基于综合特征的牌照定位与字符分割技术研究
|
摘要
车辆牌照的自动识别是数字图像处理技术与模式识别技术在交通信息系统中的重要应用。随着交通管理信息化的快速发展，车辆牌照识别技术已经成为当前研究的一项重要课题。由于现实环境中各种不可预知的因素，例如光线的变化、牌照的倾斜、牌照在图像中大小及位置的不确定性、复杂的干扰背景等，都给牌照的识别增加了很大的难度。从目前的研究成果来看，车辆牌照识别系统还远未达到完善的程度，利用各种图像处理的新理论和新方法仍是当前研究的热点之一。
在车辆牌照识别系统中，牌照的定位是最为关键的环节。为了寻找一种适应性优异的牌照定位方法，论文对数学形态学闭开运算和滤波运算、图像边缘检测算法以及基于HSV(Hue、Saturation、Value)颜色模型的色彩分析等图像处理技术做了仔细的研究与实现。对各种形态运算模板尺度的动态选取、各种边缘梯度算子的效果检测以及不同光照条件下基于区间阀值的色彩的判别等关键环节作了细致分析，并通过大量图片对分析结果进行了反复实验验证。在此基础上，提出了一种利用牌照的纹理、颜色及体态等综合特征进行牌照定位的新方法。实验结果表明，该方法在各种光照和复杂背景条件下均有很好的适应性，对牌照定位有很高的准确性。
牌照字符切分效果的好坏对后续字符识别所采用的算法与识别准确度有着重要的影响。为了减少字符识别的复杂程度，论文对字符的精确切分也提出了一系列有效的预处理方法，包括基于直线拟合与角度探测法的牌照水平及垂直倾斜校正、基于彩色投影法的牌照背景纹理过滤、基于二值投影阀值处理的非字符区域的剔除等。最终分割出的牌照字符有较好的效果，为模板匹配等简单快速的字符识别方法提供了良好的前提。
论文提出的牌照定位方法对牌照的纹理、体态及彩色特征作了充分考虑并加以综合利用，避免了以往定位方法对复杂环境适应性差的弊端。提出的多重字符分割预处理方法能够对各种不良状况的牌照加以改善，使分割出的字符效果具有最小的几何形变，减少了以往方法由于粗略分割所造成的后续字符识别率的下降。
Vehicle License Plate Recognition (VLPR) is an important application of digital image processing and pattern recognition in the transportation information system. With the fast development of transportation information system, VLPR has become an important research subject nowadays. In real conditions, a variety of causation would made License Plate Recognition more difficult, such as variety in illumination conditions, sloping license plate, the uncertainty of size and position of license plate in the captured image, the complex of image background, and etc. Current technique of License Plate Recognition is far away from perfect. Using new theory and new technology to reform license plate recognition technique is one of the research keys.
License plate's location is the key of VLPR system. To find out a highly adaptive plate's location method, mathematical morphology close and open operation, image edge detect and color analysis based on HSV (Hue, Saturation, Value) model are researched and realized. And a series of key steps of plate's location are carefully analyzed and experimented with a mount of plate images too, including calculating dynamic size of the morphology template, validating effects of a variety of image edge detect operators, color distinguish method based on range threshold. Based on these work, a new plate location method using plate's texture, shape, color characteristics was proposed. The experimental results show that the method has strong adaptability to unconstrained illumination conditions and irregular background, and is efficient in locating license plate.
The result of characters segmentation has remarkable effect on the choosing of the character recognition algorithm and the accuracy of character recognition. To reduced to the complexity of chars segmentation, paper brought forward a series of pretreatment methods to the retrieved plate, including using line imitate method and angle detect method to correct the plate's slope angle, using color projection method to eliminate conglutinative texture edge, and using bi-value image project method to eliminate plate's rivets and frame. The multiple pretreatments result in the favorable outcome, and provided the better preconditions for simple characters
recognition method that based on template match. The VLPR location method proposed in this paper fully considers and utilizes the texture, shape and color features of VLPR in VLPR location, and has better adaptability than the method used before. The proposed multiple pretreatments method can effectively mend unfavorable VLPR, based on the mended VLPR, the final segmented characters has less distortion than coarse segmentation method, and can increase accuracy of characters recognition.
