Supercharge Your Innovation With Domain-Expert AI Agents!

Bayesian estimation sparse representation face recognition method based on dictionary reconstruction

A Bayesian estimation and sparse representation technology, applied in the field of image recognition, which can solve the problems of low recognition rate and poor robustness.

Inactive Publication Date: 2014-08-20
NANJING UNIV OF INFORMATION SCI & TECH
View PDF2 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problems of poor robustness and low recognition rate when the existing recognition methods recognize face images with camouflage, the present invention provides a face recognition method based on dictionary reconstruction based on Bayesian estimation sparse representation

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
  • Bayesian estimation sparse representation face recognition method based on dictionary reconstruction
  • Bayesian estimation sparse representation face recognition method based on dictionary reconstruction
  • Bayesian estimation sparse representation face recognition method based on dictionary reconstruction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0089] Select 14 images of 100 people for testing, select 7 of them (1-7 images) for training, and the remaining 7 images (14-20 images) for testing, all images are cropped to 60 pixels × 43 pixels. Table 1 lists the recognition rates of several methods when a certain part of the face is blocked by black occluders of different sizes. Table 1 shows that the method of the present invention has the highest recognition, and the recognition rate is least affected by the occlusion rate, indicating that the method of the present invention has the best robustness.

[0090] Occlusion rate

[0091] Table 1 Recognition rates of several methods under different degrees of occlusion

Embodiment 2

[0093] Select 10 images of 50 people (with expression changes) for the test, select 8 of them (1-4, 14-17) for training, and the remaining 2 (8, 21 or 11 , 24 images) are used for testing, and all images are cropped to a size of 80 pixels × 60 pixels. Table 2 shows the recognition rate comparison of several methods under the same occlusion degree of different occluders. Table 2 shows that the method of the present invention has the highest recognition rate and the best robustness.

[0094] Recognition rate

[0095] Table 2 Recognition rates of several recognition methods under the same occlusion degree of different occluders

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 Bayesian estimation sparse representation face recognition method based on dictionary reconstruction, and belongs to the technical field of image recognition. The method is used for solving the problems that when an existing recognition method is used for recognizing an image of a face in disguise, robustness is not good, and the recognition rate is low. The method comprises the following steps that a dictionary reconstruction method is used, and after gray threshold conversion and smoothing processing are carried out on a test face image, the original test image and a processed test image are fused to obtain a new test image; the Bayesian estimation sparse representation recognition method is used for carrying out classification and recognition on the original test image. According to the Bayesian estimation sparse representation face recognition method based on dictionary reconstruction, the original image and noise can be effectively separated, the high recognition rate and the good robustness can be obtained, and the requirement in the actual application for real time performance is met; compared with an existing sparse representation method and an existing Bayesian estimation sparse representation method, the Bayesian estimation sparse representation face recognition method based on dictionary reconstruction has the greatly improved processing effect, and is high in stability and wide in application range.

Description

technical field [0001] The invention belongs to the technical field of image recognition, in particular to a face recognition method based on dictionary reconstruction based on Bayesian estimation sparse representation. Background technique [0002] Face recognition is a major research hotspot in the field of pattern recognition. It is a technology that uses computers to analyze face images to extract effective identification information to identify identities. It can be widely used in security departments, identity verification, digital surveillance and other fields. Face is a complex, changeable and high-dimensional pattern. Although it is easy for people to recognize familiar faces, it is still difficult for machines to accurately recognize faces. Face recognition is due to its Importance has also become an important research area in computer vision and pattern recognition. [0003] In the past few decades, a variety of feature extraction and recognition methods have bee...

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): G06K9/00
Inventor 郭业才张铃华费赛男黄友锐
Owner NANJING UNIV OF INFORMATION SCI & TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com