[1]倪超,李奇,夏良正.基于KPCA联合并联抑制神经网络变换的红外目标识别算法[J].东南大学学报(自然科学版),2008,38(2):329-334.[doi:10.3969/j.issn.1001-0505.2008.02.029]
 Ni Chao,Li Qi,Xia Liangzheng.Infrared target recognition based on joint KPCA shunting inhibition neural network transformation[J].Journal of Southeast University (Natural Science Edition),2008,38(2):329-334.[doi:10.3969/j.issn.1001-0505.2008.02.029]
点击复制

基于KPCA联合并联抑制神经网络变换的红外目标识别算法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
38
期数:
2008年第2期
页码:
329-334
栏目:
计算机科学与工程
出版日期:
2008-03-20

文章信息/Info

Title:
Infrared target recognition based on joint KPCA shunting inhibition neural network transformation
作者:
倪超 李奇 夏良正
东南大学自动化学院, 南京 210096
Author(s):
Ni Chao Li Qi Xia Liangzheng
School of Automation, Southeast University, Nanjing 210096, China
关键词:
KPCA KHA 广义并联抑制神经元 红外目标
Keywords:
kernel principal component analysis kernel Hebbian algorithm generalized shunting neuron infrared target
分类号:
TP391.41
DOI:
10.3969/j.issn.1001-0505.2008.02.029
摘要:
为了提高红外目标的识别性能,提出了一种KPCA联合并联抑制神经网络变换.该联合神经网络变换集成了KPCA的 KHA学习机制与神经网络误差反传机制,使得KPCA与GSN分类器有机地结合起来,通过监督学习的方式引入类别信息,能够在实现数据有效降维的同时,优化主元特征的提取,从而提高算法的分类识别性能.针对典型红外军用车辆图像,采用联合算法与传统算法分别进行对比实验.实验结果表明,算法在优化特征同时,提高了目标识别性能.
Abstract:
A novel joint KPCA(kernel principal component analysis)shunting inhibition neural network transformation is presented to improve the recognition capability of infrared target. The transformation integrates KPCA and GSN(generalized shunting neuron)classifier by combining together the learning mechanism of kernel Hebbian algorithm(KHA)based on neural network and a back propagation learning algorithm. Then the interclass information is introduced through the supervised learning manner, and better dimensionality reduction and a higher degree of discriminability can be achieved. The joint method was applied to typical infrared military vehicles in comparison with several traditional methods. Experimental results show that the method can offer more powerful target recognition with optimized feature extraction.

参考文献/References:

[1] Kim B G,Park D J.Novel target segmentation and tracking based on fuzzy membership distribution for vision-based target tracking system[J].Image and Vision Computing,2006,24(12):1319-1331.
[2] Shaik J S,Iftekharuddin K M.Automated tracking and classification of infrared images[C] //Proceedings of the International Joint Conference on Neural Networks.Oregon,Portland,2003,2:1201-1206.
[3] Sun S G,Park H W.Segmentation of forward-looking infrared image using fuzzy thresholding and edge detection[J]. Optical Engineering,2001,40(11):2638-2645.
[4] Chan L A,Der S Z,Nasrabadi N M.A joint compression-discrimination neural transformation applied to target detection[J].IEEE Trans on System,Man and Cybernetics—Part B:Cybernetics,2005,35(4):670-681.
[5] Smola S A,Müller K R.Nonlinear component analysis as a kernel eigenvalue[J].Neural Computation,1998,10(5):1299-1319.
[6] Arulampalam G,Bouzerdoum A.A generalized feedforward neural network architecture for classification and regression[J]. Neural Networks,2003,16(sup):561-568.
[7] Cao L J,Chua K S,Chong W K,et al.A comparison of PCA,KPCA and ICA for dimensionality reduction in support vector machine[J].Neurocomputing,2003,55(9):321-336.
[8] Zhu B,Jiang L,Luo Y G,et al.Gabor feature-based apple quality inspection using kernel principal component analysis[J].Journal of Food Engineering,2007,81(4):741-749.
[9] Xie X D,Lam K M.Gabor-based kernel PCA with doubly nonlinear mapping for face recognition with a single face image[J]. IEEE Trans Image Processing,2006,15(9):2481-2492.
[10] Liu C J.Gabor-based kernel PCA with fractional power polynomial models for face recognition[J].IEEE Trans Pattern Analysis and Machine Intelligence,2004,26(5):572-581.
[11] Kim K I,Franz M O,Schölkopf B.Iterative kernel principal component analysis for image modeling[J].IEEE Trans Pattern Analysis and Machine Intelligence,2005,27(9):1351-1366.
[12] Bouzerdoum A.Classification and function approximation using feed-forward shunting inhibitory artificial neural networks[C] //Proceeding of International Joint Conference on Neural Networks.Como,Italy,2000:613-618.

备注/Memo

备注/Memo:
作者简介: 倪超(1979—),男,博士生; 李奇(联系人),男,博士,教授,博士生导师,liq_kj@js.gov.cn.
引文格式: 倪超,李奇,夏良正.基于KPCA联合并联抑制神经网络变换的红外目标识别算法[J].东南大学学报:自然科学版,2008,38(2):329-334.
更新日期/Last Update: 2008-03-20