WO2022227562A1

WO2022227562A1 - Identity recognition method and apparatus, and electronic device, storage medium and computer program product

Info

Publication number: WO2022227562A1
Application number: PCT/CN2021/134598
Authority: WO
Inventors: 孙贺然; 王磊; 李佳宁
Original assignee: 北京市商汤科技开发有限公司
Priority date: 2021-04-27
Filing date: 2021-11-30
Publication date: 2022-11-03
Also published as: TW202242715A; CN113128437A

Abstract

The present disclosure relates to an identity recognition method and apparatus, and an electronic device, a storage medium and a computer program product. The method comprises: acquiring image information collected by a target image collection device; determining, from among a plurality of preset personnel libraries, a target personnel library associated with the target image collection device; and performing matching on the collected image information on the basis of the target personnel library, and determining identity information corresponding to the collected image information.

Description

Identification method and device, electronic device, storage medium and computer program product

CROSS-REFERENCE TO RELATED APPLICATIONS

The embodiments of the present disclosure are based on a Chinese patent application with an application number of 202110460309.9, an application date of April 27, 2021, and an application title of "Identity Recognition Method and Device, Electronic Device and Storage Medium", and requires the priority of the Chinese patent application The entire content of this Chinese patent application is incorporated herein by reference.

technical field

The present disclosure relates to, but is not limited to, the field of computer technology, and in particular, to an identity recognition method and apparatus, electronic equipment, storage medium, and computer program product.

Background technique

Face detection, face recognition and face segmentation are of great significance in the field of images. Through the detection and recognition of faces in images, it can provide strong support in applications such as face beautification and identity recognition.

SUMMARY OF THE INVENTION

Embodiments of the present disclosure provide at least an identity identification method and apparatus, an electronic device, a storage medium, and a computer program product.

An embodiment of the present disclosure provides an identification method, including: acquiring image information collected by a target image capture device; determining a target personnel database associated with the target image capture device from a plurality of preset personnel databases; The target personnel database is used, and the collected image information is matched to determine the identity information corresponding to the collected image information.

In some implementations, there is a first correspondence between the personnel database and the geographic area, and the determining a target personnel database associated with the target image acquisition device from a plurality of preset personnel databases includes: obtaining the target personnel database. deployment information of the target image acquisition device, and determine the target geographic area corresponding to the target image acquisition device based on the deployment information; based on the first correspondence, determine the target geographic area from the multiple personnel databases The corresponding target personnel library.

In some implementations, there is a second correspondence between the personnel database and the identification information of the image capture device, and the target personnel database associated with the target image capture device is determined from a plurality of preset personnel databases, including : Acquire the identification information of the target image acquisition device, and determine the target personnel database corresponding to the identification information of the target image acquisition device from the plurality of personnel libraries based on the second correspondence.

In some embodiments, the target person library includes a plurality of reference image information, the collected image information includes person images, and the collected image information is matched based on the target person library to determine the The identity information corresponding to the collected image information includes: performing feature extraction on the person image to obtain a first face feature; searching for a first reference matching the first face feature in the target person database image information, and determine the identity information corresponding to the first reference image information as the identity information corresponding to the collected image information.

In some embodiments, the target person library includes a plurality of reference image information, the collected image information includes a second face feature, and the collected image information is matched based on the target person library , determining the identity information corresponding to the collected image information, including: searching the target person database for second reference image information that matches the second face feature, and comparing the second reference image information with the second reference image information The corresponding identity information is determined to be the identity information corresponding to the collected image information.

In some embodiments, the method further includes: creating a personnel database according to the personnel information and the deployment information and/or identification information of the image capture device, the personnel information including the correspondence between the reference image information of the personnel and the identity information relation.

In some embodiments, the creating a personnel database according to the personnel information and the deployment information and/or identification information of the image capture device includes: acquiring the personnel information; At least part of the personnel information in the personnel information is associated with the identification information of one or more image capture devices, or is associated with the geographical area indicated by the deployment information of one or more image capture devices; based on the same identification information or the same geographical area Associate the personnel information and create a personnel library.

In some embodiments, matching the collected image information based on the target person database to determine the identity information corresponding to the collected image information includes: including a plurality of categories in the target person database In the case of a library, according to the order of the priority of the plurality of classification libraries from high to low, look for whether there is reference image information matching the collected image information one by one, until the collected image information is obtained. The reference image information whose information is matched; the identity information corresponding to the reference image information is determined as the identity information corresponding to the collected image information.

In some embodiments, the classification library includes one or more of a focused object library, a common object library, and an abnormal object library.

In some embodiments, in an educational scenario, the focused object library includes at least one of a teacher library and a student library; or, in a retail scene, the focused object library includes a member library and an employee library. at least one.

An embodiment of the present disclosure provides an identity recognition device, including: an acquisition part configured to acquire image information collected by a target image acquisition device; a determination part for determining from a plurality of preset personnel libraries the relationship with the target A target person database associated with the image acquisition device; a matching part is used to match the collected image information based on the target person database, and determine the identity information corresponding to the collected image information.

In some implementations, there is a first correspondence between the personnel database and the geographic area, and the determining part includes: a first determining sub-part, configured to acquire the deployment information of the target image acquisition device, and based on the The deployment information determines a target geographic area corresponding to the target image acquisition device; a second determination sub-section is configured to determine, from the plurality of personnel databases, all of the target geographic areas corresponding to the target geographic area based on the first correspondence. Describe the target personnel pool.

In some implementations, there is a second correspondence between the personnel database and the identification information of the image capturing device, and the determining part includes: a third determining sub-part configured to acquire the identification information of the target image capturing device, And based on the second correspondence, the target personnel database corresponding to the identification information of the target image acquisition device is determined from the plurality of personnel databases.

In some implementations, the target person library includes a plurality of reference image information, the collected image information includes a person image, and the matching part includes: a feature extraction sub-section configured to perform an analysis on the person image. Feature extraction, to obtain a first face feature; a first search subsection, configured to search for the first reference image information matching the first face feature in the target person database, and to match the first reference image information with the first face feature. The identity information corresponding to the reference image information is determined as the identity information corresponding to the collected image information.

In some embodiments, the target person database includes a plurality of reference image information, the collected image information includes a second face feature, and the matching part includes: a second search sub-part, configured to Find the second reference image information matching the second face feature in the target person database, and determine the identity information corresponding to the second reference image information as the identity information corresponding to the collected image information .

In some embodiments, the apparatus further includes: a creation part configured to create a personnel database according to the personnel information, and the deployment information and/or identification information of the image capture device, the personnel information including the reference image information of the personnel and the Correspondence between identity information.

