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

Posture recognition method of human's face based on limited Boltzmann machine neural network

A limited Boltzmann machine and limited Boltzmann machine technology, applied in the field of image recognition, can solve the problems of data innuendo, limited application, and cannot be directly applied to face gesture recognition, etc., to reduce the error rate and calculate the speed. Fast, easy-to-achieve effects

Inactive Publication Date: 2007-04-25
SHANGHAI JIAO TONG UNIV
View PDF0 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

That is, the method only learns the underlying low-dimensional structure of the given data, and it cannot use the low-dimensional structure that has been learned to map a new high-dimensional space data to the low-dimensional space
This limits the application of this method, so it cannot be directly applied to face pose recognition

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
  • Posture recognition method of human's face based on limited Boltzmann machine neural network
  • Posture recognition method of human's face based on limited Boltzmann machine neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The embodiments of the present invention are described in detail below in conjunction with the accompanying drawings: the present embodiment is implemented on the premise of the technical solution of the present invention, and detailed implementation methods and specific processes are provided, but the protection scope of the present invention is not limited to the following Example.

[0023] The whole implementation process of this embodiment is as follows:

[0024] 1. In the face bank (this face bank contains the face images of different postures of 2270 people. Each person includes the face images of 9 poses, as shown in Figure 1, Figures a, b, c, d, e , f, g, h, i these 9 face images are respectively -90°, -60°, -45°, -30°, 0°, 30°, 45°, 60°, 90°. The images in the face library can be divided into 9 categories according to their different postures, each category has 2270 images, and the images in each category have the same posture.) The face area is detected in th...

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

This invention relates to Boltzman neutral network for human face identification method in image identification technique field, which comprises the following steps: a, pre-processing human images training samples with different positions; b, initiating limited Boltzman neutral network; c, pre-training limited Boltzman neutral network; d, adjusting limited Boltzman neutral network parameters; e, identifying new human face position. This invention relates to human face testing, mode sorting, human face position identification for re-establish three dimensional human faces and identification.

Description

technical field [0001] The invention relates to a method in the technical field of image recognition, in particular to a method for face gesture recognition using a restricted Boltzmann machine neural network. Background technique [0002] With the strengthening of global security awareness, human beings have higher and higher requirements for biometric identification technology, and among many biometric identification technologies, face recognition is the most feasible. However, the traditional two-dimensional face recognition is affected by factors such as illumination and posture, which cannot meet the requirements of practical applications. Therefore, it is a trend to expand from two-dimensional face recognition to three-dimensional face recognition, because three-dimensional space can provide more information for face recognition. However, this expansion from two-dimensional recognition to three-dimensional recognition also brings new problems, that is, how to estimate...

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 杜春华杨杰张田昊吴证袁泉
Owner SHANGHAI JIAO TONG 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