Supercharge Your Innovation With Domain-Expert AI Agents!

Multimodal biometric fusion recognition method based on label identification correlation analysis

A technology of biometrics and correlation analysis, applied in biometrics recognition, use of multiple biometrics, character and pattern recognition, etc.

Active Publication Date: 2021-08-20
ANHUI UNIVERSITY
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Kernel canonical correlation analysis maps sample features to kernel space through kernel function, and performs feature extraction in kernel space. Kernel canonical correlation analysis is an extension method of canonical correlation analysis, which does not use category label information

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
  • Multimodal biometric fusion recognition method based on label identification correlation analysis
  • Multimodal biometric fusion recognition method based on label identification correlation analysis
  • Multimodal biometric fusion recognition method based on label identification correlation analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The present invention will be further described below in conjunction with the accompanying drawings and specific examples.

[0053] Such as figure 1 The shown multimodal biological feature fusion recognition method based on tag discrimination correlation analysis includes the following steps:

[0054] Step 1: Input the feature vector of the multimodal image;

[0055] Step 2: For different biological features, the category label and biological feature are fused to obtain a feature set with category label information;

[0056] Step 3: Fuse the different modal feature sets obtained in step 2, and use the maximum correlation between the two to establish a criterion function to obtain the projection vector, and then obtain the fused feature set;

[0057] Step 4: The feature sets obtained in step 3 are respectively used for parallel fusion and serial fusion, and classification and recognition are performed by the nearest neighbor method.

[0058] The category labels and fe...

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 multi-modal biological feature layer fusion recognition method based on label identification correlation analysis. First, the feature set is fused with the category label information, and a criterion function is established for it, and the optimal projection vector is obtained by using the Lagrangian function, and the feature set with category information is obtained; secondly, for the feature set with category information, While minimizing its intra-class scatter matrix, maximize the correlation of the covariance matrix between the two modal feature sets, and extract the feature vector with higher discriminative ability; finally, the proposed fusion method is applied to the multi-modal The experimental results verify the effectiveness of the method proposed in this application and the rationality of the combination of the two algorithms.

Description

technical field [0001] The invention belongs to the field of biological feature recognition, in particular to a multi-modal biological feature layer fusion recognition method based on label identification correlation analysis. Background technique [0002] With the rapid development of artificial intelligence, single-modal biometric recognition technologies, such as palmprint recognition, iris recognition, gesture recognition, etc., have achieved good results, but due to their singleness, they can no longer meet the security needs of today's society. sexual demands. Multimodal fusion recognition is to combine multiple different biological features or multiple different local features of the same modality into a whole for recognition by adopting a certain fusion rule, which has strong security and recognizability , has become a research hotspot in recent years. According to the fusion of different information, multimodal biometric fusion technology can be divided into senso...

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
CPCG06V40/70G06F18/24143G06F18/253
Inventor 王华彬张露李雪中符春兰商若凡司宏飞章达刘阳阳陶亮
Owner ANHUI UNIVERSITY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com