithm.

In one embodiment, identifying the control threshold includes at least one of an alignment threshold, a prosthesis threshold; operation 204 comprises: and when the human face recognition error feedback information is the error rejection recognition feedback information, reducing the comparison threshold value and/or increasing the prosthesis threshold value.

Specifically, when the human face recognition error feedback information is the false rejection recognition feedback information, the current human face recognition algorithm is indicated to be easy to fail to correctly record human face recognition, for example, mobile equipment records the human face of the user A, but when the user A is affected by illumination change, hair shielding, human face angle deflection and other reasons, the human face of the user A cannot be recognized, and the similarity threshold is indicated to be higher, so that the comparison threshold needs to be reduced. When the false feedback information of the face recognition is the false rejection feedback information, the current face recognition algorithm is easy to misrecognize as a false face even if the true face is detected, the threshold for explaining the true and false degree is low, and the threshold of the false body needs to be improved. It will be appreciated that the reduction of the alignment threshold and the increase of the prosthesis threshold may alternatively or simultaneously be adjusted, the magnitude of which may be matched or custom-defined with the current face recognition algorithm.

In one embodiment, prior to operation 204, as shown in fig. 5, further comprising:

operation 302, acquiring a current recognition scene corresponding to the current face recognition, and acquiring a feedback recognition scene corresponding to the face recognition error feedback information.

Operation 304, determining that when the current recognition scene matches the feedback recognition scene, if so, entering operation 204, and if not, not adjusting.

Specifically, the background pattern, illuminance, brightness, shielding degree, far-near degree, face definition and the like can be used as judging factors of different scenes, the current scene judging factors corresponding to the current face recognition are obtained by analyzing the current collected image, the current scene judging factors are compared with the feedback scene judging factors corresponding to the feedback recognition scene, whether the current recognition scene is matched with the feedback recognition scene or not is judged, and a specific matching algorithm can be defined. In one embodiment, when the similarity of the judgment factors exceeding the preset number exceeds a preset threshold, the current recognition scene is judged to be matched with the feedback recognition scene.

And the current camera frame picture and the feedback identification scene frame picture can be directly judged and identified to be the same or similar scene through an image analysis algorithm, and if the current camera frame picture and the feedback identification scene frame picture are the same or similar, the current identification scene and the feedback identification scene are matched.

In this embodiment, the recognition control threshold is adjusted only when the current recognition scene is matched with the feedback recognition scene, so that the accuracy of adjustment of the recognition control threshold is further improved, and erroneous adjustment is avoided.

In one embodiment, as shown in fig. 6, the method further comprises:

and operation 402, acquiring a feedback recognition scene corresponding to the face recognition error feedback information, and establishing a matching relationship between the feedback recognition scene and the adjusted recognition control threshold.

Specifically, different scenes corresponding to the identification error feedback information fed back by the user are obtained, and the identification control threshold value adjusted under the different scenes is obtained, so that the matching relation between the different feedback identification scenes and the adjusted identification control threshold value is established. If the face recognition is performed in the scene a and the scene B, the face recognition error feedback information is received, so that the scene a and the scene B are different feedback recognition scenes. And (3) carrying out first adjustment on the recognition control threshold under the scene A to obtain an adjusted target first recognition control threshold, carrying out second adjustment on the recognition control threshold under the scene B to obtain an adjusted target second recognition control threshold, respectively establishing a matching relationship between the scene A and the target first recognition control threshold, and establishing a matching relationship between the scene B and the target second recognition control threshold.

And operation 404, acquiring a current recognition scene corresponding to the current face recognition, and determining a target feedback recognition scene matched with the current recognition scene.

Specifically, a current recognition scene corresponding to the current face recognition is obtained through analysis of the current acquired image, the current recognition scene is compared with each feedback recognition scene in the matching relation, a target feedback recognition scene matched with the current recognition scene is obtained, the target feedback recognition scene is the same as or similar to the current recognition scene, and a specific matching algorithm can be customized.

And operation 406, obtaining a target recognition control threshold corresponding to the target feedback recognition scene according to the matching relation.

Specifically, as the recognition control thresholds corresponding to the feedback recognition scenes are all adjusted thresholds matched with the scenes, different recognition control thresholds are used in different scenes, and the accuracy of face recognition in different scenes is improved. By acquiring the target recognition control threshold corresponding to the target feedback recognition scene, the target recognition control threshold is more suitable for the current recognition scene because the target feedback recognition scene is a scene matched with the current recognition scene.

