Face recognition method and system based on elastic context relation loss function

A loss function and face recognition technology, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve the problems of lack of global information and affect the performance of face recognition, so as to speed up the training process and improve the accuracy of face recognition The effect of reducing useless redundant calculations

Active Publication Date: 2019-11-05
GUANGZHOU PIXEL SOLUTIONS
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The second is that each parameter update is only based on several pairs of sample data, lacking global information, which affects the final face recognition performance

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 elastic context relation loss function
  • Face recognition method and system based on elastic context relation loss function
  • Face recognition method and system based on elastic context relation loss function

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] The structure of the face recognition system based on the elastic context loss function of the present invention includes a preprocessing unit, a data block construction unit, a deep convolution network training unit, and a feature extraction and recognition unit. The relationship between these four units is as follows figure 1 shown.

[0041] like figure 2 Shown, the main steps of preprocessing unit among the present invention are:

[0042] Step (1): For the image to be processed, use face detection to determine whether the image contains a human face, if it does not contain a human face, re-acquire the image, otherwise proceed to step (2),

[0043] Step (2): Perform key point positioning on the included face image to obtain 25 key points in the face area.

[0044] Step (3): Use the coordinates of the 5 key points of the left and right eyes, nose tip, and left and right mouth corners to crop and normalize the image through operations such as image rotation, scaling...

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 relates to a face recognition method based on an elastic context relation loss function. According to the method, how to overcome the influence of massive unbalanced data on face recognition training is studied; according to the method, the combined data blocks can be effectively mined, useless redundant calculation is reduced, the whole training process is accelerated, the designedtarget function based on the elastic context does not need to introduce extra training parameters for each class, the influence of long tail classes in large-scale training is reduced, and meanwhile,the face recognition accuracy can be improved through soft spacing.

Description

technical field [0001] The present invention relates to the field of digital image processing, and more specifically, to a face recognition method and system based on an elastic context loss function. Background technique [0002] The current face recognition methods are mainly researched and improved on public training data sets. These databases generally have a limited number of categories, ranging from a few thousand to hundreds of thousands, and each category has a large number of samples. However, the face data obtained in actual scenes usually has two characteristics. One is that there are many categories. The data collected in actual scenes often has as many as millions or even tens of millions of people, and the collected data is only a small part. People contain rich and diverse images, and most people only have a few or even one image. For example, a large number of videos of people can be obtained in a surveillance scene, but the similarity between the images is ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/168G06V40/172G06N3/045G06F18/23213G06F18/2411
Inventor 姚若光范志鸿古竞庞恺
Owner GUANGZHOU PIXEL SOLUTIONS
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