基于粒子群神经网络的移动机器人门牌号码识别技术研究
|
摘要
科学技术的不断进步推动了机器人的发展，移动机器人的应用越来越广泛，对移动机器人的研究成为当今的热点之一。本文以AS-R移动机器人为平台，针对移动机器人视觉导航问题，研究了移动机器人门牌识别技术。
利用CCD传感器来感知环境信息是移动机器人视觉中的一个关键环节。但由于传感器精度、稳定性等问题，往往使得检测到的数据变得不完全、不连续、不可靠，不能准确地、全面地实现对环境的描述，因此要实现移动机器人通过摄像头来检测与识别目标是一项艰巨的任务。
本文在总结国内外移动机器人研究成果的基础上，给合本课题的实际情况，提出了一种新的门牌检测与识别方法。在检测方面，针对移动机器人在运动的过程中所拍摄到的图像的特点，提出一种基于HSI色彩空间模型的粗定位与基于边缘特征的细定位方法来实现门牌号码的定位，并利用门牌号码的轮廓特征来实现字符分割。在识别方面，考虑到门牌号码识别特殊性，提出了一种基于字符特殊节点与粒子群神经网络相结合的新方法。该方法是利用门牌数字的字符特殊节点，进行粗分类；再通过计算字符的不变矩，利用粒子群神经网络进行细分类。与传统的识别方法相比，该方法提高了对门牌识别的准确率，而且具有较好的鲁棒性。实验验证了方法的有效性。
最后利用Visual C++集成开发环境，编程实现各模块功能，进行实际系统调试。实验结果说明移动机器人能完成任务要求，并在满足实时性的前提下，能准确检识别门牌号码，验证了所提方法的可行性和有效性。
The Robot technique has been developing for the advancement of science. Nowadays, Robot has been widely used. And Mobile Robot research is one of the hottest researches in the world. This paper is based on the AS-R Robot platform to do a lot of work concerning about the Robot Visual Navigation, and the main work is how to let the Robot to recognize the door number quickly and precisely.
The use of CCD sensor to detect environment information is the key progress of the Robot Vision. But for the sensor is not precise and stabile enough that result in the data from the sensor would be not complete, not continue or uncertain, and the robot can not get the precise and complete information about the environment. That makes the Robot to detect and recognize an object become a difficult task.
In this paper, after summarize the current research on the mobile Robot and considering the specific of the problem, we put forward a new door number detection and recognition method. About the detection, considering the specific circumstance that during the movement of the mobile Robot, the image from the CCD camera has its particular character, we use the HSI color model to realize the rough location of the door number and use the edge character to realize the precise location of the door number. After the door number location, we use the contour character to make the door number segmentation come true. About the recognition, for the specialness of the door number, a new method combine with the number special node and neural network to recognize the number is presented. This method use the special node to make the rough classification; And calculates moment invariants as the neural network input to realize the precise classification. Compare with the traditional method, this method can reduce the recognition error and has a good adaptability.
This paper implements the module function under Visual C++ integrated develop environment. The experiment result shows that the robot could recognize the door number precisely in set time and shows that this method is feasible and effective.
利用CCD传感器来感知环境信息是移动机器人视觉中的一个关键环节。但由于传感器精度、稳定性等问题，往往使得检测到的数据变得不完全、不连续、不可靠，不能准确地、全面地实现对环境的描述，因此要实现移动机器人通过摄像头来检测与识别目标是一项艰巨的任务。
本文在总结国内外移动机器人研究成果的基础上，给合本课题的实际情况，提出了一种新的门牌检测与识别方法。在检测方面，针对移动机器人在运动的过程中所拍摄到的图像的特点，提出一种基于HSI色彩空间模型的粗定位与基于边缘特征的细定位方法来实现门牌号码的定位，并利用门牌号码的轮廓特征来实现字符分割。在识别方面，考虑到门牌号码识别特殊性，提出了一种基于字符特殊节点与粒子群神经网络相结合的新方法。该方法是利用门牌数字的字符特殊节点，进行粗分类；再通过计算字符的不变矩，利用粒子群神经网络进行细分类。与传统的识别方法相比，该方法提高了对门牌识别的准确率，而且具有较好的鲁棒性。实验验证了方法的有效性。
最后利用Visual C++集成开发环境，编程实现各模块功能，进行实际系统调试。实验结果说明移动机器人能完成任务要求，并在满足实时性的前提下，能准确检识别门牌号码，验证了所提方法的可行性和有效性。
The Robot technique has been developing for the advancement of science. Nowadays, Robot has been widely used. And Mobile Robot research is one of the hottest researches in the world. This paper is based on the AS-R Robot platform to do a lot of work concerning about the Robot Visual Navigation, and the main work is how to let the Robot to recognize the door number quickly and precisely.
The use of CCD sensor to detect environment information is the key progress of the Robot Vision. But for the sensor is not precise and stabile enough that result in the data from the sensor would be not complete, not continue or uncertain, and the robot can not get the precise and complete information about the environment. That makes the Robot to detect and recognize an object become a difficult task.
In this paper, after summarize the current research on the mobile Robot and considering the specific of the problem, we put forward a new door number detection and recognition method. About the detection, considering the specific circumstance that during the movement of the mobile Robot, the image from the CCD camera has its particular character, we use the HSI color model to realize the rough location of the door number and use the edge character to realize the precise location of the door number. After the door number location, we use the contour character to make the door number segmentation come true. About the recognition, for the specialness of the door number, a new method combine with the number special node and neural network to recognize the number is presented. This method use the special node to make the rough classification; And calculates moment invariants as the neural network input to realize the precise classification. Compare with the traditional method, this method can reduce the recognition error and has a good adaptability.
This paper implements the module function under Visual C++ integrated develop environment. The experiment result shows that the robot could recognize the door number precisely in set time and shows that this method is feasible and effective.
引文
1 李磊，叶涛，谭民等．移动机器人技术研究现状与未来[J]．机器人．2002，24(5)：475-480
2 马颂德，张正友．计算机视觉—计算理论与算法基础[M]．北京：科学出版社．1998：230-238
3 郑南宁．计算机视觉与模式识别[M]．北京：国防工业出版社，1998：1-3，24-31
4 周富强，张广军．一种单摄像机视觉导引方法[J]．仪器仪表学报．2006，27(9)：1130-1132
5 付梦印，谭国悦，王美玲．一种基于单目视觉的移动机器人室内导航方法[J]．光学技术．2006，32(4)：591-597
6 Marc Ebner, Andreas Zell. Centering behavior with a mobile robot using monocular foveated vision[J]. Robotics and Autonomous Systems. 2000, 32:207-218
7 谢云，杨宜民．基于单目视觉的自主足球机器人自定位研究[J]．电路与系统学报．2006，11(1)：30-34
8 汪卫红，王刚．目标追踪位置估计的单目视觉算法[J]．天津理工大学学报．2005，21(3)：42-45
9 周庆瑞，原魁，刘俊承．移动机器人视觉导航控制研究[J]．计算机工程与应用．2005．15：5-8
10 Tomono M, Yuta S. Mobile robot navigation in indoor environments using object and character recognition[J]. Proc of the 2000 IEEE Inter Conf on R&A. 2000: 313
11 祝世平，强锡富．用于摄像机定位的单目视觉方法研究[J]．光学学报．2001，21(3)：339-343
12 宋丽梅．双目立体机器视觉检测系统及其应用[J]．西南科技大学学报．2006，21(1)：30-34
13 Tanglx, Yutas. Vision based navigation for mobile robots in indoor environment by teaching and playing-back scheme[C]. Proceedings of the 2001 IEEE International Conference on robotics & Automation. Seoul, Korea. 2001:21-26
14 Yoshinoris, Tomohiron. A motion tracking by extracting 3D feature of moving object with binocular cooperative fixation[A]. Proceeding of the 2002 IEEE/RSJ Intl[C]. Lausanne. 2002, 13-18.
