高分辨率可见光遥感图像舰船目标识别方法研究
|
摘要
高分辨率可见光遥感图像舰船目标自动检测和识别在军事上具有十分重要意义。本文以工程应用为背景,以图像理解理论为基础,在充分分析可见光遥感图像成像特点的基础上,重点围绕可见光遥感图像舰船目标检测、目标特征提取、分类器设计等方面展开研究。建立了一个舰船目标自动识别系统,能够快速准确地从宽幅遥感图像数据中检测和识别舰船目标。主要研究内容主要包括以下几个部分:
1、针对海洋背景下舰船目标检测,提出了基于Top-Hat变换的图像恒虚警率舰船目标检测算法,能够实现舰船目标的快速检测和定位。通过大量实验数据分析,验证了该算法的有效性。
2、港口内舰船目标检测方面,采用基于卫星辅助数据和港口先验信息的目标检测方法,先在宽幅成像的遥感图像中准确定位港口位置,然后根据港口先验模板信息,检测并识别港口内舰船目标。
3、本文采用了一种新的采用独立分量分析(ICA) Zernike矩的目标形状特征识别方法。该方法基于目标分割,对分割后的目标区域进行独立分量分析,利用三阶中心矩将目标形状转化为标准形式并提取Zernike矩作为特征向量进行识别。通过理论分析与实验证明此方法性能鲁棒。
4、采取基于支持向量机分类器的方法进行分类器设计。先通过稳定性好、抗干扰能力强的特征进行粗分类,降低快速检测中的高虚警率。然后对初次分类结果再提取ICA Zernike不变矩作为特征向量进行分类识别。这种方法可以大大提高识别系统的运行效率。
详细论述了可见光遥感图像舰船目标自动识别系统的工作流程和关键技术,本文最后对研究内容进行了总结并给出了下一步研究方向。
Automatic ship target detection and recognition in high-resolution optical remote sensing images have a great value in the military. This paper, which background is engineering application, is based on the theory of the understanding of optical remote sensing image. It studies on the aspects of ship target detection, Ship feature extraction, classification design and establishment of the Sea Area target Surveillance System. It can distinguish ship target from massive remote sensing image data quickly and accurately. The paper mainly includes the following several facets:
1、For offshore ship target automatic detection, Proposes a image constant false alarm rate method base on Top-Hat transformations. And a lot of ship detection experiments were carried out and the results demonstrated the efficiency of the algorithm.
2、For in-shore ship target automatic detection. A method of target detecting and recognition based on Satellite auxiliary data and prior information of the harbors has been proposed. Firstly, the method makes sure the accurate position of the harbor target in the image of large size. Then, it detects and recognizes the ship target which lie in the harbor area, according to the structure information of the harbor target.
3、Proposed a novel feature recognition method for ship target based on the Independent Component Algorithm (ICA) zernike invariant moments. Firstly, we analyze the divided Region of Interest (ROI) with ICA method. And, we transform the shape of target to the canonical form. Then, the invariant moments of normalized shapes can be extracted. It will be used as feature vector to do further recognition. The experiment demonstrates that the performance of this method is robust.
4、A pattern recognition classifier based on support vector machine is designed in this Paper .rough classification based on stability and anti-interference characteristics used to excluded false target. Then ICA zernike invariants moment were extracted to classification. Furthermore, this method can recognize the ship target from the remote sensing images effectively.
Finally, the functional design and key technologies of the Sea Area Target Surveillance System for Remote Sensing Images are discussed. concludes the research of this thesis. Some problems and interesting area for future research are pointed out.