In some implementations, the creation part includes: an acquisition subsection, configured to acquire the personnel information; and a configuration subsection, configured to, in response to a configuration operation on the personnel information, convert at least the personnel information into Part of the personnel information is associated with the identification information of one or more image capture devices, or is associated with the geographic area indicated by the deployment information of one or more image capture devices; subsections are created, configured to be based on the same identification information or the same Personnel information associated with geographic areas to create a personnel library.

In some embodiments, the matching part includes: in the case that the target personnel database includes multiple classification databases, according to the order of the priority of the multiple classification databases from high to low, searching whether the There is reference image information matching the collected image information, until the reference image information matching the collected image information is obtained; the identity information corresponding to the reference image information is determined as the collected image information The identity information corresponding to the information.

An embodiment of the present disclosure provides an electronic device, including: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute any of the above method of identification.

An embodiment of the present disclosure provides a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, any one of the above-mentioned methods for identity recognition is implemented.

Embodiments of the present disclosure further provide a computer program product, including computer-readable code, when the computer-readable code is executed on the device, the processor in the device executes the method for implementing any one of the above-mentioned identification.

In the embodiment of the present disclosure, the target personnel database associated with the image acquisition device can be determined from a plurality of personnel databases, the image information is matched based on the target personnel database to determine the identity information, and the image information matching based on the personnel database can be narrowed down It can reduce the computational complexity and effectively improve the real-time and efficiency of identity recognition.

It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings.

Description of drawings

In order to explain the technical solutions of the embodiments of the present disclosure more clearly, the following briefly introduces the accompanying drawings required in the embodiments, which are incorporated into the specification and constitute a part of the specification. Embodiments consistent with the present disclosure are shown and used together with the description to explain the technical solutions of the present disclosure. It should be understood that the following drawings only show some embodiments of the present disclosure, and therefore should not be regarded as limiting the scope. Other related figures are obtained from these figures.

FIG. 1 is a schematic flowchart of an implementation of an identity recognition method provided by an embodiment of the present disclosure.

FIG. 2a is a schematic diagram of a configuration interface of personnel information provided by an embodiment of the present disclosure.

FIG. 2b is a schematic diagram of a configuration interface of personnel information provided by an embodiment of the present disclosure.

FIG. 3 is a schematic diagram of an identity recognition apparatus provided by an embodiment of the present disclosure.

FIG. 4 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.

FIG. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only These are some, but not all, embodiments of the present disclosure. The components of the disclosed embodiments generally described and illustrated herein may be arranged and designed in a variety of different configurations. Thus, the following detailed description of the embodiments of the present disclosure is not intended to limit the scope of the disclosure as claimed, but is merely representative of selected embodiments of the disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present disclosure.

In addition, the terms "first", "second" and the like in the description and claims in the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It is to be understood that data so used may be interchanged under appropriate circumstances so that the embodiments described herein can be practiced in sequences other than those illustrated or described herein.

The term "and/or" in this paper is an association relationship that describes an associated object, indicating that there can be three kinds of relationships, for example, A and/or B, which can mean that A exists alone, A and B exist at the same time, and B exists alone these three situations. In addition, the term "at least one" herein refers to any combination of any one of the plurality or at least two of the plurality, for example, including at least one of A, B, and C, and may mean including from A, B, and C. Any one or more elements selected from the set of B and C.

In addition, in order to better illustrate the present disclosure, numerous specific details are set forth in the following detailed description. It will be understood by those skilled in the art that the present disclosure may be practiced without certain specific details. In some instances, methods, means, components and circuits well known to those skilled in the art have not been described in detail so as not to obscure the subject matter of the present disclosure.

Face recognition technology is a kind of biometric recognition technology. It combines image processing technology, computer graphics, pattern recognition and other research fields, and is an effective means of identity recognition. The identity recognition method based on face recognition usually builds a personnel database in advance. When performing identity recognition, the collected face image of the person to be verified is compared with the face image in the personnel database to determine the identity of the person to be verified. Identity Information.

Among them, the identification method based on face recognition can be applied to scenes such as stations, shopping malls, schools, etc. In related technologies, a personnel database is usually set for a scene, for example, a personnel database corresponding to a school, a shopping mall corresponding A personnel database, such that when the data volume of identity information stored in the personnel database is large, the calculation amount of face comparison will be large, which will reduce the real-time performance and efficiency of identity recognition.

The defects existing in the above solutions are the results obtained by the inventor after practice and careful research. Therefore, the discovery process of the above problems and the solutions proposed in the following embodiments of the present disclosure for the above problems should be Contributions made by the inventors to the present disclosure during the course of this disclosure.

Based on the above research, the embodiments of the present disclosure provide an identity recognition method and device, electronic equipment, storage medium and computer program product, which associate a personnel database with an image acquisition device in a geographic area or a geographic area, and realize presets for the same scene. Multiple personnel databases, and then in the process of identification, the target personnel database can be determined from the multiple personnel databases according to the corresponding relationship between the multiple personnel databases and geographic areas or image acquisition devices, and then based on the target personnel database Realize identity recognition, thereby narrowing the scope of image information matching based on the personnel database, reducing the amount of computation, and effectively improving the real-time and efficiency of identity recognition.

In order to facilitate the understanding of this embodiment, an identification method disclosed in this embodiment of the present disclosure is first introduced in detail. The identification method provided by this embodiment of the present disclosure may be executed by an electronic device such as a terminal device or a server, and the terminal device may be User Equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, Personal Digital Assistant (PDA), handheld device, computing device, vehicle-mounted device, wearable device, etc. The methods may be implemented by a processor invoking computer readable instructions stored in a memory. Alternatively, the method may be performed by a cloud server or an edge node.

During implementation, it may be set whether the identity identification method is performed on a cloud server, a terminal device or an edge node according to actual requirements, which is not limited in this embodiment of the present disclosure. It should be understood that a plurality of preset personnel libraries may be stored in the electronic device executing the identification method, so as to determine the target personnel library and match the collected image information based on the target personnel library.

FIG. 1 is a schematic flowchart of an identity recognition method provided by an embodiment of the present disclosure. As shown in FIG. 1 , the identity recognition method includes:

In step S11, image information collected by the target image collection device is obtained;

In step S12, a target personnel library associated with the target image acquisition device is determined from a plurality of preset personnel libraries;

In step S13, based on the target person database, the collected image information is matched to determine the identity information corresponding to the collected image information.

It should be understood that a user may deploy one or more image acquisition devices in a geographic area, where the geographic area may be a school area, a shopping mall area, a store area, a station area, etc., where statistics on the flow of people are usually performed; image acquisition The devices may include: common/intelligent inter-process communication (Inter-Process Communication, IPC) devices, smart module (network version) devices, service modules/service SDK devices, etc., which are not limited in this embodiment of the present disclosure.