在车辆牌照识别系统中，牌照的定位是最为关键的环节。为了寻找一种适应性优异的牌照定位方法，论文对数学形态学闭开运算和滤波运算、图像边缘检测算法以及基于HSV(Hue、Saturation、Value)颜色模型的色彩分析等图像处理技术做了仔细的研究与实现。对各种形态运算模板尺度的动态选取、各种边缘梯度算子的效果检测以及不同光照条件下基于区间阀值的色彩的判别等关键环节作了细致分析，并通过大量图片对分析结果进行了反复实验验证。在此基础上，提出了一种利用牌照的纹理、颜色及体态等综合特征进行牌照定位的新方法。实验结果表明，该方法在各种光照和复杂背景条件下均有很好的适应性，对牌照定位有很高的准确性。
牌照字符切分效果的好坏对后续字符识别所采用的算法与识别准确度有着重要的影响。为了减少字符识别的复杂程度，论文对字符的精确切分也提出了一系列有效的预处理方法，包括基于直线拟合与角度探测法的牌照水平及垂直倾斜校正、基于彩色投影法的牌照背景纹理过滤、基于二值投影阀值处理的非字符区域的剔除等。最终分割出的牌照字符有较好的效果，为模板匹配等简单快速的字符识别方法提供了良好的前提。
论文提出的牌照定位方法对牌照的纹理、体态及彩色特征作了充分考虑并加以综合利用，避免了以往定位方法对复杂环境适应性差的弊端。提出的多重字符分割预处理方法能够对各种不良状况的牌照加以改善，使分割出的字符效果具有最小的几何形变，减少了以往方法由于粗略分割所造成的后续字符识别率的下降。
Vehicle License Plate Recognition (VLPR) is an important application of digital image processing and pattern recognition in the transportation information system. With the fast development of transportation information system, VLPR has become an important research subject nowadays. In real conditions, a variety of causation would made License Plate Recognition more difficult, such as variety in illumination conditions, sloping license plate, the uncertainty of size and position of license plate in the captured image, the complex of image background, and etc. Current technique of License Plate Recognition is far away from perfect. Using new theory and new technology to reform license plate recognition technique is one of the research keys.
License plate's location is the key of VLPR system. To find out a highly adaptive plate's location method, mathematical morphology close and open operation, image edge detect and color analysis based on HSV (Hue, Saturation, Value) model are researched and realized. And a series of key steps of plate's location are carefully analyzed and experimented with a mount of plate images too, including calculating dynamic size of the morphology template, validating effects of a variety of image edge detect operators, color distinguish method based on range threshold. Based on these work, a new plate location method using plate's texture, shape, color characteristics was proposed. The experimental results show that the method has strong adaptability to unconstrained illumination conditions and irregular background, and is efficient in locating license plate.
The result of characters segmentation has remarkable effect on the choosing of the character recognition algorithm and the accuracy of character recognition. To reduced to the complexity of chars segmentation, paper brought forward a series of pretreatment methods to the retrieved plate, including using line imitate method and angle detect method to correct the plate's slope angle, using color projection method to eliminate conglutinative texture edge, and using bi-value image project method to eliminate plate's rivets and frame. The multiple pretreatments result in the favorable outcome, and provided the better preconditions for simple characters
recognition method that based on template match. The VLPR location method proposed in this paper fully considers and utilizes the texture, shape and color features of VLPR in VLPR location, and has better adaptability than the method used before. The proposed multiple pretreatments method can effectively mend unfavorable VLPR, based on the mended VLPR, the final segmented characters has less distortion than coarse segmentation method, and can increase accuracy of characters recognition.
引文
[1] J.Barroso, A. Rafael, et al. Number plate reading using computer vision. In Proc. IEEE International Symposium on Industrial Electronics(ISIE).Portuugal.761～766
[2] R. Parisi, et al. Car Plate Recognition by Neural Networks and Image Processing. In Proc. IEEE International Symposium on Circuits and Systems,USA,2000,May 31-June 3.
[3] Coetzee C, Botha C, Weber D.PC-based number plate recognition system. Proceedings of IEEE International symposium on industrial electrortics,Pretoria: IEEE Press.1998: pp: 605～610
[4] Kanayame K. et al. Development of Vehicle-License Number Recognition System Using Real-time Image Processing and Its Application to Travel Time Measurement.Proceedings of 41 st IEEE Vehicular Technology Conference. 1991,pp.798～840
[5] Dai Yan, Ma Hong-Qing,Liu Ji-Lin.A high performance license plate recognition system based on Web technique.Proceedings of 2001 IEEE Intelligent Transportation Systems Conference Proceedings-Oakland (CA), USA, 2001.325～329
[6] Liu Ji-Lin, Songjia-Tao.Vehicle.License Plate Recognition System with High Performance. ACTA AUTOMATICA SINICA.2003, 29(3): pp.457～465
[7] Moris, Suen C Y, Yamamoto K.Historical review of OCR research and development.Proceedings of the IEEE.1992, 80(7): pp: 1029～1058
[8] Granieri M N,Stabile F,Comelli P.Recognition of Motor Vechicle License Plates in Rear-View Images.In:Sanz J L C,ed. Image Technology.Coordinated Sience Laboratory,University of Illineis at Urbana.USA, 1998,231-252.
[9] Setchell J. Applications of Computer Vision to Road-Traffic Monitoring.PH.D Thesis.University of Bristol,England, 1999,66-81.
[10] Poon J C H,et al.A Robust vision system for vehicle license plate recognition using gray-scale morphology. In:Proceedings of the 1995 IEEE
International Symposium.on Industrial Electronics,NJ,USA:IEEE. 199,Part 1(of 2):394-399.
[11] 郭捷，施鹏飞．基于颜色和纹理分析的牌照分析牌照定位方法．中国图形图像报．2002．7(5)：pp．472～476
[12] 左奇，史忠科．一种基于数学形态学的实时牌照图象分割方法．中国图形图像学报．2003．8：pp．281～285
[13] 戴青云，余英林．一种基于小波与形态学的牌照图像分割方法．中国图形图像学报．2000．5：pp．411～415
[14] 陈锻生，谢志鹏，刘征凯．复杂背景下彩色图像牌照提取与字符分割．小型微型计算机系统．2002．23(9)：pp．1144～1148
[15] 赵雪春，戚飞虎．基于彩色分割的牌照自动识别技术．上海交通大学学报．1998，32(10)：PP．4～9
[16] 张引，潘云鹤．彩色汽车图像牌照定位新方法．中国图形图像学报．2001，6(4)：PP．374～377
[17] 牛欣，沈兰荪．汽牌照照识别技术的研究．测控技术．1999，21(5)：pp．35～38
[18] 王昱，赵正校等．基于样本线搜索和霍夫变换的区域定位算法．红外与激光工程．1999，28(4)：pp．16～20
[19] 张玉娇，史忠科．牌照提取方法研究．西北工业大学学报．2003，21(1)：pp．34～37
[20] 郑翔，黄艺云．经典边缘检测模板的快速算法．信号处理．1995，11(4)：pp．317～320
[21] 李炜，黄心汉．牌照自动识别系统中牌照分割的研究．信号处理．2000．16：pp．41～44
[22] 崔江，王友仁．牌照自动识别方法中的关键技术研究计算机测量与控制．2003．11(4)：PP．260～262
[23] 洛雪超，刘贵雄等．一种基于车辆特征信息的牌照识别方法．华南理工大学学报．2003，31(4)：pp．70～73
[24] 李小平，任江兴，杨德刚．牌照识别系统中若干问题的探讨．北京理工大学学报．2001，21(1)：PP．116～119
[25] 富煜清，沈巍，黄心晔．汽牌照照的提取方法研究．模式识别与人工智
能．2000，13(3)：PP．345～348
[26] 刘效静，成瑜．汽牌照照自动识别技术研究．南京航空航天大学学报．1998，30(5)：PP．573～576
[27] 赵海燕，裴志利．基于牌照颜色变化剧烈特征的彩色牌照定位新方法．内蒙古民族大学学报(自然科学版)．2002，17(6)：pp．500～502
[28] 付仲良，黄书强等．货车图像牌照区快速定位及字符切割算法．计算机工程与设计．2003，24(1)：PP．77～79
[29] 曹刚，游志胜．一种基于自适应能量滤波的快速牌照定位方法光电子·激光．2003，14(5)：PP．523～525
[30] 郭大波，陈礼明．基于牌照底色识别的牌照定位方法．2003．24(5)：pp．81～84
[31] N.R.Pal and S.K.Pal, "A Review on Image Segmentation Techiniques", Pattern Recognition, 1993,26(9):pp.1,277～1,294
[32] Nikhil R. Pal et al.,A Review on Image Segmentation Techniques,Pattern Recognition, Vol.26, No.9:pp. 1277～1294, 1993
[33] P.K.Sahoo et al., Asurvey of Threshold Techniques, Computer Vision, Graphics, and Image Processing 29:pp. 100～132(1988)
[34] P.K.Sahoo, S.Soltani, A.K.C. Wong, and Y.C.Chen, "A Survey of Thresholding Techniques", Computer Graphics,Vision and Image Processing 1988(41):pp.233～260
[35] Makoto Miyahara, Yasuhiro Yashid. Mathematical transform(R,G,B) color data to Munsell(H,V,C) color data [A].In Visual Communications and Image Processing 88'SP IE [C].Cambridge, Massachusetts USA, 1988:pp.650～657.
