Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A face recognition method based on block collaborative representation

A face recognition and collaborative representation technology, applied in the field of face recognition, can solve the problem that the recognition rate needs to be improved, and achieve the effect of improving the robustness and improving the effect of face recognition.

Active Publication Date: 2019-06-18
HARBIN UNIV OF SCI & TECH
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the recognition rate of the above methods still needs to be improved.

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
  • A face recognition method based on block collaborative representation
  • A face recognition method based on block collaborative representation
  • A face recognition method based on block collaborative representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] Embodiment 1, experimental research on information loss of pixels.

[0056] The present invention has carried out the experimental research of missing pixel point information, randomly selects 10%, 20%, 30%, 40% of the pixel points of the face image, sets the value of the randomly selected pixel points to 0, and transforms the pixel points Does not carry valid information. According to the above specific program steps, experiments were carried out on three face databases. The experimental results of AR, Extend Yale B and ORL face databases are as follows: Image 6 , Figure 7 and Figure 8 shown. With the increase of the missing percentage of face image pixel information, the recognition rates of both FRAPRC and FRARC decreased. In the case of different pixel information missing percentages, the recognition rate of FRAPRC was higher than that of FRARC. In the case of missing, FRAPRC has a better recognition effect than FRARC; in the case of different pixel informati...

Embodiment 2

[0057] Example 2: Experimental research on different corrosion blocks.

[0058] The present invention has carried out experimental research on the presence of corrupted blocks in face images, randomly selecting 10%, 20%, 30%, and 40% of the continuous blocks of the image, and replacing them with image information that is not related to the face image, 40% of which are corrupted The face image of the block case such as Figure 9 b) as shown. According to the above specific program steps, experiments were carried out on three face databases. The experimental results of AR, Extend YaleB and ORL face databases are as follows: Figure 10 , Figure 11 and Figure 12 shown. As the percentage of corrupted face image blocks in the original face image increases, the recognition rates of both FRAPRC and FRARC decrease. In the case of partial corruption of the face image, the recognition rate of FRAPRC is higher than that of FRARC. When the face image is corrupted, FRAPRC has a bette...

Embodiment 3

[0059] Embodiment 3, experimental research on face occlusion.

[0060] The face images in the AR face database include original face images, face images occluded by glasses, and face images occluded by scarves. Figure 13 shown. When there is an occlusion problem in the image, this paper uses 14 unoccluded face images from the AR database as the training set; 7 glasses and 7 scarf occluded face images are used as the eye and scarf test sets respectively. The personal face database is tested, and the experimental results are as follows: Figure 14 shown. In the case of glasses occlusion and scarf occlusion, the recognition rate of FRAPCR is higher than that of FRACR, and in the case of glasses occlusion.

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 block collaborative representation. In practical application, the information loss (such as pixel information loss, corrosion block and shielding) of the face image can influence the pixel value of the image so as to influence the face recognition effect. The method comprises the following steps: firstly, dividing images in a face image library into a training set and a test set, searching an optimal blocking mode to block the images, and constructing a sub-block dictionary for the images after the training samples are blocked; Secondly, separating an error generated by information loss of the human face image from the original image by adopting cooperative representation (CR) of sub-blocks, so that the influence of a human face recognition result of the missing information image can be effectively reduced; Then classifying the sparse sparsity obtained by each sub-block; And finally, obtaining a final identification result based on a maximum voting criterion, thereby effectively reducing the influence of invalid classification on the identification result of the whole image caused by a large minimum coefficient error obtained by one or more sub-block characteristics, and improving the identification rate.

Description

technical field [0001] The invention relates to the field of face recognition under the condition of lack of face image information, in particular to a face recognition method based on block cooperative representation. Background technique [0002] With the gradual development of computer vision technology and the gradual increase in the demand for human-computer interaction, face recognition methods have gradually been popularized in fields such as mobile phone unlocking, secure payment, and smart door locks. A problem with missing information. Early mature face recognition methods will have poor recognition results due to problems such as lack of face information. Therefore, the research on face recognition methods under the condition of partial face information loss still has important significance and huge challenges. Existing studies are mainly divided into three categories: robust discriminant model method, subspace regression and robust error coding. [0003] Face r...

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
CPCY02D10/00
Inventor 孙崐李晓彤张天意郑婉宁殷欣
Owner HARBIN UNIV OF SCI & 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
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