1、针对海洋背景下舰船目标检测,提出了基于Top-Hat变换的图像恒虚警率舰船目标检测算法,能够实现舰船目标的快速检测和定位。通过大量实验数据分析,验证了该算法的有效性。
2、港口内舰船目标检测方面,采用基于卫星辅助数据和港口先验信息的目标检测方法,先在宽幅成像的遥感图像中准确定位港口位置,然后根据港口先验模板信息,检测并识别港口内舰船目标。
3、本文采用了一种新的采用独立分量分析(ICA) Zernike矩的目标形状特征识别方法。该方法基于目标分割,对分割后的目标区域进行独立分量分析,利用三阶中心矩将目标形状转化为标准形式并提取Zernike矩作为特征向量进行识别。通过理论分析与实验证明此方法性能鲁棒。
4、采取基于支持向量机分类器的方法进行分类器设计。先通过稳定性好、抗干扰能力强的特征进行粗分类,降低快速检测中的高虚警率。然后对初次分类结果再提取ICA Zernike不变矩作为特征向量进行分类识别。这种方法可以大大提高识别系统的运行效率。
详细论述了可见光遥感图像舰船目标自动识别系统的工作流程和关键技术,本文最后对研究内容进行了总结并给出了下一步研究方向。
Automatic ship target detection and recognition in high-resolution optical remote sensing images have a great value in the military. This paper, which background is engineering application, is based on the theory of the understanding of optical remote sensing image. It studies on the aspects of ship target detection, Ship feature extraction, classification design and establishment of the Sea Area target Surveillance System. It can distinguish ship target from massive remote sensing image data quickly and accurately. The paper mainly includes the following several facets:
1、For offshore ship target automatic detection, Proposes a image constant false alarm rate method base on Top-Hat transformations. And a lot of ship detection experiments were carried out and the results demonstrated the efficiency of the algorithm.
2、For in-shore ship target automatic detection. A method of target detecting and recognition based on Satellite auxiliary data and prior information of the harbors has been proposed. Firstly, the method makes sure the accurate position of the harbor target in the image of large size. Then, it detects and recognizes the ship target which lie in the harbor area, according to the structure information of the harbor target.
3、Proposed a novel feature recognition method for ship target based on the Independent Component Algorithm (ICA) zernike invariant moments. Firstly, we analyze the divided Region of Interest (ROI) with ICA method. And, we transform the shape of target to the canonical form. Then, the invariant moments of normalized shapes can be extracted. It will be used as feature vector to do further recognition. The experiment demonstrates that the performance of this method is robust.
4、A pattern recognition classifier based on support vector machine is designed in this Paper .rough classification based on stability and anti-interference characteristics used to excluded false target. Then ICA zernike invariants moment were extracted to classification. Furthermore, this method can recognize the ship target from the remote sensing images effectively.
Finally, the functional design and key technologies of the Sea Area Target Surveillance System for Remote Sensing Images are discussed. concludes the research of this thesis. Some problems and interesting area for future research are pointed out.
引文
[1]梅安新等.遥感导论[M].北京:高等教育出版社,2001.
[2]Eldhuset K. An Automatic Ship and ShipWake Detection System for Spaceborne SAR Images in CoastalRegions [J].IEEE Trans.on Geoscience and Remote Sensing,34(4):1010-1018,1996.
[3]种劲松.合成孔径雷达图像舰船目标检测算法与应用研究[M].中国科学院研究生院博士学位论文,2002.
[4]John M. Weiss, Ruixuan Luo, Ronald M.Welch.Automatic detection of ship tracks in satellite imagery[J].IEEE Trans.on Geoscience and Remote Sensing,l(l):160-162,1997.
[5]Smith M E,Varshney P K. Intelligent CFAR processor based on data variability.IEEE Trans.on AerosPace and Electronic Systems, Vol.36(3):837-847,2000.
[6]李开端,赵友庚,蒋定定,赵育良.利用小波变换进行海上目标识别研究[J].光学技术,29(2):153-155,2003.
[7]张雨田,曾安军.高分辨遥感图像海上运动目标检测方法[J].电信技术研究,9(9):l-8,2003.
[8]汪闽,骆剑承,明冬萍.高分辨率遥感影像上基于形状特征的船舶提取[J]武汉大学学报:信息科学版, 30(s):655-655,2005.