15 沈志华，赵英凯等．全自主机器人双目视觉运动检测研究[J]．计算机测量与控制．2006，14(1)：26-27
16 YOSHINORI S, TOMOHIRO N. A Motion Tracking by Extracting 3D Feature of Moving Object with Binocular Cooperative Fixation[A], Proceeding of the 2002 IEEE/RSJ Intl[C], Lausanne, Switzerland: IEEE/RSJIntl. 2002: 13-18.
17 LIMAA P, BONARINIA, MACHADOC C. Omnidirectional catadioptric vision for soccer robots[J]. Robotics and Autonomous Systems. 2001, 36(2): 87-102.
18 王景川，陈卫东，曹其新．基于全景视觉与里程计的移动机器人自定位方法研究[J]．机器人．2005，27(1)：41-45
19 Claude Pegard, E1 Mustapha Mouaddib. A Mobile Robot Using a Panoramic View[J]. Proceeding of the 1996 IEEE International Conference on Intelling Robotics and Automation. 1996: 89-94
20 Gaspar J, Decco C, Santos-Victor J. Constant resolution omnidirectional cameras Omnidirectional Vision, 2002. Proceedings. Third Workshop on Page(s): 27-34
21 Benosman, R. and Kang, S. B., editors. Panoramic Vision: Sensors, Theory and Applications[M]. Monographs in Computer Science Springer-Verlag. New York. 2001
22 A. Rizzi, R. Cassinis, A robot self-localization system based on omnidirectional color images[J]. Robotics and Autonomous Systems. 2001, 34: 23-38
23 D Marr. Vision: A Computational Investigation into the Human Representation and Processing of Visual Infromation[M]. Freeman, San Francisico, 1982
24 J.F. Bell Ⅲ, S. W. Squyres, K. E. Herkenhoff. The Mars Exploration Rover Athena Panoramic Camera(Pancam)Investigation[J]. 2003, 29(108):8063
25 陈小天．摄像机标定技术研究[D]．国防科技大学硕士论文．2003，12
26 潘良晨，陈卫东．室内移动机器人的视觉定位方法研究[J]．机器人．2006，28(5)：504-509
27 于秀芬，段海滨，龚华军．基于卡尔曼滤波的机器人视觉定位[J]．电光与控制．2004，11(2)：29-34．
28 刘华军，任明武，杨靖宇．一种改进的基于模糊聚类的图像分割方法[J]．中国图像图形学报．2006，11(9)：1312-1316
29 Harris C, Stephens M. A Combined Corner and Edge Detector[C]. Proceedings of 4th Alvey Vision Conference Manchester. 1988
30 LI L, CHEN W. Corner detection and interpretation on planar curves using fuzzy reasoning[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence. 1999, 21 (11): 1204-1209
31 Mikolajczyk K, Schmid C. Scale and Affine. Invariant Interest Point Detectors[J]. International Journal of Computer Vision. 2004, 60(1): 63-86
32 刘忠伟，章毓晋．综合利用颜色和纹理特征的图像检索[J]．通信学报．1999，20(5)：36-40
33 章毓晋．图像工程-图像处理与分析[M]．北京．清华大学出版社．1999
34 Hassan Y., Tazaki E., Egawa S. Rough Neural Classifier System[C]. IEEE International Conference on System Man and Cybernetics. 2002, 5
