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

Maximum and minimum network modulation of automatic computer sex identification

A gender recognition, maximum and minimum technology, applied in the field of information processing, can solve problems such as training samples for automatic gender recognition that have not yet been found

Inactive Publication Date: 2005-12-28
SHANGHAI JIAO TONG UNIV
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In further searches, no age-based decomposition of training samples for automatic gender recognition has been found, and with M 3 A report on the network's automatic gender 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
  • Maximum and minimum network modulation of automatic computer sex identification
  • Maximum and minimum network modulation of automatic computer sex identification
  • Maximum and minimum network modulation of automatic computer sex identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The present invention decomposes training samples of the same sex according to age information, and then uses M 3 The network trains the decomposed training samples, and finally recognizes them, thereby improving the recognition accuracy. Provide following embodiment in conjunction with content of the present invention:

[0019] After feature extraction of 786 male images and 1269 female images, the same number of face feature vectors are obtained respectively. According to age information such as: 0~9, 10~19, 20~29, 30~39, 40~49, 50~59, and over 60 years old, both male and female samples were decomposed into 7 subsets. These samples are trained with a max-min modular support vector machine network and then identified. The tested face feature vectors are shown in Table 1. table two and figure 1 The recognition results before improvement (original support vector machine) and after improvement (maximum-min modular support vector machine) are compared. in figure 1 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

A modularized network method for identifying sex automatically by computer includes picking up characters of human face and naming it as human face character vector to form sample set; decomposing sample set of the same sex to be subsets according to age; training these subsets by M3 network decomposition and combination to form M3 network classifier and finally carrying out sex identification.

Description

technical field [0001] The invention relates to an identification method in the technical field of information processing, in particular to a maximum and minimum modular network method for computer automatic gender identification. Background technique [0002] The basic process of computer automatic gender recognition is to extract features from face images, use the feature vectors after feature extraction to train classifiers, and then perform recognition. An effective feature extraction method is to locate the key points (eyes, nose, mouth, etc.) of the face image, and then perform Gabor wavelet transformation. Finally, a pattern classifier is trained with the obtained features of male and female face images. [0003] After searching the literature of the prior art, it was found that B.L.Lu and M.Ito published the article "Task Decomposition and Module Combination Based on Class Relations: A Modular Neural Network for Pattern Classification" ("Problem Decomposition and M...

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): G06K9/62
Inventor 连惠城吕宝粮龙川绘里奈细井圣
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