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

Recognition method based on multi-modal non-contact identity features

A technology of identity features and recognition methods, which is applied in character and pattern recognition, instruments, calculations, etc., can solve problems such as unsatisfactory real-time performance and recognition efficiency needs to be further improved, and achieve the effect of high system recognition accuracy

Inactive Publication Date: 2019-06-04
DONGHUA UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This biometric recognition technology has great advantages for face recognition with large-angle pose changes, but the recognition efficiency needs to be further improved, and it cannot meet the real-time requirements in practical application scenarios.

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
  • Recognition method based on multi-modal non-contact identity features
  • Recognition method based on multi-modal non-contact identity features
  • Recognition method based on multi-modal non-contact identity features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] In order to make the present invention more comprehensible, preferred embodiments are described in detail below with accompanying drawings.

[0048] A typical biometric identification system includes two links of registration and identification. The registration link is to save the biometric data of legal users into the system database through the registration algorithm. The identification link is to determine whether the user to be identified is a user registered in the database through the identification algorithm. The flow chart of a recognition method based on multi-modal non-contact identity features proposed by the present invention is as follows figure 1 As shown, including the registration link and identification link:

[0049] Registration link: use feature extraction method to extract face features, gait features and ear features from the face image, gait image and ear image of the user to be registered, and obtain face recognition features, gait recognition...

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 discloses a recognition method based on multimodal non-contact identity features, which comprises the following steps: for the current user to be registered, acquire S face images, S gait images and N ear images; extract S The features of the face images, S gait images and N ear images are obtained to obtain the face image feature matrix, gait image feature matrix and ear image feature matrix; step 3, image feature matrix fusion is performed to obtain the fusion matrix ;Real-time identification. The invention proposes a layered structure-based fusion recognition method of human face, gait and human ear images. The method proposed by the invention effectively fuses face recognition, gait recognition and human ear recognition.

Description

technical field [0001] The invention relates to a multimodal non-contact personal identity recognition method based on fusion of human face, gait and human ear images based on hierarchical structure, belonging to the fields of pattern recognition, digital image processing and the like. Background technique [0002] Biometric identification technology uses human physiological and behavioral characteristics for identification. Single-mode biometric identification technology has achieved rich results in both research and commercial fields. However, the single-modal biometric identification technology cannot meet the needs of large-scale applications in terms of the recognition accuracy of the algorithm and the ease of use of the product. Multimodal biometric fusion technology can not only improve the recognition accuracy of the system, but also expand the application field of the system, which is a major trend in the development of biometric identification technology. [0003]...

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
CPCG06V40/25G06V40/172G06V40/50G06F18/254
Inventor 郝矿荣赵军毛祎蒙丁永生
Owner DONGHUA 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