[9]朱长青,王耀革,马球禾,史文中.基于形态分割的高分辨率遥感影像道路提取[J].测绘学报,33(4):347-351,2004.
[10]尤晓建,徐守时,侯蕾.基于特征融合的可见光图像舰船检测新方法[J].计算机工程与应,41(19):199-202,2005.
[11]陈馄,陈学侄.一种基于几何特征的舰船与码头目标分割的新方法[J].计算机工程与应用,40(31):197-199,2004
[12]蒋李兵.基于高分辨光学遥感图像的舰船目标检测方法研究[M].国防科学技术大学硕士学位论文,2006.
[13]张振.高分辨率可见光遥感图像港口及港内目标识别方法研究[M].中国科学技术大学硕士学位论文,2009.
[14]隆刚,陈学佺.高分辨率遥感图像港内舰船的自动检测方法[J].计算机仿真,24(5):198-201,2007.
[15]Joseph Diemunseh,JohnWissinger.Moving and stationary target acquisition and recognition (MSTAR)model-based automatic target recognition:seareh technology for a robust ATR.SPIE,Vol.3370:481-492,1998.
[16]Ross T D , et al. The MSTAR evaluation methodology , SPIE, Vol.3721:705-715,1999.
[17]Timothy D R,et al.SAR ATR-so what is the Problem?- an MSTAR Perspective.SPIE, Vol.3721:662-672,1999.
[18]Shaw G A,Anderson A H,Anderson J C.Project report,RASSP-5,RASSP Benchnlark 4 TechLnical Description.Lineoln Laboratory , 9 January ,1998.
[19]Novak L M,Owirka G J,et al.Automatic target-recognition system in SAIP.Lincoln Laboratory Journal,10(2):187-202.
[20]卡斯尔曼(Castleman, K, R. )著,朱志刚,林学阁等译.数字图像处理。北京:电子工业出版社,2002.
[21]张铮等.数字图像处理与机器视觉——Visual C++与Matlab实现.北京:人民邮电出版社,2010.
[22]R.Haralick,K.Shanmugam,and I.Dinstein.Texture features for image classification . IEEE Transactions on Systems,Man,and Cybernetics.SMC-3(6):610—621,1973.
[23]Aya Soffer.Image categorization using texture features,Document Analysis and Recognition,Proceedings of the Fourth International Conference on. Volume 1,18-20,1997.
[24]邹焕新,匡纲要,蒋咏悔,郑键.一种基于矩不变的SAR海洋图像舰船目标检测算法[J].计算机工程, 29(17):114-116,2003.
[25]冈萨雷斯R C.数字图像处理(matlab版) [M].阮秋琦,译.北京:电子工业出版社, 2005.
[26]李俊山,李旭辉.数字图像处理[M].北京:清华大学出版社,2007:222-223.
[27]William W. Irving,Leslie M、Novak,Alan S. Willsky,A Multiresolution Approach to Discrimination in SAR Imagery,IEEE Trans. Aerospace and Electronic Systems,Vol.33,No.4,October 1997.
[28]Pavlidis T. Algorithms for Graphics and Image Processing. Computer Science Press, 1982.
[29]吴健康.数字图像处理.北京:人民邮电出版社,1989.
[30]Lee S,Chung S.A Comparative Performance Study of Several Global Thresholding Techniques for Segmentation[J] . Computer Vision Graphics and Image Processing.52:171-190,1990.
[31]韩思奇,王蕾.图像分割的阈值法综述[J].系统工程与电子技术, 6:91-94,2002.
[32]李弼时,彭天强,彭波.智能图像处理技术「M」.北京:电子工业出版社,2004.
[33]周拥军.遥感图像中港口目标识别技术[J].南京航天航空大学学报, 4(3):350-353,2008.
[34]刘理华,白鹏飞.遥感图像中港口水域的检测方法[J]。舰船电子工程, 9:37-38,2008.
