CN-116543431-B - Identity matching method, device, electronic equipment and computer readable storage medium

CN116543431BCN 116543431 BCN116543431 BCN 116543431BCN-116543431-B

Abstract

The application discloses an identity matching method, an identity matching device, electronic equipment and a computer readable storage medium, wherein the method comprises the steps of obtaining target archive data of a target object, wherein the target archive data comprises a face image and identified license plate information when the photographed target object drives a vehicle; and if the information quantity of the target identity information associated with each license plate information in the target archive data is equal to one, matching the face image in the target archive data with the identity image in the target identity information to obtain an identity matching result. By means of the scheme, the accuracy of identity matching can be improved.

Inventors

GAO SHENGXING
CHEN LILI
ZHOU MINGWEI

Assignees

浙江大华技术股份有限公司

Dates

Publication Date: 20260508
Application Date: 20230323

Claims (10)

1. An identity matching method, the method comprising: acquiring target archive data of a target object, wherein the target archive data comprises a face image and identified license plate information when the shot target object drives a vehicle; Taking identity information associated with license plate information in preset vehicle registration data as target identity information according to the license plate information in the target archive data, wherein the preset vehicle registration data comprises the associated identity information and license plate information; Judging whether the information data of the target identity information associated with each license plate information in the target archive data is equal to one; if the information quantity of the target identity information associated with each license plate information in the target archive data is equal to one, matching the face image in the target archive data with the identity image in the target identity information to obtain an identity matching result; Responding to the fact that the information quantity of target identity information associated with license plate information in the target archive data is larger than one, acquiring face images and other images shot when a target object in the target archive data drives a vehicle corresponding to the license plate information, wherein the other images comprise images with image quality before a preset ranking in the target archive data; Based on the matching result between the other images and the identity images in the target identity information corresponding to each license plate information in the target archive data, determining the identity images in the target identity information corresponding to each license plate information in the target archive data as target identity images; And matching the identity image in the target identity information corresponding to each license plate information in the target archive data with the face image to obtain the identity matching result.
2. The method according to claim 1, wherein the step of determining the identity image in the target identity information corresponding to each license plate information of the target profile data as the target identity image based on the matching result between the other image and the identity image in the target identity information corresponding to each license plate information in the target profile data includes: calculating the average value of the feature similarity between each other image and the identity image in the target identity information corresponding to the license plate information in the target archive data to obtain the average value of a plurality of feature similarities; and determining the identity image corresponding to the maximum average value in the average values of the plurality of feature similarities as the target identity image.
3. The method according to claim 1, wherein the step of matching the face image in the target profile data with the identity image in the target identity information to obtain an identity matching result includes: calculating the image feature similarity between the face image in the target archive data and the identity image in the target identity information; And if the image feature similarity is greater than a similarity threshold, the identity matching result is that the matching is successful.
4. The method of claim 1, wherein the step of obtaining target profile data for the target object comprises: acquiring initial archive data of the target object; The license plate information in the initial file is filtered according to the information quantity of the license plate information in the initial file data, and the filtered license plate information is obtained; And determining the filtered license plate information as license plate information of a vehicle driven by the target object in the target archive data.
5. The method of claim 4, wherein the step of filtering license plate information in the initial archive according to the number of license plate information in the initial archive data to obtain filtered license plate information comprises: if the number of license plate information in the initial archive data is equal to one, determining the license plate information in the initial archive data as the license plate information in the target archive data; If the information quantity of license plate information in the initial archive data is larger than one, determining the information quantity of each license plate information in the initial archive data; Acquiring target license plate information and other license plate information in the initial file data, wherein the target license plate information is license plate information with the largest information quantity in each license plate information; And taking the other license plate information corresponding to the ratio value of the information quantity of the other license plate information to the information quantity of the target license plate information larger than the ratio threshold value and the target license plate information as the filtered license plate information.
6. The method of claim 4, wherein the step of obtaining initial profile data for the target object comprises: acquiring collected image data of each target object in a preset space-time range; And clustering according to the image characteristics of the acquired images in the acquired image data to obtain the initial archive data of each target object.
7. The method according to claim 1, wherein the step of taking the identity information associated with the license plate information in the preset vehicle registration data as the target identity information according to the license plate information in the target profile data comprises the steps of: Selecting license plate information which is the same as the license plate information in the preset vehicle registration data; and determining the identity information corresponding to the same license plate information in the preset vehicle registration data as target identity information corresponding to the license plate information.
8. An identity matching apparatus, comprising: The acquisition module is used for acquiring target archive data of a target object, wherein the target archive data comprises a face image and identified license plate information when the shot target object drives a vehicle; The determining module is used for taking identity information associated with the license plate information in preset vehicle registration data as target identity information according to the license plate information in the target archive data, wherein the preset vehicle registration data comprises the associated identity information and license plate information; The matching module is used for judging whether the information data of the target identity information associated with each license plate information in the target archive data is equal to one; if the information quantity of the target identity information associated with each license plate information in the target archive data is equal to one, matching face images in the target archive data with identity images in the target identity information to obtain an identity matching result, responding to the fact that the information quantity of the target identity information associated with each license plate information in the target archive data is greater than one, acquiring face images and other images shot when a target object in the target archive data drives a vehicle corresponding to each license plate information, wherein the other images comprise images with image quality before a preset ranking in the target archive data, and based on the matching result between the other images and the identity images in the target identity information corresponding to each license plate information in the target archive data, determining the identity images in the target identity information corresponding to each license plate information in the target archive data as target identity images, and matching the identity images in the target identity information corresponding to each license plate information in the target archive data with the face images to obtain the identity matching result.
9. An electronic device comprising a memory and a processor for executing program instructions stored in the memory to implement the method of any one of claims 1 to 7.
10. A computer readable storage medium having stored thereon program instructions, which when executed by a processor, implement the method of any of claims 1 to 7.

