CN115482566A

CN115482566A - Face recognition method, device and equipment

Info

Publication number: CN115482566A
Application number: CN202110663443.9A
Authority: CN
Inventors: 吕瑞; 杨成平
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd
Priority date: 2021-06-15
Filing date: 2021-06-15
Publication date: 2022-12-16

Abstract

The embodiment of the specification discloses a face recognition method, a face recognition device and face recognition equipment, wherein the method comprises the following steps: acquiring an image in a current preset area, wherein the acquired image comprises a depth image, and acquiring facial recognition intention information of a user in the preset area based on the acquired image under the condition of acquiring a facial recognition request, wherein the facial recognition intention information comprises one or more of behavior and action information, facial position information and facial posture information of the user; determining target users needing face recognition in the users in the preset area based on the face recognition intention information of the users; and executing face recognition processing corresponding to the face recognition request on the target user.

Description

Face recognition method, device and equipment

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a method, an apparatus, and a device for face recognition.

Background

With the continuous development of biometric technology, face recognition has become one of the important technologies in the current biometric technology development with the advantage of simple and rapid recognition process, but face recognition also has many problems to be solved in practical application. If a plurality of different users are all in the shooting range of the camera assembly of the facial recognition device, the facial recognition device is difficult to judge which user is the user who really needs to perform facial recognition, so that the users without the intention of facial recognition may be subjected to facial recognition processing, and further the facial recognition efficiency is low, or even the facial recognition cannot be performed.

Disclosure of Invention

It is an object of the embodiments of the present specification to provide a face recognition mechanism with higher face recognition efficiency in a case where a plurality of users are within a shooting range of a camera module.

In order to implement the above technical solution, the embodiments of the present specification are implemented as follows:

an embodiment of the present specification provides a face recognition method, including: and acquiring an image in a current preset area, wherein the acquired image comprises a depth image. Acquiring facial recognition intention information of the user in the preset area based on the acquired image under the condition of acquiring a facial recognition request, wherein the facial recognition intention information comprises one or more of behavior action information, facial position information and facial posture information of the user. And determining target users needing face recognition in the users in the preset area based on the face recognition intention information of the users. And executing face recognition processing corresponding to the face recognition request on the target user.

An embodiment of the present specification provides a face recognition method, including: and acquiring an image in a current preset area, wherein the acquired image comprises a depth image. In the case of acquiring a face recognition request, acquiring face recognition intention information of a user in the preset area based on the acquired image, wherein the face recognition intention information comprises one or more of behavior action information, face position information and face posture information of the user. And providing the facial recognition intention information of the users in the preset area to a preset block chain system, so that the block chain system can recognize the facial recognition intention information of the users in the preset area through a pre-deployed intelligent contract, and a target user needing to be subjected to facial recognition in the users in the preset area is obtained. And receiving the information of the target user sent by the block chain system, and executing facial recognition processing corresponding to the facial recognition request on the target user.

An embodiment of the present specification provides a face recognition method, including: applied to a blockchain system, the method comprising: receiving facial recognition intention information of a user in a preset area sent by a facial recognition device, wherein the facial recognition intention information of the user in the preset area is that the facial recognition device collects an image in the current preset area, and under the condition of obtaining a facial recognition request, the facial recognition intention information comprises one or more of lip language information, facial position information and facial posture information of the user in the preset area, and the collected image comprises a depth image. The method comprises the steps that facial recognition intention information of users in a preset area is recognized based on a first intelligent contract which is deployed in advance, a target user needing facial recognition in the users in the preset area is obtained, and the first intelligent contract is used for triggering recognition processing of the facial recognition intention information of the users in the preset area. And sending the information of the target user to the facial recognition equipment so as to enable the facial recognition equipment to execute facial recognition processing corresponding to the facial recognition request on the target user.

An embodiment of the present specification provides a face recognition apparatus, including: the image acquisition model acquires images in a current preset area, and the acquired images comprise depth images. And the intention information acquisition module is used for acquiring facial recognition intention information of the user in the preset area based on the acquired image under the condition of acquiring a facial recognition request, wherein the facial recognition intention information comprises one or more of behavior and action information, facial position information and facial posture information of the user. And the user determination module is used for determining a target user needing face recognition in the users in the preset area based on the face recognition intention information of the users. And the facial recognition module is used for executing facial recognition processing corresponding to the facial recognition request on the target user.

An embodiment of the present specification provides a face recognition apparatus, including: the image acquisition module is used for acquiring images in a current preset area, and the acquired images comprise depth images. And the intention information acquisition module is used for acquiring facial recognition intention information of the user in the preset area based on the acquired image under the condition of acquiring a facial recognition request, wherein the facial recognition intention information comprises one or more of behavior and action information, facial position information and facial posture information of the user. And the information providing module is used for providing the facial recognition intention information of the user in the preset area to a preset block chain system so that the block chain system can perform recognition processing on the facial recognition intention information of the user in the preset area through a pre-deployed intelligent contract to obtain a target user needing facial recognition in the user in the preset area. And the information receiving module is used for receiving the information of the target user sent by the block chain system and executing facial recognition processing corresponding to the facial recognition request on the target user.

An embodiment of the present specification provides a face recognition apparatus, including: the information receiving module receives face recognition intention information of a user in a preset area sent by face recognition equipment, the face recognition intention information of the user in the preset area is that the face recognition equipment collects images in the current preset area, and under the condition that a face recognition request is obtained, the images are collected according to the collected information obtained by the images, the images are collected to include depth images, and the face recognition intention information comprises one or more of lip language information, face position information and face posture information of the user in the preset area. And the intention identification module is used for identifying the facial identification intention information of the users in the preset area based on a first intelligent contract deployed in advance to obtain target users needing facial identification in the users in the preset area, and the first intelligent contract is used for triggering the identification of the facial identification intention information of the users in the preset area. And the information sending module is used for sending the information of the target user to the facial recognition equipment so as to enable the facial recognition equipment to execute facial recognition processing corresponding to the facial recognition request on the target user.

An embodiment of the present specification provides a face recognition apparatus, including: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to: and acquiring an image in a current preset area, wherein the acquired image comprises a depth image. In the case of acquiring a face recognition request, acquiring face recognition intention information of a user in the preset area based on the acquired image, wherein the face recognition intention information comprises one or more of behavior action information, face position information and face posture information of the user. And determining target users needing face recognition in the users in the preset area based on the face recognition intention information of the users. And executing face recognition processing corresponding to the face recognition request on the target user.

An embodiment of the present specification provides a face recognition apparatus, including: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to: and acquiring an image in a current preset area, wherein the acquired image comprises a depth image. Acquiring facial recognition intention information of the user in the preset area based on the acquired image under the condition of acquiring a facial recognition request, wherein the facial recognition intention information comprises one or more of behavior action information, facial position information and facial posture information of the user. And providing the facial recognition intention information of the users in the preset area to a preset blockchain system, so that the blockchain system can recognize the facial recognition intention information of the users in the preset area through a pre-deployed intelligent contract, and a target user needing facial recognition in the users in the preset area is obtained. And receiving the information of the target user sent by the block chain system, and executing facial recognition processing corresponding to the facial recognition request on the target user.

