基于形态学理论的目标检测技术
|
摘要
图像目标的自动检测在现代高技术战争中具有十分重要的意义，研究与发展可靠性高、适应性广的检测算法与处理系统的需求越来越迫切，从而也推动了计算机视觉与自动目标识别理论的发展。由于视觉过程本身的高度非线性，采用非线性的信号处理技术就自然成为图像领域的一种重要发展趋势。数学形态学是一种颇具特色的非线性理论，本论文具体研究了利用这一理论解决目标检测所面临的关键技术问题。
利用形态学理论实现目标检测的核心内容，是基于形态学理论建立目标检测模型，并形成相应的自动处理过程。该模型由形态学统一表示定理构成的多结构基元滤波器和结构参数优化学习两个部分组成。在多结构基元滤波器设计中，通过学习人-机交互选定的目标样本，自动确定形态变换的组合规则及其结构元素，最终以神经网络形式构成滤波器。在结构参数的优化学习中，利用应用领域的先验知识，分别设计了自适应BP学习、启发式遗传学习和引导式模拟退火学习等三种最优化计算方法。
将本文提出的研究方法用于实景图像分析，获得了满意的实验结果，既可自动检测出红外运动图像目标，也能提取多种光学静态图像目标。实验结果表明，本文设计的检测算法对复杂变化的图像环境具有良好的滤波性能和稳健的适应能力。
Automatic target detection in images is of vital importance to modern high-tech warfare. Demand of researching and developing detection algorithms and processing systems with high reliability and high adaptability have been increasing more and more these years, and computer vision and automatic target recognition have been advanced as well. Because vision procedure is actually nonlinear, using nonlinear techniques become one kind of important research tend in image fields. Mathematic morphology is one of nonlinear theories, and has distinguishing features. In this paper key issues of applying the theory to target detection are studied.
The core content in realizing target detection with morphological theory is to construct a target detection model and to form a corresponding automatic process. The model consists of two parts: the multi-structuring elements filter formed according to the generalized morphological denotation theorem, and an learning procedure to obtain optimal structural parameters. In designing a multi-structuring elements filter, combination rules and structuring elements of the morphological transform are determined automatically, and one kind of neural networks is taken for the filter, In optimzing structural parameters of the filter, three computation methods are designed respectively, by adopting some priori information in application fields to guide optimal structural parameter learning procedure, which are the BP adaptive learning algorithm, the heuristic genetic learning algorithm and the inductive simulated annealing learning algorithm.
The approch developed in this paper is applied to some real image data, and satisfied results are obtained. Both the moving targets in a set of infrared images and the static targets in optical images can be detected automatically. Experimental results indicate that object detection models and relative algorithms have better and robust performance.
利用形态学理论实现目标检测的核心内容，是基于形态学理论建立目标检测模型，并形成相应的自动处理过程。该模型由形态学统一表示定理构成的多结构基元滤波器和结构参数优化学习两个部分组成。在多结构基元滤波器设计中，通过学习人-机交互选定的目标样本，自动确定形态变换的组合规则及其结构元素，最终以神经网络形式构成滤波器。在结构参数的优化学习中，利用应用领域的先验知识，分别设计了自适应BP学习、启发式遗传学习和引导式模拟退火学习等三种最优化计算方法。
将本文提出的研究方法用于实景图像分析，获得了满意的实验结果，既可自动检测出红外运动图像目标，也能提取多种光学静态图像目标。实验结果表明，本文设计的检测算法对复杂变化的图像环境具有良好的滤波性能和稳健的适应能力。
Automatic target detection in images is of vital importance to modern high-tech warfare. Demand of researching and developing detection algorithms and processing systems with high reliability and high adaptability have been increasing more and more these years, and computer vision and automatic target recognition have been advanced as well. Because vision procedure is actually nonlinear, using nonlinear techniques become one kind of important research tend in image fields. Mathematic morphology is one of nonlinear theories, and has distinguishing features. In this paper key issues of applying the theory to target detection are studied.
The core content in realizing target detection with morphological theory is to construct a target detection model and to form a corresponding automatic process. The model consists of two parts: the multi-structuring elements filter formed according to the generalized morphological denotation theorem, and an learning procedure to obtain optimal structural parameters. In designing a multi-structuring elements filter, combination rules and structuring elements of the morphological transform are determined automatically, and one kind of neural networks is taken for the filter, In optimzing structural parameters of the filter, three computation methods are designed respectively, by adopting some priori information in application fields to guide optimal structural parameter learning procedure, which are the BP adaptive learning algorithm, the heuristic genetic learning algorithm and the inductive simulated annealing learning algorithm.
The approch developed in this paper is applied to some real image data, and satisfied results are obtained. Both the moving targets in a set of infrared images and the static targets in optical images can be detected automatically. Experimental results indicate that object detection models and relative algorithms have better and robust performance.
引文
[1] Mart D著．姚国正，刘磊，汪云九译．视觉计算理论．科学出版社，1988
[2] Rumelgart D E. McClelland J L. Explorations in Paralel Distributed Processing: A Handbood of Models, Programs and Exercies. Cambridge MA: The MIT Press, 1988
[3] Churchland P D, Sejnowski T J. The Computational Brain. Cambridge, MA: MIT Press, 1992
[4] 王润生．图像理解．国防科技大学出版社，1995
[5] 赵松年，熊小芸，姚国正．同步化响应：视-脑信息处理的新发展．科学通报，1999，44(10)，1015～1025
[6] 杨雄里．视觉的神经机制．上海科学技术出版社，1996
[7] Zdelson E H et al. In Computational Models of Visual Processing. M S Landy, J. A. Movshon, ed. MIT Press, 1991:3～20.
[8] 王耀南．计算智能信息处理技术及其应用．湖南科学技术出版社，1999
[9] 蔡自兴．智能控制——基础与应用．国防工业出版社，1998
[10] Treisman A. Features and obiects: The Fourteenth Barlett Memorial Lecture. J Exp Psychol, 1988,40 A:201
[11] Hubel D H. Eye, Brain and Bision. 2nd ed. New York: Sicentific American Library, 1995
[12] 阮迪云，寿天德．神经生理学．中国科技大学出版社，1992
[13] 程相君，王春宁，陈生潭．神经网络原理及其应用．国防工业出版社，1995
[14] 寿天德．视觉信息处理的脑机制．上海科技教育出版社，1997
[15] Desimone R, Ungefieider L G. In: Boller F, Crrafrnan J eds. Handbook of Neuropsychlolgy, Vol 2. Amsterdam: Elsevier, 1989, 267～299
[16] Zeki S M. A Vision of the Brain. Oxford: Black well Scientific Publisher, 1993
[17] Singer W. Annu Rev Neurosci. 1995, 555
[18] Strogatz S H, Stewart Ⅰ. Coupled Oscillators and Bilolgical Synchronization. Scientific American, 1993, 269(6): 36～42
[19] Hopfield J J. Pattern recognition computation using action potential timing for stimulus representation. Nature, 1995, 376:33～36
[20] Navon D. Forest before Rrees: The Precedence of Global Features in Visual Perception. Cognitive Psychology, 1977, 9:353～383
[21] Chen L. Topological Structure in Visual Perception. Science, 1982, 218: 699～700
[22] Koffka K. Principles of Gestalt Psychology. New York: Harcourt, 1935
[23] 李介谷．计算机视觉的理论和实践．上海交通大学出版社，1991
[24] 吴立德．计算机视觉．复旦大学出版社，1993
[25]郑南宁．计算机视觉与模式识别．北京：国防工业出版社，1998．
[26]马颂德，张正友．计算机视觉——计算理论与算法基础．科学出版社，1998
[27]高文，陈熙霖．计算机视觉——算法与系统原理．清华大学出版社，1999
[28]朱淼良．计算机视觉．浙江大学出版社，1997
[29]章毓晋．图象工程(上册)——图象处理和分析．清华大学出版社，1999
[30]章毓晋．图象工程(下册)——图象理解与计算机视觉．清华大学出版社，2000
[31]孙即祥．数字图象处理．河北教育出版社，1993
[32]李智勇，沈振康，杨卫平，谌海新．动态图像分析．国防工业出版社，1999
[33]Serra J. Image Analysis and Mathematical Morphology. New York: Academic, 1982
[34]Serra, J. Image Analysis and Mathematical Morphology. Academic Press, London, 1988
[35]Haralick R M, Stemberg S R, Zhuang X H. Image Analysis Using Mathematical Morphology. IEEE Trans. on PAMI, 1987,(9):532～550
[36]Maragos P, et al. Morphological system for multidimensional signal processing. Proc. of IEEE, 1990,78: 690～710.
[37]Dougherty E. R, et al. Digital Image Processing Methods. Marcel Dekker, New York, 1994, 110～138.
[38]龚炜，石青云，程民德．数字空间中的数学形态学．北京：科学出版社，1997
[39]Song J, Delp E J. The analysis of morphological filters with multiple structuring elements. Computer Vision, Graphics and Image Processing, 1990,(50):308～328
[40]Pavlids T. Why progress in machine vision is so slow. Pattern Recognition Letters, 1991, 13(4): 221～225
[41]Rosenfeld A, Aloimons Y. Reply a response to "ignorance, myopia, and naviete in computer vision systems" by Jain R C and Binford T O. CVGIP:IU, 1991, 53(1): 120～124
[42]Kohonen T. Self-organization and assiciative memory,Springer-Vering,Third edition, 1989
[43]郭雷，郭宝龙．视觉神经系统与分布式推理理论．西安电子科技大学出版社，1995
[44]Paradiso M A, Nakayama K. Brightness perception snd filling-in, Vision Res. 1991(31):1221～1236
[45]Grossberg S, Wyse L. A neural network architecture for figure-ground separation of connected scenic figures. Neural Networks, 1991(4):723～742
[48]Tukey J W. Nonlinear (nonsuperposable) methods for smoothing data. In Conf. Rec.,1974 EASCON: 673
[46]吴宗凡，柳美琳，张绍举等．红外与激光技术．国防工业出版社，1998
[47]章明．视觉认知心理学．上海：华东师范大学出版社，1991
[49] Pratt W D. Digital Image Processing. New York: Wiley, 1978
[50] 袁亚湘，孙文瑜．最优化理论与方法．科学出版社，1997
[51] Bovik A C, Huang T S and Munson D C. A generalization of median filtering using linear combinations of order statistics. IEEE Trans. Acoust., Speech, Signal Procesing, 1983, vol. ASSP-31:1342～1350
[52] Arie P and Amir A. Digital image thresholding based on topological stable-state. Pattern Recognition, vol. 29(1996), No. 5:829～843
[53] Bertero M, Poggio T A. Ill-posed problems in early vision. Proc. IEEE, 1988, 76(8): 11～34
[54] 郭爱克，马颂德，齐翔林．视觉信息的群体动态时空编码和选择性注意机制．国家自然科学基金2000年重点项目简介．科学出版社，2000
[55] Davidson J L, Sun K. Template Learning in Morphological Neural Nets. SPIE, Vol.1568, 1991:176～187
[56] Davidson J. L. and F. Hummer F. Morphology neural network: An introduction with applications. IEEE Stst. Signal Processing, vol. 12, no. 2, 1993, 177～210
[57] Davidson J. L. and Talukder A. Template identification using simulated annealing in morphology neural networks. 2nd Annu. Midwest Electrotechnol. Conf., Ames, IA, IEEE Central lowa Section, Apr. 1993, 64～67
[58] Suarez-Araujo C. P. Novel neural-network models for computing homothetic invariances: An image algebra notation. J. Math. Imaging and Vision, vol. 7, no.1, 1997, 69～83.
[59] Won Y G, et al. Morphological Shared-Weight Networks with Applications to Automatic Target Recognition. IEEE Trans. Neural Networks, vol. 8, no. 5, 1997, 1195～1203
[60] Gerhard X. Ritter. Morphological Associatiative Memories. IEEE Trans. Neural Networks, vol. 9, no. 2, 1998, 281～292
[61] 李吉成，李飚，沈振康．灰度形态滤波器的神经网络实现方法．系统工程与电子技术，1999，21(3)，56～59
[62] Yu N, Wang R S. Optimal structuring element training algorithm on morphological filters. SPIE, 1999, Vol.3871:176～179
[63] Yu N. Optimization of morphological filters using genetic algorithm for image target detection. 16th IFIP World Computer Congress, 2000, 5th International Conference on Processing Proceedings, IEEE Press: 401～404
[64] Fox G C. Physical computation. Concurrency: Practice ang Experience, 1991, 3(6), 627～653
[65] 钱敏平，龚光鲁．从数学角度看计算智能．科学通报，1998，43(16)：1681～1695
[66] Hubel D H, Wiesel T N. Functional architecture macague monkey visual cortex. Proc Roy Soc, 1977B,198:1～59
[67] 赵树智，宋汉阁．科学的突破．科学出版社，1998
[68] 汪云九，崔翯，齐翔林．BP学习网络中权值的感受野型初始化研究．自然科学进展，1996，6(3)：346～350
[69] 齐翔林，汪云九，朱舜山．初级视觉信息的Gabor小波表达研究．自然科学进展，1996，6(5)：608～612
[70] Rudolph G. Convergence analysis of canonical genetic algorithms. IEEE Trans on Neural Networks, 1994, 5(1): 96～101
