A face recognition method and device based on a high-definition camera and a medium

Abstract

The application discloses a face recognition method and device based on a high-definition camera and a medium, to solve the problem that the existing face recognition is uploaded to the cloud for processing and analysis by a camera to collect face pictures, which occupies a large network bandwidth, causes great pressure on cloud computing, and has poor real-time performance and data privacy. The method comprises the following steps: acquiring pictures in a monitoring range by a high-definition camera and scanning to determine whether a candidate region has a face; if the candidate region has a face, positioning key point coordinates of the face and recognizing face attribute features in the pictures; comparing the face attribute features with a plurality of face attribute features in a database monitoring list, respectively, and determining a plurality of similarities between the face attribute features and the plurality of face attribute features in the monitoring list; determining a plurality of similarities greater than a preset threshold value, and sorting the similarities in a descending order to determine that a face attribute feature with the highest similarity in the sorted column and a face attribute feature corresponding to the pictures belong to the same person, thereby completing face recognition.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of face recognition, and in particular to a face recognition method based on a high-definition camera, a device and a medium. BACKGROUND

[0002] Face recognition is a biometric technology that identifies the identity of a person based on the facial feature information of the person. When an image or a video stream containing a face is collected by a camera or a camera head, it is first determined whether a face exists in the image or the video stream. If a face exists, the position, size and position information of each major facial organ of the face are further given. Based on the information, the identity features contained in each face are further extracted, and the identity features are compared with known face features, so as to identify the identity of each face.

[0003] At present, the existing face recognition camera architecture is a single-processor architecture, that is, the business is realized, and the algorithm is also realized. Moreover, the camera is only responsible for snapshot, and the recognition function is run in the cloud. The single-processor solution has a high requirement for the performance of the processor, and the cost is relatively high. The camera is only responsible for collecting face pictures, and the recognition function needs to upload the pictures to the cloud for processing and analysis, which occupies more network bandwidth, increases the computing pressure of the cloud, and reduces the real-time performance and data privacy. SUMMARY

[0004] The embodiments of the present application provide a face recognition method based on a high-definition camera, a device and a medium, to solve the technical problem that the existing face recognition is to collect face pictures by a camera and upload the pictures to the cloud for processing and analysis, which occupies a large amount of network bandwidth, has a large computing pressure of the cloud, and has poor real-time performance and data privacy.

[0005] In one aspect, the embodiments of the present application provide a face recognition method based on a high-definition camera, comprising:

[0006] acquiring pictures in a monitoring range by a high-definition camera, and scanning the pictures to determine whether a face exists in a candidate region of the pictures;

[0007] if the face exists, positioning each key point coordinate of the face in the pictures, and identifying the facial attribute features of the face in the pictures according to each key point coordinate;

[0008] comparing the identified facial attribute features with a plurality of facial attribute features in a monitoring list of a database, and determining a plurality of similarities between the facial attribute features and the plurality of facial attribute features in the monitoring list, respectively;

[0009] The plurality of similarities greater than the preset threshold are determined, and the plurality of similarities are sorted in a descending order to determine that the face attribute feature with the highest similarity in the sorted list and the face attribute feature corresponding to the picture belong to the same person, thereby completing face recognition.

[0010] In an implementation manner of the present application, the picture in the monitoring range is acquired by the high-definition camera, and the picture is scanned to determine whether a face exists in a candidate region of the picture.

[0011] It is determined, based on a preset monitoring component, whether a monitoring target exists in the monitoring range of the high-definition camera, and in a case where it is monitored that the monitoring target exists in the monitoring range, a picture of the monitoring target in the monitoring range is acquired by the high-definition camera; the monitoring target is a human body.

[0012] The acquired pictures are preprocessed to delete abnormal pictures in the pictures; the abnormal pictures at least include a blurred picture or a partially photographed picture.

[0013] The preprocessed pictures are scanned respectively, and it is determined whether a face exists in a candidate region of each picture.

[0014] In an implementation manner of the present application, if the face exists, each key point coordinate of the face in the picture is located, and a face attribute feature of the face in the picture is identified according to the key point coordinates.

[0015] In a case where the face exists in the picture, each region in the picture is identified respectively, and each key point in the face of the picture is determined.