An embodiment of the present specification provides a face recognition apparatus, including: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to: receiving facial recognition intention information of a user in a preset area sent by a facial recognition device, wherein the facial recognition intention information of the user in the preset area is that the facial recognition device collects an image in the current preset area, and under the condition of obtaining a facial recognition request, the facial recognition intention information comprises one or more of lip language information, facial position information and facial posture information of the user in the preset area, and the collected image comprises a depth image. The method comprises the steps that facial recognition intention information of users in a preset area is recognized based on a first intelligent contract which is deployed in advance, target users needing facial recognition in the users in the preset area are obtained, and the first intelligent contract is used for triggering recognition processing of the facial recognition intention information of the users in the preset area. And sending the information of the target user to the facial recognition device so that the facial recognition device executes facial recognition processing corresponding to the facial recognition request on the target user.

Embodiments of the present specification also provide a storage medium, where the storage medium is used to store computer-executable instructions, and the executable instructions, when executed, implement the following processes: and acquiring an image in a current preset area, wherein the acquired image comprises a depth image. Acquiring facial recognition intention information of the user in the preset area based on the acquired image under the condition of acquiring a facial recognition request, wherein the facial recognition intention information comprises one or more of behavior action information, facial position information and facial posture information of the user. And determining target users needing face recognition in the users in the preset area based on the face recognition intention information of the users. And executing face recognition processing corresponding to the face recognition request on the target user.

The present specification also provides a storage medium, wherein the storage medium is used for storing computer executable instructions, and the executable instructions implement the following processes when executed: and acquiring an image in a current preset area, wherein the acquired image comprises a depth image. In the case of acquiring a face recognition request, acquiring face recognition intention information of a user in the preset area based on the acquired image, wherein the face recognition intention information comprises one or more of behavior action information, face position information and face posture information of the user. And providing the facial recognition intention information of the users in the preset area to a preset blockchain system, so that the blockchain system can recognize the facial recognition intention information of the users in the preset area through a pre-deployed intelligent contract, and a target user needing facial recognition in the users in the preset area is obtained. And receiving the information of the target user sent by the block chain system, and executing facial recognition processing corresponding to the facial recognition request on the target user.

The present specification also provides a storage medium, wherein the storage medium is used for storing computer executable instructions, and the executable instructions implement the following processes when executed: receiving facial recognition intention information of a user in a preset area sent by a facial recognition device, wherein the facial recognition intention information of the user in the preset area is that the facial recognition device collects an image in the current preset area, and under the condition of obtaining a facial recognition request, the facial recognition intention information comprises one or more of lip language information, facial position information and facial posture information of the user in the preset area, and the collected image comprises a depth image. The method comprises the steps that facial recognition intention information of users in a preset area is recognized based on a first intelligent contract which is deployed in advance, a target user needing facial recognition in the users in the preset area is obtained, and the first intelligent contract is used for triggering recognition processing of the facial recognition intention information of the users in the preset area. And sending the information of the target user to the facial recognition device so that the facial recognition device executes facial recognition processing corresponding to the facial recognition request on the target user.

Drawings

In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the description below are only some embodiments described in the present specification, and for those skilled in the art, other drawings may be obtained according to these drawings without creative efforts.

FIG. 1 illustrates an embodiment of a face recognition method of the present disclosure;

FIG. 2 is another embodiment of a face recognition method of the present disclosure;

FIG. 3 is a diagram of yet another embodiment of a face recognition method of the present disclosure;

FIG. 4 is a diagram of another embodiment of a face recognition method;

FIG. 5 is a diagram of yet another embodiment of a face recognition method;

FIG. 6 illustrates an embodiment of a facial recognition apparatus of the present disclosure;

FIG. 7 is another embodiment of a facial recognition apparatus of the present disclosure;

FIG. 8 is a further embodiment of a facial recognition apparatus herein;

fig. 9 is an embodiment of a face recognition apparatus of the present specification.

Detailed Description

The embodiment of the specification provides a face recognition method, a face recognition device and face recognition equipment.

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present specification, and not all of the embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments in the present specification without any inventive step should fall within the scope of protection of the present specification.

Example one

As shown in fig. 1, an execution subject of the method may be a facial recognition device, which may be a terminal device or an implement capable of performing facial recognition, and the like, where the terminal device may be a mobile terminal device such as a mobile phone, a tablet computer, and the like. The machine can be a vending machine of a certain commodity or a pass verification machine of a certain area and the like. The method may specifically comprise the steps of:

in step S102, an image in a current preset area is acquired, where the acquired image includes a depth image.

The preset area may be within a shooting range of a camera assembly of the face recognition device, or may also be a designated area within the shooting range, which may be specifically set according to an actual situation, and this is not limited in this specification. The depth image may be an image in which the distance (depth) from the camera module to each point in the scene is used as a pixel value, the depth image may directly reflect the geometric shape of the visible surface of the scene, the depth image may be calculated as point cloud data through coordinate conversion, and the point cloud data with regular and necessary information may be inversely calculated as depth image data.

In implementation, with the continuous development of biometric technology, face recognition has become one of the important technologies in the current biometric technology development with the advantage of simple and rapid recognition process, but face recognition also has many problems to be solved in practical application. If a plurality of different users are all in the shooting range of the camera assembly of the facial recognition device, the facial recognition device is difficult to judge which user is the user who really needs to perform facial recognition, so that the users without the intention of facial recognition may be subjected to facial recognition processing, and further the facial recognition efficiency is low, or even the facial recognition cannot be performed. The embodiment of the present specification provides an implementable technical solution, which may specifically include the following contents:

for the case that the faces of a plurality of different users are all located within the shooting range of the camera assembly of the face recognition device or within a specified area within the shooting range (i.e. within a preset area), if the face recognition mechanism of the face recognition device is triggered, it is difficult for the face recognition device to accurately determine which user needs to perform face recognition, and based on this, it can be determined whether the user within the preset area has a desire to perform face recognition. The camera assembly may be located at the top, middle, or bottom of the facial recognition device, etc. The face recognition device may further include a face recognition trigger button, which may be a physical button or a virtual button disposed in a display module of the face recognition device. The specific treatment may be as follows: when a certain user needs to perform face recognition, the face recognition device can be faced, the face recognition device can start the camera shooting assembly to collect images in a current preset area, and the camera shooting assembly can be a depth camera, so that one or more images including depth images in the current preset area can be collected through the camera shooting assembly, the number of the face of each user can be numbered, real-time tracking can be performed, and a basis is provided for the follow-up face recognition intention of the user to be accurately judged.

In step S104, in the case where the face recognition request is acquired, face recognition intention information of the user within the preset area is acquired based on the acquired image, the face recognition intention information including one or more of behavior action information, face position information, and face posture information of the user.

The face recognition request may be a notification message requesting face recognition, and the face recognition request may be triggered in various ways, for example, a user may click a face recognition key in a face recognition device to trigger the face recognition device to generate a face recognition request, which may be specifically set according to an actual situation, which is not limited in this description of the embodiment. The user may be a user whose facial information can be collected by a camera assembly in the facial recognition device, and the camera assembly may be a component for collecting images in the facial recognition device, such as a camera or a video camera of a vending machine. The face recognition intention information may be information for determining whether a certain user has an intention to perform face recognition. The behavior action information may be information of operation behaviors of the user in the process of executing one or more services or tasks, for example, information of various operation behaviors of the user in the process of clicking a designated key in the face recognition device by the user, and the like. The face position information may be a coordinate position or a region where the face of a certain user is located in the image preview interface of the camera module, or the like. The facial pose information may be information of a pose of the face of the user, and the facial pose information may include, for example, an angle that the face of the user and a specified reference plane present, and may be specifically set according to an actual situation, which is not limited in this specification.

In implementation, the face recognition device may further include a trigger key for face recognition, where the trigger key may be a physical key, or a virtual key disposed in a display component of the face recognition device. When a certain user needs to perform face recognition, a trigger key on the face recognition device can be clicked, at this time, the face recognition device can generate a face recognition request, at this time, the face recognition device can acquire the face recognition request, and at the same time, the face recognition device can also record an operation behavior of the user in the process of clicking the trigger key, an image shot by the camera assembly is recorded, then the face recognition device can acquire an image shot by the camera assembly before the face recognition request is acquired, and can analyze the image, wherein the depth image can be analyzed, various operation behavior actions of various users before the face recognition request is acquired can be determined, and based on a face image of each user in a shooting range of the camera assembly, the face position information and the face posture information of each user in the image can be determined, the face of each user can be numbered, real-time tracking can be performed, and a basis is provided for accurately judging the face recognition intention of the user subsequently.

After the face recognition request is obtained by the face recognition device, the face recognition intention information of each user in the shooting range of the camera assembly can be obtained, and the face recognition intention information can be one or more of the behavior action information, the face position information and the face posture information of each user in the shooting range of the camera assembly.

It should be noted that, the above is only one achievable processing manner, in practical applications, the facial recognition intention information of the user may also include multiple types, which may be specifically set according to practical situations, and this is not limited in this embodiment of the specification.

In step S106, a target user who needs to perform face recognition among the users in the preset area is determined based on the face recognition intention information of the users.

In an implementation, if a plurality of different users are included in a shooting range of the camera module, and not all of the plurality of different users need to perform face recognition, in order to accurately determine which user needs to perform face recognition, the determination may be performed based on face recognition intention information of the user, specifically, behavior and action information of each user in a preset area may be acquired, and the behavior and action information of each user may be analyzed to determine whether the user performs an operation of clicking the trigger key, and if it is determined that the user performs an operation of clicking the trigger key, it may be determined that the user has a face recognition intention and needs to perform face recognition, and at this time, the user may be marked. If it is determined that the user does not perform the operation of clicking the above trigger key, it may be determined that the user does not have a facial recognition intention. In addition, the face position information of each user in the preset area can be acquired, and the face position information of each user can be analyzed to determine the position of the user. The position of the user can be combined with the behavior action information, so that the user who has the intention of face recognition can be more accurately judged. In addition, facial pose information of each user within the preset area may be obtained, and the facial pose information of each user may be analyzed to determine the facial pose of the user, and thus the user may be tracked. The position, the facial posture and the behavior action information of the user can be combined, so that the user who has the intention of face recognition can be more accurately judged. By analyzing the facial recognition intention information of each user, target users needing facial recognition in the users in the preset area can be obtained.

In step S108, the face recognition processing corresponding to the face recognition request is executed for the target user.

In implementation, after the facial recognition device determines that the target user is a user who needs to perform facial recognition, a facial recognition mechanism corresponding to the facial recognition request may be started for the target user, through the facial recognition mechanism, a facial image of the target user may be acquired through the camera component, and the acquired facial image may be compared with a pre-stored reference image, if the two images match, it may be determined that the target user has passed facial recognition processing, otherwise, the target user may be notified that facial recognition fails, and the like.

The embodiment of the specification provides a face recognition method, which includes the steps of collecting an image in a current preset area, wherein the collected image comprises a depth image, under the condition that a face recognition request is obtained, obtaining face recognition intention information of a user in the preset area based on the collected image, wherein the face recognition intention information comprises one or more of behavior action information, face position information and face posture information of the user, then determining a target user needing face recognition in the user in the preset area based on the face recognition intention information of the user, and executing face recognition processing corresponding to the face recognition request on the target user.

Example two

As shown in fig. 2, an embodiment of the present specification provides a face recognition method, where an execution subject of the method may be a face recognition device, and the face recognition device may be a terminal device or an implement capable of performing face recognition, where the terminal device may be a mobile terminal device such as a mobile phone and a tablet computer. The machine can be a vending machine of a certain commodity or a pass verification machine of a certain area and the like. The method may specifically comprise the steps of:

in practical applications, in order to improve the data processing efficiency and the accuracy of user intention recognition, a model for recognizing the intention of the user, i.e., an intention recognition model, may be trained in advance, and specifically, refer to the following processing of step S202 and step S204.

In step S202, historical facial recognition intention information of a plurality of different users is acquired, the historical facial recognition intention information including one or more of historical behavioral action information, historical facial position information, and historical facial pose information of the plurality of different users.

The historical facial recognition intention information may be information of facial recognition intention of the user at a certain time point or time period in the history.

In implementation, historical facial recognition intention information of a plurality of different users may be obtained in a plurality of different manners, for example, behavior and action information, facial position information, and facial posture information of a user during a facial recognition processing process performed by the user using a facial recognition device at a certain time point or within a certain time period may be purchased from different users in a purchasing manner, or alternatively, a user may be invited to a certain application developed by a preferred experience in an exchange manner, information such as behavior and action information, facial position information, and facial posture information generated by the user during the use of the application may be used by a developer to perform model training, and the like.

In step S204, a wish recognition model is model-trained according to the historical facial recognition wish information, so as to obtain a trained wish recognition model.

In implementation, a corresponding algorithm may be preset according to an actual situation, the algorithm may be a machine learning related algorithm, or may be other algorithms, and specifically, the algorithm may be a preset expert decision algorithm or a preset evaluation algorithm, and a model architecture of the will identification model may be constructed through the algorithm, and the model architecture may include one or more different parameters to be determined. Then, model training may be performed on the intention recognition model according to the obtained historical facial recognition intention information of the plurality of different users, specifically, the historical facial recognition intention information of the plurality of different users may be input into the intention recognition model to obtain an equation set about the parameter to be determined, solving the equation sequence may obtain an initial value of each parameter, then, the historical facial recognition intention information of the remaining users may be input into the intention recognition model with the initial values of the parameters, and finally, an updated parameter value may be obtained, and in this way, a better parameter value of the parameter may be obtained, and finally, the trained intention recognition model may be obtained.

It should be noted that, because the training data includes the behavior and action information of the user, the intention recognition model may have capabilities of user behavior detection and behavior recognition, and the user behavior detection or behavior recognition may be to arrange the position information of the user in a time sequence to obtain user position information based on a time sequence, and then may pre-process the user position information based on the time sequence, extract a feature vector for recognizing the behavior and action type of the user according to the pre-processed user position information, and may recognize the behavior and action type of the user according to the feature vector.

In step S206, an image in the current preset area is acquired, where the acquired image includes a depth image and an RGB image.

The RGB image may be an image in which the color of one pixel is identified using 3 components of red, green, and blue, and an image of an arbitrary color may be synthesized by the 3 primary colors.