[71] Mahalb U et al. Genetic algorithm for optical pattern recognition Optecs Letters 1991, 16(9):648～650
[72] Bhandarkar S M. and Zhang H.. Image segmentation using evolutionary computation. IEEE Trans on Evolutionary Computauion, 1999, 3(1): 1～21
[73] Ehrhardt R. Morphological filter design with genetic algorithms. SPIE, 1994, vol. 2300:2～12
[74] Huttunen H and Kuosmanen P. Optimization of soft morphological filters by genetic algorithms. SPIE, 1994,vol.2300,13～24
[75] Srinivas M and Patnaik L M. Adaptive probabilities of crossover and mutation in genetic algorithms. IEEE Trans on Systems, Man and Cybernetecs, 1994, vol. 24(4):656～667
[76] 张讲社，徐宗本，梁怡．整体退火遗传算法及其收敛充要条件．中国科学，E辑，1997，27(2)：154～164
[77] Eren P E,et al. Robust, object-based high-resolution image reconstruction from low-resolution video. IEEE Trans. Image Processing, 1997,6(10): 1446～1451
[78] Kim S P and Su W Y. Recursive high-resolution reconstruction of blurred multiframe image. IEEE Trans. Image Processing., 1993,2(4):534～539
[79] Loce R P, Corp X, Dougherty. Optimal restoration using the morphological hitor-miss transform. SPIE, 1992, vol. 1769: 94～105
[80] Davidson J L. Simulated annealing and morphololgy neural networds. SPIE, 1992, vol. 1769:119～127
[81] Simon H A. Why should machine learn? Machine Leafing, vol. 1: 17～24
[82] Michalski R S. Understanding the natures of learning: Issues and research directions. Machine Learning, vol.2:3～25
[83] Carbonell J G. Machine Learning: Paradigms and Methods. The MIT Press, Cambridge. MA: 1990
[84] 卢美律，张渡．机器学习：理论、方法及应用．科学(双月刊)，1995，2：12～16
[85] Vapnik V N. The Nature of Statistecal Learning Theory. New York: Springer-Verlag, 1995
[86] Cortes C, Vapnic V. Support-vector networds. Machine Learning, 1995,20(3): 273～297
[87] Cherkassdy V, Mulier F. Learning from Data: Concepts, Theory and Methods. NY: john Viley & Sons, 1997
[88]黄德双．神经网络模式识别系统理论．电子工业出版社，1996
[89]Kohonen T. Self-organization and Associative Memory, Springer-Verlag Berlin Heidelberg New York, 1989
[90]赵振宇，徐用懋．模糊理论和神经网络的基础与应用．清华大学出版社,1996
[91]程兴新，曹敏．统计计算方法．北京大学出版社，1989
[92]吴翊，李永乐，胡庆军．应用数理统计．国防科技大学出版社，1995
[93]国家自然科学基金委员会．自动化科学与技术——自然科学学科发展战略调研报告．科学出版社，1995
[94]国家自然科学基金委员会．电子学与信息系统——自然科学学科发展战略调研报告．科学出版社，1995
[95]杨广文，李晓明，王义和．确定性退火技术．计算机学报，1998，8：765～768
[96]Hecht-Nielsen R. Theory of the backpropagation neural networks. Proc. of the International Joint Conference on Neural Networds, 1989, Ⅰ: 593～611
[97]Holland J H. Adaptation in Natural and Artificial Systems. The University of Michigan Press, 1975
[98]Kirkpatrick S, Gelatt Jr C C, Vecchi M P. Optimization by simulated annealing. Science, 1983:671～670
[99]Serra J. Mathematical Morphology and its Applications to Image Processing. Kluwer Academic Publishers, 1994
[100]Fang H, Gong G, Qian M P. An improved annealing method and its large time behavior. Stochastic Processes and their Appl, 1997, 71(1): 55
[101]陈继明．统一进化理论刍议．科学通报，1999，8(16)：1786～1792
[102]陈继明．再谈生物进化理论．科学通报，2000，4(8)：890～896
[103]康立山，谢云，尤矢勇等．非数值并行算法——模拟退火算法．北京：科学出版社，1998
[104]庄越挺，潘云鹤，芮勇．基于内容的图像检索综述．模式识别与人工智能，1999，12(2)：170～177
[105]Eren P E, et al. Robust, object-based high-resolution image reconstruction from low-resolution video. IEEE Trans. Image Processing, 1997,6(10): 1446～1451
[106]Kim S P and Su W Y. Recursive high-resolution reconstruction of blurred multiframe image. IEEE Trans. Image Processing, 1993,2(4):534～539
[107]勒蕃．ANN应当怎样向BNN学习．科学，1999，51(2)：3～5
[108]魏政刚，袁杰辉，蔡元龙．一种基于视觉感知的图像质量评价方法．电子学报，1999，27(4)：79～82