[36] Wezka J S, Rosenfeld A. Histogram modification for threshold selection. IEEE Trans, 1979; SMC-9(1):pp.38～52.
[37] Chaudhuri, B.B,Sarkar,N., 1995.Texture segmentation using fractal dimension. IEEE Trans.Pattern Anal.Machine Intel.17: pp.72-77.
[38] Birchfield, S. Elliptical head tracking using intensity gradients and color histograms. In: Proceedings of the IEEE Conference on CV PR'98. Santa Barbara, CA, 1998.232～237.
[39] 张引．基于空间分布的最大类间方差牌照图像二值化算法．浙江大学学报．2001，35(3)：pp．272～275
[40] 吴传孙，邹扬德等．二值化算法在牌照识别中的应用．计算机与现代化．2003，6：pp．13～16
[41] 陈黎，黄心汉等．基于聚类分析的牌照字符分割方法．计算机工程与应用．2002，6：pp．．221～222
[42] 张玉娇，史忠科．一种新的牌照预处理算法．西北工业大学学报．2002，20(1)：PP．83～86
[43] 周妮娜，王敏等．牌照字符识别的预处理算法．计算机工程与应用．2003，15：pp．220～232
[44] 刘健庄，栗文表．灰度图象的二维Otsu自动阀值分割法．自动化学报．1991，19(1)：pp．101～105
[45] 吴全，朱兆达．“图像处理中灰度级阈值选取方法30年(1962-1992)的进展(一)”，数据采集与处理．1993，8(3-4)：PP．193～201
[46] 罗希平等．图像分割方法综述．模式识别与人工智能．1999，12(3)：PP．301～312
[47] 孟章荣．各种颜色模型选用需求分析．中国图像图形学报．1996，1(3)：PP．238～241．
[48] 刘文萍，吴立德．图像分割中阈值选取方法比较研究．模式识别与人工智能．1997，10(3)：PP．271～277
[49] 郑南宁，刘建勤．基于区域特征的自适应图像分割方法．电子学报．1995，7：pp．98～101
[50] 潘晨．阈值分割与颜色聚类相结合的色度学图象分割方法．计算机应用研究．2001，12：pp．53～55
[51] 黄晓东，周源华．用小波变换及颜色聚类提取的视频图像内中文字幕．计算机工程．2003，29(1)：pp．43～44
[52] 张丽，毕岗等．HSV空间自适应背景模板在运动车辆实时检测中的应用．公路交通科技．2003，20(4)：PP．88～91
[53] 刘湘滨，邹北冀．一种新的颜色聚类算法及其图象检索．计算机工程与应用．2001，13：pp．126～128
[54] Feng Yuan. Windows Graphics Programming. Prentice Hall PTR.2000
[55] Rafael C.Gonzalez,Richard E.Woods．《数字图像处理》，电子工业出版社．2003
[56] 章晋．《图像处理和分析》．清华大学出版社．1999
[57] Kenneth R.Castleman．《数字图像处理》．清华大学出版社．1998
[58] 崔屹．《数字图像处理技术及应用》．电子工业出版社．1997
[59] 龚炜，石青云等．《数字空间中的数学形态学—理论及应用》．科学出版社．1997
[60] 贾云得．《机器视觉》．科学出版社．2000
[61] 赵荣椿等．《数字图象处理导论》．西北工业大学出版社．2000
[62] 边肇祺．《模式识别》．清华大学出版社．1987
[2] R. Parisi, et al. Car Plate Recognition by Neural Networks and Image Processing. In Proc. IEEE International Symposium on Circuits and Systems,USA,2000,May 31-June 3.
[3] Coetzee C, Botha C, Weber D.PC-based number plate recognition system. Proceedings of IEEE International symposium on industrial electrortics,Pretoria: IEEE Press.1998: pp: 605～610
[4] Kanayame K. et al. Development of Vehicle-License Number Recognition System Using Real-time Image Processing and Its Application to Travel Time Measurement.Proceedings of 41 st IEEE Vehicular Technology Conference. 1991,pp.798～840
[5] Dai Yan, Ma Hong-Qing,Liu Ji-Lin.A high performance license plate recognition system based on Web technique.Proceedings of 2001 IEEE Intelligent Transportation Systems Conference Proceedings-Oakland (CA), USA, 2001.325～329
[6] Liu Ji-Lin, Songjia-Tao.Vehicle.License Plate Recognition System with High Performance. ACTA AUTOMATICA SINICA.2003, 29(3): pp.457～465
[7] Moris, Suen C Y, Yamamoto K.Historical review of OCR research and development.Proceedings of the IEEE.1992, 80(7): pp: 1029～1058
[8] Granieri M N,Stabile F,Comelli P.Recognition of Motor Vechicle License Plates in Rear-View Images.In:Sanz J L C,ed. Image Technology.Coordinated Sience Laboratory,University of Illineis at Urbana.USA, 1998,231-252.
[9] Setchell J. Applications of Computer Vision to Road-Traffic Monitoring.PH.D Thesis.University of Bristol,England, 1999,66-81.
[10] Poon J C H,et al.A Robust vision system for vehicle license plate recognition using gray-scale morphology. In:Proceedings of the 1995 IEEE
International Symposium.on Industrial Electronics,NJ,USA:IEEE. 199,Part 1(of 2):394-399.
[11] 郭捷，施鹏飞．基于颜色和纹理分析的牌照分析牌照定位方法．中国图形图像报．2002．7(5)：pp．472～476
[12] 左奇，史忠科．一种基于数学形态学的实时牌照图象分割方法．中国图形图像学报．2003．8：pp．281～285
[13] 戴青云，余英林．一种基于小波与形态学的牌照图像分割方法．中国图形图像学报．2000．5：pp．411～415
[14] 陈锻生，谢志鹏，刘征凯．复杂背景下彩色图像牌照提取与字符分割．小型微型计算机系统．2002．23(9)：pp．1144～1148
[15] 赵雪春，戚飞虎．基于彩色分割的牌照自动识别技术．上海交通大学学报．1998，32(10)：PP．4～9
[16] 张引，潘云鹤．彩色汽车图像牌照定位新方法．中国图形图像学报．2001，6(4)：PP．374～377
[17] 牛欣，沈兰荪．汽牌照照识别技术的研究．测控技术．1999，21(5)：pp．35～38
[18] 王昱，赵正校等．基于样本线搜索和霍夫变换的区域定位算法．红外与激光工程．1999，28(4)：pp．16～20
[19] 张玉娇，史忠科．牌照提取方法研究．西北工业大学学报．2003，21(1)：pp．34～37
[20] 郑翔，黄艺云．经典边缘检测模板的快速算法．信号处理．1995，11(4)：pp．317～320
[21] 李炜，黄心汉．牌照自动识别系统中牌照分割的研究．信号处理．2000．16：pp．41～44
[22] 崔江，王友仁．牌照自动识别方法中的关键技术研究计算机测量与控制．2003．11(4)：PP．260～262
[23] 洛雪超，刘贵雄等．一种基于车辆特征信息的牌照识别方法．华南理工大学学报．2003，31(4)：pp．70～73
[24] 李小平，任江兴，杨德刚．牌照识别系统中若干问题的探讨．北京理工大学学报．2001，21(1)：PP．116～119
[25] 富煜清，沈巍，黄心晔．汽牌照照的提取方法研究．模式识别与人工智
能．2000，13(3)：PP．345～348
[26] 刘效静，成瑜．汽牌照照自动识别技术研究．南京航空航天大学学报．1998，30(5)：PP．573～576
[27] 赵海燕，裴志利．基于牌照颜色变化剧烈特征的彩色牌照定位新方法．内蒙古民族大学学报(自然科学版)．2002，17(6)：pp．500～502
[28] 付仲良，黄书强等．货车图像牌照区快速定位及字符切割算法．计算机工程与设计．2003，24(1)：PP．77～79
[29] 曹刚，游志胜．一种基于自适应能量滤波的快速牌照定位方法光电子·激光．2003，14(5)：PP．523～525
[30] 郭大波，陈礼明．基于牌照底色识别的牌照定位方法．2003．24(5)：pp．81～84
[31] N.R.Pal and S.K.Pal, "A Review on Image Segmentation Techiniques", Pattern Recognition, 1993,26(9):pp.1,277～1,294
[32] Nikhil R. Pal et al.,A Review on Image Segmentation Techniques,Pattern Recognition, Vol.26, No.9:pp. 1277～1294, 1993
[33] P.K.Sahoo et al., Asurvey of Threshold Techniques, Computer Vision, Graphics, and Image Processing 29:pp. 100～132(1988)
[34] P.K.Sahoo, S.Soltani, A.K.C. Wong, and Y.C.Chen, "A Survey of Thresholding Techniques", Computer Graphics,Vision and Image Processing 1988(41):pp.233～260
[35] Makoto Miyahara, Yasuhiro Yashid. Mathematical transform(R,G,B) color data to Munsell(H,V,C) color data [A].In Visual Communications and Image Processing 88'SP IE [C].Cambridge, Massachusetts USA, 1988:pp.650～657.