[0016] Each key point of the face in the picture is located, and each key point coordinate in the picture is determined.

[0017] According to the key point coordinates in the picture, a face attribute feature corresponding to the picture is determined respectively; the face attribute feature at least includes gender, age, posture and expression.

[0018] In an implementation manner of the present application, in a case where the face exists in the picture, each region in the picture is identified respectively.

[0019] In a case where the face exists in the picture, a specified operation instruction is sent to a user in the monitoring range by the high-definition camera, and a user operation corresponding to the user is acquired by the high-definition camera.

[0020] According to the user operation, it is determined whether the face in the picture is from an attack prosthesis, and in a case where it is determined that the face in the picture is from the user himself, each region in the picture is respectively identified; the attack prosthesis at least includes a user photo or a user video.

[0021] In an implementation manner of the present application, before the identified face attribute features are respectively compared with the face attribute features of a plurality of persons in a monitoring list in a database, the method further comprises:

[0022] A face coordinate frame corresponding to the face is determined, and a plurality of face sample pictures are obtained;

[0023] The face coordinate frame is respectively registered with the plurality of face sample pictures, and a corresponding registration result is obtained;

[0024] According to the registration result, a sequence of facial feature points corresponding to each face sample picture is respectively determined, and the sequences of facial feature points corresponding to the plurality of face sample pictures are stored in the database.

[0025] In an implementation manner of the present application, after the sequences of facial feature points corresponding to the plurality of face sample pictures are stored in the database, the method further comprises:

[0026] A plurality of monitoring targets corresponding to the high-definition camera are obtained at a preset time interval, and the plurality of monitoring targets are compared with the plurality of face sample pictures in the database;

[0027] A monitoring target that does not exist in the database is determined, and a face sample picture corresponding to the monitoring target that does not exist in the database is stored in the database;

[0028] A face sample picture that does not exist in the plurality of monitoring targets is determined, and a sequence of facial feature points corresponding to the face sample picture that does not exist in the plurality of monitoring targets in the database is deleted, so as to realize synchronization of the monitoring targets in the database.

[0029] In an implementation manner of the present application, the plurality of similarities greater than the preset threshold are determined, and the plurality of similarities are sorted in a descending order, so as to determine that the face attribute feature with the highest similarity in the sorted list and the face attribute feature corresponding to the picture belong to the same person, and face recognition is completed, and specifically comprising:

[0030] The plurality of similarities are respectively compared with a preset threshold, and a plurality of similarities greater than the preset threshold are determined;

[0031] The plurality of similarities are sorted in descending order, and the plurality of similarities greater than the preset threshold are sorted, and the face attribute feature corresponding to the face sample picture with the highest similarity in the plurality of similarities is determined from the sorted list.

[0032] The face attribute feature corresponding to the face sample picture with the highest similarity in the plurality of similarities is determined to belong to the same person as the face attribute feature corresponding to the picture, so as to complete face recognition in the monitoring range of the high-definition camera.

[0033] In an implementation manner of the present application, the identified face attribute feature is compared with a plurality of face attribute features in a monitoring list in a database, respectively, and a plurality of similarities between the face attribute feature and the plurality of face attribute features in the monitoring list are determined, specifically including:

[0034] The database is queried according to the face attribute feature corresponding to the picture, and the face attribute feature corresponding to the picture is compared with a plurality of face attribute features corresponding to a plurality of face sample pictures in a monitoring list in the database, respectively;

[0035] According to the comparison result, a plurality of similarities between the face attribute feature corresponding to the picture and a plurality of face attribute features corresponding to a plurality of face sample pictures in the monitoring list in the database are determined.

[0036] On the other hand, the present application also provides a face recognition device based on a high-definition camera, which comprises:

[0037] At least one processor;

[0038] and a memory in communication connection with the at least one processor;

[0039] Wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the face recognition method based on the high-definition camera as described above.

[0040] On the other hand, the present application also provides a non-volatile computer storage medium, which stores computer executable instructions, and the computer executable instructions are configured to:

[0041] The face recognition method based on the high-definition camera as described above.

[0042] The present application provides a face recognition method, device and medium based on a high-definition camera, which at least includes the following beneficial effects:

[0043] By embedding the god's eye intelligent algorithm in the high-definition camera, the high-definition camera can support face snapshot in complex environment, obtain pictures in the monitoring range, and determine whether the candidate region of the picture exists face; by positioning the coordinates of each key point of the face in the picture, the face attribute features in the picture can be identified according to the coordinates of each key point, and then the face attribute features in the picture can be compared with the face attribute features in the monitoring list of the database, a plurality of similarities are obtained to determine whether the user in the picture is the user in the monitoring list, so that the face attribute feature with the highest similarity can be found in the plurality of similarities greater than the preset threshold, so as to determine that the user in the picture and the face attribute feature with the highest similarity in the database belong to the same person, and the face recognition is completed. BRIEF DESCRIPTION OF DRAWINGS

[0044] The drawings described herein are used to provide further understanding of the present application, and form a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application, and do not constitute improper limitations on the present application. In the drawings:

[0045] Figure 1 A flowchart of a face recognition method based on a high-definition camera provided by an embodiment of the present application;

[0046] Figure 2 An internal structure diagram of a face recognition device based on a high-definition camera provided by an embodiment of the present application. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme of the present application will be described clearly and completely in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0048] The embodiment of the present application provides a face recognition method, device and medium based on a high-definition camera, by embedding a god's eye intelligent algorithm in the high-definition camera, so that the high-definition camera can support face snapshot in a complex environment, acquire pictures in a monitoring range, and determine whether a candidate region of the pictures exists a face; by positioning each key point coordinate of the face in the pictures, face attribute features in the pictures can be recognized according to the key point coordinates, and then the face attribute features in the pictures can be compared with face attribute features in a monitoring list of a database, a plurality of similarities are obtained, so as to determine whether the user in the pictures is a user in the monitoring list, so that the face attribute features with the highest similarity can be found in the plurality of similarities greater than a preset threshold, so that it is determined that the user in the pictures and the face attribute features with the highest similarity in the database belong to the same person, and face recognition is completed. The technical problem that the existing face recognition is uploaded to the cloud for processing and analysis by a camera, occupies a plurality of network bandwidths, has great cloud computing pressure, and has poor real-time performance and data privacy is solved.

[0049] The technical solutions provided by the embodiments of the present application are described in detail below with reference to the drawings.

[0050] Figure 1 A flowchart of a face recognition method based on a high-definition camera provided by the embodiment of the present application is shown in FIG. 1. Figure 1 As shown in FIG. 1, the face recognition method based on the high-definition camera provided by the embodiment of the present application comprises the following steps.

[0051] 101, acquiring pictures in a monitoring range by a high-definition camera, and scanning the pictures to determine whether a face exists in a candidate region of the pictures.

[0052] The high-definition camera in the present application is actually a special camera, and the face recognition speed is quite fast, only about 0.3 seconds. And because the latest face recognition algorithm is used, even if disguise is changed, it is also difficult to deceive the eyes of the high-definition camera. The high-definition camera in the present application has a database with storage function, as long as the face attribute features of some users with potential danger are input into the storage database, when the users with potential danger enter the area without authorization, they can be found out within 0.3 seconds, and at the same time, an alarm is sent to other security centers. In addition, only specific personnel are allowed to enter and exit some important areas such as control centers, at this time, all people whose face archives information are not stored in the system will trigger an alarm.

[0053] The high-definition camera is an intelligent video monitoring product for real-time tracking and alarm of key monitoring personnel, which is developed by combining face recognition algorithm and video monitoring technology based on the demand of control and monitoring. It is especially suitable for public places such as shopping malls, airports, checkpoints, railway stations, bus stations, wharfs and banks.

[0054] Specifically, the server can determine whether there is a monitoring target in the monitoring range of the high-definition camera based on the preset monitoring component, and in the case that the monitoring target is monitored in the monitoring range, the server acquires pictures of the monitoring target in the monitoring range through the high-definition camera. It should be noted that the monitoring target in the embodiment of the present application is a human body.

[0055] The server pre-processes the acquired pictures, and deletes abnormal pictures in the pictures. It should be noted that the abnormal pictures in the embodiment of the present application at least include blurred pictures or incomplete pictures. Then, the server scans the pre-processed pictures respectively, and determines whether there is a face in the candidate region of each picture.

[0056] 102、If there is a face, the coordinates of each key point of the face in the picture are located, and the facial attribute features of the face in the picture are identified according to the coordinates of each key point.

[0057] Specifically, the server identifies each region in the picture in the case that there is a face in the picture, determines each key point of the face in the picture, locates each key point of the face in the picture, and determines the coordinates of each key point in the picture. Then, the server can determine the facial attribute features corresponding to the picture according to the coordinates of each key point in the picture. It should be noted that the facial attribute features in the embodiment of the present application at least include gender, age, posture and expression.

[0058] In an embodiment of the present application, the server sends a specified operation instruction to the user in the monitoring range through the high-definition camera in the case that there is a face in the picture, acquires the user operation corresponding to the user through the high-definition camera, and determines whether the face in the picture is from an attack dummy according to the user operation, and identifies each region in the picture in the case that the face in the picture is from the user himself. It should be noted that the attack dummy in the embodiment of the present application at least includes a user photo or a user video.

[0059] 103、The identified facial attribute features are compared with the facial attribute features of several persons in the monitoring list of the database respectively, and several similarities between the facial attribute features and the facial attribute features of several persons in the monitoring list are determined.

[0060] Specifically, the server queries the database according to the face attribute feature corresponding to the picture, and compares the face attribute feature corresponding to the picture with a plurality of face attribute features corresponding to a plurality of face sample pictures in the monitoring list of the database, so as to determine a plurality of similarities between the face attribute feature corresponding to the picture and the plurality of face attribute features corresponding to the plurality of face sample pictures according to the comparison results.

[0061] In an embodiment of the present application, the server determines the face coordinate frame corresponding to the face before comparing the identified face attribute feature with a plurality of face attribute features in the monitoring list of the database, obtains a plurality of face sample pictures, then respectively registers the face coordinate frame with the plurality of face sample pictures, and obtains corresponding registration results, and the server respectively determines a sequence of facial feature points corresponding to each face sample picture according to the registration results, and stores the sequences of facial feature points corresponding to the plurality of face sample pictures in the database.

[0062] In an embodiment of the present application, the server stores the sequences of facial feature points corresponding to the plurality of face sample pictures in the database, and then acquires a plurality of monitoring targets corresponding to the high-definition camera at a preset time interval, and compares the plurality of monitoring targets with the plurality of face sample pictures in the database, so that the server can determine a monitoring target that does not exist in the database, and store a face sample picture corresponding to the monitoring target that does not exist in the database in the database, and the server can also determine a face sample picture that does not exist in the plurality of monitoring targets, and delete the facial feature points corresponding to the face sample picture that does not exist in the plurality of monitoring targets in the database, thereby realizing synchronization of the monitoring targets in the database.

[0063] 104、Determine a plurality of similarities greater than a preset threshold, and sort the plurality of similarities in descending order to determine that the face attribute feature with the highest similarity in the sorted list belongs to the same person as the face attribute feature corresponding to the picture, and complete face recognition.

[0064] Specifically, the server compares a plurality of similarities with a preset threshold, and determines a plurality of similarities greater than the preset threshold, then sorts the plurality of similarities greater than the preset threshold in descending order, and determines the face attribute feature corresponding to the face sample picture with the highest similarity in the plurality of similarities from the sorted list, so that the server can determine that the face attribute feature corresponding to the face sample picture with the highest similarity in the plurality of similarities belongs to the same person as the face attribute feature corresponding to the picture, to complete face recognition in the monitoring range of the high-definition camera.

[0065] The above is a method embodiment of the present application. Based on the same inventive concept, the present application embodiment also provides a high-definition camera-based face recognition device, the structure of which is shown in Figure 2 .