Wherein, the image acquisition equipment in the geographical area can be connected with the above electronic equipment, so as to send the collected image information to the electronic equipment, and realize the above identification method. It should be understood that there is a corresponding relationship between image capturing devices and geographic regions, and the target image capturing device may be one or more image capturing devices in the geographic region.

In some embodiments, the collected image information may include: a person image collected by a target image collection device, and/or a face feature of the person image.

Wherein, in the case where the collected image information is a face feature of a person image, the image collection device can perform face feature extraction on the collected person image, and send the extracted face feature to the above electronic device. In this way, the privacy of the objects in the collected image information can be protected, and the probability of illegally obtaining images of persons can be reduced.

During implementation, a facial feature extraction network may be deployed in the image acquisition device, so as to perform facial feature extraction on the collected personnel images through the facial feature extraction network. The embodiments of the present disclosure do not limit the network structure, network type, and training method of the facial feature extraction network.

At the same time, considering that some image acquisition devices may not have computing and storage capabilities, the image acquisition device can also send the collected personnel images to the above-mentioned electronic equipment, and perform facial feature extraction on the collected personnel images in the electronic equipment. .

In some embodiments, the collected image information may also carry the identification information of the image collection device, so that the identification information can be used to distinguish which image collection device collected the collected image information, and it is also convenient to determine which image collection device is the same as the image collection device. The associated target person library is used to match the collected image information based on the target person library. Wherein, the identification information may be represented in the form of a character string, and may also be represented in other forms, which are not limited in this embodiment of the present disclosure.

In some embodiments, in step S12, the preset multiple personnel libraries may be personnel libraries that are pre-built according to actual needs. The number and construction method of the personnel libraries are not limited in this embodiment of the present disclosure. For example, it can be Use the existing staff library as the construction basis, or rebuild the staff library, etc. The personnel database may store at least the reference image information of the person and the corresponding identity information, that is, the corresponding relationship between the reference image information and the identity information of the person is stored.

The reference image information may include a face image and/or a face feature; the identity information may be, for example, a customer or an employee, a general customer or a member customer, etc. The content of the identity information is not limited in the embodiments of the present disclosure.

In some implementations, multiple personnel libraries may be pre-associated with the image acquisition device, or multiple personnel libraries may be associated with the geographic area, ie, multiple personnel libraries exist between the image acquisition equipment and/or the geographic area Correspondence. In this way, in step S12, the target personnel library associated with the target image acquisition device can be determined from the preset multiple personnel libraries according to the corresponding relationship.

In some embodiments, in step S13, based on the target person database, the collected image information is matched to determine the identity information corresponding to the collected image information, which may include: determining the collected image information and the reference in the target person database The similarity between image information; according to the similarity, the reference image information matching the collected image information is determined from the target personnel database; the identity information corresponding to the reference image information matching the collected image information is determined as the collected image information. The identity information corresponding to the image information.

During implementation, the similarity between the collected image information and the reference image information may be determined according to the distance between the collected image information and the reference image information, for example, it may be determined according to the face features in the collected image information and the reference image The distance between the facial features in the information determines the similarity between the collected image information and the reference image information.

The distance may include, but is not limited to, cosine distance, Euclidean distance, Mahalanobis distance, and the like. It should be understood that the distance and the similarity may be negatively correlated, that is, the closer the distance, the higher the similarity between the collected image information and the reference image information in the target personnel library; the lower the similarity.

In some embodiments, determining the reference image information matching the collected image information from the target person database according to the similarity may include: determining the reference image information in the target person database whose similarity exceeds a similarity threshold as the same as the collected image information. The image information matches the reference image information. Among them, the size of the similarity threshold can be set according to the extraction accuracy of facial features, the calculation accuracy of similarity, the processing capability or resource occupancy of the equipment used to achieve feature extraction and similarity calculation, etc. For example, it can be set as 0.86, which is not limited in this embodiment of the present disclosure.

In the embodiment of the present disclosure, the target personnel database associated with the image acquisition device can be determined from a plurality of personnel libraries, the collected image information is matched based on the target personnel database to determine the identity information, and the collection based on the personnel database can be narrowed down. The matching range of image information can be reduced, and the amount of calculation can be reduced, and the real-time performance and efficiency of identity recognition can be effectively improved.

As described above, there may be correspondences between multiple person pools and geographic regions. In some embodiments, there is a first correspondence between the personnel database and the geographical area. In step S12, a target personnel database associated with the target image acquisition device is determined from a plurality of preset personnel databases, including:

The deployment information of the target image acquisition device is acquired, and the target geographic area corresponding to the target image acquisition device is determined based on the deployment information; based on the first correspondence, the target personnel database corresponding to the target geographic area is determined from a plurality of personnel databases.

As mentioned above, one or more image acquisition devices may be deployed within a geographic area. The geographic area in which the target image acquisition device is located may be the target geographic area.

Wherein, the deployment information may include information such as the geographic location of the target image acquisition device, the identification of the deployment area, and the like. The geographic location may be global positioning system (Global Positioning System, GPS) positioning, and the deployment area identifier represents the geographic area where the image acquisition device is located. It should be understood that, the target geographic area corresponding to the target image capturing device may be determined according to the above at least one kind of deployment information.

As described above, the first correspondence may further include the correspondence between the geographic area and the identification information of the image capturing device, and based on this, the target geographic area may also be determined according to the identification information of the target image capturing device.

In some embodiments, the first correspondence between the personnel database and the geographic area can be preset according to actual requirements. For example, the geographic area can be set to correspond to one or more personnel databases. For example, the personnel database a and the shop A can be set. Correspondingly, the personnel library b corresponds to the shop B, and the personnel libraries c1 and c2 correspond to the shop C respectively, which is not limited in the embodiment of the present disclosure. Based on this, the target person database corresponding to the target geographic area may include one or more.

In the embodiment of the present disclosure, the target personnel database can be determined based on the first correspondence between the geographical area and the personnel database, and the image information collected in the same geographical area can be effectively matched with the corresponding target personnel database. match the reference image information.

Due to the different shooting coverage areas of each image acquisition device in a geographical area, for example, for a school area, each class can be equipped with an image acquisition device, and each class can correspond to its own personnel database, then the personnel database of the class can be set to match the The image acquisition equipment in the class is associated, so that the target personnel database can be determined for matching according to the image acquisition equipment associated with the class, thereby further narrowing the matching range of the collected image information, reducing the amount of calculation, and effectively improving the identity. Real-time recognition and efficiency.

As described above, there may be a correspondence between multiple personnel libraries and image capture devices. In some embodiments, a second correspondence relationship between the personnel database and the identification information of the image capture device may also be set. In step S12, the target associated with the target image capture device is determined from a plurality of preset personnel databases. Personnel library, including:

The identification information of the target image capturing device is acquired, and based on the second correspondence, the target personnel database corresponding to the identification information of the target image capturing device is determined from the plurality of personnel databases.