In step S208, in the case where the face recognition request is acquired, the RGB image and the depth image are subjected to registration and coordinate mapping processing to fuse the RGB image and the depth image, resulting in a fused three-dimensional image.

In implementation, in order to accurately recognize a behavior action of a user, the behavior action may be realized by a three-dimensional image, specifically, the face recognition device may acquire an RGB image and a depth image of a preset region by using a camera component, then may sort the RGB image in a time sequence, may also sort the depth image in the time sequence, may perform alignment processing (or registration) on the RGB image of a time sequence and the depth image of the time sequence, and may perform coordinate mapping on the RGB image and the depth image of the time sequence, so as to perform fusion processing on the RGB image and the depth image of the same time, and finally may obtain a fused three-dimensional image.

In step S210, behavior and action information of the user in the preset region is acquired based on the fused three-dimensional image.

In implementation, in order to accurately identify the action of the user triggering the facial recognition, the trigger button may be disposed at the top of the facial recognition device, so that it may be easily determined whether a certain user performs the action of triggering the facial recognition, and specifically, the fused three-dimensional image may be analyzed, and it may be determined from the analysis whether there is a user who raises an arm and has the arm extending direction at the position where the image pickup assembly is located. In addition, the behavior of each user in the fused three-dimensional image may also be determined through analysis of the fused three-dimensional image, which may be specifically set according to an actual situation, and this is not limited in this embodiment of the specification.

In practical applications, the processing of step S210 may be various, and an alternative processing manner is provided as follows, which may specifically include the following: and performing limb detection and tracking on the fused three-dimensional image, performing time sequence classification processing on the fused three-dimensional image, and determining behavior and action information of the user in a preset area.

The time sequence classification may be to sort the relevant information such as the user position information according to a time sequence to obtain the relevant information such as the user position information based on the time sequence, then extract a feature vector for identifying the behavior action type of the user based on the relevant information such as the user position information based on the time sequence, and identify the behavior action type of the user according to the feature vector, thereby obtaining a corresponding classification.

In implementation, three-dimensional human body detection (namely three-dimensional limb detection) can be carried out on the fused three-dimensional image so as to detect the spatial positions of different users, in addition, three-dimensional human body tracking can be carried out on the fused three-dimensional image so as to accurately mark each different user, and in addition, three-dimensional time sequence classification can be carried out on the fused three-dimensional image so as to accurately judge different types of behavior actions executed by each user. The behavior and action information of the user in the preset area can be determined through the processing.

In practical applications, the processing of step S210 may be various, and an alternative processing manner may be provided below, which may specifically include the following: inputting a plurality of different fused three-dimensional images into a pre-trained behavior detection model to perform limb detection and tracking on the fused three-dimensional images, and performing time sequence classification processing on the fused three-dimensional images to obtain behavior and action information of users in a preset area, wherein the behavior detection model is obtained by performing model training through a deep learning algorithm based on a plurality of different historical three-dimensional images.

The behavior detection model may be constructed in a variety of different manners, for example, the behavior detection model may be constructed through a neural network model, or may also be constructed through a clustering algorithm and a principal component analysis algorithm, and the like, and may be specifically set according to an actual situation, which is not limited in the embodiments of the present specification.

In implementation, a plurality of different historical three-dimensional images can be acquired in a plurality of different ways, and then a preset machine learning algorithm can be used for constructing a model framework of the behavior detection model, wherein the model framework can comprise one or more different parameters to be determined. Then, the behavior detection model may be subjected to model training through the obtained multiple different historical three-dimensional images, specifically, the multiple different historical three-dimensional images may be input into the behavior detection model to obtain an equation set about the parameter to be determined, an initial value of each parameter may be obtained by solving the equation sequence, then, the remaining historical three-dimensional images are input into the behavior detection model with the initial value of the parameter, and finally, an updated parameter value may be obtained, and in this way, a better parameter value of the parameter may be obtained, and finally, the trained behavior detection model may be obtained.

A plurality of different fused three-dimensional images can be input into a pre-trained behavior detection model, limb detection and tracking can be performed on the fused three-dimensional images through the behavior detection model, and time sequence classification processing can be performed on the fused three-dimensional images to obtain behavior and action information of users in a preset area.

In step S212, the face position information and face posture information of the user within the preset area are acquired based on the captured image.

The collected image may include the RGB image and the depth image.

In step S214, it is determined whether there is a user of a behavioral action that triggers face recognition among users within the preset area based on the behavioral action information of the user.

In implementation, as described above, the trigger button may be disposed at the top of the facial recognition device, and then the fused three-dimensional image may be analyzed, so as to determine whether there is a user who lifts up the arm and has the arm extending direction at the position of the camera module, that is, whether there is a user who triggers a behavior action of facial recognition among users in the preset area may be determined.

In step S216, if the target user exists, the facial recognition intention information of the users in the preset area is input into the pre-trained intention recognition model, and the target user who needs to perform facial recognition among the users in the preset area is obtained.

In step S218, the face recognition processing corresponding to the face recognition request described above is performed on the target user.

The embodiment of the specification provides a face recognition method, which includes the steps of collecting an image in a current preset area, wherein the collected image comprises a depth image, under the condition that a face recognition request is obtained, obtaining face recognition intention information of a user in the preset area based on the collected image, wherein the face recognition intention information comprises one or more of behavior action information, face position information and face posture information of the user, then determining a target user needing face recognition in the user in the preset area based on the face recognition intention information of the user, and executing face recognition processing corresponding to the face recognition request on the target user. In addition, a face brushing intention identification method based on data acquisition, three-dimensional image fusion, behavior identification of three-dimensional images, intention identification and face identification is further provided.

EXAMPLE III

As shown in fig. 3, an embodiment of the present specification provides a face recognition method, where an execution subject of the method may be a face recognition device, and the face recognition device may be a terminal device or an implement capable of performing face recognition, where the terminal device may be a mobile terminal device such as a mobile phone or a tablet computer. The machine can be a vending machine of a certain commodity or a pass verification machine of a certain area and the like. The method may specifically comprise the steps of:

in step S302, an image in a current preset area is acquired, where the acquired image includes a depth image.

In step S304, in the case where the face recognition request is acquired, face recognition intention information of the user within the preset area is acquired based on the acquired image, the face recognition intention information including one or more of behavior action information, face position information, and face posture information of the user.

In step S306, the facial recognition intention information of the user in the preset area is provided to the preset blockchain system, so that the blockchain system performs recognition processing on the facial recognition intention information of the user in the preset area through a pre-deployed intelligent contract to obtain a target user that needs to perform facial recognition among the users in the preset area.

The intelligent contract can be provided with corresponding rules for identifying the face identification intention information of the user, target users needing face identification in the users in the preset area can be determined through the rules set in the intelligent contract, and due to the tamper resistance of the block chain system, the accuracy of identifying the face identification intention of the user can be ensured.

In step S308, the information of the target user sent by the block chain system is received, and the face recognition process corresponding to the face recognition request is performed on the target user.