[109]Furht B, et al. Video and image processing in multimedia systems. Kluwer Academic Publishers, 1995: 226～270
[110]Gross M H. Koch R, Lippert L. Multiscals Image Texture Analysis in Wlvelet Spaces. Proc IEEE Int Conf on Image Proc, 1994:168～174
[111] 陈定昌等．精确制导武器发展趋势．现代防御技术，2000，28(4)：41～47
[112] 陈朝阳，张桂林，张天序．图像模糊点扩散函数的求解．中国图象图形学报，1999(A版)，4(2)：120～123
[113] Pitas Ⅰ, Venetsanopoulos A N. Nonlinear Digital Filters: Principles and Ppplications, Kluwer Academic, 1990
[114] Matheron G. Random Sets and Integral Geometry. New York: Wiley, 1975
[115] Giardina G, Dougherty E. Morphological Methods in Image and Signal Processing. Englewood Cliffs, NJ: Prentice-Hall, 1988
[116] 吴敏金．图象形态学．上海科学技术文献出版社，1991
[117] Dougherty E, et al. Mathematical Morphology in Image Processing. Eekker, New York, 1993
[118] Maragos P. Pattern Spectrum and Multiscale Shape Representation. IEEE Trans. on PAMI, 1989, 11(7): 701～716
[119] Jones R, Svalbe R. Algorithms for the Decomposition of Gray-Scale Morphological Operations. IEEE Trans. on PAMI, 1994, 16(6): 581～588
[120] Maragos P, Ziff R D. Threshold Superposition in Morphological Image Analysis Systems. IEEE Trans. on PAMI., 1990, 12(5):498～504
[121] Salembier P, Jaquenoud. Adaptive Morphological Multiresolution Decomposition. SPIE, Vol. 1568, 1991: 26～37
[122] Park H, Chin R T. Optimal Decomposition of Convex Morphological Stucturing Elements for 4-Connected Paralles Array Processors. IEEE Trans. on PAMI, 1994, 16(3): 304～313
[123] 周晓琪，袁保宗．灰度图像广义形态骨架变换．电子学报，1995，23(7)：92～94
[124] Yuille A., Vincent L, Geiger D. Statistical Morphology. SPIE, Vol. 1568, 1991: 271～282
[125] Rea J A, Longbotham H G, Kothari H N. Fuzzy Logic and Mathematical Morphology: Implementation by Stack Filters. IEEE Trans. on Signal Processing, 1996, 44(1): 142～147
[126] 崔屹．图象处理与分析——数学形态学方法及应用．科学出版社，2000
[127] 丁晓青．图象形态谱分析方法和物体形态表示．电子学报，1989，7(6)：45～54
[128] Zhuang X and Haralick R M. Morphological structuring element decomposition. CVGIP, Vol.35, 1986, No.3:370～382
[129] 国防科技参考．国防科技大学国防科技发展战略研究中心，2000(试刊号)
[130] 王建华，俞孟蕻，李众．智能控制基础．科学出版社，1998
[2] Rumelgart D E. McClelland J L. Explorations in Paralel Distributed Processing: A Handbood of Models, Programs and Exercies. Cambridge MA: The MIT Press, 1988
[3] Churchland P D, Sejnowski T J. The Computational Brain. Cambridge, MA: MIT Press, 1992
[4] 王润生．图像理解．国防科技大学出版社，1995
[5] 赵松年，熊小芸，姚国正．同步化响应：视-脑信息处理的新发展．科学通报，1999，44(10)，1015～1025
[6] 杨雄里．视觉的神经机制．上海科学技术出版社，1996
[7] Zdelson E H et al. In Computational Models of Visual Processing. M S Landy, J. A. Movshon, ed. MIT Press, 1991:3～20.
[8] 王耀南．计算智能信息处理技术及其应用．湖南科学技术出版社，1999
[9] 蔡自兴．智能控制——基础与应用．国防工业出版社，1998
[10] Treisman A. Features and obiects: The Fourteenth Barlett Memorial Lecture. J Exp Psychol, 1988,40 A:201
[11] Hubel D H. Eye, Brain and Bision. 2nd ed. New York: Sicentific American Library, 1995
[12] 阮迪云，寿天德．神经生理学．中国科技大学出版社，1992
[13] 程相君，王春宁，陈生潭．神经网络原理及其应用．国防工业出版社，1995
[14] 寿天德．视觉信息处理的脑机制．上海科技教育出版社，1997
[15] Desimone R, Ungefieider L G. In: Boller F, Crrafrnan J eds. Handbook of Neuropsychlolgy, Vol 2. Amsterdam: Elsevier, 1989, 267～299
[16] Zeki S M. A Vision of the Brain. Oxford: Black well Scientific Publisher, 1993
[17] Singer W. Annu Rev Neurosci. 1995, 555
[18] Strogatz S H, Stewart Ⅰ. Coupled Oscillators and Bilolgical Synchronization. Scientific American, 1993, 269(6): 36～42
[19] Hopfield J J. Pattern recognition computation using action potential timing for stimulus representation. Nature, 1995, 376:33～36
[20] Navon D. Forest before Rrees: The Precedence of Global Features in Visual Perception. Cognitive Psychology, 1977, 9:353～383
[21] Chen L. Topological Structure in Visual Perception. Science, 1982, 218: 699～700
[22] Koffka K. Principles of Gestalt Psychology. New York: Harcourt, 1935
[23] 李介谷．计算机视觉的理论和实践．上海交通大学出版社，1991
[24] 吴立德．计算机视觉．复旦大学出版社，1993
[25]郑南宁．计算机视觉与模式识别．北京：国防工业出版社，1998．
[26]马颂德，张正友．计算机视觉——计算理论与算法基础．科学出版社，1998
[27]高文，陈熙霖．计算机视觉——算法与系统原理．清华大学出版社，1999
[28]朱淼良．计算机视觉．浙江大学出版社，1997
[29]章毓晋．图象工程(上册)——图象处理和分析．清华大学出版社，1999
[30]章毓晋．图象工程(下册)——图象理解与计算机视觉．清华大学出版社，2000
[31]孙即祥．数字图象处理．河北教育出版社，1993
[32]李智勇，沈振康，杨卫平，谌海新．动态图像分析．国防工业出版社，1999
[33]Serra J. Image Analysis and Mathematical Morphology. New York: Academic, 1982
[34]Serra, J. Image Analysis and Mathematical Morphology. Academic Press, London, 1988
[35]Haralick R M, Stemberg S R, Zhuang X H. Image Analysis Using Mathematical Morphology. IEEE Trans. on PAMI, 1987,(9):532～550
[36]Maragos P, et al. Morphological system for multidimensional signal processing. Proc. of IEEE, 1990,78: 690～710.
[37]Dougherty E. R, et al. Digital Image Processing Methods. Marcel Dekker, New York, 1994, 110～138.
[38]龚炜，石青云，程民德．数字空间中的数学形态学．北京：科学出版社，1997
[39]Song J, Delp E J. The analysis of morphological filters with multiple structuring elements. Computer Vision, Graphics and Image Processing, 1990,(50):308～328
[40]Pavlids T. Why progress in machine vision is so slow. Pattern Recognition Letters, 1991, 13(4): 221～225
[41]Rosenfeld A, Aloimons Y. Reply a response to "ignorance, myopia, and naviete in computer vision systems" by Jain R C and Binford T O. CVGIP:IU, 1991, 53(1): 120～124
[42]Kohonen T. Self-organization and assiciative memory,Springer-Vering,Third edition, 1989
[43]郭雷，郭宝龙．视觉神经系统与分布式推理理论．西安电子科技大学出版社，1995
[44]Paradiso M A, Nakayama K. Brightness perception snd filling-in, Vision Res. 1991(31):1221～1236
[45]Grossberg S, Wyse L. A neural network architecture for figure-ground separation of connected scenic figures. Neural Networks, 1991(4):723～742
[48]Tukey J W. Nonlinear (nonsuperposable) methods for smoothing data. In Conf. Rec.,1974 EASCON: 673
[46]吴宗凡，柳美琳，张绍举等．红外与激光技术．国防工业出版社，1998
[47]章明．视觉认知心理学．上海：华东师范大学出版社，1991
[49] Pratt W D. Digital Image Processing. New York: Wiley, 1978
[50] 袁亚湘，孙文瑜．最优化理论与方法．科学出版社，1997
[51] Bovik A C, Huang T S and Munson D C. A generalization of median filtering using linear combinations of order statistics. IEEE Trans. Acoust., Speech, Signal Procesing, 1983, vol. ASSP-31:1342～1350
[52] Arie P and Amir A. Digital image thresholding based on topological stable-state. Pattern Recognition, vol. 29(1996), No. 5:829～843
[53] Bertero M, Poggio T A. Ill-posed problems in early vision. Proc. IEEE, 1988, 76(8): 11～34
[54] 郭爱克，马颂德，齐翔林．视觉信息的群体动态时空编码和选择性注意机制．国家自然科学基金2000年重点项目简介．科学出版社，2000
[55] Davidson J L, Sun K. Template Learning in Morphological Neural Nets. SPIE, Vol.1568, 1991:176～187
[56] Davidson J. L. and F. Hummer F. Morphology neural network: An introduction with applications. IEEE Stst. Signal Processing, vol. 12, no. 2, 1993, 177～210
[57] Davidson J. L. and Talukder A. Template identification using simulated annealing in morphology neural networks. 2nd Annu. Midwest Electrotechnol. Conf., Ames, IA, IEEE Central lowa Section, Apr. 1993, 64～67
[58] Suarez-Araujo C. P. Novel neural-network models for computing homothetic invariances: An image algebra notation. J. Math. Imaging and Vision, vol. 7, no.1, 1997, 69～83.
[59] Won Y G, et al. Morphological Shared-Weight Networks with Applications to Automatic Target Recognition. IEEE Trans. Neural Networks, vol. 8, no. 5, 1997, 1195～1203
[60] Gerhard X. Ritter. Morphological Associatiative Memories. IEEE Trans. Neural Networks, vol. 9, no. 2, 1998, 281～292
[61] 李吉成，李飚，沈振康．灰度形态滤波器的神经网络实现方法．系统工程与电子技术，1999，21(3)，56～59
[62] Yu N, Wang R S. Optimal structuring element training algorithm on morphological filters. SPIE, 1999, Vol.3871:176～179
[63] Yu N. Optimization of morphological filters using genetic algorithm for image target detection. 16th IFIP World Computer Congress, 2000, 5th International Conference on Processing Proceedings, IEEE Press: 401～404
[64] Fox G C. Physical computation. Concurrency: Practice ang Experience, 1991, 3(6), 627～653
[65] 钱敏平，龚光鲁．从数学角度看计算智能．科学通报，1998，43(16)：1681～1695
[66] Hubel D H, Wiesel T N. Functional architecture macague monkey visual cortex. Proc Roy Soc, 1977B,198:1～59
[67] 赵树智，宋汉阁．科学的突破．科学出版社，1998
[68] 汪云九，崔翯，齐翔林．BP学习网络中权值的感受野型初始化研究．自然科学进展，1996，6(3)：346～350
[69] 齐翔林，汪云九，朱舜山．初级视觉信息的Gabor小波表达研究．自然科学进展，1996，6(5)：608～612
[70] Rudolph G. Convergence analysis of canonical genetic algorithms. IEEE Trans on Neural Networks, 1994, 5(1): 96～101
[71] Mahalb U et al. Genetic algorithm for optical pattern recognition Optecs Letters 1991, 16(9):648～650
[72] Bhandarkar S M. and Zhang H.. Image segmentation using evolutionary computation. IEEE Trans on Evolutionary Computauion, 1999, 3(1): 1～21
[73] Ehrhardt R. Morphological filter design with genetic algorithms. SPIE, 1994, vol. 2300:2～12
[74] Huttunen H and Kuosmanen P. Optimization of soft morphological filters by genetic algorithms. SPIE, 1994,vol.2300,13～24
[75] Srinivas M and Patnaik L M. Adaptive probabilities of crossover and mutation in genetic algorithms. IEEE Trans on Systems, Man and Cybernetecs, 1994, vol. 24(4):656～667
[76] 张讲社，徐宗本，梁怡．整体退火遗传算法及其收敛充要条件．中国科学，E辑，1997，27(2)：154～164
[77] Eren P E,et al. Robust, object-based high-resolution image reconstruction from low-resolution video. IEEE Trans. Image Processing, 1997,6(10): 1446～1451
[78] Kim S P and Su W Y. Recursive high-resolution reconstruction of blurred multiframe image. IEEE Trans. Image Processing., 1993,2(4):534～539
[79] Loce R P, Corp X, Dougherty. Optimal restoration using the morphological hitor-miss transform. SPIE, 1992, vol. 1769: 94～105
[80] Davidson J L. Simulated annealing and morphololgy neural networds. SPIE, 1992, vol. 1769:119～127
[81] Simon H A. Why should machine learn? Machine Leafing, vol. 1: 17～24
[82] Michalski R S. Understanding the natures of learning: Issues and research directions. Machine Learning, vol.2:3～25
[83] Carbonell J G. Machine Learning: Paradigms and Methods. The MIT Press, Cambridge. MA: 1990
[84] 卢美律，张渡．机器学习：理论、方法及应用．科学(双月刊)，1995，2：12～16
[85] Vapnik V N. The Nature of Statistecal Learning Theory. New York: Springer-Verlag, 1995
[86] Cortes C, Vapnic V. Support-vector networds. Machine Learning, 1995,20(3): 273～297
[87] Cherkassdy V, Mulier F. Learning from Data: Concepts, Theory and Methods. NY: john Viley & Sons, 1997
[88]黄德双．神经网络模式识别系统理论．电子工业出版社，1996
[89]Kohonen T. Self-organization and Associative Memory, Springer-Verlag Berlin Heidelberg New York, 1989
[90]赵振宇，徐用懋．模糊理论和神经网络的基础与应用．清华大学出版社,1996
[91]程兴新，曹敏．统计计算方法．北京大学出版社，1989
[92]吴翊，李永乐，胡庆军．应用数理统计．国防科技大学出版社，1995
[93]国家自然科学基金委员会．自动化科学与技术——自然科学学科发展战略调研报告．科学出版社，1995
