Pedestrian gender identification method based on regional blocks

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

Active Publication Date: 2015-12-16
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF6 Cites 23 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
  • Pedestrian gender identification method based on regional blocks
  • Pedestrian gender identification method based on regional blocks
  • Pedestrian gender identification method based on regional blocks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

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

[0019] Training phase:

[0020] Step 1. Collect the database. Monitoring video is collected by monitoring equipment, and pedestrians are manually intercepted from the monitoring 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 location of pedestrians.

[0021] Step 2: Given a pedestrian picture, select the pedestrian area through the manually marked location information frame, and then split the pedestrian into the head, upper body, and lower body. In order to get the best split ratio, select some pedestrian pictures and measure the segmentation ratio. The area segmentation is divided 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 identification method based on regional blocks. The pedestrian gender identification method provided by the invention comprises: at first, detecting a pedestrian in a picture, then dividing the detected pedestrian into a head, an upper half body and a lower half body according to a certain rule, respectively extracting color features, gradient histogram features and edge gradient features of the parts, and training a gender classifier according to these features to identify the gender of the pedestrian through the classifier. The pedestrian gender identification method provided by the invention is used for identifying the gender attribute of the pedestrian through descriptions on the clothing, the hair style and the outline of the pedestrian, compared with the existing methods by extracting facial features, the challenge caused by obscure human face in the picture can be effectively avoided, the pedestrian genders in a monitoring picture and other scenes can be quickly and effectively identified based on the method of extracting general features of the pedestrians, and thus having very high robustness for different monitoring scenes.

Description

Technical field [0001] The invention relates to picture detection and recognition technology. Background technique [0002] The research on gender recognition of characters began in the 1990s. At first, the problem was studied by psychologists, who were devoted 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, with the main goal of obtaining a classifier that can distinguish gender. For more than ten years, the gender recognition of characters has achieved unprecedented development. Especially in recent years, it has become a hot research topic, attracting a large number of researchers from the fields of computer vision, pattern recognition, artificial intelligence, system monitoring and psychology. . Gender recognition has been widely used in many aspects. Gender recognition can act as a filter in identity recognition. The use of detected gender informatio...

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 Applications(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 Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap