Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Face recognition method and device

A face recognition and to-be-recognized technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of changing recognition conditions and the degradation of the recognition performance of the fixed weight scheme, so as to achieve a flexible weight scheme and improve recognition. The effect of pass rate

Active Publication Date: 2014-07-02
HANVON CORP
View PDF4 Cites 52 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to propose an adaptive multi-feature weight fusion face recognition scheme to solve the change of recognition conditions, such as different light sources or changes in the occlusion information characteristics of appearance, etc., when different feature performance changes, the fixed weight scheme Identify issues with degraded 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 device
  • Face recognition method and device
  • Face recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Embodiment 1, set the clustering feature as the light source information feature, such as figure 2 and image 3 Shown is the implementation principle block diagram adopting the face recognition method of the present invention, and its specific implementation process is as follows:

[0045] When the clustering features are light source information features, the training process of the face recognition method is as follows:

[0046] In this embodiment, it is assumed that there is no change in the light source environment in the registration set, and there is a change in the light source environment in the test set.

[0047] Step 1: collect face image samples under various clustering feature conditions, and construct a training sample set, which includes: a test face image set and a registered face image set.

[0048] The training sample set covers samples under various light source conditions. In the technical solution of the present invention, it is necessary to coll...

specific Embodiment approach

[0056] The optimal weight value can be obtained by measuring the maximum recognition rate, minimum equal error rate, and maximum pass rate of various samples. The present invention adopts the weight when the recognition rate is maximum as the best weight, and the specific implementation is as follows:

[0057] Suppose there are M face samples in the template set T, T={t 1 , t 2 ,...,t M}, template t i The corresponding label is labelt i (i=1, . . . , M). The set X that is divided into the kth light source in the training set X k There are N face samples in total, X k ={x 1 , x 2 ,...,x M}, training sample x j The corresponding label is labelx j (j=1, . . . , N). The features used for identification are class P. Assume that the weight of the lth feature in the best weight combination of the kth class is The best weight W of class k k can be expressed as The overall optimal threshold W can be expressed as W={W k ,k=1,...,K}

[0058] Given a training sample x ...

Embodiment 2

[0081] Embodiment 2, set the clustering feature as the occlusion information feature of appearance, which can reflect the occlusion information feature of the face, such as figure 2 and Figure 4 Shown is a block diagram of the implementation principle of the face recognition method of the present invention, and its specific implementation process is as follows: wherein, the occlusion factor in this embodiment is set as a combination of glasses and glasses reflection.

[0082] When the clustering feature reflects the face occlusion information feature, the training process of the face recognition method is as follows:

[0083] Step 1: collect face image samples under various clustering feature conditions, and construct a training sample set, which includes: a test face image set and a registered face image set.

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 device. The method includes the steps of extracting clustering features of preprocessed template face images and face images to be recognized; inputting the extracted clustering features into a clustering category model trained in advance, and determining a clustering category; extracting N recognition features of the preprocessed template face images and the face images to be recognized, wherein N is a natural number larger than 1; calculating similarity between N the recognition features of the face images to be recognized and N recognition features of the template face images, selecting the optimal weight combination and a dynamic threshold determined in advance according to the determined clustering category, carrying out weight fusion on similarity of the N extracted recognition features, and obtaining comprehensive similarity scores of the face images to be recognized and the template face images; selecting the highest comprehensive similarity score of the face images to be recognized and the template face images to be compared with the dynamic threshold; carrying out recognition if the highest comprehensive similarity score is not smaller than the dynamic threshold; refusing to recognize if the highest comprehensive similarity score is smaller than the dynamic threshold.

Description

technical field [0001] The invention relates to the field of digital image processing and pattern recognition based on computer vision, in particular to a face recognition method and device. Background technique [0002] Biometric feature recognition technology is an effective technology for identification, and the fastest growing recently is face recognition technology and biometric feature recognition technology integrated with face recognition technology. [0003] In order to improve the performance of face recognition classifiers, multi-feature weighted fusion is commonly used at present. For different features, the recognition performance is not the same, and weighting is to fuse different features with different weights. The weight of each feature is determined by the characteristics of the feature itself (separability, recognition rate, etc.), and different fusion features correspond to different fusion weights. A larger weight is given to features with good recogni...

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): G06K9/00G06K9/62
Inventor 黄磊任智杰彭菲
Owner HANVON CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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