35 Zhaocong Wu. Research on Remote Sensing Image Classification Using Neural Network Based on Rough Sets[C]. International Conference on Info-tech and Info-net. Beijing. 2001, 1
36 CHAO K, SRINATH M D. Combined features of cubic B-spline wavelet moments and Zernike moments for invariant character recognition[A]. In: Proceedings of International Conference on Information Technology[C]. Las Vegas. 2001:511-515
37 Sonka M等．图像处理、分析与机器视觉[M]．北京．人民邮电出版社．2003，9
38 徐慧．Visual C++数字图像实用工程案例精选[M]．北京．人民邮电出版社．2004
39 陈兵旗，孙明．Visual C++实用图像处理专业教程[M]．北京．清华大学出版社．2004
40 Kittler J, Illingworth J. Minimum Error Thresholding[J]. Pattern Recongnition, 1994, 19(1):41-47
41 张旭，王宏安，戴国忠．面向车牌识别的区域分割技术[J]．计算机工程．2002，28(4)：113-115
42 陈黎，黄心汉，王敏等．基于聚类分析的车牌字符分割方法[J]．计算机工程与应用．2002，6：221-222，156
43 Dong-JuneLee, Seong-WhanLee. A new Methodology for Gray-Scale Character Segmentation and Recognition[J]. IEEE Trans on Pattern Analysis and Machine Intelligence. 1996, 18(10): 524-527
44 Casey Richard. G, Lecolinet Eric. A Survey of Methods and Strategies in Character Segmentation[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1996, 18(7): 690-706
45 张云刚，张长水．利用Hough变换和先验知识的车牌字符分割算法[J]．计算机学报．2004，27(1)：130-135
46 袁曾任．人工神经元网络及应用[M]．第一版．北京：清华大学出版社，1999
47 高隽．人工神经网络原理及仿真实例[M]．北京．机械工业出版社．2003
48 王玫，朱云龙，何小贤．群体智能研究综述[J]．计算机工程．2005，31(22)：194-197
49 Kennedy J, Eberhart R C. Swarm Intelligence[M]. USA: Academic Press, 2001
50 单世民，邓贵仕．群智能在知识发现中的实现方法对比研究[J]．计算机应用研究． 2006. 7:7-10
51 Dorigo M, Maniezzo V, Colorni A. Ant system: optimization by a colony of cooperating[J]. IEEE Trans on Systems, Man and Cybernetics. PartB: Cybernetics, 1996, 26 (1):29-41
52 Kennedy J, Eberhart R C. Particle swarm optimization[C]. IEEE service center IEEE int'l conf. on neural networks, Piscataway, NJ, 1995, 4: 1942-1948
53 Y.Shi, R.C.Eberhart. A modified particle swarm optimizer[J]. Proceedings of the International Joint Conference on Evolutionary Computation, 1998: 69-73.
54 熊凌，赵明旺．基于遗传算法的BP网络全局收敛的混合智能算法[J]．武汉科技大学学报．2000，23(3)：183-186．
55 高艳霞，李禹生．基于粒子群优化算法的BP神经网络在图像识别中的应用[J]．武汉工业学院学报．2006，25(4)：35-38
56 江涛，张玉芳．一种改进的粒子群算法在BP网络中的应用研究[J]．计算机科学．2006，33(9)：164-165
57 飞思科技产品研发中心．Matlab 6.5辅助优化计算与设计[M]．北京．电子工业出版社．2003
58 边肇祺，张学工．模式识别(第二版)[M]．北京．清华大学出版社．1999
59 胡小锋，赵辉．Visual C++／Matlab图像处理与识别实用案例精选[M]．北京．人民邮电出版社．2004
60 杨枝灵，王开．Visual C++数字图像获取、处理及实践应用[M]．北京．人民邮电出版社．2003
61 郑胜林，赵学军．字符识别中加权极向笔道密度特征[J]．微电子学与计算机．2004，21(6)：35-38
