Cross-pose face recognition method based on progressive neural network and attention mechanism

A neural network and face recognition technology, applied in the field of face recognition, can solve the problem of increasing the amount of parameters and calculation

Active Publication Date: 2021-05-18
SOUTH CHINA UNIV OF TECH
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this can flexibly deal with faces of different poses, the use of multiple

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
  • Cross-pose face recognition method based on progressive neural network and attention mechanism
  • Cross-pose face recognition method based on progressive neural network and attention mechanism
  • Cross-pose face recognition method based on progressive neural network and attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0069] Example

[0070] like figure 1 As shown, this embodiment provides a cross-pose face recognition method based on a progressive neural network and an attention mechanism, including the following steps:

[0071] S1: Face data preprocessing: use the MTCNN tool to detect the face and 5 key points of the face, and align them;

[0072] In this embodiment, MTCNN is used to detect the face boundingbox and 5 key points of the face, and TCDCN is used to detect 68 key points of the face according to the face image and boundingbox, and then according to the detected 5 face key points and the standard The alignment template is affine transformed to align faces. For the training set, if the face data of key points and bounding boxes cannot be detected, they are directly filtered; for the test set, manual annotation is appropriately performed.

[0073] S2: Detect the angle of the face data in the training set, that is, estimate the pose information of the face;

[0074] In the pres...

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 discloses a cross-pose face recognition method based on a progressive neural network and an attention mechanism. The cross-pose face recognition method comprises the following steps: performing face detection and key point alignment by using an MTCNN tool; estimating attitude information of each face image; sampling a front face image for each face image to serve as a reference image, forming image pairs, inputting the image pairs into a designed progressive neural network, extracting face feature pairs, and performing identity prediction; calculating an attention weighted mean square error loss function by using the feature pairs, and training a neural network in combination with a classified cross entropy loss function; and extracting face features by using the trained neural network and performing face verification. According to the invention, a new lightweight progressive network structure and an attention-based loss function are constructed, and the features of the side face image can be effectively adjusted in a feature space, so that the problem that the face recognition performance is reduced due to posture change in the face recognition field is solved.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a cross-pose face recognition method based on a progressive neural network and an attention mechanism. Background technique [0002] Face recognition is a key technology that is widely used in banking, e-commerce, Internet finance, electronic entertainment, education, finance, securities and other fields. However, although the current face recognition technology has achieved remarkable recognition accuracy, when dealing with faces with large poses, the recognition accuracy of most face verification algorithms tends to drop compared to faces with smaller poses. very obvious. Senguptal et al pointed out in the 2016 IEEE WACV conference article that the recognition accuracy of these algorithms dropped by more than 10% when recognizing large pose faces. This means that the impact of face posture changes has become an important challenge in the field of face recognition, an...

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
IPC IPC(8): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V40/165G06V40/171G06V10/462G06N3/048G06F18/22G06F18/241
Inventor 黄俊阳丁长兴
Owner SOUTH CHINA UNIV OF TECH
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