The embodiment of the specification provides a face recognition method, under the condition that a face recognition request is obtained, face recognition intention information of a user in a preset area is obtained, the face recognition intention information comprises one or more of lip language information, face position information and face posture information of the user in the preset area, the face recognition intention information of the user in the preset area is provided for a preset block chain system, the block chain system conducts recognition processing on the face recognition intention information of the user in the preset area through a pre-deployed intelligent contract, a target user needing face recognition in the user in the preset area is obtained, information of the target user sent by the block chain system is received, and face recognition processing corresponding to the face recognition request is executed on the target user, therefore, the face recognition method based on the information of lip language, face position and face posture of the user is provided, the user really needing face recognition in multiple different users in a shooting range of a camera assembly of face recognition equipment can be accurately recognized, the face recognition efficiency is improved, and face recognition experience is enriched, and face recognition risks exist in face recognition. In addition, the intention of the user is identified through the block chain system, and the accuracy of the intention identification process of the user is improved.

Example four

As shown in fig. 4, an execution subject of the method may be a blockchain system, and the blockchain system may be composed of a terminal device or a server, where the terminal device may be a mobile terminal device such as a mobile phone or a tablet computer, or may also be a device such as a personal computer. The server may be an independent server, a server cluster including a plurality of servers, or the like. The method specifically comprises the following steps:

in step S402, facial recognition intention information of a user in a preset area, which is sent by a facial recognition device, is received, the facial recognition intention information of the user in the preset area is that the facial recognition device acquires an image in the current preset area, and in the case of acquiring a facial recognition request, the acquired image includes a depth image based on information acquired from the acquired image, the facial recognition intention information including one or more of behavior action information, facial position information, and facial posture information of the user in the preset area.

In step S404, the facial recognition intention information of the users in the preset area is identified based on a first intelligent contract deployed in advance, so as to obtain a target user that needs to perform facial recognition among the users in the preset area, where the first intelligent contract is used to trigger the identification of the facial recognition intention information of the users in the preset area.

The first intelligent contract may be provided with corresponding rules for identifying facial recognition intention information of the user, for example, an analysis rule of behavior and an analysis rule of facial gestures, and the like, and may be specifically set according to an actual situation, which is not limited in the embodiment of the present specification. The target user needing face recognition in the users in the preset area can be determined through the rule set in the first intelligent contract, and due to the tamper resistance of the block chain system, the accuracy of recognition of the face recognition intention of the user can be guaranteed.

In step S406, the information of the target user is transmitted to the face recognition apparatus to cause the face recognition apparatus to perform face recognition processing corresponding to the face recognition request for the target user.

EXAMPLE five

As shown in fig. 5, an execution subject of the method may be a blockchain system, and the blockchain system may be composed of a terminal device or a server, where the terminal device may be a mobile terminal device such as a mobile phone or a tablet computer, or may also be a device such as a personal computer. The server may be an independent server, or a server cluster including a plurality of servers. The method specifically comprises the following steps:

in practical application, the facial recognition intention of the user may be analyzed through the pre-trained model, and in addition, considering that the pre-trained model often needs to be updated continuously, the pre-trained model may be stored in a designated storage device, and a storage address of the model may be uploaded to the block chain system, where the training process of the model may refer to the above-mentioned related contents, and is not described herein again. Then, a corresponding intelligent contract may be constructed based on the rule for analyzing the facial recognition intention of the user, and the intelligent contract may be deployed in the blockchain system, which may be specifically referred to as the following relevant contents:

in step S502, facial recognition intention information of a user in a preset area, which is sent by a facial recognition device, is received, the facial recognition intention information of the user in the preset area is that the facial recognition device acquires an image in the current preset area, and in the case of acquiring a facial recognition request, a depth image is included in the acquired image based on acquired image acquisition information, and the facial recognition intention information includes one or more of behavior action information, facial position information, and facial posture information of the user in the preset area.

In step S504, index information of a pre-trained intent recognition model is obtained from the blockchain system based on the first intelligent contract, and the intent recognition model is obtained based on the index information.

In step S506, based on the first intelligent contract, the facial recognition intention information of the users in the preset area is input into the pre-trained intention recognition model, and information of target users who need to perform facial recognition among the users in the preset area is obtained.

In step S508, the information of the target user is transmitted to the face recognition apparatus to cause the face recognition apparatus to perform face recognition processing corresponding to the face recognition request for the target user.

In step S510, a face recognition request of a target user sent by a face recognition device is received, the face recognition request including a face image of the target user captured by the face recognition device.

In step S512, identity authentication is performed on the target user based on a second intelligent contract and the face image, which are deployed in advance, to obtain a corresponding authentication result, where the second intelligent contract is used to trigger identity authentication on a user who initiates face recognition.

In step S514, the authentication result is transmitted to the face recognition apparatus.

The processing in steps S510 to S514 may be: receiving a service request of a target user sent by a face recognition device, wherein the service request comprises a face image of the target user collected by the face recognition device; based on a third intelligent contract and the face image which are deployed in advance, performing identity authentication on a target user to obtain a corresponding authentication result, and processing a service corresponding to the service request based on the authentication result of the identity authentication, wherein the third intelligent contract is used for triggering the identity authentication on a user initiating face identification, and processing the service corresponding to the service request based on the authentication result of the identity authentication; and sending the authentication result and the service processing result to the face recognition equipment.

In addition, the block chain system may also perform analysis processing on the fused three-dimensional image, specifically as follows: receiving a fused three-dimensional image sent by face recognition equipment, wherein the fused three-dimensional image is obtained by carrying out registration and coordinate mapping processing on an RGB (red, green and blue) image and a depth image in an acquired image by the face recognition equipment so as to fuse the RGB image and the depth image; acquiring index information of a pre-trained behavior detection model from the block chain system based on a pre-deployed fourth intelligent contract, and acquiring the behavior detection model based on the index information; and based on a fourth intelligent contract, inputting a plurality of different fused three-dimensional images into the behavior detection model so as to perform limb detection and tracking on the fused three-dimensional images, performing time sequence classification processing on the fused three-dimensional images to obtain behavior and action information of the user in the preset area, and sending the behavior and action information of the user in the preset area to the face recognition equipment.

EXAMPLE six

Based on the same idea, the face recognition method provided in the embodiments of the present specification further provides a face recognition apparatus, as shown in fig. 6.

The face recognition apparatus includes: an image acquisition module 601, a will information acquisition module 602, an information providing module 603, and an information receiving module 604, wherein:

the image acquisition module 601 is used for acquiring an image in a current preset area, wherein the acquired image comprises a depth image;

a intention information obtaining module 602, configured to, in a case that a face recognition request is obtained, obtain face recognition intention information of a user in the preset area based on the acquired image, where the face recognition intention information includes one or more of behavior and action information, face position information, and face posture information of the user;

the information providing module 603 is configured to provide the facial recognition intention information of the user in the preset area to a preset blockchain system, so that the blockchain system performs recognition processing on the facial recognition intention information of the user in the preset area through a pre-deployed intelligent contract to obtain a target user needing facial recognition among the users in the preset area;

the information receiving module 604 receives the information of the target user sent by the blockchain system, and performs facial recognition processing corresponding to the facial recognition request on the target user.

EXAMPLE seven

Based on the same idea, the embodiments of the present specification further provide a face recognition apparatus, as shown in fig. 7.

The face recognition apparatus includes: an information receiving module 701, a will identification module 702 and an information sending module 703, wherein:

an information receiving module 701, configured to receive facial recognition intention information of a user in a preset area, where the facial recognition intention information of the user in the preset area is sent by a facial recognition device, the facial recognition intention information of the user in the preset area is obtained by the facial recognition device by acquiring an image in a current preset area, and when a facial recognition request is obtained, the acquired image includes a depth image based on information acquired from the acquired image, and the facial recognition intention information includes one or more of lip language information, facial position information, and facial posture information of the user in the preset area;

a wish recognition module 702, configured to perform recognition processing on the facial recognition wish information of the users in the preset area based on a pre-deployed first intelligent contract, so as to obtain a target user that needs to perform facial recognition among the users in the preset area, where the first intelligent contract is used to trigger recognition processing on the facial recognition wish information of the users in the preset area;

an information sending module 703, configured to send the information of the target user to the facial recognition device, so that the facial recognition device performs a facial recognition process corresponding to the facial recognition request on the target user.

In this embodiment of the present specification, the willingness recognition module 702 includes:

the model acquisition unit is used for acquiring index information of a pre-trained wisdom recognition model from the block chain system based on the first intelligent contract and acquiring the wisdom recognition model based on the index information;

and the intention identification unit is used for inputting the facial identification intention information of the users in the preset area into a pre-trained intention identification model based on the first intelligent contract to obtain the information of target users needing to perform facial identification in the users in the preset area.

In an embodiment of this specification, the apparatus further includes:

the request receiving module is used for receiving a face recognition request of the target user sent by the face recognition equipment, wherein the face recognition request comprises a face image of the target user collected by the face recognition equipment;

the authentication module is used for carrying out identity authentication on the target user based on a third intelligent contract and the face image, which are deployed in advance, so as to obtain a corresponding authentication result, and the third intelligent contract is used for triggering the identity authentication on the user initiating face recognition;

and the authentication result sending module is used for sending the authentication result to the facial recognition equipment.

The embodiment of the specification provides a face recognition device, under the condition of acquiring a face recognition request, acquiring face recognition intention information of a user in a preset area, wherein the face recognition intention information comprises one or more of lip language information, face position information and face posture information of the user in the preset area, providing the face recognition intention information of the user in the preset area to a preset block chain system, so that the block chain system performs recognition processing on the face recognition intention information of the user in the preset area through a pre-deployed intelligent contract, obtaining a target user needing face recognition in the user in the preset area, receiving information of the target user sent by the block chain system, and performing face recognition processing corresponding to the face recognition request on the target user. In addition, the intention of the user is identified through the block chain system, and the accuracy of the intention identification process of the user is improved.

Example eight

Based on the same idea, the face recognition method provided in the embodiments of the present specification further provides a face recognition apparatus, as shown in fig. 8.

The face recognition apparatus includes: an image acquisition module 801, a will information acquisition module 802, a user determination module 803, and a face recognition module 804, wherein:

the image acquisition module 801 is used for acquiring an image in a current preset area, wherein the acquired image comprises a depth image;

a wish information obtaining module 802, configured to, in a case that a face recognition request is obtained, obtain face recognition wish information of a user in the preset area based on the collected image, where the face recognition wish information includes one or more of behavior and action information, face position information, and face posture information of the user;

a user determining module 803, configured to determine, based on the facial recognition intention information of the user, a target user that needs to perform facial recognition among users in the preset area;

and the facial recognition module 804 is used for executing facial recognition processing corresponding to the facial recognition request on the target user.

In the embodiment of the present specification, the captured image further includes an RGB image, the facial recognition intention information includes behavioral action information of the user,

the willingness information obtaining module 802 includes:

the fusion unit is used for carrying out registration and coordinate mapping processing on the RGB image and the depth image so as to fuse the RGB image and the depth image to obtain a fused three-dimensional image;

and the behavior information acquisition unit is used for acquiring the behavior and action information of the user in the preset area based on the fused three-dimensional image.

In an embodiment of this specification, the behavior information obtaining unit performs limb detection and tracking on the fused three-dimensional image, performs time-series classification processing on the fused three-dimensional image, and determines behavior and action information of a user in the preset area.

In an embodiment of this specification, the behavior information obtaining unit inputs a plurality of different fused three-dimensional images into a pre-trained behavior detection model to perform limb detection and tracking on the fused three-dimensional images, and performs time-series classification processing on the fused three-dimensional images to obtain behavior and action information of a user in the preset area, where the behavior detection model is obtained by performing model training through a deep learning algorithm based on a plurality of different historical three-dimensional images.

In this embodiment of the present specification, the user determining module 803 inputs the facial recognition intention information of the users in the preset area into a pre-trained intention recognition model, so as to obtain a target user that needs to perform facial recognition among the users in the preset area.

In an embodiment of this specification, the apparatus further includes:

the historical information acquisition module is used for acquiring historical facial recognition intention information of a plurality of different users, wherein the historical facial recognition intention information comprises one or more of historical behavior action information, historical facial position information and historical facial posture information of the different users;

and the model training module is used for performing model training on the intention identification model according to the historical facial identification intention information to obtain the trained intention identification model.

In this embodiment of the present specification, the facial recognition intention information includes behavior and action information of the user, and the user determination module 803 includes:

the judging unit is used for determining whether a user triggering the facial recognition action exists in the users in the preset area or not based on the behavior action information of the user;

and if the target user exists, determining a target user needing face recognition in the users in the preset area based on the face recognition intention information of the user.

The embodiment of the specification provides a face recognition device, which collects an image in a current preset area, wherein the collected image comprises a depth image, and when a face recognition request is obtained, face recognition intention information of a user in the preset area is obtained based on the collected image, and the face recognition intention information comprises one or more of behavior action information, face position information and face posture information of the user. In addition, a face brushing intention identification method based on data acquisition, three-dimensional image fusion, behavior identification of three-dimensional images, intention identification and face identification is further provided.

Example nine

Based on the same idea, the facial recognition apparatus provided in the embodiments of the present specification further provides a facial recognition device, as shown in fig. 9.

The face recognition device may be the terminal device or the block chain node in the block chain system provided in the above embodiments.

Facial recognition devices may vary widely in configuration or performance and may include one or more processors 901 and memory 902, where one or more stored applications or data may be stored in memory 902. Memory 902 may be, among other things, transient storage or persistent storage. The application stored in memory 902 may include one or more modules (not shown), each of which may include a series of computer-executable instructions for a face recognition device. Still further, the processor 901 may be configured to communicate with the memory 902 to execute a series of computer-executable instructions in the memory 902 on the facial recognition device. The facial recognition apparatus may also include one or more power supplies 903, one or more wired or wireless network interfaces 904, one or more input-output interfaces 905, one or more keyboards 906.

In particular, in this embodiment, the facial recognition device includes a memory, and one or more programs, where the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the facial recognition device, and the one or more programs configured to be executed by the one or more processors include computer-executable instructions for:

acquiring an image in a current preset area, wherein the acquired image comprises a depth image;

under the condition that a face recognition request is acquired, acquiring face recognition intention information of a user in the preset area based on the acquired image, wherein the face recognition intention information comprises one or more of behavior action information, face position information and face posture information of the user;

determining target users needing face recognition in the users in the preset area based on the face recognition intention information of the users;

and executing face recognition processing corresponding to the face recognition request on the target user.

the acquiring facial recognition intention information of the user in the preset area based on the acquired image comprises:

carrying out registration and coordinate mapping processing on the RGB image and the depth image so as to fuse the RGB image and the depth image to obtain a fused three-dimensional image;

and acquiring behavior and action information of the user in the preset area based on the fused three-dimensional image.

