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

A Pedestrian Gender Recognition Method Based on Area Segmentation

A technology for gender recognition and pedestrians, applied in character and pattern recognition, instruments, calculations, etc., can solve problems such as complex methods, reduced real-time performance, and difficulty in gender recognition by facial features, to achieve improved recognition accuracy, high robustness, The effect of high recognition ability

Active Publication Date: 2019-02-15
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in scenarios such as monitoring screens, the face is not clear, and it is quite difficult to identify gender by extracting facial features
On the other hand, the method of extracting features for faces is more complicated, which reduces the real-time 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
  • A Pedestrian Gender Recognition Method Based on Area Segmentation
  • A Pedestrian Gender Recognition Method Based on Area Segmentation
  • A Pedestrian Gender Recognition Method Based on Area Segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The invention is divided into two stages of training and testing of the pedestrian gender recognition classifier. Specific steps such as figure 1 as shown,

[0019] Training phase:

[0020] Step 1. Collect the database. Surveillance video is collected by monitoring equipment, and pedestrians are manually intercepted from the surveillance video as a database. The intercepted pedestrians are divided into two image sets of male and female according to gender. Randomly select half of the samples as training data, and manually mark the position of pedestrians.

[0021] Step 2. Given a pedestrian picture, select the pedestrian area through the manually marked position information frame, and then split the pedestrian into head, upper body, and lower body parts. In order to obtain the best splitting ratio, select some pedestrian pictures, measure the splitting ratio, and split the area according to four parameters, respectively, the neck position coefficient is 0.15, the sh...

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 provides a pedestrian gender recognition method based on area segmentation. The present invention firstly detects the pedestrians in the picture, and then divides the detected pedestrians into three parts according to certain criteria: the head, the upper body, and the lower body, and extracts the color features, gradient histogram features, and edge gradient features of each part respectively. Features to train a gender classifier, so that the gender of pedestrians can be identified by the classifier. The present invention identifies the gender attributes of pedestrians by describing pedestrian clothing, hairstyles, and outlines. Compared with existing methods, it can effectively avoid the challenges caused by unclear faces of people in the picture by extracting facial features. Based on The method of extracting the whole body features of pedestrians can quickly and effectively identify the gender of people in scenes such as surveillance pictures, and has high robustness for different surveillance scenes.

Description

technical field [0001] The invention relates to picture detection and recognition technology. Background technique [0002] The research on character gender recognition began in the 1990s. The problem was initially studied by psychologists, who were committed to studying the recognition mechanism of human beings to distinguish between men and women. Then, some scholars conducted research from the perspective of computer vision, and their main goal was to obtain a classifier that can distinguish gender. For more than ten years, the gender recognition of people has achieved unprecedented development, especially in recent years, it has become a hot research topic, and has attracted the attention of a large number of researchers in the fields of computer vision, pattern recognition, artificial intelligence, system monitoring and psychology. . Gender recognition is widely used in several ways. Gender recognition can act as a filter function in identity recognition. Using the d...

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): G06K9/00G06K9/62
CPCG06V20/53G06F18/2411
Inventor 李宏亮杨德培罗雯怡姚梦琳侯兴怀李君涵马金秀
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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