[0066] Figure 2 An internal structure diagram of a high-definition camera-based face recognition device provided by the present application embodiment is shown in Figure 2 . The device includes:

[0067] at least one processor;

[0068] and a memory in communication connection with the at least one processor;

[0069] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0070] acquire pictures within a monitoring range through a high-definition camera, and scan the pictures to determine whether there is a face in a candidate region of the pictures;

[0071] if there is a face, locate coordinates of each key point of the face in the pictures, and identify face attribute features of the face in the pictures according to the coordinates of each key point;

[0072] compare the identified face attribute features with several face attribute features in a monitoring list of a database respectively, and determine several similarities between the face attribute features and the several face attribute features in the monitoring list respectively;

[0073] determine multiple similarities greater than a preset threshold, and sort the multiple similarities in a descending order to determine that a face attribute feature with the highest similarity in the sorted list and a face attribute feature corresponding to the pictures belong to the same person, thereby completing face recognition.

[0074] The present application embodiment also provides a non-volatile computer storage medium, which stores computer executable instructions, and the computer executable instructions are set to:

[0075] acquire pictures within a monitoring range through a high-definition camera, and scan the pictures to determine whether there is a face in a candidate region of the pictures;

[0076] if there is a face, locate coordinates of each key point of the face in the pictures, and identify face attribute features of the face in the pictures according to the coordinates of each key point;

[0077] compare the identified face attribute features with several face attribute features in a monitoring list of a database respectively, and determine several similarities between the face attribute features and the several face attribute features in the monitoring list respectively;

[0078] The plurality of similarities greater than the preset threshold are determined, and the plurality of similarities are sorted in a descending order to determine that the face attribute feature with the highest similarity in the sorted list and the face attribute feature corresponding to the picture belong to the same person, and face recognition is completed.

[0079] Each of the embodiments in the present application is described in a progressive manner, and the same or similar parts of each of the embodiments can be referred to each other. Each of the embodiments mainly explains the difference from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the related parts can be referred to the part of the method embodiments.

[0080] The device and medium provided by the embodiments of the present application are one-to-one corresponding to the method, and therefore, the device and medium also have the similar beneficial technical effects as the method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the device and medium will not be described here.

[0081] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0082] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device implemented in the flowcharts and / or block diagrams. Figure 1 The function of one flow or multiple flows and / or blocks Figure 1 The device for implementing the function of one block or multiple blocks.

[0083] These computer program instructions can also be stored in a computer readable storage medium capable of guiding the computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable storage medium produce a product including instruction devices, which implement the flowcharts and / or block diagrams. Figure 1 The function of one flow or multiple flows and / or blocksFigure 1 the function(s) specified in the block or blocks.

[0084] These computer program instructions can also be loaded into computer or other programmable data processing devices to cause a series of operational steps to be performed on the computer or other programmable devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable devices provide steps for implementing the flowchart block(s) or flowchart flow(s) and / or portions thereof. Figure 1 the flowchart flow(s) and / or block(s) Figure 1 the function(s) specified in the block or blocks.

[0085] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0086] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) about which the computer stores information about an operating system, application software, and / or the like. Memory is an example of computer readable media.

[0087] Computer readable media includes permanent and non-permanent, moveable and non- moveable media that can be implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital versatile disks (DVDs) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that is accessible to a computing device. According to the definition provided herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0088] It is also important to note that the terms "comprises", "comprising", or other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0089] The above merely provides an example of the present application, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application should be included in the scope of claims of the present application.