62 孙即祥．现代模式识别[M]．长沙．国防科技大学出版社．2001
63 高珊，刘万春，朱玉文．基于SVM的车牌字符分割和识别方法[J]．微电子学与计算机．2005，22(6)：34-37
64 路小波，凌小静，刘斌．基于组合特征的车牌字符识别[J]．仪器仪表学报．2006，27(6)：698-702
65 张鸽，陈书开．基于SVM的手写体阿拉伯数字识别[J]．军民两用技术与产品．2005，9：41-44
66 Nello Cristianini, John Shawe Taylor. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods[M]. Publishing House of Electronics Industry. 2004
67 Hu M K. Visual patterm recognition by moment invariants[J]. IRETrans Information Theory，1962，IT(8)：pp．179-187
68 王耀明．图像的矩函数[M]．上海．华东理工大学出版社．2002．
69 候小静．贝叶斯分类器研究及其在Web文档分类中的应用[D]．郑州大学硕士学位论文．2005
70 芮同林．人脸识别与特征提取[D]．西北工业大学硕士学位论文．2006
71 张志刚．基于神经网络／HMM的语音识别算法的研究[D]．武汉理工大学硕士学位论文．2006
72 邹文辉．改进的RBF神经网络及其在字符识别中的应用[D]．四川大学硕士学位论文．2005
2 马颂德，张正友．计算机视觉—计算理论与算法基础[M]．北京：科学出版社．1998：230-238
3 郑南宁．计算机视觉与模式识别[M]．北京：国防工业出版社，1998：1-3，24-31
4 周富强，张广军．一种单摄像机视觉导引方法[J]．仪器仪表学报．2006，27(9)：1130-1132
5 付梦印，谭国悦，王美玲．一种基于单目视觉的移动机器人室内导航方法[J]．光学技术．2006，32(4)：591-597
6 Marc Ebner, Andreas Zell. Centering behavior with a mobile robot using monocular foveated vision[J]. Robotics and Autonomous Systems. 2000, 32:207-218
7 谢云，杨宜民．基于单目视觉的自主足球机器人自定位研究[J]．电路与系统学报．2006，11(1)：30-34
8 汪卫红，王刚．目标追踪位置估计的单目视觉算法[J]．天津理工大学学报．2005，21(3)：42-45
9 周庆瑞，原魁，刘俊承．移动机器人视觉导航控制研究[J]．计算机工程与应用．2005．15：5-8
10 Tomono M, Yuta S. Mobile robot navigation in indoor environments using object and character recognition[J]. Proc of the 2000 IEEE Inter Conf on R&A. 2000: 313
11 祝世平，强锡富．用于摄像机定位的单目视觉方法研究[J]．光学学报．2001，21(3)：339-343
12 宋丽梅．双目立体机器视觉检测系统及其应用[J]．西南科技大学学报．2006，21(1)：30-34
13 Tanglx, Yutas. Vision based navigation for mobile robots in indoor environment by teaching and playing-back scheme[C]. Proceedings of the 2001 IEEE International Conference on robotics & Automation. Seoul, Korea. 2001:21-26
14 Yoshinoris, Tomohiron. A motion tracking by extracting 3D feature of moving object with binocular cooperative fixation[A]. Proceeding of the 2002 IEEE/RSJ Intl[C]. Lausanne. 2002, 13-18.
15 沈志华，赵英凯等．全自主机器人双目视觉运动检测研究[J]．计算机测量与控制．2006，14(1)：26-27
16 YOSHINORI S, TOMOHIRO N. A Motion Tracking by Extracting 3D Feature of Moving Object with Binocular Cooperative Fixation[A], Proceeding of the 2002 IEEE/RSJ Intl[C], Lausanne, Switzerland: IEEE/RSJIntl. 2002: 13-18.
17 LIMAA P, BONARINIA, MACHADOC C. Omnidirectional catadioptric vision for soccer robots[J]. Robotics and Autonomous Systems. 2001, 36(2): 87-102.