[35]胡俊华,徐守时.基于局部自相似性的遥感图像港口舰船检测[J].中国图象图形学报, 14(4):591-597,2009.
[36]D . Lowe . Distinctive image features from scale-invariant key-points . International Journal of Computer Vision,60(2):91-110,2004.
[37]Koendetink.The structure of images[J].Biological Cybernetics.1984.
[38]Linderberg T . Scale-space theory:A basic tool for analyzing structures at different scales . Journal of Applied Statistics. 21(2):224-270,1994.
[39]Beis and D.G.Lowe.Shape indexing using approximate nearest-neighbor search in high-dimensional spaces.IEEE Conference on Computer Vision and Pattern Recognition,Puerto Rico,pp.1000-1006.1997.
[40]陈付幸,王润生.基于预检验的快速随机抽样一致性算法[J].软件学报,Vol.16,No.8:1434-1473,2005.
[41]M.A.Fishler,R.C.Bolles.Random sample concensus:A Paradigm for model fitting with applications to image analysis and automated cartograPhy[C].Communieations of ACM , Vol.24 , No.6 ,March1981:381-395.
[42]VVapnik. An overview of Statistical Learning Theory[J]. IEEE Transactions on NeuralNetworks, 10(5): 988-999,1999.
[43]C Cortes, V Vapnik. Support Vector Networks[J]. Machine Learning, 20: 273-297,1995.
[44]曹茂永,孙农亮,郁道银.几种边界特征描述方法的比较研究[J].光学技术,Vol.29 (3):284-287,2003.
[45]应义斌.水果形状的傅里叶描述子研究[J].生物数学学报.16 (2):234-240. 2001.
[46]王彬生,黄乡生.Hough变换及其在几何特征检测中的应用[J].计算机与现代化,(4):20-22,2008.
[47]李宗明.矩方法及其在几何形状描述中的应用[M].中国科学院博士学位论文,2005.
[48]A. Khotanzad and Y. H. Hong,“Invariant image recognition by zernike moments,”IEEE Trans. Pattern Anal. Mach. Intell., 1990.vol. 12, no. 5: 489–497.
[49]Whoi-Yul Kim, Yong-Sung Kim. A region-based shape descriptor using Zernike moments[J]. Signal Processing: Image Communication, Vol.16 (1-2):95-102. 2000.
[50]王耀明。图像的矩函数-原理、算法及应用[M].上海:华东理工大学出版社,2002.
[51]刘茂福,胡慧君,何炎祥.主成分分析在图像Zernike矩特征降维中的应用[J].计算机应用,Vol. 27 (3):696-698. 2007.
[52]杨政武,方涛.基于Zernike矩的图像归一化技术的研究[J].计算机工程, Vol. 30 (12):34-36, 56,2004.
[53]叶斌,彭嘉雄.Zernike矩不变性分析及其改进(英文)[J].红外与激光工程, (01): 37-41. 2003.
[54]管庶安,周红,刘光蓉.基于Zernike矩的米粒形状模糊分类[M]。河南工业大学学报,26 (1):23-25,2005.
[55]M. Zuliani, S. Bhagavathy, S. Manjunath and C. S.Kenney. Affine-Invariant Curve Matching [J]. IEEE Int.Conf. Image Processing, Singapore,Oct. Vol. 5:3041-3044,2004.
[56]Y. Avritris, Y. Xirouhakis and S. Kollias. Affine-Invariant Curve Normalization for Object Shape Representation,Classification and Retrieval [J].Machine Vision and Applications, Springer Verlag, Vol. 13, Issue2: 80-94,2001.
[57]W. A. Wolovich and M. Unel. The Determination of Implicit Polynomial Canonical Curves[J].IEEE Trans.PAMI, Vol. 20, No. 10: 1080-1090, 1998.