As described above, the captured image information may carry identification information of the target image device, and the identification information may identify different image capture devices, wherein the identification information of the target image device may be obtained from the captured image information.

It should be understood that the second correspondence between the personnel database and the identification information of the image acquisition device reflects the correspondence between the personnel database and the image acquisition device. The second correspondence between the personnel database and the identification information of the image acquisition device may be set according to actual requirements, and the target image acquisition device may correspond to one or more target personnel databases.

In the embodiment of the present disclosure, a target person database with a smaller amount of data corresponding to the target image acquisition device can be determined, the matching range of image information collected based on the target person database can be narrowed, the amount of computation can be reduced, and the Real-time and efficient identification.

When implemented, the collected image information may include images of persons collected by the image collection device. In some embodiments, the target person database includes a plurality of reference image information, and the collected image information includes person images. In step S13, the collected image information is matched based on the target person database, and the collected image information is determined to be the same as the collected image. The identity information corresponding to the information, including:

Perform feature extraction on the person image to obtain the first face feature;

Search for the first reference image information matching the first face feature in the target person database, and determine the identity information corresponding to the first reference image information as the identity information corresponding to the collected image information.

Wherein, the facial feature extraction may be performed on the person image through the above-mentioned facial feature extraction network. It can be understood that the person image may contain the facial features of at least one object. It should be understood that the facial feature extraction network is deployed in the above electronic device.

The reference image information in the target person database may include: face images and/or face features. In the case that the reference image information only includes face images, searching for the first reference image information matching the first face features in the target person database may include: extracting the face features of the face images in the target person database one by one, Then, it is matched with the first face feature to find out the first reference image information matching the first face feature.

In some embodiments, when the reference image information in the target person database includes facial features, a first reference image matching the first facial features can be found in the target person database according to the first facial features information. In this way, the real-time performance and efficiency of identity recognition can be improved.

During implementation, the reference image information matching the collected image information may be determined according to the similarity between the collected image information and the reference image information. Searching for the first reference image information matching the first face feature in the target person database may include: calculating the similarity between the face features in the target person database and the first face feature one by one, and set the similarity less than the similarity The facial features in the target person database with the degree threshold are used as the first reference image information matched with the first facial features.

Reference image information and corresponding identity information are stored in the personnel database. In the case where the first reference image information matching the first face feature is determined, the identity information corresponding to the first reference image information can be obtained, for example, whether the object is a member or an ordinary customer, so as to facilitate the identification of the information in the personnel database. Statistical analysis of personnel behavior.

In some embodiments, after determining the identity information corresponding to the collected image information, the behavior information of the object corresponding to the identity information can be recorded based on the identity information. For example, member 001 enters the store at a certain time, and leaves the store at a certain time. ; It can also count the number of times that ordinary customers 002 enter the store in a statistical period, etc.

In some embodiments, if there is no first reference image information matching the first face feature in the target person database, the identity information and Referring to the image information and recording the behavior information of the object, it is convenient to analyze the passenger flow situation in the geographical area, which is not limited in this embodiment of the present disclosure.

In the embodiment of the present disclosure, the identity information corresponding to the collected image information can be effectively determined according to the first face feature in the collected image information and the target person database.

During implementation, in order to protect the privacy of the object in the image information and reduce the probability of illegally obtaining the image of the person, the collected image information may also be the face feature of the image of the person. In some embodiments, the target person database includes a plurality of reference image information, and the collected image information includes a second face feature. In step S13, the collected image information is matched based on the target person database, Determining the identity information corresponding to the collected image information may include:

Search for the second reference image information matching the second face feature in the target person database, and determine the identity information corresponding to the second reference image information as the identity information corresponding to the collected image information.

As described above, the facial feature extraction network can be deployed in the image acquisition device, and the facial feature extraction of the acquired person images is performed in the image acquisition device. Based on this, the second face feature may be a face feature obtained by performing feature extraction on the collected image of the person executed in the image collection device.

Wherein, searching for the second reference image information matching the second facial feature in the target person database may be in the same manner as the above-mentioned searching for the first reference image information matching the first facial feature in the target person database, I won't go into details here.

Reference image information and corresponding identity information are stored in the personnel database. In the case where the second reference image information matching the second face feature is determined, the identity information corresponding to the second reference image information can be obtained, so as to facilitate the statistical analysis of the behavior of the personnel in the personnel database.

In the embodiment of the present disclosure, not only the privacy of the object in the image information can be protected, but also the identity information corresponding to the collected image information can be determined effectively according to the second face feature and the target person database.

In some embodiments, the method may further include: creating a personnel database according to the personnel information, and the deployment information and/or identification information of the image capture device, where the personnel information includes the relationship between the reference image information of the personnel and the identification information. Correspondence.

The reference image information of the person may include pre-collected person images and/or pre-extracted facial features in the person images. The correspondence between the reference image information and the identity information may include: the reference image information, and the identity information corresponding to the reference image information, and the identity information may include information such as personnel number and personnel identity.

The personnel number may be information that uniquely identifies the person, such as a mobile phone number, job number, and/or ID number; the personnel identity may be information set according to the application scenario of the personnel database to characterize the identity of the person, for example, for the store scene, Personnel identities may include members, employees, abnormal customers, normal customers, etc.; for school scenarios, personnel identities may include students, teachers, abnormal visitors, normal visitors, etc., which are not limited in this embodiment of the present disclosure.

In some embodiments, creating a personnel database according to the personnel information and the deployment information and/or identification information of the image capture device may include: establishing a personnel database according to the personnel information; setting the distance between the personnel database and the geographical area indicated by the deployment information and/or setting a second correspondence between the personnel database and the identification information of the image acquisition device, so as to create a personnel database.

In the embodiment of the present disclosure, a personnel database can be created according to the personnel information, and the deployment information and/or identification information of the image acquisition device, so as to improve the processing efficiency of the identification during the identification process.

In some embodiments, creating a personnel database according to personnel information and deployment information and/or identification information of the image capture device includes:

Obtaining personnel information; in response to a configuration operation on the personnel information, associating at least part of the personnel information in the personnel information with identification information of one or more image capture devices, or with the geographic location indicated by the deployment information of one or more image capture devices Areas are associated; based on the person information associated with the same identification information or the same geographic area, create a person pool.

Among them, the user can import the personnel information into the specified database to obtain the personnel information imported by the user. For example, the personnel information may be imported into a specified database by adding one by one or importing in batches, which is not limited in this embodiment of the present disclosure.