And operation 408, performing face recognition according to the current face recognition algorithm corresponding to the target recognition control threshold.

Specifically, the current face recognition algorithm is obtained according to the target recognition control threshold value to perform face recognition, and the fact that the previously adjusted control threshold value matched with the current recognition scene is used in the current recognition scene is guaranteed, so that the accuracy of face recognition in the current recognition scene is improved.

In one embodiment, as shown in FIG. 7, operation 204 comprises:

And step 204a, acquiring an initial recognition control threshold corresponding to the current face recognition algorithm.

Specifically, the initial recognition control threshold is a recognition control threshold which is not adjusted, such as a recognition control threshold corresponding to an initial model corresponding to the current face recognition algorithm, and the recognition control threshold can be customized.

And 204b, acquiring an identification control threshold adjustment range, and adjusting a corresponding identification control threshold in the current face identification algorithm according to the face identification error feedback information, so that the difference between the adjusted current identification control threshold and the initial identification control threshold is within the identification control threshold adjustment range.

Specifically, the recognition control threshold adjustment range controls the recognition control threshold within a certain range, if the initial recognition control threshold is 10 in one embodiment, the recognition control threshold adjustment range is [ -10-10], which means that the recognition control threshold can be adjusted by 10 degrees only, and if the recognition control threshold exceeds the recognition control threshold adjustment range after adjustment, the recognition control threshold is excessively adjusted. Because the threshold value is adjusted to have a certain range and cannot be too wide, otherwise, the false acceptance rate and the false rejection rate are seriously affected, wherein the false acceptance rate is the probability of successful verification after the false face is subjected to algorithm recognition, and the false rejection rate is the probability of failure of verification after the correct face is subjected to algorithm recognition. The adjustment of the threshold allows slight fluctuations, but needs to be restored in a proper case, because from the big data point of view, the false acceptance rate and the false rejection rate of the default threshold belong to a relatively balanced state, and a long time of breaking this balance may introduce new problems in other scenarios.

In this embodiment, the difference between the adjusted current recognition control threshold and the initial recognition control threshold is within the adjustment range of the recognition control threshold, so as to ensure the stability of face recognition.

As shown in fig. 8, the following describes the face recognition data processing method in detail in connection with a specific example. Firstly, assuming that the mobile device displays different feedback controls on different interfaces, the mobile device is in a screen locking state, a first control is displayed on the interface corresponding to the screen locking state, and a character is displayed on the first control, wherein the character is' can not be unlocked? And the user is prompted to operate the first control to feed back the wrong rejection identification feedback information when the user cannot unlock the first control.

At operation 502, the mobile device receives feedback false reject identification feedback information via the first control, and the user notifies the false reject identification feedback information to the system layer via the UI interface. For example, the face of the user a is input, and if the user a cannot unlock, the first control receives the click operation of the user a, and the first control transmits the false rejection identification feedback information to the face identification algorithm module of the system layer.

In operation 504, when the system layer receives the false rejection identification feedback information, the alignment threshold is lowered, the prosthesis threshold is raised, and the adjusted alignment threshold and the prosthesis threshold are ensured to be respectively within the corresponding adjustment range.

Operation 506, when the user B successfully unlocks, displaying a second control on the interface of successful unlocking, and displaying a character "is not self unlocked? And the user is prompted to operate the first control to feed back the error acceptance identification feedback information when the user is not unlocking. The mobile device receives feedback error receiving identification feedback information through the second control, for example, the face of the user A is input, the face of the user B passes verification, and the screen is successfully unlocked.

And operation 508, when the system layer receives the error acceptance identification feedback information, increasing the comparison threshold value, decreasing the prosthesis threshold value, and ensuring that the adjusted comparison threshold value and the prosthesis threshold value are respectively in the corresponding adjustment range.

In this embodiment, after the face is misidentified, the defect of the feedback algorithm can be given to the system through the operation of the control, so as to adjust the identification control threshold, automatically adjust the threshold through the feedback information, and then unlock the face by the same user under the same scene, so that the misidentification phenomenon can be reduced, and the accuracy of face identification can be improved. And the whole adjustment process does not need to update the software version, so that the development cost is reduced.

It should be understood that, although the steps in the flowcharts of fig. 2, 5-8 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps of fig. 2, 5-8 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the sub-steps or stages are performed necessarily occur sequentially, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

The embodiment of the application also provides mobile equipment. The mobile device includes a memory and a processor, the memory having stored therein computer readable instructions that when executed by the processor cause the processor to perform the steps of: receiving human face identification error feedback information through mobile equipment; adjusting a corresponding recognition control threshold value in the current face recognition algorithm according to the face recognition error feedback information; and carrying out face recognition according to the current face recognition algorithm after the recognition control threshold is adjusted.

In one embodiment, a mobile device receives face recognition error feedback information, comprising: and receiving the human face recognition error feedback information through a control displayed on the screen of the mobile device, wherein different controls transmit different human face recognition error feedback information.

In one embodiment, receiving face recognition error feedback information via a control displayed on a screen of a mobile device includes: generating error acceptance identification feedback information in response to an operation acting on a first control displayed on a screen of the mobile device, and taking the error acceptance identification feedback information as face recognition error feedback information; and receiving error acceptance identification feedback information transmitted by the first control.

In one embodiment, generating false acceptance identification feedback information in response to an operation on a first control displayed on a screen of a mobile device includes: the mobile equipment acquires a current face image; when the current face image is not actually matched with the preset unlocking face image, the current face image is mistakenly identified as the preset unlocking face by the current face recognition algorithm, and the screen of the mobile device is triggered to be successfully unlocked, erroneous acceptance identification feedback information is generated in response to the operation acting on the first control.

In one embodiment, receiving face recognition error feedback information via a control displayed on a screen of a mobile device includes: generating false rejection identification feedback information in response to an operation acting on a second control displayed on a screen of the mobile device, and taking the false rejection identification feedback information as face recognition false feedback information; and receiving error rejection identification feedback information transmitted by the second control.

In one embodiment, generating false rejection identification feedback information in response to an operation on a second control displayed on a screen of a mobile device includes: acquiring a current face image through mobile equipment; when the current face image is actually matched with the preset unlocking face image, the current face image is mistakenly identified as a non-preset unlocking face by the current face recognition algorithm, and the screen unlocking of the mobile device fails, wrong rejection recognition feedback information is generated in response to the operation acting on the second control.

In one embodiment, identifying the control threshold includes at least one of an alignment threshold, a prosthesis threshold; and adjusting a corresponding recognition control threshold value in the current face recognition algorithm according to the face recognition error feedback information, wherein the method comprises the following steps: and when the human face recognition error feedback information is the error acceptance recognition feedback information, increasing the comparison threshold value and/or reducing the prosthesis threshold value.

In one embodiment, identifying the control threshold includes at least one of an alignment threshold, a prosthesis threshold; the method for adjusting the corresponding recognition control threshold value in the current face recognition algorithm according to the face recognition error feedback information comprises the following steps: the mobile equipment acquires a current face image; when the current face image is not actually matched with the preset unlocking face image, the current face image is mistakenly identified as the preset unlocking face by the current face recognition algorithm, and the screen of the mobile equipment is triggered to be successfully unlocked, erroneous acceptance identification feedback information is generated in response to the operation acting on the first control.

In one embodiment, receiving face recognition error feedback information through a control displayed on a screen of the mobile device includes: generating false rejection identification feedback information in response to an operation acting on a second control displayed on a screen of the mobile device, and taking the false rejection identification feedback information as face recognition false feedback information; and receiving error rejection identification feedback information transmitted by the second control.

In one embodiment, generating false rejection identification feedback information in response to an operation on a second control displayed on the mobile device screen includes: acquiring a current face image through mobile equipment; when the current face image is actually matched with the preset unlocking face image, the current face image is mistakenly identified as a non-preset unlocking face by the current face recognition algorithm, and the screen unlocking of the mobile device fails, the false rejection recognition feedback information is generated in response to the operation acting on the second control.

In one embodiment, identifying the control threshold includes at least one of an alignment threshold, a prosthesis threshold; the method for adjusting the corresponding recognition control threshold value in the current face recognition algorithm according to the face recognition error feedback information comprises the following steps: and when the human face recognition error feedback information is the error acceptance recognition feedback information, the comparison threshold value is increased and/or the prosthesis threshold value is reduced.