[58]Qiong Jackson, David Landgrebe, An Adaptive Classifier Design for High-Dimensional Data Analysis with a Limited Training Data Set, Master thesis, IEEE Transactions on Geoscience and Remote Sensing in an issue to appear soon,2001.
[59]B. Bargel, K.- H. Bers, K. Jager, G. Schwan, Adaptive classification for image segmentation and target recognition, Automatic Target Recognition XII, Proceedings of SPIE, 4726: 230-240,2002.
[60]T.W. Lee. Independent Component Analysis-Theory and Applications, Boston,Kluwer Academic Publishers[M],:87-109,1998.
[61]A. Hyvrinen. Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans. On Neural Networks, vol. 10, No. 3: 626-634,1999.
[62]J. J. Lee, Md. Zia Uddin, and T.-S. Kim . Spatiotemporal Human Facial Expression Recognition Using Fisher Independent Component Analysis and Hidden Markov Model [J].30th Annual International IEEE EMBS Conference Vancouver, British Columbia, Canada, August 20-24, 2008:2546-2549.
[63]Yunxia Li,Changyuan Fan. Face Recognition by Nonnegative Independent Component Analysis[J]. 2009 Fifth International Conference on Natural Computation, Tianjin, Vol.2:555-558. 2009.
[64]王晓红,赵荣椿.矩技术在计算机图像学中的应用综述[J].中国体视学与图像分析, 7(1): 53-57,2002.
[2]Eldhuset K. An Automatic Ship and ShipWake Detection System for Spaceborne SAR Images in CoastalRegions [J].IEEE Trans.on Geoscience and Remote Sensing,34(4):1010-1018,1996.
[3]种劲松.合成孔径雷达图像舰船目标检测算法与应用研究[M].中国科学院研究生院博士学位论文,2002.
[4]John M. Weiss, Ruixuan Luo, Ronald M.Welch.Automatic detection of ship tracks in satellite imagery[J].IEEE Trans.on Geoscience and Remote Sensing,l(l):160-162,1997.
[5]Smith M E,Varshney P K. Intelligent CFAR processor based on data variability.IEEE Trans.on AerosPace and Electronic Systems, Vol.36(3):837-847,2000.
[6]李开端,赵友庚,蒋定定,赵育良.利用小波变换进行海上目标识别研究[J].光学技术,29(2):153-155,2003.
[7]张雨田,曾安军.高分辨遥感图像海上运动目标检测方法[J].电信技术研究,9(9):l-8,2003.
[8]汪闽,骆剑承,明冬萍.高分辨率遥感影像上基于形状特征的船舶提取[J]武汉大学学报:信息科学版, 30(s):655-655,2005.
[9]朱长青,王耀革,马球禾,史文中.基于形态分割的高分辨率遥感影像道路提取[J].测绘学报,33(4):347-351,2004.
[10]尤晓建,徐守时,侯蕾.基于特征融合的可见光图像舰船检测新方法[J].计算机工程与应,41(19):199-202,2005.
[11]陈馄,陈学侄.一种基于几何特征的舰船与码头目标分割的新方法[J].计算机工程与应用,40(31):197-199,2004
[12]蒋李兵.基于高分辨光学遥感图像的舰船目标检测方法研究[M].国防科学技术大学硕士学位论文,2006.
[13]张振.高分辨率可见光遥感图像港口及港内目标识别方法研究[M].中国科学技术大学硕士学位论文,2009.
[14]隆刚,陈学佺.高分辨率遥感图像港内舰船的自动检测方法[J].计算机仿真,24(5):198-201,2007.
[15]Joseph Diemunseh,JohnWissinger.Moving and stationary target acquisition and recognition (MSTAR)model-based automatic target recognition:seareh technology for a robust ATR.SPIE,Vol.3370:481-492,1998.
[16]Ross T D , et al. The MSTAR evaluation methodology , SPIE, Vol.3721:705-715,1999.
