Check patentability & draft patents in minutes with Patsnap Eureka AI!

Super-resolution face recognition method based on relevant characteristic and non-liner mapping

A nonlinear mapping and related feature technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve problems such as complex learning process of objective function parameters

Inactive Publication Date: 2010-05-19
XI AN JIAOTONG UNIV
View PDF0 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Pablo et al. proposed a low-resolution face recognition method combining super-resolution reconstruction and feature extraction. The regularized objective function model proposed by this method can clearly express the limitations of super-resolution reconstruction results and recognition results at the same time, but The learning process of the objective function parameters is more complicated

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
  • Super-resolution face recognition method based on relevant characteristic and non-liner mapping
  • Super-resolution face recognition method based on relevant characteristic and non-liner mapping
  • Super-resolution face recognition method based on relevant characteristic and non-liner mapping

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific examples. These examples are illustrative only and not restrictive of the invention.

[0028] The problem of face image recognition feature super-resolution can be described as: two corresponding high-resolution and low-resolution face image training sets I H and I L Or the feature vector set X of two corresponding face image recognition features H and x L , input a low-resolution face image I l , find the recognition feature c of the corresponding high-resolution face image h .

[0029] The theory of manifold learning considers that the face subspace is an embedded manifold structure, which shows that the high-dimensional structure composed of the face dataset is topologically homeomorphic to a low-dimensional Euclidean space in a local sense. The c...

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 discloses a super-resolution face recognition method based on relevant characteristic and non-liner mapping. Aiming at the problem of low recognition rate of a low-resolution face image, the invention provides a method which uses relevant characteristic and non-liner mapping to reconstruct super resolution of recognition characteristics to obtain the corresponding relevant characteristic of the low-resolution face image in a super-resolution space. The invention utilizes a typical correlation analysis to build the relevant subspace of super-resolution and low-resolution face image characteristics to obtain relevant characteristics; then, a radial basis function is used to build the relation between super-resolution and low-resolution face image characteristics so as to obtain and test the approximation characteristic of the low-resolution face image in the super-resolution space to be used for face recognition finally. Compared with other methods, the invention is slightly affected by face gesture and expression variation and has high recognition rate.

Description

technical field [0001] The invention relates to the field of face recognition, in particular to a super-resolution face recognition method based on correlation features and nonlinear mapping. Background technique [0002] Face recognition is an important biometric authentication technology. In the past three decades, researchers have proposed a large number of methods, which have been widely used in security systems such as video surveillance. However, due to the limitations of distance and hardware conditions, the resolution of the face images of interest captured in large-scene video surveillance systems is often relatively low, thereby reducing the performance of face recognition. How to improve the recognition effect under low-resolution conditions is a problem that needs to be solved in face recognition at present. [0003] Image super-resolution (SR) refers to the use of an algorithm to obtain one or a series of high-resolution (high-resolution, HR) images from one or...

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): G06K9/00G06K9/66
Inventor 黄华何惠婷
Owner XI AN JIAOTONG UNIV
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