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

Face visual feature representation method based on attribute space

An attribute space and attribute technology, applied in the field of face visualization feature representation based on attribute space, can solve the problems of complex face and difficult face recognition.

Inactive Publication Date: 2013-09-11
HEFEI UNIV OF TECH
View PDF2 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] People have made many beneficial attempts in the field of face recognition and achieved fruitful results, but there are still many difficulties in using computers for automatic and efficient face recognition. Affected by factors including lighting, expression, posture, shooting angle and even camera specifications

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 visual feature representation method based on attribute space
  • Face visual feature representation method based on attribute space
  • Face visual feature representation method based on attribute space

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The basic idea of ​​the present invention is to associate the input face with the attribute space by modeling the attributes of the face, use the Gaussian mixture model to mine the visual features of the input face, and perform face recognition and verification in the high-level features.

[0029] According to above idea, the present invention flow process is as follows figure 1 Shown, the method of the present invention is further described below in conjunction with technical scheme and accompanying drawing.

[0030] First, analyze the impact of various face attributes on face recognition, obtain the global and local attributes of the face, and perform data simulation and evaluation on various face attributes. Second, image preprocessing is performed on the input face and simulated data, and "bottom-level" features are extracted. Thirdly, the attribute is modeled according to the Gaussian mixture model and various visual features of the input face in the attribute spa...

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 face visual feature representation method based on attribute space. The face visual feature representation method includes digitally simulating, preprocessing and performing data evaluation on overall or partial attributes of 64 kinds of human faces, and acquiring 'bottom' features of data; utilizing a Gaussian mixture model to evaluate attribute data distribution so as to form a human face attribute space; projecting inputted human face data to the attribute space to acquire quantized human face visual features; and standardizing visual features through a Z-score method to more effectively recognize inputted data. The face visual feature representation method based on the attribute space can more accurately acquire features needed to recognize human faces, and is widely applicable to other kinds of recognition and advanced intelligent domain models.

Description

technical field [0001] The invention belongs to the technical field of image processing and pattern recognition, and relates to a face visualization feature representation method based on attribute space. Background technique [0002] With the rapid development of computer and image processing technology, public safety issues have attracted more and more attention from the society, and various identification technologies have emerged in an endless stream. Face recognition has great advantages because of its directness, convenience, friendliness, and concealment. Face recognition involves pattern recognition, computer vision, intelligent human interaction, computer graphics, cognitive science and other disciplines. As a key technology of biometric identification, face recognition has good application prospects in information security, security, finance and other fields. [0003] People have made many beneficial attempts in the field of face recognition and achieved fruitful...

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
Inventor 陈雁翔董绪文刘盛中龙润田
Owner HEFEI UNIV OF 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