In an embodiment of this specification, the acquiring behavior and action information of the user in the preset region based on the fused three-dimensional image includes:

and performing limb detection and tracking on the fused three-dimensional image, performing time sequence classification processing on the fused three-dimensional image, and determining behavior and action information of the user in the preset area.

In an embodiment of this specification, the performing limb detection and tracking on the fused three-dimensional image, performing time-series classification processing on the fused three-dimensional image, and determining behavior and action information of a user in the preset area includes:

inputting a plurality of different fused three-dimensional images into a pre-trained behavior detection model to perform limb detection and tracking on the fused three-dimensional images, and performing time sequence classification processing on the fused three-dimensional images to obtain behavior and action information of the user in the preset area, wherein the behavior detection model is obtained by performing model training through a deep learning algorithm based on a plurality of different historical three-dimensional images.

In an embodiment of this specification, the determining, based on the facial recognition intention information of the user, a target user that needs to perform facial recognition among users in the preset area includes:

and inputting the facial recognition intention information of the users in the preset area into a pre-trained intention recognition model to obtain target users needing facial recognition in the users in the preset area.

In the embodiment of this specification, the method further includes:

acquiring historical facial recognition intention information of a plurality of different users, wherein the historical facial recognition intention information comprises one or more of historical behavior action information, historical facial position information and historical facial posture information of the plurality of different users;

and performing model training on the intention recognition model through the historical facial recognition intention information to obtain the trained intention recognition model.

In an embodiment of this specification, the determining, by the facial recognition intention information, a target user that needs to be subjected to facial recognition among users in the preset area based on the facial recognition intention information of the user includes:

determining whether a user triggering a behavior action of facial recognition exists in the users in the preset area or not based on the behavior action information of the user;

and if so, determining a target user needing face recognition in the users in the preset area based on the face recognition intention information of the users.

Further, in particular embodiments, the facial recognition device includes a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the facial recognition device, and the one or more programs configured to be executed by the one or more processors include computer-executable instructions for:

providing the facial recognition intention information of the users in the preset area to a preset blockchain system, so that the blockchain system can perform recognition processing on the facial recognition intention information of the users in the preset area through a pre-deployed intelligent contract to obtain target users needing facial recognition in the users in the preset area;

and receiving the information of the target user sent by the block chain system, and executing facial recognition processing corresponding to the facial recognition request on the target user.

Additionally, in particular embodiments, the facial recognition device includes a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the facial recognition device, and execution of the one or more programs by the one or more processors includes computer-executable instructions for:

receiving face recognition intention information of a user in a preset area, wherein the face recognition intention information of the user in the preset area is sent by face recognition equipment, the face recognition intention information of the user in the preset area is that the face recognition equipment collects an image in the current preset area, and under the condition that a face recognition request is obtained, the collected image comprises a depth image based on the information obtained by the collected image, and the face recognition intention information comprises one or more of behavior and action information, face position information and face posture information of the user in the preset area;

identifying the facial recognition intention information of the users in the preset area based on a first intelligent contract which is deployed in advance to obtain target users needing facial recognition in the users in the preset area, wherein the first intelligent contract is used for triggering the identification of the facial recognition intention information of the users in the preset area;

and sending the information of the target user to the facial recognition device so that the facial recognition device executes facial recognition processing corresponding to the facial recognition request on the target user.

In an embodiment of this specification, the identifying, based on a first intelligent contract deployed in advance, facial recognition intention information of users in the preset area to obtain a target user that needs to perform facial recognition among the users in the preset area includes:

acquiring index information of a pre-trained wisdom recognition model from the block chain system based on the first intelligent contract, and acquiring the wisdom recognition model based on the index information;

and on the basis of the first intelligent contract, inputting the facial recognition intention information of the users in the preset area into a pre-trained intention recognition model to obtain the information of target users needing facial recognition in the users in the preset area.

In the embodiment of this specification, the method further includes:

receiving a face recognition request of the target user sent by the face recognition device, wherein the face recognition request comprises a face image of the target user collected by the face recognition device;

based on a second intelligent contract and the face image which are deployed in advance, identity authentication is carried out on the target user to obtain a corresponding authentication result, and the second intelligent contract is used for triggering identity authentication on a user initiating face recognition;

and sending the authentication result to the facial recognition device.

The embodiment of the specification provides a face recognition device, which collects an image in a current preset area, wherein the collected image comprises a depth image, and under the condition of obtaining a face recognition request, face recognition intention information of a user in the preset area is obtained based on the collected image, and the face recognition intention information comprises one or more of behavior action information, face position information and face posture information of the user. In addition, a face brushing intention identification method based on data acquisition, three-dimensional image fusion, behavior identification of three-dimensional images, intention identification and face identification is further provided.

Example ten

Further, based on the methods shown in fig. 1 and fig. 5, one or more embodiments of the present specification further provide a storage medium for storing computer-executable instruction information, in a specific embodiment, the storage medium may be a usb disk, an optical disk, a hard disk, and the like, and when the storage medium stores the computer-executable instruction information, the storage medium can implement the following process when being executed by a processor:

In the embodiment of the present specification, the captured images further include RGB images, the facial recognition intention information includes behavioral and action information of the user,

the acquiring facial recognition intention information of the user in the preset area based on the acquired image comprises the following steps:

and detecting and tracking the limbs of the fused three-dimensional image, carrying out time sequence classification processing on the fused three-dimensional image, and determining behavior and action information of the user in the preset area.

inputting a plurality of different fused three-dimensional images into a pre-trained behavior detection model to perform limb detection and tracking on the fused three-dimensional images, and performing time sequence classification processing on the fused three-dimensional images to obtain behavior and action information of users in the preset area, wherein the behavior detection model is obtained by performing model training through a deep learning algorithm based on a plurality of different historical three-dimensional images.

In the embodiment of this specification, the method further includes:

and if the target user exists, determining the target user needing face recognition in the users in the preset area based on the face recognition intention information of the users.

In another specific embodiment, the storage medium may be a usb disk, an optical disk, a hard disk, or the like, and when executed by the processor, the storage medium stores computer-executable instruction information that implement the following processes:

In another specific embodiment, the storage medium may be a usb disk, an optical disk, a hard disk, or the like, and when executed by the processor, the storage medium stores computer executable instruction information that implement the following process:

receiving face recognition intention information of a user in a preset area, wherein the face recognition intention information of the user in the preset area is sent by a face recognition device, the face recognition intention information is obtained by the face recognition device through collecting an image in the current preset area, and under the condition that a face recognition request is obtained, the collected image comprises a depth image based on the collected image, and the face recognition intention information comprises one or more of behavior and action information, face position information and face posture information of the user in the preset area;

identifying the face recognition intention information of the users in the preset area based on a first intelligent contract which is deployed in advance to obtain target users needing face recognition in the users in the preset area, wherein the first intelligent contract is used for triggering the face recognition intention information of the users in the preset area to be identified;

acquiring index information of a pre-trained wishlist recognition model from the block chain system based on the first intelligent contract, and acquiring the wishlist recognition model based on the index information;

In the embodiment of this specification, the method further includes:

and sending the authentication result to the facial recognition device.