18 王景川，陈卫东，曹其新．基于全景视觉与里程计的移动机器人自定位方法研究[J]．机器人．2005，27(1)：41-45
19 Claude Pegard, E1 Mustapha Mouaddib. A Mobile Robot Using a Panoramic View[J]. Proceeding of the 1996 IEEE International Conference on Intelling Robotics and Automation. 1996: 89-94
20 Gaspar J, Decco C, Santos-Victor J. Constant resolution omnidirectional cameras Omnidirectional Vision, 2002. Proceedings. Third Workshop on Page(s): 27-34
21 Benosman, R. and Kang, S. B., editors. Panoramic Vision: Sensors, Theory and Applications[M]. Monographs in Computer Science Springer-Verlag. New York. 2001
22 A. Rizzi, R. Cassinis, A robot self-localization system based on omnidirectional color images[J]. Robotics and Autonomous Systems. 2001, 34: 23-38
23 D Marr. Vision: A Computational Investigation into the Human Representation and Processing of Visual Infromation[M]. Freeman, San Francisico, 1982
24 J.F. Bell Ⅲ, S. W. Squyres, K. E. Herkenhoff. The Mars Exploration Rover Athena Panoramic Camera(Pancam)Investigation[J]. 2003, 29(108):8063
25 陈小天．摄像机标定技术研究[D]．国防科技大学硕士论文．2003，12
26 潘良晨，陈卫东．室内移动机器人的视觉定位方法研究[J]．机器人．2006，28(5)：504-509
27 于秀芬，段海滨，龚华军．基于卡尔曼滤波的机器人视觉定位[J]．电光与控制．2004，11(2)：29-34．
28 刘华军，任明武，杨靖宇．一种改进的基于模糊聚类的图像分割方法[J]．中国图像图形学报．2006，11(9)：1312-1316
29 Harris C, Stephens M. A Combined Corner and Edge Detector[C]. Proceedings of 4th Alvey Vision Conference Manchester. 1988
30 LI L, CHEN W. Corner detection and interpretation on planar curves using fuzzy reasoning[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence. 1999, 21 (11): 1204-1209
31 Mikolajczyk K, Schmid C. Scale and Affine. Invariant Interest Point Detectors[J]. International Journal of Computer Vision. 2004, 60(1): 63-86
32 刘忠伟，章毓晋．综合利用颜色和纹理特征的图像检索[J]．通信学报．1999，20(5)：36-40
33 章毓晋．图像工程-图像处理与分析[M]．北京．清华大学出版社．1999
34 Hassan Y., Tazaki E., Egawa S. Rough Neural Classifier System[C]. IEEE International Conference on System Man and Cybernetics. 2002, 5
35 Zhaocong Wu. Research on Remote Sensing Image Classification Using Neural Network Based on Rough Sets[C]. International Conference on Info-tech and Info-net. Beijing. 2001, 1
36 CHAO K, SRINATH M D. Combined features of cubic B-spline wavelet moments and Zernike moments for invariant character recognition[A]. In: Proceedings of International Conference on Information Technology[C]. Las Vegas. 2001:511-515
37 Sonka M等．图像处理、分析与机器视觉[M]．北京．人民邮电出版社．2003，9
38 徐慧．Visual C++数字图像实用工程案例精选[M]．北京．人民邮电出版社．2004
39 陈兵旗，孙明．Visual C++实用图像处理专业教程[M]．北京．清华大学出版社．2004