[94]国家自然科学基金委员会．电子学与信息系统——自然科学学科发展战略调研报告．科学出版社，1995
[95]杨广文，李晓明，王义和．确定性退火技术．计算机学报，1998，8：765～768
[96]Hecht-Nielsen R. Theory of the backpropagation neural networks. Proc. of the International Joint Conference on Neural Networds, 1989, Ⅰ: 593～611
[97]Holland J H. Adaptation in Natural and Artificial Systems. The University of Michigan Press, 1975
[98]Kirkpatrick S, Gelatt Jr C C, Vecchi M P. Optimization by simulated annealing. Science, 1983:671～670
[99]Serra J. Mathematical Morphology and its Applications to Image Processing. Kluwer Academic Publishers, 1994
[100]Fang H, Gong G, Qian M P. An improved annealing method and its large time behavior. Stochastic Processes and their Appl, 1997, 71(1): 55
[101]陈继明．统一进化理论刍议．科学通报，1999，8(16)：1786～1792
[102]陈继明．再谈生物进化理论．科学通报，2000，4(8)：890～896
[103]康立山，谢云，尤矢勇等．非数值并行算法——模拟退火算法．北京：科学出版社，1998
[104]庄越挺，潘云鹤，芮勇．基于内容的图像检索综述．模式识别与人工智能，1999，12(2)：170～177
[105]Eren P E, et al. Robust, object-based high-resolution image reconstruction from low-resolution video. IEEE Trans. Image Processing, 1997,6(10): 1446～1451
[106]Kim S P and Su W Y. Recursive high-resolution reconstruction of blurred multiframe image. IEEE Trans. Image Processing, 1993,2(4):534～539
[107]勒蕃．ANN应当怎样向BNN学习．科学，1999，51(2)：3～5
[108]魏政刚，袁杰辉，蔡元龙．一种基于视觉感知的图像质量评价方法．电子学报，1999，27(4)：79～82
[109]Furht B, et al. Video and image processing in multimedia systems. Kluwer Academic Publishers, 1995: 226～270
[110]Gross M H. Koch R, Lippert L. Multiscals Image Texture Analysis in Wlvelet Spaces. Proc IEEE Int Conf on Image Proc, 1994:168～174
[111] 陈定昌等．精确制导武器发展趋势．现代防御技术，2000，28(4)：41～47
[112] 陈朝阳，张桂林，张天序．图像模糊点扩散函数的求解．中国图象图形学报，1999(A版)，4(2)：120～123
[113] Pitas Ⅰ, Venetsanopoulos A N. Nonlinear Digital Filters: Principles and Ppplications, Kluwer Academic, 1990
[114] Matheron G. Random Sets and Integral Geometry. New York: Wiley, 1975
[115] Giardina G, Dougherty E. Morphological Methods in Image and Signal Processing. Englewood Cliffs, NJ: Prentice-Hall, 1988
[116] 吴敏金．图象形态学．上海科学技术文献出版社，1991
[117] Dougherty E, et al. Mathematical Morphology in Image Processing. Eekker, New York, 1993
[118] Maragos P. Pattern Spectrum and Multiscale Shape Representation. IEEE Trans. on PAMI, 1989, 11(7): 701～716
[119] Jones R, Svalbe R. Algorithms for the Decomposition of Gray-Scale Morphological Operations. IEEE Trans. on PAMI, 1994, 16(6): 581～588
[120] Maragos P, Ziff R D. Threshold Superposition in Morphological Image Analysis Systems. IEEE Trans. on PAMI., 1990, 12(5):498～504
[121] Salembier P, Jaquenoud. Adaptive Morphological Multiresolution Decomposition. SPIE, Vol. 1568, 1991: 26～37
[122] Park H, Chin R T. Optimal Decomposition of Convex Morphological Stucturing Elements for 4-Connected Paralles Array Processors. IEEE Trans. on PAMI, 1994, 16(3): 304～313
[123] 周晓琪，袁保宗．灰度图像广义形态骨架变换．电子学报，1995，23(7)：92～94
[124] Yuille A., Vincent L, Geiger D. Statistical Morphology. SPIE, Vol. 1568, 1991: 271～282
[125] Rea J A, Longbotham H G, Kothari H N. Fuzzy Logic and Mathematical Morphology: Implementation by Stack Filters. IEEE Trans. on Signal Processing, 1996, 44(1): 142～147
[126] 崔屹．图象处理与分析——数学形态学方法及应用．科学出版社，2000
[127] 丁晓青．图象形态谱分析方法和物体形态表示．电子学报，1989，7(6)：45～54
[128] Zhuang X and Haralick R M. Morphological structuring element decomposition. CVGIP, Vol.35, 1986, No.3:370～382
[129] 国防科技参考．国防科技大学国防科技发展战略研究中心，2000(试刊号)
[130] 王建华，俞孟蕻，李众．智能控制基础．科学出版社，1998