In one embodiment, identifying the control threshold includes at least one of an alignment threshold, a prosthesis threshold; the method for adjusting the corresponding recognition control threshold value in the current face recognition algorithm according to the face recognition error feedback information comprises the following steps: and when the human face recognition error feedback information is the error rejection recognition feedback information, reducing the comparison threshold value and/or increasing the prosthesis threshold value.

In one embodiment, the processor performs the steps of: acquiring a current recognition scene corresponding to the current face recognition, and acquiring a feedback recognition scene corresponding to the feedback information of the face recognition errors; and when the current recognition scene is matched with the feedback recognition scene, entering a step of adjusting a corresponding recognition control threshold value in the current face recognition algorithm according to the face recognition error feedback information.

In one embodiment, the processor performs the steps of: acquiring feedback recognition scenes corresponding to the human face recognition error feedback information, and establishing a matching relation between the feedback recognition scenes and the adjusted recognition control threshold; acquiring a current recognition scene corresponding to the current face recognition, and determining a target feedback recognition scene matched with the current recognition scene; acquiring a target recognition control threshold corresponding to the target feedback recognition scene according to the matching relation; and carrying out face recognition according to the current face recognition algorithm corresponding to the target recognition control threshold.

In one embodiment, adjusting the corresponding recognition control threshold in the current face recognition algorithm according to the face recognition error feedback information includes: acquiring an initial recognition control threshold corresponding to a current face recognition algorithm; acquiring an adjustment range of an identification control threshold; and adjusting a corresponding recognition control threshold value in the current face recognition algorithm according to the face recognition error feedback information, so that the difference between the adjusted current recognition control threshold value and the initial recognition control threshold value is within the adjustment range of the recognition control threshold value.

Fig. 7 is a block diagram of a face recognition data processing apparatus in one embodiment. As shown in fig. 5, a face recognition data processing apparatus includes a receiving module 602, an adjusting module 604, and an identifying module 606. Wherein:

the receiving module 602 is configured to receive, by the mobile device, the face recognition error feedback information.

The adjustment module 604 is configured to adjust a corresponding recognition control threshold in the current face recognition algorithm according to the face recognition error feedback information.

The recognition module 606 is configured to perform face recognition according to a current face recognition algorithm after the recognition control threshold is adjusted.

In one embodiment, the receiving module 602 is further configured to receive the face recognition error feedback information through a control displayed on a screen of the mobile device, where different controls transmit different face recognition error feedback information.

In one embodiment, the receiving module 602 is further configured to generate error acceptance identification feedback information in response to an operation on the first control displayed on the screen of the mobile device, use the error acceptance identification feedback information as the face recognition error feedback information, and receive the error acceptance identification feedback information transmitted by the first control.

In one embodiment, the receiving module 602 is further configured to obtain, by using the mobile device, a current face image, and when the current face image is not actually matched with the preset unlock face image, the current face image is misidentified as the preset unlock face by the current face recognition algorithm, and the screen of the mobile device is triggered to be successfully unlocked, the misacceptance identification feedback information is generated in response to the operation acting on the first control.

In one embodiment, the receiving module 602 is further configured to generate false rejection identification feedback information in response to an operation on a second control displayed on a screen of the mobile device, and use the false rejection identification feedback information as the face recognition false feedback information; and receiving error rejection identification feedback information transmitted by the second control.

In one embodiment, the receiving module 602 is further configured to obtain, by using the mobile device, a current face image, and when the current face image is actually matched with a preset unlock face image, the current face image is misidentified as a non-preset unlock face by the current face recognition algorithm, so that when unlocking of the screen of the mobile device fails, misrejection recognition feedback information is generated in response to an operation acting on the second control.

In one embodiment, identifying the control threshold includes at least one of an alignment threshold, a prosthesis threshold; the adjustment module 604 is further configured to increase the alignment threshold and/or decrease the prosthesis threshold when the face recognition error feedback information is the error acceptance recognition feedback information.

In one embodiment, identifying the control threshold includes at least one of an alignment threshold, a prosthesis threshold; the adjustment module 604 is further configured to decrease the alignment threshold and/or increase the prosthesis threshold when the face recognition error feedback information is a false rejection recognition feedback information.

In one embodiment, the apparatus further comprises:

The scene matching module is configured to obtain a current recognition scene corresponding to the current face recognition, obtain a feedback recognition scene corresponding to the feedback information of the face recognition error, and enter the adjustment module 604 when the current recognition scene matches with the feedback recognition scene.