Description

Identity matching method, device, electronic equipment and computer readable storage medium Technical Field The present application relates to the field of security protection and image processing technologies, and in particular, to an identity matching method, an identity matching device, an electronic device, and a computer readable storage medium. Background At present, the identity recognition based on the face image is generally to compare the characteristics of the collected face image with the images in the database, and judge that the face image is matched with the corresponding identity when the characteristic comparison result meets a certain threshold value. However, due to the influence of an image snapshot scene, the quality of the snapshot image is uneven due to the fact that the speed of the vehicle is too high or the reflection of the window glass causes blurring of the snapshot face image, and then the accuracy of identity matching is reduced. Disclosure of Invention The application provides at least one identity matching method, device, electronic equipment and computer readable storage medium. The application provides an identity matching method, which comprises the steps of obtaining target archive data of a target object, wherein the target archive data comprise face images and identified license plate information when the target object drives a vehicle, taking identity information associated with the license plate information in preset vehicle registration data as target identity information according to the license plate information in the target archive data, wherein the preset vehicle registration data comprise the associated identity information and the license plate information, and matching the face images in the target archive data with the identity images in the target identity information to obtain an identity matching result if the information quantity of the target identity information associated with each license plate information in the target archive data is equal to one. In an embodiment, the method further comprises the steps of responding to the fact that the information quantity of target identity information associated with license plate information in the target archive data is larger than one, acquiring face images and other images shot when a target object in the target archive data drives a vehicle corresponding to the license plate information, wherein the other images comprise images with image quality in the target archive data before a preset ranking, determining identity images in the target identity information corresponding to the license plate information in the target archive data as target identity images based on matching results between the other images and the identity images in the target identity information corresponding to the license plate information in the target archive data, and matching the identity images in the target identity information corresponding to the license plate information in the target archive data with the target identity images to obtain the identity matching results. In an embodiment, the step of determining the identity image in the target identity information corresponding to each license plate information of the target archive data as the target identity image based on the matching result between the other images and the identity image in the target identity information corresponding to each license plate information of the target archive data includes calculating an average value of feature similarities between each other image and the identity image in the target identity information corresponding to each license plate information of the target archive data to obtain an average value of a plurality of feature similarities, and determining the identity image corresponding to the largest average value of the average values of the plurality of feature similarities as the target identity image. In an embodiment, the step of matching the face image in the target profile data with the identity image in the target identity information to obtain an identity matching result includes calculating an image feature similarity between the face image in the target profile data and the identity image in the target identity information, and if the image feature similarity is greater than a similarity threshold, obtaining the identity matching result as a successful matching result. In an embodiment, the step of obtaining the target archive data of the target object includes obtaining initial archive data of the target object, filtering license plate information in the initial archive according to the information quantity of the license plate information in the initial archive data to obtain filtered license plate information, and determining the filtered license plate information as license plate information of a vehicle driven by the target object in the target archive data. In an embodiment, the step of filtering the license plate i