Journal of the Institute of Electronics Engineers of Korea SP (대한전자공학회논문지SP)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Cluster-based Linear Projection and %ixture of Experts Model for ATR System

자동 목표물 인식 시스템을 위한 클러스터 기반 투영기법과 혼합 전문가 구조

  • 신호철 (한국과학기술원 전자전산학과) ;
  • 최재철 (한국과학기술원 전자전산학과) ;
  • 이진성 (한국과학기술원 전자전산학과) ;
  • 조주현 (한국과학기술원 전자전산학과) ;
  • 김성대 (한국과학기술원 전자전산학과)
  • Published : 2003.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper a new feature extraction and target classification method is proposed for the recognition part of FLIR(Forwar Looking Infrared)-image-based ATR system. Proposed feature extraction method is "cluster(=set of classes)-based"version of previous fisherfaces method that is known by its robustness to illumination changes in face recognition. Expecially introduced class clustering and cluster-based projection method maximizes the performance of fisherfaces method. Proposed target image classification method is based on the mixture of experts model which consists of RBF-type experts and MLP-type gating networks. Mixture of experts model is well-suited with ATR system because it should recognizee various targets in complexed feature space by variously mixed conditions. In proposed classification method, one expert takes charge of one cluster and the separated structure with experts reduces the complexity of feature space and achieves more accurate local discrimination between classes. Proposed feature extraction and classification method showed distinguished performances in recognition test with customized. FLIR-vehicle-image database. Expecially robustness to pixelwise sensor noise and un-wanted intensity variations was verified by simulation.

Keywords

References

  1. Baoxin Li, Qinfen Zheng, Sandor Der, Rama Chellappa, Nasser M. Nasrabadi, Lipchen A.Chan and linCheng Wang, 'Experimental Evaluation of Neural, Statistical and Model-Based Approaches to FLIR ATR,' Part of the SPIE Conference on Automatic Target Recognition Ⅷ, Vol. 3371, pp. 388-397, 1998 https://doi.org/10.1117/12.323856
  2. James A. Ratches, C.P. Walters, Rudolf G. Buser and B.D. Guenther, 'Aided and automatic target recognition based upon sensory inputs from image forming systems,' IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 19, No.9, pp. 1004-1019, 1997 https://doi.org/10.1109/34.615449
  3. Mohamed A. KHabou, 'Morphological Shared-Weight Neural Networks: a Tool for Automatic Target Recognition Beyond the Vision Spectrum,' Computer Vision Beyond the Visible Spectrum:Methods and Applications, 1999.(CVBVS'99) Proceedings. IEEE Workshop on, 1999 https://doi.org/10.1109/CVBVS.1999.781099
  4. David Gross, 'A Neural Network ATR for High Range Resolution Radar Signature Recognition of Moving Ground Targets,' Signals, Systems, and Computers, 1999. Conference Record of the Thirty-Third Asilomar Conference onVolume:2 , 1999 https://doi.org/10.1109/ACSSC.1999.831904
  5. Vasconcelos, G.C., 'Neural network based automatic target processing and recognition,' Image Processing And Its Applications, 1999. Seventh International Conference on(Conf. Publ. No. 465), Volume: 1, 1999
  6. Baback Moghaddam and Alex Pentland, 'Probabilistic Visual Learning for Object Representation,' IEEE Trans Pattern Analysis and Machine Intelligence, Vol. 19, No. 7, 1997 https://doi.org/10.1109/34.598227
  7. Peter N.Belhumeur, Joao P.Hespanha, and David J.Kriegman, 'Eigenfaces vs. Fisherfaces:Recognition Using Class Specific Linear Projection,' IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 19, No.7, pp. 713-714, July 1997 https://doi.org/10.1109/34.598228
  8. Chengjun Liu, and Harry Wechsler, 'A Shape and Texture-Based Enhanced Fisher Classifier for Face Recognition,' IEEE Trans. Image Processing, Vol. 10, No. 4, pp. 602-604, APRIL 2001 https://doi.org/10.1109/83.913594
  9. Cappelli, R; Maltoni, D, 'Multispace KL for pattern representation and classification,' Pattern Analysis and Machine Intelligence IEEE Transactions on , Volume : 23 Issue : 9, pp. 977-996, Sep 2001 https://doi.org/10.1109/34.955111
  10. M. Turk and A. Pantland, 'Eigenface for Recognition,' Journal of Congnitive Neuroscience, Vol.3, No.1, pp. 71-86, 1991
  11. Zhujie, Y.L.Yu, 'Face Recognition with Eigenfaces,' Proceeding of the IEEE International Conference on Industrial Technology, pp. 434-438, 1994 https://doi.org/10.1109/ICIT.1994.467155
  12. Simon Haykin, 'NEURAL NETWORKS - A Comprehensive Foundation-Second Edition,' Prentice Hall International, Inc., pp. 368-381, 1999
  13. Ahuja, N., Kriegman, D., Yang, M.-H., 'Face recognition using kernel eigenfaces,' Image Processing, 2000, Volume: 1, pp. 37-40 vol.1, MARCH 2000 https://doi.org/10.1109/ICIP.2000.900886
  14. M. Sonka, V .Hlavac, R. Boyle, 'Image Processing, Analysis and Machine Vision,' PWS publishing, 1999
  15. 권재한, 이광연, 김성대, '적외선 영상에서의 불변 특징 정보를 이용한 목표물 인식,' 23회 대한전자공학회 추계합동 학술대회 논문집 Ⅳ, Vol.23, No.2, pp. 65-68, 2000
  16. 신호철, 최해철, 이진성, 조주현, 김성대, '밝기-윤곽선 정보 기반의 목표물 인식 기법,' 제140회 신호처리합동학술대회 논문집, pp. 411-414, 2001
  17. 신호철,최해철,최학훈,김성대, 'DCT 기법을 활용한 불록 기반의 적외선 영상 차원 감축 및 인식기법,' 한국군사과학기술학회 2002년도 종합학술대회 논문집, Vol.2, pp. 659, 2002
  18. http://sdvision.kaist.ac.kr/~horse/ATRDB
  19. 조주현, 최해철, 이진성, 신호철, 김성대, '다중 센서 융합과 배경 추정을 이용한 물체 영역 검출', 14회 신호처리 합동학술대회, 제14권, 제1호, pp. 443-446, 2001
  20. 14회 신호처리 합동학술대회 v.14 no.1 다중 센서 융합과 배경 추정을 이용한 물체 영역 검출 조주현;최해철;이진성;신호철;김성대