Kernel generalized neighbor discriminant embedding for SAR automatic target recognition

详细信息    查看全文

• 作者：Yulin Huang (1)
  Jifang Pei (1)
  Jianyu Yang (1)
  Tao Wang (1)
  Haiguang Yang (1)
  Bing Wang (1)
  
  1. Department of Electronic Engineering ; University of Electronic Science and Technology of China (UESTC) ; Chengdu ; China
  
• 关键词：Synthetic aperture radar ; Automatic target recognition ; Feature extraction ; Manifold learning
• 刊名：EURASIP Journal on Advances in Signal Processing
• 出版年：2014
• 出版时间：December 2014
• 年：2014
• 卷：2014
• 期：1
• 全文大小：635 KB
• 参考文献：1. Mishra AK, Mulgrew B: Bistatic SAR ATR Using PCA-based Features. In / Proceedings of the SPIE 6234, Automatic Target Recognition XVI. United Kingdom: University of Edinburgh; 18 May 2006, doi:10.1117/12.664117
  2. Mishra AK: / Validation of PCA and LDA for SAR ATR. Paper presented at IEEE Region 10 Conference. Guwahati: IIT Guwahati; 19鈥?1 Nov 2008
  3. Gunn, SR (2010) Support Vector Machines for Classification and Regression. Analyst, University of Southampton, Technical Report
  4. Zhao, Q, Principe, JC (2001) Support vector machines for SAR automatic target recognition. IEEE Trans. Aerosp. Electron. Syst 2: pp. 643-654 CrossRef
  5. Li Y, Zhang XQ, Bai BD, Zhang YN: / Information Compression and Speckle Reduction for Multifrequency Polarimetric SAR Imagery using KPCA. Paper presented at the 2007 International Conference on Machine Learning and Cybernetics. Xi鈥檃n: Northwest Polytechnical University; 19鈥?2 Aug 2007
  6. Han P, Wu RB, Wang YH, Wang ZH: / An efficient SAR ATR approach. Paper presented at the 2003 IEEE International Conference on the ICASSP. Tian jin: Tian jin University; 6鈥?0 April 2003
  7. He, X, Niyogi, P (2003) Locality preserving projections. Paper presented at the 16th Processing Conference on the Neural Information Processing Systems.
  8. Yan, S, Xu, D, Zhang, BY, Zhang, HJ, Yang, Q, Li, S (2007) Graph embedding and extensions: a general framework for dimensionality reduction. IEEE Trans. Pattern Anal. Mach. Intell 1: pp. 40-51 CrossRef
  9. Ross T, Worrell S, Velten V, Mossing J, Bryant M: Standard SAR ATR evaluation experiments using the MSTAR public release data set. Paper presented at the Processing Conference on the SPIE. 15 September 1998
  10. Cover, TM (1968) Estimation by the nearest neighbor rule. IEEE Trans. Inf. Theory 1: pp. 50-55 CrossRef
  
• 刊物主题：Signal, Image and Speech Processing;
• 出版者：Springer International Publishing
• ISSN：1687-6180

文摘

In this paper, we propose a new supervised feature extraction algorithm in synthetic aperture radar automatic target recognition (SAR ATR), called generalized neighbor discriminant embedding (GNDE). Based on manifold learning, GNDE integrates class and neighborhood information to enhance discriminative power of extracted feature. Besides, the kernelized counterpart of this algorithm is also proposed, called kernel-GNDE (KGNDE). The experiment in this paper shows that the proposed algorithms have better recognition performance than PCA and KPCA.