The configuration operation for personnel information can be realized through the configuration interface of the personnel database configuration system. Fig. 2a is a schematic diagram of a configuration interface 1000 of personnel information provided by an embodiment of the present disclosure. As shown in Fig. 2a, the user can select the one associated with the geographic area in the drop-down box 1001 of "person library" in Fig. 2a. Personnel library, such as "personnel library c1" in Fig. 2a; in the drop-down box 1002 at "geographical area" in Fig. 2a, select the area identifier of the geographic area associated with the personnel library, such as "area 0079" in the figure; and By clicking the "Finish" button 1003, the association between the personnel database and the geographic area is realized.

Fig. 2b is a schematic diagram of a configuration interface 2000 of personnel information provided by an embodiment of the present disclosure. As shown in Fig. 2b, a user can select to associate and bind with an image capture device through a drop-down box 2001 at "person library" in Fig. 2b and in the drop-down list 2002 at the "image acquisition device" in Fig. 2b, select the identification information of the image acquisition device to be associated with the personnel library by single or multiple selection The bound image acquisition device; and by clicking the "Finish" button 2003, the associated binding between the personnel library and the image acquisition device is realized. It should be understood that, the drop-down list may provide a selection control for single selection or multiple selection, and a slider control for sliding to view identification information, which is not limited to this embodiment of the present disclosure.

Associating at least part of the personnel information in the personnel information with the identification information of one or more image capture devices can be understood as being able to configure an image capture device to be associated with some or all of the personnel information imported by the user. Associating at least part of the personnel information with the geographic area indicated by the deployment information of one or more image capture devices can be understood as configuring a certain geographic area to be associated with some or all of the personnel information imported by the user. The geographic area indicated by the deployment information of the one or more image capturing devices, that is, the geographic area where the one or more image capturing devices are located.

It should be understood that the personnel information imported by the user may be stored in one or more designated databases, or stored in one or more designated tables in the same designated database. Associating at least part of the personnel information with the image capture device or with the geographic area may include: associating at least part of the designated database or at least part of the designated table with the image capture device or with the geographic area, so as to realize the identification based on the same identification information or the same geographic area. Areas are associated with personnel information to create a personnel library.

Wherein, the same identification information can be understood as the same image acquisition device, and the personnel information associated with the same identification information can be understood as personnel information in a specified database or specified table associated with the same image acquisition device. Personnel information associated with the same geographic area may be understood as personnel information in a specified database or specified table associated with the same geographic area.

For example, personnel information may include all students and all teachers of a school. Personnel information of all students of the school can be stored in one student database, and students of different classes can be stored in different class tables in the one student database. The number of teachers is smaller than the number of students, and all teachers can be stored in a grade table in a teacher database according to grade. Based on this, the image capture devices of each class can be configured to associate with the student database, and the image capture devices of each class can also be configured to be associated with the corresponding class table; and the image capture devices of each class under different grades can be configured to be associated with the teacher database. The image acquisition devices of each class under the same grade can be configured to associate with the corresponding grade table.

In the embodiment of the present disclosure, a personnel database can be created effectively according to the personnel information and the deployment information and/or identification information of the image capture device, so as to narrow down the identification and identification information according to the deployment information and/or identification information of the image capture device. When the matching range of image information collected based on the target personnel database can be reduced, the calculation amount can be reduced, and the real-time performance and processing efficiency based on identity recognition can be improved.

During implementation, the personnel library may include one or more classification libraries. In the case that the personnel library includes multiple category libraries, priorities are set for the multiple category libraries, and matching reference image information is searched according to the priorities. In some embodiments, in step S13, based on the target person database, the collected image information is matched to determine the identity information corresponding to the collected image information, which may include:

In the case that the target personnel database includes multiple classification databases, according to the priority of the multiple classification databases from high to low, look for whether there is any reference image information matching the collected image information one by one, until the collected image information is obtained. The reference image information that matches the image information of the image information; the identity information corresponding to the reference image information is determined as the identity information corresponding to the collected image information.

In some embodiments, the classification library includes one or more of a focused object library, a common object library, and an abnormal object library. In an educational scenario, the focused object library includes at least one of a teacher library and a student library; or, in a retail scene, the focused object library includes at least one of a member library and an employee library.

The common object library may refer to the whitelisted personnel library, for example, the common visitor library; the abnormal object library may refer to the blacklisted personnel library, for example, the abnormal visitor library.

It should be understood that the priority of the classification library may be set according to actual needs, and this embodiment of the present disclosure does not limit it. The higher the level; for another example, it can be set according to the degree of attention to the object category indicated by the classification library, that is, the priority of the classification library corresponding to the most concerned object category is set to the highest, and so on. For example, you can set the priority of member database, employee database, abnormal object database and common object database in descending order. Information matching the reference image information.

In order to facilitate the understanding of the above, according to the order of the priority of the multiple classification libraries from high to low, search whether there is reference image information matching the collected image information one by one, until the reference image information matching the collected image information is obtained. The process, taking the setting of the priority of the member library, employee library, abnormal object library and common object library in the retail scenario, decreases in order as an example, the description is as follows:

The member database can be searched first; when the member database finds the reference image information matching the collected image information, the personal identity of the visitor is determined as a member. At this point, the member's behavior information, such as the visit time, the number of visits, etc., can be recorded, and the search is ended. If the member database does not search for reference image information matching the collected image information, the search continues in the next classification database (employee database).

In the case that the reference image information matching the collected image information is found in the employee database, the personal identity of the visitor is determined to be an employee. At this point, the search can be ended. If the reference image information matching the collected image information is not searched in the employee database, the search continues in the next classification database (abnormal object database).

In the case that the reference image information matching the collected image information is found in the abnormal object library, the personal identity of the visitor is determined to be a blacklisted person. At this time, the behavior information of the blacklisted person can be recorded, such as the visit time, the number of visits, etc., and the search can be ended. Optionally, the alarm information of the visit of the blacklisted personnel may also be pushed to the end user. If the abnormal object library does not find the reference image information matching the collected image information, the search continues in the next classification library (ordinary object library).

In the case that the reference image information matching the collected image information is found in the common object library, the personal identity of the visitor is determined as a common visitor. At this point, the behavior information of the common visitor, such as the visit time, the number of visits, etc., can be recorded, and the search can be ended. In the case that the reference image information matching the collected image information is not found in the common object library, the face image and/or face feature information of the common visitor can be added to the common object library, for example, it can indicate that the store has got a new customer.

In the embodiment of the present disclosure, the classification library can be searched effectively and sequentially to perform image matching, which improves the processing efficiency of identity recognition.

In some embodiments, after obtaining the identity information and behavior information of the object, the method may further include: sending at least one of the identity information and behavior information of the object to the terminal.

In some embodiments, the terminal includes a personal computer PC, a smart phone, a wearable device or a tablet computer, or the like. The cloud server can push various information to the terminal through the network. When the cloud server determines the identity information of the object, it can push at least one of the identity information and behavior information of the object to the terminal. The behavior information may include one or more of visit time, visit times, and visit area.