40 Kittler J, Illingworth J. Minimum Error Thresholding[J]. Pattern Recongnition, 1994, 19(1):41-47
41 张旭，王宏安，戴国忠．面向车牌识别的区域分割技术[J]．计算机工程．2002，28(4)：113-115
42 陈黎，黄心汉，王敏等．基于聚类分析的车牌字符分割方法[J]．计算机工程与应用．2002，6：221-222，156
43 Dong-JuneLee, Seong-WhanLee. A new Methodology for Gray-Scale Character Segmentation and Recognition[J]. IEEE Trans on Pattern Analysis and Machine Intelligence. 1996, 18(10): 524-527
44 Casey Richard. G, Lecolinet Eric. A Survey of Methods and Strategies in Character Segmentation[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1996, 18(7): 690-706
45 张云刚，张长水．利用Hough变换和先验知识的车牌字符分割算法[J]．计算机学报．2004，27(1)：130-135
46 袁曾任．人工神经元网络及应用[M]．第一版．北京：清华大学出版社，1999
47 高隽．人工神经网络原理及仿真实例[M]．北京．机械工业出版社．2003
48 王玫，朱云龙，何小贤．群体智能研究综述[J]．计算机工程．2005，31(22)：194-197
49 Kennedy J, Eberhart R C. Swarm Intelligence[M]. USA: Academic Press, 2001
50 单世民，邓贵仕．群智能在知识发现中的实现方法对比研究[J]．计算机应用研究． 2006. 7:7-10
51 Dorigo M, Maniezzo V, Colorni A. Ant system: optimization by a colony of cooperating[J]. IEEE Trans on Systems, Man and Cybernetics. PartB: Cybernetics, 1996, 26 (1):29-41
52 Kennedy J, Eberhart R C. Particle swarm optimization[C]. IEEE service center IEEE int'l conf. on neural networks, Piscataway, NJ, 1995, 4: 1942-1948
53 Y.Shi, R.C.Eberhart. A modified particle swarm optimizer[J]. Proceedings of the International Joint Conference on Evolutionary Computation, 1998: 69-73.
54 熊凌，赵明旺．基于遗传算法的BP网络全局收敛的混合智能算法[J]．武汉科技大学学报．2000，23(3)：183-186．
55 高艳霞，李禹生．基于粒子群优化算法的BP神经网络在图像识别中的应用[J]．武汉工业学院学报．2006，25(4)：35-38
56 江涛，张玉芳．一种改进的粒子群算法在BP网络中的应用研究[J]．计算机科学．2006，33(9)：164-165
57 飞思科技产品研发中心．Matlab 6.5辅助优化计算与设计[M]．北京．电子工业出版社．2003
58 边肇祺，张学工．模式识别(第二版)[M]．北京．清华大学出版社．1999
59 胡小锋，赵辉．Visual C++／Matlab图像处理与识别实用案例精选[M]．北京．人民邮电出版社．2004
60 杨枝灵，王开．Visual C++数字图像获取、处理及实践应用[M]．北京．人民邮电出版社．2003
61 郑胜林，赵学军．字符识别中加权极向笔道密度特征[J]．微电子学与计算机．2004，21(6)：35-38
62 孙即祥．现代模式识别[M]．长沙．国防科技大学出版社．2001
63 高珊，刘万春，朱玉文．基于SVM的车牌字符分割和识别方法[J]．微电子学与计算机．2005，22(6)：34-37
64 路小波，凌小静，刘斌．基于组合特征的车牌字符识别[J]．仪器仪表学报．2006，27(6)：698-702
65 张鸽，陈书开．基于SVM的手写体阿拉伯数字识别[J]．军民两用技术与产品．2005，9：41-44
66 Nello Cristianini, John Shawe Taylor. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods[M]. Publishing House of Electronics Industry. 2004
67 Hu M K. Visual patterm recognition by moment invariants[J]. IRETrans Information Theory，1962，IT(8)：pp．179-187
68 王耀明．图像的矩函数[M]．上海．华东理工大学出版社．2002．
69 候小静．贝叶斯分类器研究及其在Web文档分类中的应用[D]．郑州大学硕士学位论文．2005
70 芮同林．人脸识别与特征提取[D]．西北工业大学硕士学位论文．2006
71 张志刚．基于神经网络／HMM的语音识别算法的研究[D]．武汉理工大学硕士学位论文．2006
72 邹文辉．改进的RBF神经网络及其在字符识别中的应用[D]．四川大学硕士学位论文．2005