In one embodiment, the apparatus further comprises:

And the matching relation module is used for acquiring a feedback recognition scene corresponding to the face recognition error feedback information and establishing a matching relation between the feedback recognition scene and the adjusted recognition control threshold value.

The scene adjustment module is used for acquiring a current recognition scene corresponding to the current face recognition, determining a target feedback recognition scene matched with the current recognition scene, and acquiring a target recognition control threshold corresponding to the target feedback recognition scene according to the matching relation.

The recognition module 606 is further configured to perform face recognition according to a current face recognition algorithm corresponding to the target recognition control threshold.

In one embodiment, the adjusting module 604 is further configured to obtain an initial recognition control threshold corresponding to the current face recognition algorithm; acquiring an adjustment range of an identification control threshold; and adjusting a corresponding recognition control threshold value in the current face recognition algorithm according to the face recognition error feedback information, so that the difference between the adjusted current recognition control threshold value and the initial recognition control threshold value is within the adjustment range of the recognition control threshold value.

The implementation of each module in the face recognition data processing device provided in the embodiment of the application can be in the form of computer readable instructions. The computer readable instructions may run on a terminal or a server. Program modules may be stored in the memory of the terminal or server. The computer readable instructions, when executed by a processor, implement the steps of the methods described in embodiments of the present application.

Fig. 10 is a schematic diagram of an internal structure of a mobile device in one embodiment. As shown in fig. 10, the mobile device includes a processor and a memory connected by a system bus. Wherein the processor is configured to provide computing and control capabilities to support operation of the entire electronic device. The memory may include a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer readable instructions. The computer readable instructions are executable by a processor for implementing a face recognition data processing method provided in the following embodiments. The internal memory provides a cached operating environment for operating system computer readable instructions in a non-volatile storage medium. The mobile device may be a cell phone, tablet computer or personal digital assistant or wearable device, etc.

The embodiment of the application also provides mobile equipment. The mobile device may be any terminal device including a mobile phone, a tablet computer, a PDA (Personal digital assistant), a POS (Point of Sales), a car-mounted computer, a wearable device, and the like, taking the mobile device as an example.

The embodiment of the application also provides mobile equipment. The mobile device includes image Processing circuitry, which may be implemented using hardware and/or software components, and may include various Processing units defining ISP (IMAGE SIGNAL Processing) pipelines. FIG. 11 is a schematic diagram of an image processing circuit in one embodiment. As shown in fig. 11, for convenience of explanation, only aspects of the image processing technology related to the embodiment of the present application are shown.

As shown in fig. 11, the image processing circuit includes an ISP processor 740 and a control logic 750. Image data captured by imaging device 710 is first processed by ISP processor 740, where ISP processor 740 analyzes the image data to capture image statistics that may be used to determine and/or one or more control parameters of imaging device 710. Imaging device 710 may include a camera having one or more lenses 712 and an image sensor 714. Image sensor 714 may include a color filter array (e.g., bayer filter), and image sensor 714 may obtain light intensity and wavelength information captured with each imaging pixel of image sensor 714 and provide a set of raw image data that may be processed by ISP processor 740. The sensor 720 (e.g., gyroscope) may provide parameters of the captured image processing (e.g., anti-shake parameters) to the ISP processor 740 based on the type of interface of the sensor 720. The sensor 720 interface may utilize an SMIA (Standard Mobile Imaging Architecture ) interface, other serial or parallel camera interfaces, or a combination of the above.

In addition, image sensor 714 may also send raw image data to sensor 720, sensor 720 may provide raw image data to ISP processor 740 based on the type of interface of sensor 720, or sensor 720 may store raw image data in image memory 730.

ISP processor 740 processes the raw image data on a pixel-by-pixel basis in a variety of formats. For example, each image pixel may have a bit depth of 8, 10, 12, or 14 bits, and ISP processor 740 may perform one or more image processing operations on the raw image data, collecting statistical information about the image data. Wherein the image processing operations may be performed with the same or different bit depth precision.

ISP processor 740 may also receive image data from image memory 730. For example, the sensor 720 interface sends the raw image data to the image memory 730, where the raw image data in the image memory 730 is provided to the ISP processor 740 for processing. Image memory 730 may be part of a memory device, a storage device, or a separate dedicated memory within an electronic device, and may include DMA (Direct Memory Access ) features.

