Face recognition method and system based on regional attention, medium and terminal

A technology of face recognition and attention, which is applied in the field of face recognition, can solve problems such as the inability to realize face recognition, and achieve the effect of solving the decline in recognition accuracy, strengthening feature attention, and improving robustness

Pending Publication Date: 2021-07-23
WINNER TECH CO INC
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a face recognition method, system, medium and terminal based on regional attention, which is used to solve the problem that the existing face recognition technology relies on facial features information Face recognition, when the user's face is blocked, face recognition cannot be realized

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Face recognition method and system based on regional attention, medium and terminal
  • Face recognition method and system based on regional attention, medium and terminal
  • Face recognition method and system based on regional attention, medium and terminal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0102] In one embodiment, the face recognition method based on regional attention is applied in an actual scene wearing a mask; specifically, the working principle of the face recognition method based on regional attention is as follows:

[0103] When the user wears a mask, the face image to be recognized collected by the front-end face acquisition device is the face image of the face wearing the mask, that is, the collected face image, the nose and mouth of the face are blocked by the mask state, the facial features that can be obtained are only local areas such as the forehead, eyebrows, and eyes. At this time:

[0104] Such as Figure 6 As shown, first, face frame detection is performed on the face image collected by the face acquisition device through retinaface, and five key points of the face wearing a mask are predicted, namely: left and right eyes, nose and left and right mouth corners; The obtained five key points are mapped to the frontal face template for face alig...

Embodiment 2

[0111] In one embodiment, before face recognition is performed, a face recognition model is built and trained.

[0112] Specifically, a face recognition model composed of a preprocessing module, an image interception module, a feature reasoning module and a feature matching module is built, wherein the feature reasoning module includes a region attention unit.

[0113] It should be noted that the feature extraction module, image interception module, feature reasoning module and feature matching module respectively correspond to the above-mentioned steps S1-S4, and the working principles of the above-mentioned steps S1-S4 are the same, so they will not be described in detail here. .

[0114] It should be noted that the training of the above face recognition model includes the following steps:

[0115] Step 1. Obtain the dataset.

[0116] Specifically, the open source public data set is used to clean and label the data, and the data set is divided into a training set and a tes...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a face recognition method and system based on regional attention, a medium and a terminal. The method comprises the following steps: preprocessing a to-be-recognized face image to obtain a preprocessed full face image; according to a preset interception mode, intercepting the full face image, and obtaining an intercepted local face image; performing feature reasoning on the full face image and the local face image to obtain face features; performing feature matching on the face features to realize face recognition; the face recognition method based on the region attention mechanism is adopted, the overall features of the face image and the features of the local region are integrated, a scheme for learning by using different receptive field features is provided, feature attention of the non-shielded region of the face is enhanced through feature splicing and fusion, therefore, when the face of the user is shielded, the face recognition can still be effectively realized.

Description

technical field [0001] The invention belongs to the technical field of face recognition, and in particular relates to a face recognition method, system, medium and terminal based on area attention. Background technique [0002] With the development and implementation of deep learning technology, face recognition has been applied to various fields such as security and payment, and has become the most widely used technology for artificial intelligence. [0003] At present, face recognition technology is an algorithm based on the characteristics of the entire face image, which relies on the comparison and recognition of the features obtained from the facial features of the face. When the user's face is blocked, it is often impossible to achieve face recognition. For example, affected by the new crown epidemic at this stage, whether it is security in public areas or payment in stores, most of the face data collected are wearing masks. Because the masks block the nose and mouth, ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08G06N5/04
CPCG06N3/08G06N5/04G06V40/171G06V10/462G06N3/045G06F18/22
Inventor 马卫民成西锋袁德胜杨祥如游浩泉林治强党毅飞崔龙李伟超王海涛
Owner WINNER TECH CO INC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap