实时景物理解系统研究
摘要
本课题所研究的景物理解系统作为一种智能识别系统，可以实时对周围的景物环境变化做出反应。本课题详细研究景物理解的功能，使景物理解系统能够对摄像机所拍摄的景物图像进行处理、分析、判断，从而对景物中的人类、非人类、烟雾、火等重要信息进行识别，并发出警告信息。
首先本文介绍一种实时人形识别方法，使用这个方法，可以自动监测进入摄像机镜头拍摄范围内的物体，并识别其是否是人类。其主要步骤包括，预处理其中包含了除背景之外的其它物体的图像，即，去掉背景图像，并得到该物体的形状图像，然后提取其七个不变矩，利用贝叶斯分类器做主要手段对不变矩进行分类，另外采用辅助手段修正分类结果，识别该物体的形状是否为人形，从而判断出是否有人类经过。
本课题还详细研究了对火焰、烟雾等重要的火灾信息的检测。传统的火灾报警系统一般基于红外传感器和烟雾传感器，但在大空间场合的火灾报警中失败率较高。本文利用火焰的颜色信息，火焰的图像序列的边缘不稳定和相似性等可识别特征，实现对火焰的识别。
对于烟雾的检测本系统采用边缘检测与直方图统计相结合的方式。首先对背景图像作边缘检测，并计算背景图像边缘像素占全图像素个数的百分比，然后，对序列图像的当前帧作边缘检测，并计算图像边缘像素占全图像素个数的百分比，再将两个百分比值作比，根据最后所得比值来判断是否产生大量的烟雾。
经过大量实验证明，本课题所设计的景物理解系统的检测效果很好，误判率较低，同时本系统还具有可扩展性，可以在原有的功能基础之上增加、改进各种景物理解功能，因此可以应用于很多领域。
Scenery understanding system, which this paper researched as a kind of intelligent recognition system, may respond to the change of the surrounding scenery by real time. Our task is researching the function of scenery understanding in detail, and being able to process, analyze, judge the scenery's images which are obtained by video camera, so the scenery understanding system can recognize the important information, for example, human, non human, smoke, fire, etc, and raise the alarm.
First, we present a real-time human shape recognition method, which can monitor the object moving in the shooting scope of the video camera, and recognize the object being human or not. Following are the approaches used in this paper. First, we pretreat the image which include the other object besides background, that is ,getting rid of background image and obtain the shape image of the object. Second, we calculate the seven moment invariants of that image. Finally, we use Beyas assorting approach as main method assort the moment invariants and use other assistant methods to correct the result in order to recognize the human shape and judge whether human has passed or not.
In this paper, we also researched the recognition of fire and smoke. The traditional fire alarming system is usually based on infrared sensor and smog sensor, but if it is in big space, the lost rate is high. This paper use effective character of the fire, for example, color information, instability and comparability of the edge of image sequence to realize the automatic alarming for fire.
For the recognition of smog, the system uses the technique of integrating the edge abstracting with count histogram. First, abstract the edge of background image, and count the percentage of edge pixels in it. Second, abstract the edge of current frame image of sequence, and count the percentage of edge pixels. Finally, compare these two percentages to judge whether there is much smog or not.
Many experiments proved that this scenery comprehending system is able to work well with a low lost rate. At the same time, the system is developable, that is,
the system can be added or improved all sorts of scenery understanding functions based on original functions, so it can be applied in many fields.
首先本文介绍一种实时人形识别方法，使用这个方法，可以自动监测进入摄像机镜头拍摄范围内的物体，并识别其是否是人类。其主要步骤包括，预处理其中包含了除背景之外的其它物体的图像，即，去掉背景图像，并得到该物体的形状图像，然后提取其七个不变矩，利用贝叶斯分类器做主要手段对不变矩进行分类，另外采用辅助手段修正分类结果，识别该物体的形状是否为人形，从而判断出是否有人类经过。
本课题还详细研究了对火焰、烟雾等重要的火灾信息的检测。传统的火灾报警系统一般基于红外传感器和烟雾传感器，但在大空间场合的火灾报警中失败率较高。本文利用火焰的颜色信息，火焰的图像序列的边缘不稳定和相似性等可识别特征，实现对火焰的识别。
对于烟雾的检测本系统采用边缘检测与直方图统计相结合的方式。首先对背景图像作边缘检测，并计算背景图像边缘像素占全图像素个数的百分比，然后，对序列图像的当前帧作边缘检测，并计算图像边缘像素占全图像素个数的百分比，再将两个百分比值作比，根据最后所得比值来判断是否产生大量的烟雾。
经过大量实验证明，本课题所设计的景物理解系统的检测效果很好，误判率较低，同时本系统还具有可扩展性，可以在原有的功能基础之上增加、改进各种景物理解功能，因此可以应用于很多领域。
Scenery understanding system, which this paper researched as a kind of intelligent recognition system, may respond to the change of the surrounding scenery by real time. Our task is researching the function of scenery understanding in detail, and being able to process, analyze, judge the scenery's images which are obtained by video camera, so the scenery understanding system can recognize the important information, for example, human, non human, smoke, fire, etc, and raise the alarm.