Upon receiving raw image data from the image sensor 714 interface or from the sensor 720 interface or from the image memory 730, the ISP processor 740 may perform one or more image processing operations, such as temporal filtering. The processed image data may be sent to image memory 730 for additional processing before being displayed. ISP processor 740 receives the processed data from image memory 730 and processes the processed data for image data in the original domain and in the RGB and YCbCr color spaces. The image data processed by ISP processor 740 may be output to display 770 for viewing by a user and/or further processing by a graphics engine or GPU (Graphics Processing Unit, graphics processor). Further, the output of ISP processor 740 may also be sent to image memory 730, and display 770 may read image data from image memory 730. In one embodiment, image memory 730 may be configured to implement one or more frame buffers. In addition, the output of ISP processor 740 may be sent to encoder/decoder 760 in order to encode/decode image data. The encoded image data may be saved and decompressed prior to display on display 770. The encoder/decoder 760 may be implemented by a CPU or GPU or co-processor.

The statistics determined by ISP processor 740 may be sent to control logic 750 unit. For example, the statistics may include image sensor 714 statistics for auto-exposure, auto-white balance, auto-focus, flicker detection, black level compensation, lens 712 shading correction, and the like. Control logic 750 may include a processor and/or microcontroller that executes one or more routines (e.g., firmware) that may determine control parameters of imaging device 710 and control parameters of ISP processor 740 based on the received statistics. For example, control parameters of the imaging device 710 may include sensor 720 control parameters (e.g., gain, integration time for exposure control, anti-shake parameters, etc.), camera flash control parameters, lens 712 control parameters (e.g., focal length for focusing or zooming), or a combination of these parameters. The ISP control parameters may include gain levels and color correction matrices for automatic white balancing and color adjustment (e.g., during RGB processing), as well as lens 712 shading correction parameters.

In an embodiment of the present application, the ISP processor 740 included in the mobile device performs the steps of the face recognition data processing method when executing computer readable instructions stored on a memory.

The embodiment of the application also provides a computer readable storage medium. One or more non-transitory computer-readable storage media containing computer-readable instructions that, when executed by a processor, perform the steps of: receiving human face identification error feedback information through mobile equipment; adjusting a corresponding recognition control threshold value in the current face recognition algorithm according to the face recognition error feedback information; and carrying out face recognition according to the current face recognition algorithm after the recognition control threshold is adjusted.

In one embodiment, the computer readable instructions are executed by a processor to: acquiring a current recognition scene corresponding to the current face recognition, and acquiring a feedback recognition scene corresponding to the feedback information of the face recognition errors; and when the current recognition scene is matched with the feedback recognition scene, entering a step of adjusting a corresponding recognition control threshold value in the current face recognition algorithm according to the face recognition error feedback information.

In one embodiment, the computer readable instructions are executed by a processor to: acquiring feedback recognition scenes corresponding to the human face recognition error feedback information, and establishing a matching relation between the feedback recognition scenes and the adjusted recognition control threshold; acquiring a current recognition scene corresponding to the current face recognition, and determining a target feedback recognition scene matched with the current recognition scene; acquiring a target recognition control threshold corresponding to the target feedback recognition scene according to the matching relation; and carrying out face recognition according to the current face recognition algorithm corresponding to the target recognition control threshold.

The embodiment of the application also provides a computer readable instruction product. A computer readable instruction product containing instructions which, when run on a computer, cause the computer to perform a face recognition data processing method.

Those skilled in the art will appreciate that implementing all or part of the above-described methods may be accomplished by computer readable instructions to instruct associated hardware, and that the program may be stored on a non-transitory computer readable storage medium, which when executed may include the steps of the above-described embodiments of the methods. Any reference to memory, storage, database, or other medium used in connection with the present application may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM), which acts as external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.

Claims

1. A face recognition data processing method, characterized by comprising:

Performing face recognition according to the current face recognition algorithm after the recognition control threshold is adjusted; the recognition control threshold comprises an alignment threshold and a prosthesis threshold;

The adjusting the corresponding recognition control threshold value in the current face recognition algorithm according to the face recognition error feedback information comprises the following steps: when the face recognition error feedback information is the error acceptance recognition feedback information, the comparison threshold value is improved; and when the human face recognition error feedback information is false rejection recognition feedback information, the prosthesis threshold value is increased.

2. The method of claim 1, wherein the mobile device receiving face recognition error feedback information comprises:

and receiving the human face recognition error feedback information through a control displayed on the screen of the mobile device, wherein different controls transmit different human face recognition error feedback information.

