Face recognition method and system based on discriminative dictionary learning based on adaptive local constraints

A technology of local constraints and dictionary learning, applied in the field of image recognition, can solve problems such as reducing the classification performance of face recognition systems

Active Publication Date: 2019-10-18
HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, face images are easily affected by factors such as illumination, posture, and occlusion. As a result, local features calculated directly using face images may not truly reflect the feature relationship between faces, which reduces the classification of face recognition systems based on dictionary learning. 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 discriminative dictionary learning based on adaptive local constraints
  • Face recognition method and system based on discriminative dictionary learning based on adaptive local constraints
  • Face recognition method and system based on discriminative dictionary learning based on adaptive local constraints

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] The present invention will be further described in detail below through specific embodiments in conjunction with the accompanying drawings.

[0058] If the dictionary is learned using the k-means algorithm, the dictionary can inherit the structural features in the training samples. According to this idea, consider using the local features of atoms to inherit the structural features of training samples, and design discriminative constraints to improve the discriminative performance of the dictionary. On this basis, a discriminative dictionary learning algorithm based on adaptive local constraints is designed to improve the classification performance of face recognition. The algorithm steps that the present invention proposes are as follows:

[0059] The first step: Use atoms to construct the local feature model of the dictionary. Since graphs can effectively represent the relationship between data, graphs can be used to represent the similarity features between atoms. ...

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 proposes a discriminative dictionary learning algorithm based on adaptive local constraints to solve the problems existing in the dictionary learning algorithm in face recognition. The present invention firstly utilizes atoms to construct an adaptive Laplacian graph, so that it can keep the local structural features of the dictionary. Then, use the row vector of the coding coefficient matrix and the Laplace graph of the dictionary to design the discriminant term of local constraints, so that the dictionary has stronger discriminative performance, and then design a face recognition system model based on adaptive local constraint discriminative dictionary learning , to improve the classification performance of face recognition. The smooth development of the algorithm of the present invention will enrich and develop the theoretical system of dictionary learning based on constraints, and play an important guiding role in enhancing the performance of dictionary identification and improving the ability of face recognition.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a discriminant dictionary learning algorithm and a face recognition system. Background technique [0002] The local features of training samples play a very important role in improving the discriminative performance based on dictionary learning. However, face images are easily affected by factors such as illumination, posture, and occlusion. As a result, the local features directly calculated by using face images may not truly reflect the feature relationship between faces, which reduces the classification of face recognition systems based on dictionary learning. performance. Contents of the invention [0003] The purpose of the present invention is to provide a discriminant dictionary learning algorithm based on adaptive local constraints to solve the problems existing in the dictionary learning algorithm in face recognition. [0004] For reaching above-mentioned o...

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
CPCG06V40/172
Inventor 李争名徐勇
Owner HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
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