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

A Robust Face Recognition Method Based on Dictionary Decomposition and Sparse Representation

A sparse representation and robust person technology, applied in the field of robust face recognition, can solve the problem of SRC being ineffective

Active Publication Date: 2019-04-30
CHINA JILIANG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But when the training samples are polluted, SRC does not have the desired effect. In 2011, the Robust Principal Component Analysis (RPCA) proposed by Candès, Li, Ma and Wright provides a method that can be used to solve this shortcoming. RPCA Decompose the training samples of each class into a low-rank matrix and the sum of a sparse matrix, and identify by reconstructing decontaminated images

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 Robust Face Recognition Method Based on Dictionary Decomposition and Sparse Representation
  • A Robust Face Recognition Method Based on Dictionary Decomposition and Sparse Representation
  • A Robust Face Recognition Method Based on Dictionary Decomposition and Sparse Representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0077] The present invention designs a large number of experiments to verify the method of the present invention. The present invention will be further described below in conjunction with the AR face database covered by sunglasses.

[0078] The AR face database has a total of 100 different individuals, including 50 females and 50 males, and each person has 26 pictures. Among the 26 pictures, the 1st to 7th and the 14th to 20th pictures only contain For the pictures of expression and light changes, the 8th to 10th and 21st to 23rd pictures are pictures with sunglasses occlusion, and the 11th to 13th and 24th to 26th pictures are occlusion pictures with silk scarves. Each image is cropped to a size of 165×120 pixels, and then each image is pulled into a column vector to form a 19800×2600 matrix.

[0079] This example selects the 1st to 7th pictures without occlusion in the database and randomly selects a picture with sunglasses occlusion from the 8th to 10th pictures as training...

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 belongs to the field of pattern recognition, in particular to a robust face recognition method based on dictionary decomposition and sparse representation. Design a dictionary decomposition model to extract the class-specific information in the face image from the given face image training data set, and then calculate a mapping matrix to describe the mapping relationship between the class-specific information and the original training data, and get The mapping matrix of the test image is corrected, and then the principal component analysis (PCA) is used to reduce the dimensionality, and finally the sparse representation classifier (SRC) is used for recognition and classification. The invention can effectively avoid the problem that the recognition rate is greatly reduced due to the contamination, occlusion, or lack of training data during the SRC recognition process, and can obtain a high and stable recognition effect.

Description

technical field [0001] The invention belongs to the field of pattern recognition, in particular to a robust face recognition method based on dictionary decomposition and sparse representation. Background technique [0002] Face recognition technology refers to the input video stream or static image, after judging the presence of a face and further marking the position of the face, extracting the feature information of the face, comparing it with the pre-stored image database, and finally A technique for authenticating or identifying one or more individuals. With its wide range of practical applications, face recognition has become a hot topic in the field of computer vision and pattern recognition in recent years. Early face recognition algorithms first performed dimensionality reduction on face images (essentially face feature extraction), and then simply applied the nearest neighbor classifier (nearest neighbor classifier) ​​for classification. [0003] In 1991, Turk and...

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 Patents(China)
IPC IPC(8): G06K9/00
CPCG06V40/168G06V40/172
Inventor 曹飞龙冯鑫山赵建伟周正华
Owner CHINA JILIANG UNIV
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