First, we present a real-time human shape recognition method, which can monitor the object moving in the shooting scope of the video camera, and recognize the object being human or not. Following are the approaches used in this paper. First, we pretreat the image which include the other object besides background, that is ,getting rid of background image and obtain the shape image of the object. Second, we calculate the seven moment invariants of that image. Finally, we use Beyas assorting approach as main method assort the moment invariants and use other assistant methods to correct the result in order to recognize the human shape and judge whether human has passed or not.
In this paper, we also researched the recognition of fire and smoke. The traditional fire alarming system is usually based on infrared sensor and smog sensor, but if it is in big space, the lost rate is high. This paper use effective character of the fire, for example, color information, instability and comparability of the edge of image sequence to realize the automatic alarming for fire.
For the recognition of smog, the system uses the technique of integrating the edge abstracting with count histogram. First, abstract the edge of background image, and count the percentage of edge pixels in it. Second, abstract the edge of current frame image of sequence, and count the percentage of edge pixels. Finally, compare these two percentages to judge whether there is much smog or not.
Many experiments proved that this scenery comprehending system is able to work well with a low lost rate. At the same time, the system is developable, that is,
the system can be added or improved all sorts of scenery understanding functions based on original functions, so it can be applied in many fields.
引文
1 M.K.Hu. Visual pattern recognition by moment invariants. IEEE Trans. On Information Theory, Feb. 1962． IT-8:179-187．
2 Jain A K, Vailaga A. Image retrieval using color and shape. Pattern Recognition, 1996,29(8) : 1233-1244．
3 Prokop R J, Reeves A P. A Survey of moment-based techniques for unoccluded object representation and recognition. CVGIP, 1992, 9(5) :438-460．
4 Persoon E, Fu K S. Shape discrimination using Fourier descriptors. IEEE Trans Syst Man Cybern, 1977, SMC-7:388-397．
5 Rosenfeld. Digital Picture Processing. Academic Press, 1976:366-369．
6 Mitzias D A, Merzios B G. Shape rccogniton with neural classifier based on a fast polygon approximation technique. Pattern Recognition, 1994, 27(5) :627-636．
7 Loncaric S. A survey of shape analysis techniques. Pattern Recognition, 1998, 31(8) :983-1001
8 Pal N P, Pal S K. A review on image segmentation techniques. Pattern Recognition, 1993,26(9) : 1277-1294
9 Rondey A Brooks. Symbolic reasoning among 3-D models and 2-D images. Artificial Intelligence, 1981, 17:285-350
10 T.N.Tan. Locationg and Recognising Road Vehicles,Optical Engineering vol 37:1998． 1:202-207
11 Sing H. Lee. Optical implementations of digital algorithms for pattern recognition. Opt.Egn, 1986,25(1)
12 Gene R. Gindi and Arthur F. Gimtro. Optical feature extraction via the Radon transform. Opt.Eng, 1984,23(5) :499-506
13 Hyun Mug and Jae Kyung Pan. Optical/digital invariant recognition of two-dimensional patterns with straight lines. Opt.Eng, 1996,35(4) :997-1002
14 Deliang L. Wang. Object selection by oscillatory correlation. Proc. Chinese Congress on Neuro computing Science, 1997:19-24
15 Fridtjof Stein. Sturctrual indexing:efficient 2-D object recognition. IEEE Trans on PAMI,1992,14(12) : 36-38
16 Forsth D, Mundy J I, Zisscrman A, et al. Invariant descriptors for 3D object recognition and pose, IEEE Trans. PAMI, 1991,13(10) :971-991
17 Barrett E B, Brill M H, Haag N N, et al. Invariant linear methods in photogrammetry matching, Geometric Invariance in Computer Vision, Chapter 14, 1992:277-292
18 Yoshinori Kuno, Osamu Takuya, Takuya Takahashi, et al. Object recognition using multiple view invariance based on complex features. In Pro IEEE CVPR, 1996:129-134
19 Vinther S, Cipolla R. Towards 3D object model acquisition and recognition using 3D affinc Invariants. Technical Report CUED/F-1NFENG/TR136, 1993
20 Cem Yuceer, Kemal Oflazer. A rotation, scaling, and translation invariant pattern classification system. Pattern Recognition,26,687-710
21 Perantonis Stavros J, Lisboa Paulo J G. Translation, rotation, and scale invariant pattern recognition by high-order neural networks and moment classifiers. IEEE Trans. Neural Network, 1992,3:241-251
22 Bhanu B. Automatic target recognition: State of the Art Survey. IEEE Trans. On AES, 1986,22(4) :364-379
23 Pavlids T. Structural pattern recognition. Berlin: Springer-Verlag, 1977
24 Canny J. A computational approach to edge detection. IEEE Trans on PAMI, 1988
25 Matsuyama T, Hwang V. SIGMA: A Knowledge-Based Aerial Image Understanding System. Plenum. New York, 1990
26 J. Subrahmonia, D. B. Cooper and D. Keren. Practical Reliable Bayesian Recognition of 2D and 3D Object Using Implicit Polynomials and Algebraic Invariants. IEEE Trans. PAMI, 1996, 16(5) : 505-519
27 D. Forsyth, L.Mundy et al. Invariant Descriptors for 3D Object Recognition and Pose. IEEE Trans. PAMI 1991, 13(10) : 971-991
28 Bhandarkar S M and Siebert A. An Intergrated System for Range Image Understanding. International Journal of Pattern Recognition and Artificial Intelligence, 1992
29 S.R. Fountain and T.N.Tan. Efficient Rotation Invariant Texture Features for Content-Based Image Retrieval. Pattern Recognition, Vol.31, No.11:pp.1725-1732, 1998
30 刘非，唐振民，基于不变矩的实时人形监测与识别系统．小型微型计算机系统，2002
31 刘菲，曹冠华，唐振民．基于不变矩的实时人形识别研究．计算机工程，2002．9
32 姚玉荣，章毓晋．利用小波和矩进行基于形状的图像检索．中国图像图形学报，2000．5
33 唐国良，姚庆栋．基于矩特征的三维飞机目标识别．电子学报，1995．4
34 范成法，叶秀消，一个基于知识的道路图像理解系统．计算机研究与发展，1999
35 王润生，刘桂清．二维形状的层次识别．模式识别和人工智能，第五卷第四期，1992
36 舒志龙．基于视觉的感知用户界面研究．中国图像图形学报，2000．8
37 王辰．基于声、像特征的视频暴力场面的探测．小型微型计算机系统，2001．4
38 卢瑞祥．火灾的图像识别方法与应用．计算机应用研究，1998．9
39 沈俊．边界探测最佳线性算子．模式识别与人工智能，1987，1
40 丁明跃，常金玲，彭嘉雄．不变矩算法研究．数据采集与处理．1992．7：1-9
41 王海英，郭志芬．一种复杂图像目标的分割与识别．北京理工大学学报．2000．4
42 杜亚娟，潘泉．基于矩特征的三维飞机目标识别．数据采集与处理．2000．9
43 王建刚．三维物体识别及姿态测定的推理系统．机器人．1994．3
44 杨波，徐光．基于分形特征的自然景物图像分割方法．中国图像图形学报，1999．1
45 王勇，吴立德．图像恢复和边缘提取的后验均值方法．电子学报，1994
46 陈振羽，关于计算机图像理解的知识与知识表达．红外与激光工程，2000
47 佘新平．一种具有抗噪声干扰的图像边缘提取算法的研究．电子技术应用，1999
48 任文君．一种复杂背景下基于知识的目标识别方法的研究．模式识别与人工智能，1996．7
49 廖佩朝．自动目标识别器的发展现状及应用分析．红外与激光技术，1992．2：1-9
50 邢延，张天序．复杂背景下基于知识的目标识别算法研究．模式识别与人工智能，Vol．8 No．3 Sep．1995：237-239
51 刘申，金缓．模式以别图像预处理中的目标快速定位法．光电子·激光，1998．10
52 朱贵明，郭志芬．智能图像目标识别与跟踪．北京理工大学学报，1995．5
53 S Meeran，M J Pratt．二维图形特征的自动识别额，1994．9
54 田谨，许蔓苓．基于多视点不变量的三维物体识别．北京工业大学计算机学院，2000．3
55 赵正校，杨硕．基于直线边缘识别的图像区域定位算法．计算机工程，1999．9
56 王秋让，赵荣椿，郑南宁．一种航空照片中小目标识别方法．中国图像图形学报，1998．12
57 万里青，赵荣椿，孙隆和．不变性目标识别方法研究．信号处理，1996，12(2)
58 许毅，洪恩，王植桓，自动目标识别可靠性研究．激光杂志，2000，21(2)
59 苏康，金善良．智能地物景像匹配定位技术研究．红外与激光工程，2000
60 熊艳，彭嘉雄，丁明跃．基于人工智能的复杂背景中目标识别方法研究．华中理工大学学报，1996，8
61 王程，王涧生．野外复杂背景下红外图像的目标检测．红外与激光工程，2000
62 章毓晋．图像工程——图像处理和分析．清华大学出版社，2000．8
63 郑南宁．计算机视觉与模式识别．国防工业出版社，1998．3
64 夏德深，傅德胜．现代图像处理技术与应用．东南大学出版社，1997
65 边肇祺．模式识别．清华大学出版社，2000
66 夏良正．数字图像处理．东南大学出版社，1999．9
67 余英林．数字图像处理及模式识别．华南理工大学出版社，1990．10
68 王润生．图像理解．国防科技大学出版社，1995
69 章毓晋．图像工程——图像理解与计算机视觉．清华大学出版社，2000，8
70 沈庭芝，方子文．数字图像处理及模式识别．北京理工大学出版社，1998
71 马颂德，张正友．计算机视觉与计算机理论与算法基础．科学出版社，1998
72 D．马尔著，姚国正译．视觉计算理论．科学出版社，1998
73 李月景．图像识别技术及其应用．机械工业出版社，1985
74 林福宗．图像文件格式——Windows编程．清华大学出版社，1996
75 余兆明，禹志华．监控电视系统原理与设计．中国广播电视出版社，1990
76 徐建华．图像处理与分析．北京科学出版社，1992
77 杨静宇，曹雨龙．计算机图像处理及常用算法手册．南京大学出版社，1997
78 容观澳．计算机图像处理．清华大学出版社，2000
79 Kenneth.R.Castleman.Digital Image Processing．电子工业出版社，1998
80 李介谷，蔡国廉．计算机模式识别技术．上海大学出版社，1983
81 傅京孙．模式识别及其应用．科学出版社，1983
82 陈尚勤，魏鸿骏．模式识别理论及应用．成都电讯工程学院出版社，1989
83 罗耀光，盛立东．模式识别．人民邮电出版社，1989
84 荆仁杰．计算机图像处理．浙江大学出版社，1990
85 余松煜，周源华．数字图像处理．电子工业出版社，1989
86 周冠雄．计算机模式识别-结构方法．华中工学院出版社，1987
2 Jain A K, Vailaga A. Image retrieval using color and shape. Pattern Recognition, 1996,29(8) : 1233-1244．
3 Prokop R J, Reeves A P. A Survey of moment-based techniques for unoccluded object representation and recognition. CVGIP, 1992, 9(5) :438-460．
4 Persoon E, Fu K S. Shape discrimination using Fourier descriptors. IEEE Trans Syst Man Cybern, 1977, SMC-7:388-397．
5 Rosenfeld. Digital Picture Processing. Academic Press, 1976:366-369．
6 Mitzias D A, Merzios B G. Shape rccogniton with neural classifier based on a fast polygon approximation technique. Pattern Recognition, 1994, 27(5) :627-636．
7 Loncaric S. A survey of shape analysis techniques. Pattern Recognition, 1998, 31(8) :983-1001
8 Pal N P, Pal S K. A review on image segmentation techniques. Pattern Recognition, 1993,26(9) : 1277-1294
9 Rondey A Brooks. Symbolic reasoning among 3-D models and 2-D images. Artificial Intelligence, 1981, 17:285-350
10 T.N.Tan. Locationg and Recognising Road Vehicles,Optical Engineering vol 37:1998． 1:202-207
11 Sing H. Lee. Optical implementations of digital algorithms for pattern recognition. Opt.Egn, 1986,25(1)
12 Gene R. Gindi and Arthur F. Gimtro. Optical feature extraction via the Radon transform. Opt.Eng, 1984,23(5) :499-506
13 Hyun Mug and Jae Kyung Pan. Optical/digital invariant recognition of two-dimensional patterns with straight lines. Opt.Eng, 1996,35(4) :997-1002
14 Deliang L. Wang. Object selection by oscillatory correlation. Proc. Chinese Congress on Neuro computing Science, 1997:19-24
15 Fridtjof Stein. Sturctrual indexing:efficient 2-D object recognition. IEEE Trans on PAMI,1992,14(12) : 36-38
16 Forsth D, Mundy J I, Zisscrman A, et al. Invariant descriptors for 3D object recognition and pose, IEEE Trans. PAMI, 1991,13(10) :971-991
17 Barrett E B, Brill M H, Haag N N, et al. Invariant linear methods in photogrammetry matching, Geometric Invariance in Computer Vision, Chapter 14, 1992:277-292
18 Yoshinori Kuno, Osamu Takuya, Takuya Takahashi, et al. Object recognition using multiple view invariance based on complex features. In Pro IEEE CVPR, 1996:129-134
19 Vinther S, Cipolla R. Towards 3D object model acquisition and recognition using 3D affinc Invariants. Technical Report CUED/F-1NFENG/TR136, 1993
20 Cem Yuceer, Kemal Oflazer. A rotation, scaling, and translation invariant pattern classification system. Pattern Recognition,26,687-710
21 Perantonis Stavros J, Lisboa Paulo J G. Translation, rotation, and scale invariant pattern recognition by high-order neural networks and moment classifiers. IEEE Trans. Neural Network, 1992,3:241-251
22 Bhanu B. Automatic target recognition: State of the Art Survey. IEEE Trans. On AES, 1986,22(4) :364-379
23 Pavlids T. Structural pattern recognition. Berlin: Springer-Verlag, 1977
24 Canny J. A computational approach to edge detection. IEEE Trans on PAMI, 1988
25 Matsuyama T, Hwang V. SIGMA: A Knowledge-Based Aerial Image Understanding System. Plenum. New York, 1990
26 J. Subrahmonia, D. B. Cooper and D. Keren. Practical Reliable Bayesian Recognition of 2D and 3D Object Using Implicit Polynomials and Algebraic Invariants. IEEE Trans. PAMI, 1996, 16(5) : 505-519
27 D. Forsyth, L.Mundy et al. Invariant Descriptors for 3D Object Recognition and Pose. IEEE Trans. PAMI 1991, 13(10) : 971-991
28 Bhandarkar S M and Siebert A. An Intergrated System for Range Image Understanding. International Journal of Pattern Recognition and Artificial Intelligence, 1992
29 S.R. Fountain and T.N.Tan. Efficient Rotation Invariant Texture Features for Content-Based Image Retrieval. Pattern Recognition, Vol.31, No.11:pp.1725-1732, 1998
30 刘非，唐振民，基于不变矩的实时人形监测与识别系统．小型微型计算机系统，2002
31 刘菲，曹冠华，唐振民．基于不变矩的实时人形识别研究．计算机工程，2002．9
32 姚玉荣，章毓晋．利用小波和矩进行基于形状的图像检索．中国图像图形学报，2000．5
33 唐国良，姚庆栋．基于矩特征的三维飞机目标识别．电子学报，1995．4
34 范成法，叶秀消，一个基于知识的道路图像理解系统．计算机研究与发展，1999
35 王润生，刘桂清．二维形状的层次识别．模式识别和人工智能，第五卷第四期，1992
36 舒志龙．基于视觉的感知用户界面研究．中国图像图形学报，2000．8
37 王辰．基于声、像特征的视频暴力场面的探测．小型微型计算机系统，2001．4
38 卢瑞祥．火灾的图像识别方法与应用．计算机应用研究，1998．9
39 沈俊．边界探测最佳线性算子．模式识别与人工智能，1987，1
40 丁明跃，常金玲，彭嘉雄．不变矩算法研究．数据采集与处理．1992．7：1-9
41 王海英，郭志芬．一种复杂图像目标的分割与识别．北京理工大学学报．2000．4
42 杜亚娟，潘泉．基于矩特征的三维飞机目标识别．数据采集与处理．2000．9
43 王建刚．三维物体识别及姿态测定的推理系统．机器人．1994．3
44 杨波，徐光．基于分形特征的自然景物图像分割方法．中国图像图形学报，1999．1
45 王勇，吴立德．图像恢复和边缘提取的后验均值方法．电子学报，1994
46 陈振羽，关于计算机图像理解的知识与知识表达．红外与激光工程，2000
47 佘新平．一种具有抗噪声干扰的图像边缘提取算法的研究．电子技术应用，1999
48 任文君．一种复杂背景下基于知识的目标识别方法的研究．模式识别与人工智能，1996．7
49 廖佩朝．自动目标识别器的发展现状及应用分析．红外与激光技术，1992．2：1-9
50 邢延，张天序．复杂背景下基于知识的目标识别算法研究．模式识别与人工智能，Vol．8 No．3 Sep．1995：237-239
51 刘申，金缓．模式以别图像预处理中的目标快速定位法．光电子·激光，1998．10
52 朱贵明，郭志芬．智能图像目标识别与跟踪．北京理工大学学报，1995．5
53 S Meeran，M J Pratt．二维图形特征的自动识别额，1994．9
54 田谨，许蔓苓．基于多视点不变量的三维物体识别．北京工业大学计算机学院，2000．3
55 赵正校，杨硕．基于直线边缘识别的图像区域定位算法．计算机工程，1999．9
56 王秋让，赵荣椿，郑南宁．一种航空照片中小目标识别方法．中国图像图形学报，1998．12
57 万里青，赵荣椿，孙隆和．不变性目标识别方法研究．信号处理，1996，12(2)
58 许毅，洪恩，王植桓，自动目标识别可靠性研究．激光杂志，2000，21(2)
59 苏康，金善良．智能地物景像匹配定位技术研究．红外与激光工程，2000
60 熊艳，彭嘉雄，丁明跃．基于人工智能的复杂背景中目标识别方法研究．华中理工大学学报，1996，8
61 王程，王涧生．野外复杂背景下红外图像的目标检测．红外与激光工程，2000
62 章毓晋．图像工程——图像处理和分析．清华大学出版社，2000．8
63 郑南宁．计算机视觉与模式识别．国防工业出版社，1998．3
64 夏德深，傅德胜．现代图像处理技术与应用．东南大学出版社，1997
65 边肇祺．模式识别．清华大学出版社，2000
66 夏良正．数字图像处理．东南大学出版社，1999．9
67 余英林．数字图像处理及模式识别．华南理工大学出版社，1990．10
68 王润生．图像理解．国防科技大学出版社，1995
69 章毓晋．图像工程——图像理解与计算机视觉．清华大学出版社，2000，8
70 沈庭芝，方子文．数字图像处理及模式识别．北京理工大学出版社，1998
71 马颂德，张正友．计算机视觉与计算机理论与算法基础．科学出版社，1998
72 D．马尔著，姚国正译．视觉计算理论．科学出版社，1998
73 李月景．图像识别技术及其应用．机械工业出版社，1985
74 林福宗．图像文件格式——Windows编程．清华大学出版社，1996
75 余兆明，禹志华．监控电视系统原理与设计．中国广播电视出版社，1990
76 徐建华．图像处理与分析．北京科学出版社，1992
77 杨静宇，曹雨龙．计算机图像处理及常用算法手册．南京大学出版社，1997
78 容观澳．计算机图像处理．清华大学出版社，2000
79 Kenneth.R.Castleman.Digital Image Processing．电子工业出版社，1998
80 李介谷，蔡国廉．计算机模式识别技术．上海大学出版社，1983
81 傅京孙．模式识别及其应用．科学出版社，1983
82 陈尚勤，魏鸿骏．模式识别理论及应用．成都电讯工程学院出版社，1989
83 罗耀光，盛立东．模式识别．人民邮电出版社，1989
84 荆仁杰．计算机图像处理．浙江大学出版社，1990
85 余松煜，周源华．数字图像处理．电子工业出版社，1989
86 周冠雄．计算机模式识别-结构方法．华中工学院出版社，1987