[36] Wezka J S, Rosenfeld A. Histogram modification for threshold selection. IEEE Trans, 1979; SMC-9(1):pp.38～52.
[37] Chaudhuri, B.B,Sarkar,N., 1995.Texture segmentation using fractal dimension. IEEE Trans.Pattern Anal.Machine Intel.17: pp.72-77.
[38] Birchfield, S. Elliptical head tracking using intensity gradients and color histograms. In: Proceedings of the IEEE Conference on CV PR'98. Santa Barbara, CA, 1998.232～237.
[39] 张引．基于空间分布的最大类间方差牌照图像二值化算法．浙江大学学报．2001，35(3)：pp．272～275
[40] 吴传孙，邹扬德等．二值化算法在牌照识别中的应用．计算机与现代化．2003，6：pp．13～16
[41] 陈黎，黄心汉等．基于聚类分析的牌照字符分割方法．计算机工程与应用．2002，6：pp．．221～222
[42] 张玉娇，史忠科．一种新的牌照预处理算法．西北工业大学学报．2002，20(1)：PP．83～86
[43] 周妮娜，王敏等．牌照字符识别的预处理算法．计算机工程与应用．2003，15：pp．220～232
[44] 刘健庄，栗文表．灰度图象的二维Otsu自动阀值分割法．自动化学报．1991，19(1)：pp．101～105
[45] 吴全，朱兆达．“图像处理中灰度级阈值选取方法30年(1962-1992)的进展(一)”，数据采集与处理．1993，8(3-4)：PP．193～201
[46] 罗希平等．图像分割方法综述．模式识别与人工智能．1999，12(3)：PP．301～312
[47] 孟章荣．各种颜色模型选用需求分析．中国图像图形学报．1996，1(3)：PP．238～241．
[48] 刘文萍，吴立德．图像分割中阈值选取方法比较研究．模式识别与人工智能．1997，10(3)：PP．271～277
[49] 郑南宁，刘建勤．基于区域特征的自适应图像分割方法．电子学报．1995，7：pp．98～101
[50] 潘晨．阈值分割与颜色聚类相结合的色度学图象分割方法．计算机应用研究．2001，12：pp．53～55
[51] 黄晓东，周源华．用小波变换及颜色聚类提取的视频图像内中文字幕．计算机工程．2003，29(1)：pp．43～44
[52] 张丽，毕岗等．HSV空间自适应背景模板在运动车辆实时检测中的应用．公路交通科技．2003，20(4)：PP．88～91
[53] 刘湘滨，邹北冀．一种新的颜色聚类算法及其图象检索．计算机工程与应用．2001，13：pp．126～128
[54] Feng Yuan. Windows Graphics Programming. Prentice Hall PTR.2000
[55] Rafael C.Gonzalez,Richard E.Woods．《数字图像处理》，电子工业出版社．2003
[56] 章晋．《图像处理和分析》．清华大学出版社．1999
[57] Kenneth R.Castleman．《数字图像处理》．清华大学出版社．1998
[58] 崔屹．《数字图像处理技术及应用》．电子工业出版社．1997
[59] 龚炜，石青云等．《数字空间中的数学形态学—理论及应用》．科学出版社．1997
[60] 贾云得．《机器视觉》．科学出版社．2000
[61] 赵荣椿等．《数字图象处理导论》．西北工业大学出版社．2000
[62] 边肇祺．《模式识别》．清华大学出版社．1987