The embodiment of the specification provides a storage medium, which collects an image in a current preset area, wherein the collected image comprises a depth image, under the condition that a face recognition request is obtained, face recognition intention information of a user in the preset area is obtained based on the collected image, the face recognition intention information comprises one or more of behavior action information, face position information and face posture information of the user, then, a target user needing face recognition in the user in the preset area is determined based on the face recognition intention information of the user, and face recognition processing corresponding to the face recognition request is executed on the target user. In addition, a face brushing intention identification method based on data acquisition, three-dimensional image fusion, behavior identification of three-dimensional images, intention identification and face identification is further provided.

The foregoing description of specific embodiments has been presented for purposes of illustration and description. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development, but the original code before compiling is also written in a specific Programming Language, which is called Hardware Description Language (HDL), and the HDL is not only one kind but many kinds, such as abll (Advanced boot Expression Language), AHDL (alternate hard Description Language), traffic, CUPL (computer universal Programming Language), HDCal (Java hard Description Language), lava, lola, HDL, PALASM, software, rhydl (Hardware Description Language), and vhul-Language (vhyg-Language), which is currently used in the field. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC625D, atmel AT91SAM, microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller in purely computer readable program code means, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be regarded as a hardware component and the means for performing the various functions included therein may also be regarded as structures within the hardware component. Or even means for performing the functions may be conceived to be both a software module implementing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the various elements may be implemented in the same one or more software and/or hardware implementations in implementing one or more embodiments of the present description.

As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, one or more embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

Embodiments of the present description are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable fraud case serial-parallel apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable fraud case serial-parallel apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable fraud case to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable fraud case serial-parallel apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a process, method, article, or apparatus comprising the element.

One or more embodiments of the present description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. One or more embodiments of the specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only an example of the present disclosure, and is not intended to limit the present disclosure. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.

Claims

1. A method of facial recognition, the method comprising:

and executing face recognition processing corresponding to the face recognition request for the target user.

2. The method of claim 1, wherein the captured images further include RGB images, the facial recognition intent information includes behavioral action information of the user,

3. The method according to claim 2, wherein the acquiring behavioral and action information of the user in the preset region based on the fused three-dimensional image comprises:

4. The method according to claim 3, wherein the limb detection and tracking of the fused three-dimensional image and the time-series classification processing of the fused three-dimensional image are performed to determine the behavior and action information of the user in the preset area, and the method comprises:

5. The method of claim 1, wherein the determining, based on the facial recognition intention information of the user, a target user who needs to perform facial recognition among the users in the preset area comprises:

6. The method of claim 5, further comprising:

7. The method of claim 1, wherein the facial recognition intention information includes behavior and action information of the user, and the determining a target user who needs to be subjected to facial recognition among the users in the preset area based on the facial recognition intention information of the user comprises:

8. A method of facial recognition, the method comprising:

9. A face recognition method applied to a blockchain system, the method comprising:

and sending the information of the target user to the facial recognition equipment so as to enable the facial recognition equipment to execute facial recognition processing corresponding to the facial recognition request on the target user.

10. The method according to claim 9, wherein the identifying, based on a first pre-deployed intelligent contract, facial recognition intention information of users in the preset area to obtain a target user that needs to perform facial recognition among the users in the preset area includes:

11. The method of claim 9, further comprising:

performing identity authentication on the target user based on a second intelligent contract and the face image, wherein the second intelligent contract is deployed in advance and is used for triggering identity authentication on a user initiating face recognition;

and sending the authentication result to the facial recognition equipment.

12. A facial recognition apparatus, the apparatus comprising:

the image acquisition model is used for acquiring an image in a current preset area, wherein the acquired image comprises a depth image;

the system comprises a wish information acquisition module, a user identification request acquisition module and a user identification module, wherein the wish information acquisition module is used for acquiring the facial identification wish information of a user in the preset area based on the acquired image under the condition of acquiring the facial identification request, and the facial identification wish information comprises one or more of behavior and action information, facial position information and facial posture information of the user;

the user determination module is used for determining a target user needing face recognition in the users in the preset area based on the face recognition intention information of the users;

and the facial recognition module is used for executing facial recognition processing corresponding to the facial recognition request on the target user.

13. A facial recognition apparatus, the apparatus comprising:

the image acquisition module is used for acquiring an image in a current preset area, wherein the acquired image comprises a depth image;

the facial recognition system comprises a intention information acquisition module, a face recognition request acquisition module and a face recognition processing module, wherein the intention information acquisition module is used for acquiring facial recognition intention information of a user in the preset area based on the acquired image under the condition of acquiring a facial recognition request, and the facial recognition intention information comprises one or more of behavior and action information, facial position information and facial posture information of the user;

the information providing module is used for providing the facial recognition intention information of the users in the preset area to a preset block chain system so that the block chain system can perform recognition processing on the facial recognition intention information of the users in the preset area through a pre-deployed intelligent contract to obtain target users needing facial recognition in the users in the preset area;

and the information receiving module is used for receiving the information of the target user sent by the block chain system and executing facial recognition processing corresponding to the facial recognition request on the target user.

14. A facial recognition apparatus, the apparatus comprising:

the system comprises an information receiving module, a face recognition device and a face recognition module, wherein the information receiving module is used for receiving face recognition intention information of a user in a preset area, the face recognition intention information of the user in the preset area is sent by the face recognition device, the face recognition intention information of the user in the preset area is obtained by the face recognition device through collecting an image in the current preset area, and under the condition that a face recognition request is obtained, the collected image comprises a depth image based on the information obtained by the collected image, and the face recognition intention information comprises one or more of lip language information, face position information and face posture information of the user in the preset area;

the system comprises a wish identification module, a first intelligent contract and a second intelligent contract, wherein the wish identification module is used for identifying the face identification wish information of users in the preset area based on a first intelligent contract which is deployed in advance to obtain target users needing face identification in the users in the preset area, and the first intelligent contract is used for triggering the identification of the face identification wish information of the users in the preset area;

and the information sending module is used for sending the information of the target user to the facial recognition equipment so as to enable the facial recognition equipment to execute facial recognition processing corresponding to the facial recognition request on the target user.

15. A facial recognition device, the facial recognition device comprising:

a processor; and

a memory arranged to store computer executable instructions that, when executed, cause the processor to:

16. A storage medium for storing computer-executable instructions, which when executed implement the following:

17. A facial recognition device, the facial recognition device comprising:

a processor; and

18. A storage medium for storing computer-executable instructions, which when executed implement the following:

19. A facial recognition device, the facial recognition device comprising:

a processor; and

receiving face recognition intention information of a user in a preset area, wherein the face recognition intention information of the user in the preset area is sent by a face recognition device, the face recognition intention information is obtained by the face recognition device through collecting an image in the current preset area, and under the condition that a face recognition request is obtained, the collected image comprises a depth image based on the collected image, and the face recognition intention information comprises one or more of lip language information, face position information and face posture information of the user in the preset area;

20. A storage medium for storing computer-executable instructions that when executed perform the following: