A New Method of Feature-level Fusion Recognition Based on Complex-valued Independent Component Analysis (ICA)

doi:null

您当前的位置：

首页 >

文章列表页 >

A New Method of Feature-level Fusion Recognition Based on Complex-valued Independent Component Analysis (ICA)

Article | 更新时间：2020-08-12

- A New Method of Feature-level Fusion Recognition Based on Complex-valued Independent Component Analysis (ICA)
- Optics and Precision Engineering Vol. 17, Issue 8, Pages: 2024-2032(2009)
- 作者机构：
  
  中国科学院长春光学机密机械与物理研究所2. 中国科学院长春光学精密机械与物理研究所
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Received：12 August 2008，
  
  Revised：31 October 2008，
  
  Published Online：20 August 2009，
  
  Published：20 August 2009
- 稿件说明：
移动端阅览
王大伟,纪华,王延杰. 一种新的复值独立分量分析的特征融合识别方法[J]. 光学精密工程, 2009,17(8):2024-2032

A New Method of Feature-level Fusion Recognition Based on Complex-valued Independent Component Analysis (ICA)[J]. Optics and precision engineering, 2009, 17(8): 2024-2032.
王大伟,纪华,王延杰. 一种新的复值独立分量分析的特征融合识别方法[J]. 光学精密工程, 2009,17(8):2024-2032 DOI：

A New Method of Feature-level Fusion Recognition Based on Complex-valued Independent Component Analysis (ICA)[J]. Optics and precision engineering, 2009, 17(8): 2024-2032. DOI：

摘要

摘要：介绍了复值独立分量分析(Complex ICA)的基本原理和算法

并提出了基于复值独立分量分析的目标识别方法。该方法首先利用快速独立分量分析算法(FICA)对目标训练集图像进行ICA分解

然后分别提取基于独立分量的训练集和测试集目标特征

采用线性判据对训练集目标特征进行分类训练，找到合理的分类阈值，最后对测试集图像进行分类识别。本文的创新点在于把复数值独立分量分析的方法应用于多传感器融合的目标识别。实验结果表明

本文提出的方法是可行的，并能获得较高的目标识别准确率。

Abstract

Abstract: In our paper

we introduce the basic principle and algorithm of the Complex Valued ICA

and a new target recognition algorithm based on Complex Valued ICA is proposed. With our method

we must compose complex value training group matrix with two images from different cameras

secondly

the Fast ICA algorithm is performed on the matrix to get independent components (ICs)

in the third step

we need extract the training set and testing set’s features based on ICs

then Fisher discriminant analysis is introduced to train target features’ pattern

at last

the classification of targets in testing set is performed. Our experimental data show that the method proposed in our paper is feasible and the target recognition rate is satisfied.

关键词

Keywords

references

Views

340

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A method for dense occlusion target recognition of service robots based on improved YOLOv7

Saliency maps for point cloud recognition models

Super-resolution reconstruction of micro-scanning images

Path planning strategy of amphibious spherical robot

SAR ATR based on disentangled representation learning generative adversarial networks and support vector machine

Related Author

CHEN Renxiang

QIU Tianran

YANG Lixia

YU Tenwei

JIA Fei

CHEN Cai

LIANG Ao

ZHANG Hao

Related Institution

Chongqing Intelligent Robot Research Institute， Chongqing 4000714

School of Business Administration， Chongqing University of Science and Technology

Chongqing Engineering Laboratory of Traffic Engineering Application Robot， Chongqing Jiaotong University

Shenyang Institute of Automation， Chinese Academy of Sciences

Key Laboratory of Opto-Electronic Information Processing，Chinese Academy of Sciences

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