3. The method of claim 2, wherein the receiving face recognition error feedback information via a control displayed on the screen of the mobile device comprises:

generating error acceptance identification feedback information in response to an operation acting on a first control displayed on a screen of the mobile device, and taking the error acceptance identification feedback information as the face recognition error feedback information;

And receiving the error acceptance identification feedback information transmitted by the first control.

4. The method of claim 3, wherein generating false acceptance identification feedback information in response to an operation on a first control displayed on the mobile device screen comprises:

the mobile equipment acquires a current face image;

When the current face image is not actually matched with the preset unlocking face image, the current face image is mistakenly identified as the preset unlocking face by the current face recognition algorithm, and the screen of the mobile device is triggered to be successfully unlocked, the false acceptance identification feedback information is generated in response to the operation acting on the first control.

5. The method of claim 2, wherein the receiving face recognition error feedback information via a control displayed on the screen of the mobile device comprises:

Generating false rejection identification feedback information in response to an operation acting on a second control displayed on the screen of the mobile device, wherein the false rejection identification feedback information is used as the face recognition false feedback information;

And receiving the false rejection identification feedback information transmitted by the second control.

6. The method of claim 5, wherein generating false rejection identification feedback information in response to an operation on a second control displayed on the mobile device screen comprises:

the mobile equipment acquires a current face image;

When the current face image is actually matched with the preset unlocking face image, the current face image is mistakenly identified as a non-preset unlocking face by the current face recognition algorithm, and the screen unlocking of the mobile device fails, the false rejection recognition feedback information is generated in response to the operation acting on the second control.

7. The method according to claim 1, wherein said adjusting the corresponding recognition control threshold in the current face recognition algorithm according to the face recognition error feedback information further comprises:

and when the human face recognition error feedback information is the error acceptance recognition feedback information, the prosthesis threshold value is reduced.

8. The method according to claim 1, wherein said adjusting the corresponding recognition control threshold in the current face recognition algorithm according to the face recognition error feedback information further comprises:

And when the human face recognition error feedback information is the error rejection recognition feedback information, reducing the comparison threshold.

9. The method according to claim 1, wherein before adjusting the corresponding recognition control threshold in the current face recognition algorithm according to the face recognition error feedback information, further comprises:

Acquiring a current recognition scene corresponding to the current face recognition, and acquiring a feedback recognition scene corresponding to the face recognition error feedback information;

and when the current recognition scene is matched with the feedback recognition scene, entering the step of adjusting the corresponding recognition control threshold value in the current face recognition algorithm according to the face recognition error feedback information.

10. The method according to claim 1, wherein the method further comprises:

Acquiring a feedback recognition scene corresponding to the human face recognition error feedback information, and establishing a matching relation between the feedback recognition scene and an adjusted recognition control threshold;

acquiring a current recognition scene corresponding to the current face recognition, and determining a target feedback recognition scene matched with the current recognition scene;

Acquiring a target recognition control threshold corresponding to the target feedback recognition scene according to the matching relation;

and carrying out face recognition according to the current face recognition algorithm corresponding to the target recognition control threshold.

11. The method according to claim 1, wherein said adjusting the corresponding recognition control threshold in the current face recognition algorithm according to the face recognition error feedback information comprises:

acquiring an initial recognition control threshold corresponding to the current face recognition algorithm;

Acquiring an adjustment range of an identification control threshold;

And adjusting a corresponding recognition control threshold value in the current face recognition algorithm according to the face recognition error feedback information, so that the difference between the adjusted current recognition control threshold value and the initial recognition control threshold value is within the adjustment range of the recognition control threshold value.

12. A face recognition data processing apparatus, comprising:

The recognition module is used for carrying out face recognition according to the current face recognition algorithm after the recognition control threshold is adjusted; the recognition control threshold comprises an alignment threshold and a prosthesis threshold;

13. A mobile device comprising a memory and a processor, the memory having stored therein computer readable instructions which, when executed by the processor, cause the processor to perform the steps of the method of any of claims 1 to 11.

14. A computer readable storage medium having stored thereon computer readable instructions which, when executed by a processor, cause the processor to perform the steps of the method of any of claims 1 to 11.

15. A computer readable instruction product, characterized in that the computer readable instruction product containing instructions, when run on a computer, causes the computer to perform the steps of the method of any of claims 1 to 11.