Face recognition method, device and equipment and readable storage medium
A face recognition and recognition technology, applied in the field of computer vision, can solve problems such as the decline of recognition rate
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0052] Please refer to figure 1 , figure 1 It is a flow chart of a face recognition method in an embodiment of the present invention, and the method includes the following steps:
[0053] S101. Obtain the face image of the person to be identified, input the face image into the target network model, and obtain the target group category label and feature data of the face.
[0054] Wherein, the person to be identified may be a person to be identified in a video or a photo. For example, a suspicious person such as a thief appearing in surveillance video. There are many ways to obtain face images. The first way is to directly read the face image from the storage device; the second way is to perform face detection on the video data to obtain the face image; Detect and get a face image. The following describes in detail the process of performing face detection from a real-time monitoring scene and obtaining a face image. The process of obtaining the face image of the person to b...
Embodiment 2
[0098] In order to facilitate those skilled in the art to better understand the face recognition method provided by the embodiment of the present invention, the face recognition method provided by the embodiment of the present invention will be described in detail below by taking a specific application scenario as an example.
[0099] Please refer to figure 2 , figure 2 It is a specific implementation flowchart of a face recognition method in the embodiment of the present invention. First of all, collect face samples from different sources, the order of magnitude is tens of millions, and manually calibrate the category labels of these samples, and some public sets that have been marked can also be obtained. Perform face detection and face key point positioning on these faces, and normalize them to the same size of 112x112.
[0100] Randomly select some samples from the above normalized face samples for the training of the IndexIVFKmeans method, the order of magnitude is 10...
Embodiment 3
[0110] Corresponding to the above method embodiments, the embodiment of the present invention also provides a face recognition device, and the face recognition device described below and the face recognition method described above can be referred to in correspondence.
[0111] see Figure 4 As shown, the device includes the following modules:
[0112] The image information acquisition module 101 is used to obtain the face image of the person to be identified, input the face image into the target network model, and obtain the target group category label and feature data of the face;
[0113] Comparison data screening module 102, for reading from the database with target group category label and marked personal face image feature data;
[0114] The comparison and recognition module 103 is configured to compare the feature data with the face image feature data, and determine the identity information of the person to be identified according to the comparison result.
[0115] App...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com