In some embodiments, for retail scenarios, when the cloud server determines that the identity of the object is member z, the cloud server can push the behavior information of member z to the terminal, so that the user can check the visit status of member z and take corresponding countermeasures . For example, according to information such as the historical shopping records of member z, products and promotions can be pushed to member z.

In some embodiments, the creation process of the personnel library may include: establishing a personnel library; adding personnel to the personnel library; setting an execution subject of the identification method; associating the personnel library with a geographic area, or associating the personnel library with an image acquisition device .

In some embodiments, different types of personnel databases are established according to requirements. The types of personnel databases can be divided into six categories: member database, employee database, whitelist database, blacklist database, student database, and teacher database. Among them, teacher database and student database The library is mainly used in educational scenarios, and the membership library is mainly used in store scenarios.

In some embodiments, after the personnel database is created, personnel can be added to a specific personnel database, or a personnel management page can be entered to directly add personnel. Among them, adding personnel can be added individually or imported in batches. The import is divided into two parts, a picture of multiple people and an Excel table that includes all the personnel information. The associated item in the Excel table is the only corresponding item of the picture and each person in Excel, and cannot be repeated. Personnel number is a unique code to identify the person's identity, which can be mobile phone number, work number, ID number, etc.

In some embodiments, it is possible to set whether the identity recognition function compared with the static face database (person database) is performed in the cloud or in the edge node according to individual needs. The default is in the cloud. If the edge node or smart terminal is selected , then do it at a specific edge node or intelligent terminal.

In some implementations, the personnel database can be set to be associated with a specific branch (geographical area), the branch mainly refers to a certain store, a certain school, etc. If the personnel database is bound to a branch, the same branch Organizations use this one staff pool for comparison.

In some embodiments, if the number of personnel pools is too large, binding to a branch may lead to a long time for base pool comparison. For example, a scenario is a school, and different classes want to use different student pools, then this At the same time, the personnel library can be bound to a specific capture device (image acquisition device): including ordinary/intelligent IPC, intelligent module (network version), business module/business SDK. In this way, a personnel database with a small amount of data can be obtained for each device, which reduces the probability that the misrecognition rate is likely to increase due to too many personnel in the base library, and also reduces the time-consuming comparison.

In some embodiments, data will be reported normally after setting according to the above process. At this time, you can check the identities and records of different people compared with the personnel database, the number of people with special identities, and you can also export reports for further analysis.

According to the identity recognition method of the embodiment of the present disclosure, for a variety of different terminal types: intelligent modules, intelligent IPCs, service SDKs, and edge nodes, different image acquisition devices can be set to realize the offload processing of the personnel database and improve the performance. and accuracy. In addition, users can flexibly configure the personnel database to be bound to branches or specific devices according to their own needs, which is convenient and intuitive to use.

In the usage scenario of the personnel library in the related art, a large personnel library is set up for a merchant, so there is a problem that when the number of personnel library is very large, the processing time will be too long and the delay will be large. And because the personnel base is too large, the probability of the same person being identified as another person is also high. In order to solve this situation, the embodiment of the present disclosure divides the larger personnel library into different personnel small libraries and sends them to Binding image acquisition devices, different image acquisition devices can perform corresponding differentiated processing for different personnel libraries, which can effectively solve the above problems.

According to the identification method of the embodiment of the present disclosure, for the application scenario of the personnel library, the personnel library and the equipment are bound and managed in the case where the terminal device, edge node, and cloud service use the personnel library in multiple ways, so as to better realize the personnel library. distribution, improve the processing efficiency of personnel database comparison, and reduce the amount of calculation.

The identification method according to the embodiment of the present disclosure can be applied to products that require personnel database management, such as schools, commercial supermarkets, stores, and 4S stores.

The identity recognition method according to the embodiment of the present disclosure can support targeted distribution of personnel database on edge nodes or intelligent IPC devices, and reduce the time-consuming of loading or processing large databases.

It can be understood that the foregoing method embodiments mentioned in the present disclosure can be combined with each other to form a combined embodiment without violating the principle and logic. Those skilled in the art can understand that in the above method of the specific implementation, the writing order of each step does not mean a strict execution order but constitutes any limitation on the implementation process, and the specific execution order of each step should be based on its function and possible Internal logic is determined.

Based on the same inventive concept, the embodiments of the present disclosure also provide an identity recognition device corresponding to the identity recognition method. See implementation of the method.

FIG. 3 is a schematic diagram of an identification device provided by an embodiment of the present disclosure. As shown in FIG. 3 , the device includes:

an acquisition part 101, configured to acquire image information acquired by a target image acquisition device;

The determining part 102 is configured to determine a target personnel library associated with the target image acquisition device from a plurality of preset personnel libraries;

The matching part 103 is configured to match the collected image information based on the target person database, and determine the identity information corresponding to the collected image information.

In some embodiments, there is a first correspondence between the personnel database and the geographical area, and the determining part 102 includes: a first determining sub-part, configured to acquire the deployment information of the target image capturing device, and based on the The deployment information determines the target geographic area corresponding to the target image acquisition device; the second determination subsection is configured to determine, based on the first correspondence, the target geographic area corresponding to the target geographic area from the plurality of personnel databases The target personnel library.

In some embodiments, there is a second correspondence between the personnel database and the identification information of the image capturing device, and the determining part 102 is configured as: a third determining sub-part configured to obtain the identification information of the target image capturing device. identification information, and based on the second correspondence, the target personnel library corresponding to the identification information of the target image acquisition device is determined from the plurality of personnel libraries.

In some embodiments, the target person library includes a plurality of reference image information, the collected image information includes a person image, and the matching part 103 includes: a feature extraction sub-section configured to Perform feature extraction to obtain the first face feature; the first search subsection is configured to search for the first reference image information matching the first face feature in the target person database, and match the first reference image information with the first face feature. The identity information corresponding to the reference image information is determined as the identity information corresponding to the collected image information.

In some embodiments, the target person database includes a plurality of reference image information, the collected image information includes second face features, and the matching part 103 includes: a second search sub-part, configured to Searching for the second reference image information matching the second face feature in the target person database, and determining the identity information corresponding to the second reference image information as the identity corresponding to the collected image information information.

In some embodiments, the apparatus further includes: a creation part configured to create a personnel database according to the personnel information and the deployment information and/or identification information of the image capture device, the personnel information including the reference image information and the identity of the personnel Correspondence between information.

In some implementation manners, the matching part 103 includes: in the case that the target personnel database includes multiple classification databases, according to the order of the priority of the multiple classification databases from high to low, searching the classification databases one by one Whether there is reference image information matching the collected image information, until the reference image information matching the collected image information is obtained; determine the identity information corresponding to the reference image information as the collected image information. The identity information corresponding to the image information.

In the embodiment of the present disclosure, a target personnel library associated with the image acquisition device can be determined from a plurality of personnel libraries, and the collected image information is matched based on the target personnel library to determine the identity information, and the images based on the personnel library can be reduced. The scope of information matching can reduce the amount of calculation and effectively improve the real-time efficiency of identity recognition.

In some embodiments, the functions or included parts of the apparatus provided in the embodiments of the present disclosure may be used to execute the methods described in the above method embodiments, and reference may be made to the descriptions in the above method embodiments for specific implementation.

In the embodiments of the present disclosure and other embodiments, a "part" may be a part of a circuit, a part of a processor, a part of a program or software, etc., of course, a unit, a module or a non-modularity.

Embodiments of the present disclosure further provide a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the foregoing method is implemented. Computer-readable storage media can be volatile or non-volatile computer-readable storage media.

An embodiment of the present disclosure further provides an electronic device, including: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to invoke the instructions stored in the memory to execute the above method. The electronic device may be provided as a terminal, server or other form of device. FIG. 4 is a schematic structural diagram of an electronic device 400 according to an embodiment of the present disclosure. For example, electronic device 400 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, fitness device, personal digital assistant, etc. terminal.

4, electronic device 400 may include one or more of the following components: processing component 402, memory 404, power supply component 406, multimedia component 408, audio component 410, input/output (I/O) interface 412, sensor component 414 , and the communication component 416 .

The processing component 402 generally controls the overall operation of the electronic device 400, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 402 may include one or more processors 420 to execute instructions to perform all or some of the steps of the methods described above. Additionally, processing component 402 may include one or more sections that facilitate interaction between processing component 402 and other components. For example, processing component 402 may include a multimedia portion to facilitate interaction between multimedia component 408 and processing component 402.

Memory 404 is configured to store various types of data to support operation at electronic device 400 . Examples of such data include instructions for any application or method operating on electronic device 400, contact data, phonebook data, messages, pictures, videos, and the like. Memory 404 may be implemented by any type of volatile or non-volatile storage device or combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic or Optical Disk.

Power supply assembly 406 provides power to various components of electronic device 400 . Power supply components 406 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 400 .

Multimedia component 408 includes a screen that provides an output interface between the electronic device 400 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, swipe, and gestures on the touch panel. The touch sensor may not only sense the boundaries of a touch or swipe action, but also detect the duration and pressure associated with the touch or swipe action. In some embodiments, multimedia component 408 includes a front-facing camera and/or a rear-facing camera. When the electronic device 400 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each of the front and rear cameras can be a fixed optical lens system or have focal length and optical zoom capability.

Audio component 410 is configured to output and/or input audio signals. For example, audio component 410 includes a microphone (MIC) that is configured to receive external audio signals when electronic device 400 is in operating modes, such as calling mode, recording mode, and voice recognition mode. The received audio signal may be further stored in memory 404 or transmitted via communication component 416 . In some embodiments, audio component 410 also includes a speaker for outputting audio signals.

The I/O interface 412 provides an interface between the processing component 402 and a peripheral interface module, which may be a keyboard, a click wheel, a button, or the like. These buttons may include, but are not limited to: home button, volume buttons, start button, and lock button.

Sensor assembly 414 includes one or more sensors for providing electronic device 400 with various aspects of status assessment. For example, the sensor assembly 414 can detect the open/closed state of the electronic device 400, the relative positioning of the components, such as the display and the keypad of the electronic device 400, and the sensor assembly 414 can also detect the electronic device 400 or one of the electronic devices 400. Changes in the positions of components, presence or absence of user contact with the electronic device 400 , orientation or acceleration/deceleration of the electronic device 400 and changes in the temperature of the electronic device 400 . Sensor assembly 414 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact. Sensor assembly 414 may also include a light sensor, such as a complementary metal oxide semiconductor (CMOS) or charge coupled device (CCD) image sensor, for use in imaging applications. In some embodiments, the sensor assembly 414 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

Communication component 416 is configured to facilitate wired or wireless communication between electronic device 400 and other devices. The electronic device 400 can access a wireless network based on communication standards, such as wireless network (WiFi), second generation mobile communication technology (2G), third generation mobile communication technology (3G), long term evolution technology (Long Term Evolution, LTE) Or fifth generation mobile communication technology (5G), or a combination of them. In one exemplary embodiment, the communication component 416 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 416 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

In an exemplary embodiment, electronic device 400 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable A programmed gate array (FPGA), controller, microcontroller, microprocessor or other electronic component implementation is used to perform the above method.

In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 404 comprising computer program instructions executable by the processor 420 of the electronic device 400 to perform the above method.

FIG. 5 is a schematic structural diagram of an electronic device 500 according to an embodiment of the present disclosure. For example, the electronic device 500 may be provided as a server. 5, an electronic device 500 includes a processing component 501, which further includes one or more processors, and a memory resource represented by memory 502 for storing instructions executable by the processing component 501, such as an application program. An application program stored in memory 502 may include one or more portions, each corresponding to a set of instructions. Furthermore, the processing component 501 is configured to execute instructions to perform the above-described method.

The electronic device 500 may also include a power supply assembly 503 configured to perform power management of the electronic device 500, a wired or wireless network interface 504 configured to connect the electronic device 500 to a network, and an input output (I/O) interface 505 . The electronic device 500 can operate based on an operating system stored in the memory 502, such as a Microsoft server operating system (Windows Server ^™ ), a graphical user interface based operating system (Mac OS X ^™ ) introduced by Apple, a multi-user multi-process computer operating system (Unix ^™ ), Free and Open Source Unix-like Operating System (Linux ^™ ), Open Source Unix-like Operating System (FreeBSD ^™ ) or the like.

In an exemplary embodiment, a non-volatile computer-readable storage medium, such as memory 502 comprising computer program instructions executable by the processing component 501 of the electronic device 500 to perform the above-described method is also provided.

Embodiments of the present disclosure also provide a computer program product, including computer-readable codes. When the computer-readable codes are run on a device, a processor in the device executes a method for implementing the identification method provided by any of the above embodiments. instruction.

An embodiment of the present disclosure further provides another computer program product for storing computer-readable instructions, which, when executed, cause the computer to perform the operations of the identification method provided by any of the foregoing embodiments.

Embodiments of the present disclosure may be apparatus, systems, methods and/or computer program products. The computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of the present disclosure.

A computer-readable storage medium may be a tangible device that can hold and store instructions for use by the instruction execution device. The computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of computer readable storage media include: portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM) or flash memory), static random access memory (SRAM), portable compact disk read only memory (CD-ROM), digital versatile disk (DVD), memory sticks, floppy disks, mechanically coded devices, such as printers with instructions stored thereon Hole cards or raised structures in grooves, and any suitable combination of the above. Computer-readable storage media, as used herein, are not to be construed as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (eg, light pulses through fiber optic cables), or through electrical wires transmitted electrical signals.