[17]Timothy D R,et al.SAR ATR-so what is the Problem?- an MSTAR Perspective.SPIE, Vol.3721:662-672,1999.
[18]Shaw G A,Anderson A H,Anderson J C.Project report,RASSP-5,RASSP Benchnlark 4 TechLnical Description.Lineoln Laboratory , 9 January ,1998.
[19]Novak L M,Owirka G J,et al.Automatic target-recognition system in SAIP.Lincoln Laboratory Journal,10(2):187-202.
[20]卡斯尔曼(Castleman, K, R. )著,朱志刚,林学阁等译.数字图像处理。北京:电子工业出版社,2002.
[21]张铮等.数字图像处理与机器视觉——Visual C++与Matlab实现.北京:人民邮电出版社,2010.
[22]R.Haralick,K.Shanmugam,and I.Dinstein.Texture features for image classification . IEEE Transactions on Systems,Man,and Cybernetics.SMC-3(6):610—621,1973.
[23]Aya Soffer.Image categorization using texture features,Document Analysis and Recognition,Proceedings of the Fourth International Conference on. Volume 1,18-20,1997.
[24]邹焕新,匡纲要,蒋咏悔,郑键.一种基于矩不变的SAR海洋图像舰船目标检测算法[J].计算机工程, 29(17):114-116,2003.
[25]冈萨雷斯R C.数字图像处理(matlab版) [M].阮秋琦,译.北京:电子工业出版社, 2005.
[26]李俊山,李旭辉.数字图像处理[M].北京:清华大学出版社,2007:222-223.
[27]William W. Irving,Leslie M、Novak,Alan S. Willsky,A Multiresolution Approach to Discrimination in SAR Imagery,IEEE Trans. Aerospace and Electronic Systems,Vol.33,No.4,October 1997.
[28]Pavlidis T. Algorithms for Graphics and Image Processing. Computer Science Press, 1982.
[29]吴健康.数字图像处理.北京:人民邮电出版社,1989.
[30]Lee S,Chung S.A Comparative Performance Study of Several Global Thresholding Techniques for Segmentation[J] . Computer Vision Graphics and Image Processing.52:171-190,1990.
[31]韩思奇,王蕾.图像分割的阈值法综述[J].系统工程与电子技术, 6:91-94,2002.
[32]李弼时,彭天强,彭波.智能图像处理技术「M」.北京:电子工业出版社,2004.
[33]周拥军.遥感图像中港口目标识别技术[J].南京航天航空大学学报, 4(3):350-353,2008.
[34]刘理华,白鹏飞.遥感图像中港口水域的检测方法[J]。舰船电子工程, 9:37-38,2008.
[35]胡俊华,徐守时.基于局部自相似性的遥感图像港口舰船检测[J].中国图象图形学报, 14(4):591-597,2009.
[36]D . Lowe . Distinctive image features from scale-invariant key-points . International Journal of Computer Vision,60(2):91-110,2004.
[37]Koendetink.The structure of images[J].Biological Cybernetics.1984.
[38]Linderberg T . Scale-space theory:A basic tool for analyzing structures at different scales . Journal of Applied Statistics. 21(2):224-270,1994.
[39]Beis and D.G.Lowe.Shape indexing using approximate nearest-neighbor search in high-dimensional spaces.IEEE Conference on Computer Vision and Pattern Recognition,Puerto Rico,pp.1000-1006.1997.
[40]陈付幸,王润生.基于预检验的快速随机抽样一致性算法[J].软件学报,Vol.16,No.8:1434-1473,2005.
[41]M.A.Fishler,R.C.Bolles.Random sample concensus:A Paradigm for model fitting with applications to image analysis and automated cartograPhy[C].Communieations of ACM , Vol.24 , No.6 ,March1981:381-395.
[42]VVapnik. An overview of Statistical Learning Theory[J]. IEEE Transactions on NeuralNetworks, 10(5): 988-999,1999.
[43]C Cortes, V Vapnik. Support Vector Networks[J]. Machine Learning, 20: 273-297,1995.
[44]曹茂永,孙农亮,郁道银.几种边界特征描述方法的比较研究[J].光学技术,Vol.29 (3):284-287,2003.
[45]应义斌.水果形状的傅里叶描述子研究[J].生物数学学报.16 (2):234-240. 2001.
[46]王彬生,黄乡生.Hough变换及其在几何特征检测中的应用[J].计算机与现代化,(4):20-22,2008.
[47]李宗明.矩方法及其在几何形状描述中的应用[M].中国科学院博士学位论文,2005.
[48]A. Khotanzad and Y. H. Hong,“Invariant image recognition by zernike moments,”IEEE Trans. Pattern Anal. Mach. Intell., 1990.vol. 12, no. 5: 489–497.
[49]Whoi-Yul Kim, Yong-Sung Kim. A region-based shape descriptor using Zernike moments[J]. Signal Processing: Image Communication, Vol.16 (1-2):95-102. 2000.
[50]王耀明。图像的矩函数-原理、算法及应用[M].上海:华东理工大学出版社,2002.
[51]刘茂福,胡慧君,何炎祥.主成分分析在图像Zernike矩特征降维中的应用[J].计算机应用,Vol. 27 (3):696-698. 2007.
[52]杨政武,方涛.基于Zernike矩的图像归一化技术的研究[J].计算机工程, Vol. 30 (12):34-36, 56,2004.
[53]叶斌,彭嘉雄.Zernike矩不变性分析及其改进(英文)[J].红外与激光工程, (01): 37-41. 2003.
[54]管庶安,周红,刘光蓉.基于Zernike矩的米粒形状模糊分类[M]。河南工业大学学报,26 (1):23-25,2005.
[55]M. Zuliani, S. Bhagavathy, S. Manjunath and C. S.Kenney. Affine-Invariant Curve Matching [J]. IEEE Int.Conf. Image Processing, Singapore,Oct. Vol. 5:3041-3044,2004.
[56]Y. Avritris, Y. Xirouhakis and S. Kollias. Affine-Invariant Curve Normalization for Object Shape Representation,Classification and Retrieval [J].Machine Vision and Applications, Springer Verlag, Vol. 13, Issue2: 80-94,2001.
[57]W. A. Wolovich and M. Unel. The Determination of Implicit Polynomial Canonical Curves[J].IEEE Trans.PAMI, Vol. 20, No. 10: 1080-1090, 1998.
[58]Qiong Jackson, David Landgrebe, An Adaptive Classifier Design for High-Dimensional Data Analysis with a Limited Training Data Set, Master thesis, IEEE Transactions on Geoscience and Remote Sensing in an issue to appear soon,2001.
[59]B. Bargel, K.- H. Bers, K. Jager, G. Schwan, Adaptive classification for image segmentation and target recognition, Automatic Target Recognition XII, Proceedings of SPIE, 4726: 230-240,2002.
[60]T.W. Lee. Independent Component Analysis-Theory and Applications, Boston,Kluwer Academic Publishers[M],:87-109,1998.
[61]A. Hyvrinen. Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans. On Neural Networks, vol. 10, No. 3: 626-634,1999.
[62]J. J. Lee, Md. Zia Uddin, and T.-S. Kim . Spatiotemporal Human Facial Expression Recognition Using Fisher Independent Component Analysis and Hidden Markov Model [J].30th Annual International IEEE EMBS Conference Vancouver, British Columbia, Canada, August 20-24, 2008:2546-2549.
[63]Yunxia Li,Changyuan Fan. Face Recognition by Nonnegative Independent Component Analysis[J]. 2009 Fifth International Conference on Natural Computation, Tianjin, Vol.2:555-558. 2009.
[64]王晓红,赵荣椿.矩技术在计算机图像学中的应用综述[J].中国体视学与图像分析, 7(1): 53-57,2002.