Claims

1. A high-definition camera-based face recognition method, characterized in that, The method comprises: acquiring pictures in a monitoring range through a high-definition camera, and scanning the pictures to determine whether a face exists in a candidate region of the pictures; if a face exists, locating coordinates of each key point of the face in the pictures, and identifying face attribute features in the pictures according to the coordinates of each key point; comparing the identified face attribute features with a plurality of face attribute features in a monitoring list in a database, respectively, and determining a plurality of similarities between the face attribute features and the plurality of face attribute features in the monitoring list, respectively; determining a plurality of similarities greater than a preset threshold, and sorting the plurality of similarities in a descending order to determine that a face attribute feature with the highest similarity in the sorted list belongs to the same person as a face attribute feature corresponding to the pictures, thereby completing face recognition; the method of acquiring pictures in a monitoring range through a high-definition camera, and scanning the pictures to determine whether a face exists in a candidate region of the pictures, specifically comprises: determining whether a monitoring target exists in the monitoring range of the high-definition camera based on a preset monitoring component, and acquiring pictures of the monitoring target in the monitoring range through the high-definition camera in the case that the monitoring target is monitored in the monitoring range; the monitoring target is a human body; preprocessing a plurality of acquired pictures to delete abnormal pictures in the plurality of pictures; the abnormal pictures at least include blurred pictures or incompletely photographed pictures; scanning a plurality of preprocessed pictures, respectively, and determining whether a face exists in a candidate region of each picture; in the case that a face exists in the pictures, identifying each region in the pictures, specifically comprising: in the case that a face exists in the pictures, sending a specified operation instruction to a user in the monitoring range through the high-definition camera, and acquiring a user operation corresponding to the user through the high-definition camera; determining whether the face in the pictures is from an attack dummy according to the user operation, and identifying each region in the pictures in the case that the face in the pictures is determined to be from the user himself; the attack dummy at least includes a user photo or a user video; in the case that a face exists in the pictures, identifying each region in the pictures, and determining each key point in the face of the pictures, specifically comprising: in the case that a face exists in the pictures, identifying each region in the pictures, and determining each key point in the face of the pictures; locating each key point of the face in the pictures, and determining coordinates of each key point in the pictures, respectively; determining face attribute features corresponding to the pictures according to the coordinates of each key point in the pictures; the face attribute features at least include gender, age, posture, and expression. The plurality of similarities greater than the preset threshold are determined, and the plurality of similarities are sorted in descending order to determine that the face attribute features with the highest similarity in the sorted list belong to the same person as the face attribute features corresponding to the picture, thereby completing face recognition, and specifically comprising: The plurality of similarities greater than the preset threshold are determined; The plurality of similarities greater than the preset threshold are sorted in descending order, and the face attribute features corresponding to the face sample picture with the highest similarity in the plurality of similarities are determined from the sorted list; It is determined that the face attribute features corresponding to the face sample picture with the highest similarity in the plurality of similarities belong to the same person as the face attribute features corresponding to the picture, thereby completing face recognition in the monitoring range of the high-definition camera.

2. The face recognition method based on high-definition camera according to claim 1, characterized in that, Before the identified face attribute features are compared with the plurality of face attribute features in the monitoring list of the database, the method further comprises: Determine the face coordinate frame corresponding to the face, and obtain a plurality of face sample pictures; Align the face coordinate frame with the plurality of face sample pictures respectively, and obtain the corresponding alignment results; According to the alignment results, the five key point coordinate sequences corresponding to each face sample picture are determined respectively, and the five key point coordinate sequences corresponding to the plurality of face sample pictures are stored in the database. 3.The method of claim 2, wherein, After the five key point coordinate sequences corresponding to the plurality of face sample pictures are stored in the database, the method further comprises: According to a preset time interval, the plurality of monitoring targets corresponding to the high-definition camera are obtained, and the plurality of monitoring targets are compared with the plurality of face sample pictures in the database; Determine the monitoring target that does not exist in the database, and store the face sample picture corresponding to the monitoring target that does not exist in the database in the database; And determine the face sample picture that does not exist in the plurality of monitoring targets, and delete the five key point coordinates corresponding to the face sample picture that does not exist in the plurality of monitoring targets in the database, to realize synchronization of the monitoring targets in the database.

4. The face recognition method based on high-definition camera of claim 1, wherein, The identified face attribute features are compared with the plurality of face attribute features in the monitoring list of the database, and the plurality of similarities between the face attribute features and the plurality of face attribute features in the monitoring list are determined, and specifically comprising: According to the face attribute features corresponding to the picture, the database is queried, and the face attribute features corresponding to the picture are compared with the plurality of face attribute features corresponding to the plurality of face sample pictures in the monitoring list of the database respectively; According to the comparison results, the plurality of similarities between the face attribute features corresponding to the picture and the plurality of face attribute features corresponding to the plurality of face sample pictures in the monitoring list of the database are determined.

5. A high-definition camera-based face recognition device, characterized by, The device comprises: At least one processor; And a memory connected in communication with the at least one processor; The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the face recognition method based on the high-definition camera according to any one of claims 1-4.

6. A non-transitory computer storage medium storing computer-executable instructions that, when executed, cause a computer to perform: The computer executable instructions are configured to: The face recognition method based on the high-definition camera according to any one of claims 1-4.

Images