The computer readable program instructions described herein may be downloaded to various computing/processing devices from a computer readable storage medium, or to an external computer or external storage device over a network such as the Internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers. A network adapter card or network interface in each computing/processing device receives computer-readable program instructions from a network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing/processing device .

Computer program instructions for carrying out operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or instructions in one or more programming languages. Source or object code, written in any combination, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as the "C" language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server implement. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider through the Internet connect). In some embodiments, custom electronic circuits, such as programmable logic circuits, field programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), can be personalized by utilizing state information of computer readable program instructions. Computer readable program instructions are executed to implement various aspects of the present disclosure.

Aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer readable program instructions.

These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer or other programmable data processing apparatus to produce a machine that causes the instructions when executed by the processor of the computer or other programmable data processing apparatus , resulting in means for implementing the functions/acts specified in one or more blocks of the flowchart and/or block diagrams. These computer readable program instructions can also be stored in a computer readable storage medium, these instructions cause a computer, programmable data processing apparatus and/or other equipment to operate in a specific manner, so that the computer readable medium storing the instructions includes An article of manufacture comprising instructions for implementing various aspects of the functions/acts specified in one or more blocks of the flowchart and/or block diagrams.

Computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other equipment to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other equipment to produce a computer-implemented process , thereby causing instructions executing on a computer, other programmable data processing apparatus, or other device to implement the functions/acts specified in one or more blocks of the flowcharts and/or block diagrams.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more functions for implementing the specified logical function(s) executable instructions. In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented in dedicated hardware-based systems that perform the specified functions or actions , or can be implemented in a combination of dedicated hardware and computer instructions.

The computer program product can be specifically implemented by hardware, software or a combination thereof. In an optional embodiment, the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), etc. Wait.

Finally, it should be noted that the above-mentioned embodiments are only specific implementations of the present disclosure, and are used to illustrate the technical solutions of the present disclosure, but not to limit them. The protection scope of the present disclosure is not limited to this, although the aforementioned The embodiments describe the present disclosure in detail, and those skilled in the art should understand that: any person skilled in the art can still modify the technical solutions described in the foregoing embodiments within the technical scope disclosed by the present disclosure. Or can easily think of changes, or equivalently replace some of the technical features; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be covered in the present disclosure. within the scope of protection.

Industrial Applicability

Embodiments of the present disclosure provide an identity recognition method and device, an electronic device, a storage medium, and a computer program product, wherein the identity recognition method includes: acquiring image information collected by a target image acquisition device; A target person database associated with the target image acquisition device is determined; based on the target person database, the collected image information is matched to determine the identity information corresponding to the collected image information. The above solution can narrow the scope of image information matching based on the personnel database, reduce the amount of computation, and effectively improve the real-time performance and efficiency of identity recognition.

Claims

A method of identification comprising:

Obtain the image information collected by the target image collection device;

determining a target personnel library associated with the target image acquisition device from a plurality of preset personnel libraries;

Based on the target person database, the collected image information is matched to determine the identity information corresponding to the collected image information.
The method of claim 1, wherein there is a first correspondence between the personnel database and the geographic area,

Determining the target personnel library associated with the target image acquisition device from the preset multiple personnel libraries includes:

acquiring deployment information of the target image capture device, and determining a target geographic area corresponding to the target image capture device based on the deployment information;

Based on the first correspondence, the target personnel library corresponding to the target geographic area is determined from the plurality of personnel libraries.
The method according to claim 1 or 2, wherein there is a second correspondence between the personnel database and the identification information of the image acquisition device,

Determining the target personnel library associated with the target image acquisition device from the preset multiple personnel libraries includes:

The identification information of the target image capture device is acquired, and based on the second correspondence, the target personnel database corresponding to the identification information of the target image capture device is determined from the plurality of personnel databases.
The method according to any one of claims 1 to 3, wherein the target personnel library includes a plurality of reference image information, and the collected image information includes personnel images,

Matching the collected image information based on the target personnel database, and determining the identity information corresponding to the collected image information, including:

performing feature extraction on the person image to obtain a first face feature;

Search for the first reference image information matching the first face feature in the target person database, and determine the identity information corresponding to the first reference image information as corresponding to the collected image information Identity Information.
The method according to any one of claims 1 to 4, wherein the target person database includes a plurality of reference image information, and the collected image information includes a second face feature,

Matching the collected image information based on the target personnel database, and determining the identity information corresponding to the collected image information, including:

Search for the second reference image information matching the second face feature in the target person database, and determine the identity information corresponding to the second reference image information as corresponding to the collected image information Identity Information.
The method according to any one of claims 1 to 5, wherein the method further comprises:

According to the personnel information, and the deployment information and/or identification information of the image acquisition device, a personnel database is created, and the personnel information includes the correspondence between the reference image information of the personnel and the identity information.
The method according to claim 6, wherein, according to the personnel information, and the deployment information and/or identification information of the image capture device, creating a personnel database, comprising:

obtain information about said personnel;

In response to the configuration operation on the personnel information, associating at least part of the personnel information with the identification information of the one or more image capture devices, or with the geographic location indicated by the deployment information of the one or more image capture devices area to associate;

Create a person pool based on person information associated with the same identification information or the same geographic area.
The method according to any one of claims 1 to 7, wherein, based on the target person database, the collected image information is matched to determine the identity information corresponding to the collected image information, comprising: :

In the case that the target personnel database includes multiple classification databases, according to the order of the priority of the multiple classification databases from high to low, look for whether there is reference image information matching the collected image information one by one classification database , until the reference image information matching the collected image information is obtained;

The identity information corresponding to the reference image information is determined as the identity information corresponding to the collected image information.
The method of claim 8, wherein the classification library includes one or more of a focused object library, a common object library, and an abnormal object library.
The method according to claim 9, wherein, in an educational scenario, the focused object library includes at least one of a teacher library and a student library;

Or, in a retail scenario, the focused object library includes at least one of a member library and an employee library.
An identification device, comprising:

an acquisition part, configured to acquire image information acquired by the target image acquisition device;

a determining part, configured to determine a target personnel library associated with the target image acquisition device from a plurality of preset personnel libraries;

The matching part is configured to match the collected image information based on the target person database, and determine the identity information corresponding to the collected image information.
An electronic device, comprising: a processor and a memory for storing instructions executable by the processor; wherein the processor is configured to invoke the instructions stored in the memory to execute the instructions of any one of claims 1 to 10 method described.
A computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement the method of any one of claims 1 to 10.
A computer program product comprising computer readable code, when the computer readable code is run on a device, a processor in the device executes a method for implementing the method of any one of claims 1 to 10.