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

Multi-biological-feature fusion algorithm based on particle swarm algorithm and typical association analysis method

A particle swarm algorithm and typical correlation technology, applied in the field of multi-biological feature fusion algorithm, can solve problems such as insufficient accuracy and stability, and achieve the effect of improving learning speed, high accuracy and stability

Inactive Publication Date: 2018-05-29
TIANJIN UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing multimodal biometric fusion technology still has shortcomings in the accuracy and stability of biometric identification.

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
  • Multi-biological-feature fusion algorithm based on particle swarm algorithm and typical association analysis method
  • Multi-biological-feature fusion algorithm based on particle swarm algorithm and typical association analysis method
  • Multi-biological-feature fusion algorithm based on particle swarm algorithm and typical association analysis method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] Embodiments of the present invention will be described in further detail below in conjunction with the accompanying drawings.

[0036] A multi-biological feature fusion algorithm based on particle swarm optimization and typical correlation analysis, such as figure 1 shown, including the following steps:

[0037] Step 1: Image preprocessing: the original biometric image is reconstructed into a 32*32 image.

[0038] In this step, the original dataset image (ORL face image 112*92; finger vein image 60*128) needs to be reconstructed into a 32*32 image. The image reconstruction method is expressed as follows:

[0039] I = imread('IMG.jpg');

[0040] I=imresize(I,[32,32]);

[0041] Among them, IMG.jpg represents the original dataset image, and I represents the reconstructed image representation.

[0042] Step 2: Feature extraction, such as figure 2 As shown, through two convolution operations, feature selection operations and full connection operations, the preprocesse...

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 relates to a multi-biological-feature fusion algorithm based on a particle swarm algorithm and a typical association analysis method. The algorithm is characterized in that an original data set image is reconstructed to be a 32*32 image; two-times convolution, feature selection, and full connection are carried out to use 120-dimensional one-dimensional feature vectors for the 32*32 image after pretreatment; the one-dimensional feature vector is analyzed by using a typical association analysis method to obtain a feature vector with the highest association degree, wherein the feature vector is used as a multi-biological-feature fusion feature vector; and the fusion feature vector is sent into an ELM classifier for classification. According to the invention, on the basis of theconvolutional neural network structure, different biological-feature image features are fused by introducing the particle swarm optimization algorithm and the typical correlation analysis method to obtain a complete biological feature set, thereby carrying out effective authentication. The multi-biological-feature fusion algorithm having high accuracy and stability can be applied to fields of image recognition and security inspection and the like.

Description

technical field [0001] The invention belongs to the technical field of biological feature image recognition, in particular to a multi-biological feature fusion algorithm based on a particle swarm algorithm and a typical correlation analysis method. Background technique [0002] At present, biometric identification technology is playing an increasingly important role in the field of identity authentication, and image fusion technology can obtain more biometric details and information, which can greatly improve the recognition performance, so it attracts more and more researchers' attention. Among them, multimodal biometric fusion technology is an important direction. Multimodal biometric fusion includes the following three levels: feature layer fusion refers to the strategy of fusing biological features after extraction; matching layer fusion is to fuse the matching values ​​of different feature vectors to obtain a new set of matching Value and identity authentication; deci...

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): G06K9/62
CPCG06F18/253G06F18/24
Inventor 杨巨成孙文辉李建荣胡志强王嫄陈亚瑞赵婷婷张传雷王晓靖韩书杰王洁
Owner TIANJIN UNIVERSITY OF SCIENCE AND TECHNOLOGY
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