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

Gait data-based identity recognition method

A technology of identity recognition and gait, applied in digital data authentication, character and pattern recognition, instruments, etc., can solve the problems of increasing the difficulty of application and promotion of gait recognition methods, achieve strong sparsity, improve accuracy, and maintain local The effect of details

Active Publication Date: 2017-11-28
CHINA JILIANG UNIV
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When the existing gait recognition algorithm extracts gait features, it usually needs to segment the gait cycle first, which greatly increases the difficulty of the application and promotion of the gait recognition method

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
  • Gait data-based identity recognition method
  • Gait data-based identity recognition method
  • Gait data-based identity recognition method

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0061] Example 1: Using Dataset B of the CASIA gait database to test the accuracy of identification

[0062] CASIA Dataset B is a large-scale multi-view gait dataset. The dataset was collected in 2005 and contains 15,004 gait videos of 124 individuals. The gait of each person is collected from 11 viewing angles (0, 18, 36, ..., 180 degrees), and the walking conditions include three types: normal conditions, wearing a coat and backpack. The recognition results of this embodiment were compared with methods based on HMM (Hidden Markov Model), CNN (Convolutional Neural Network), and VTM (View Transformation Matrix). Training data acquisition method: Randomly select gait data of different proportions of each person's 90-degree viewing angle under normal conditions for training, and the remaining 90-degree viewing angle data and other viewing angle data are used for identity recognition testing. The method that the application proposes and the comparative experiment result of thre...

example 2

[0063] Example 2: Using Dataset C of the CASIA gait database to test the accuracy of identification

[0064] CASIA Dataset C is a large-scale gait dataset collected with infrared cameras for nighttime scenes. The dataset was collected in 2005 and contains 1583 gait videos of 153 individuals. Each person's walking conditions include four types: normal walking, fast walking, slow walking and walking with bags. The recognition results of this embodiment were compared with methods based on HMM (Hidden Markov Model), CNN (Convolutional Neural Network), and VTM (View Transformation Matrix). Training data acquisition method: Randomly select different proportions of gait data from normal walking data for training, and the remaining normal walking data and other conditional data are used for identity recognition testing. The method that the application proposes and the comparative experiment result of three kinds of existing methods are as follows Figure 5 As shown, the horizontal ...

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 gait data-based identity recognition method. The method comprises the following steps of: firstly extracting gait profile curves of training samples and a to-be-recognized sample; processing the gait profile curves by utilizing a line-by-line scanning method so as to obtain a high-dimensional gait feature matrix; carrying out dimensionality reduction on the high-dimensional gait feature matrix by utilizing an improved smooth auto-encoder; and finally judging which category of training samples is nearest to the to-be-recognized sample by utilizing a nearest neighbor algorithm. According to the identity recognition method provided by the invention, a new gait feature is adopted, and the improved smooth auto-encoder and a nearest neighbor theory are utilized to carry out feature dimensionality reduction and similarity judgement, so that structure information in two-dimensional gait images can be sufficiently utilized to describe gait differences between different persons, thereby improving the gait information-based identity recognition correctness.

Description

technical field [0001] The invention belongs to the technical field of identity recognition and authentication in pattern recognition, in particular to an identity recognition method based on gait data. Background technique [0002] With the popularization of computer science and the development of Internet technology, the importance of user identification in people's life and work is increasing day by day. User identification can effectively guarantee the security of access and is the basis of information security and Internet applications. Traditional user identification methods include password identification and smart card technologies, but due to their inherent limitations, they are far from meeting the requirements. Passwords are easily forgotten, and items such as smart cards can be lost, and once they are lost or stolen, the identity of their representatives can be easily impersonated. [0003] Biometrics-based identification technology is an important research con...

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): G06F21/32G06K9/00
CPCG06F21/32G06V40/25
Inventor 王修晖刘砚秋
Owner CHINA JILIANG 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