基于图像的水表读数智能识别应用研究
|
摘要
水表智能识别系统是计算机视觉在日常生活中的一个重要应用,而图像处理和字符识别技术是其中两个关键技术。在此论文中,我们根据真彩水表图像自身的特点,构建一个水表字符自动识别系统。该系统包括图像预处理、特征提取和分类器三个部分。
图像预处理部分主要基于图像的HSV色彩空间。对于采集到的彩色水表表盘图像,分析图像自身特点,分别提取其V、S和H分量有用信息,并结合相关算法,对其进行了有效的预处理。将图像格式从RBG空间装换到HSV空间后:对于V分量,我们利用其对图像进行灰度化,用Canny算子检测图像边缘,并对所得边缘图像使用Hough变换来检测水表字符边框以获得倾角,然后根据旋转算法进行倾斜校正,读数区域的水平定位也由Hough变换检测出的平行直线所确定;对于S和H分量信息,在图像二值化中得到充分利用:我们提出彩色水表图像基于S分量阈值法与H分量阈值法融合的二值化方法和基于色彩聚类与H分量阈值法融合的图像二值化方法,并通过实验证明了这两种方法在彩色水表图像二值化中的有效性;并探讨了两种方法的优缺点,最终选取了基于色彩聚类与H分量阈值法融合的图像二值化方法。字符分割步骤,考虑到字符粘连情况的存在,采用双次分割办法:首先进行基于直方图的阈值分割,然后进行基于字符轮廓的字符粘连分割。最后对所得图像进行归一化处理。实验证明,对于我们采集到的水表图像,此种基于HSV空间图像预处理方法比之RGB空间有显著的优势。
在字符特征提取阶段,讨论了字符的轮廓特征和统计特征提取的优缺点,并最终采用统计网格特征:即将每幅数字图像平均分割为9个面,统计每个面中数字点所占个数,然后与面积取商。
字符识别器采用现在通用的BP网络:根据本系统图像特点,构建一个三层BP网络来识别数字;中间层神经元的个数由matlab模拟BP网络误差逼进结果来确定。
使用采集的水表图像对所设计识别系统进行试验,对所得结果进行分析,对系统存在问题进行改进,最终获得具有较好的鲁棒性识别系统。
Water meter automatic recognition system is an important application of pattern recognition and computer vision in our daily life;and the image processing and digits recognition are its two core technologies.In this paper,we will introduce a way to build a recognition system based on the features of the true color images,including image pre-processing,feature extraction and classifying.
The image pre-processing mainly based on the HSV color space.The useful information of the three parameters(H,S,V) and the significant algorithm form a effective image pre-processing.We should first convert the format of the color images from RGB to HSV.Then we can detect the parallel through the algorithm of Canny and Hough to obtain the obliquity of the image to correct it,and this is based on the parameter of V.Also,we use the parallel to locate the digits region.In binarization step,the H and S parameter are useful:we propose the S parameter and H parameter features fusion ruler and the C-means and H parameter features fusion ruler to distinguish the digits from background.The two means are effective and both have its merit and defect,and the C-means and H parameter threshold fusion ruler is the final choise.Two major units compose the segment of digits:the pixels and the figure of the digits.Finally,we resize all the pictures into the same size.
We choose the statistical features as the extraction features of digits.Four lines(including two horizontal and two vertical lines) divide the digit into nine regions.We total the number of the black dots to divide the total dots in each region as the features of the digits.
Finally,a three-layer BP neural network is applied in this system to identify the number 0 to 9;the number of the neurons in the middle-layer of BP network is defined by the experiment result on matlab.
We test the system by hundreds of water meter images available,and improve the system according to the experimental results.The results show the final proposed scheme is feasible and has great robustness.
图像预处理部分主要基于图像的HSV色彩空间。对于采集到的彩色水表表盘图像,分析图像自身特点,分别提取其V、S和H分量有用信息,并结合相关算法,对其进行了有效的预处理。将图像格式从RBG空间装换到HSV空间后:对于V分量,我们利用其对图像进行灰度化,用Canny算子检测图像边缘,并对所得边缘图像使用Hough变换来检测水表字符边框以获得倾角,然后根据旋转算法进行倾斜校正,读数区域的水平定位也由Hough变换检测出的平行直线所确定;对于S和H分量信息,在图像二值化中得到充分利用:我们提出彩色水表图像基于S分量阈值法与H分量阈值法融合的二值化方法和基于色彩聚类与H分量阈值法融合的图像二值化方法,并通过实验证明了这两种方法在彩色水表图像二值化中的有效性;并探讨了两种方法的优缺点,最终选取了基于色彩聚类与H分量阈值法融合的图像二值化方法。字符分割步骤,考虑到字符粘连情况的存在,采用双次分割办法:首先进行基于直方图的阈值分割,然后进行基于字符轮廓的字符粘连分割。最后对所得图像进行归一化处理。实验证明,对于我们采集到的水表图像,此种基于HSV空间图像预处理方法比之RGB空间有显著的优势。
在字符特征提取阶段,讨论了字符的轮廓特征和统计特征提取的优缺点,并最终采用统计网格特征:即将每幅数字图像平均分割为9个面,统计每个面中数字点所占个数,然后与面积取商。
字符识别器采用现在通用的BP网络:根据本系统图像特点,构建一个三层BP网络来识别数字;中间层神经元的个数由matlab模拟BP网络误差逼进结果来确定。
使用采集的水表图像对所设计识别系统进行试验,对所得结果进行分析,对系统存在问题进行改进,最终获得具有较好的鲁棒性识别系统。
Water meter automatic recognition system is an important application of pattern recognition and computer vision in our daily life;and the image processing and digits recognition are its two core technologies.In this paper,we will introduce a way to build a recognition system based on the features of the true color images,including image pre-processing,feature extraction and classifying.
The image pre-processing mainly based on the HSV color space.The useful information of the three parameters(H,S,V) and the significant algorithm form a effective image pre-processing.We should first convert the format of the color images from RGB to HSV.Then we can detect the parallel through the algorithm of Canny and Hough to obtain the obliquity of the image to correct it,and this is based on the parameter of V.Also,we use the parallel to locate the digits region.In binarization step,the H and S parameter are useful:we propose the S parameter and H parameter features fusion ruler and the C-means and H parameter features fusion ruler to distinguish the digits from background.The two means are effective and both have its merit and defect,and the C-means and H parameter threshold fusion ruler is the final choise.Two major units compose the segment of digits:the pixels and the figure of the digits.Finally,we resize all the pictures into the same size.
We choose the statistical features as the extraction features of digits.Four lines(including two horizontal and two vertical lines) divide the digit into nine regions.We total the number of the black dots to divide the total dots in each region as the features of the digits.
Finally,a three-layer BP neural network is applied in this system to identify the number 0 to 9;the number of the neurons in the middle-layer of BP network is defined by the experiment result on matlab.
We test the system by hundreds of water meter images available,and improve the system according to the experimental results.The results show the final proposed scheme is feasible and has great robustness.
引文
[1]董建,常正跃.智能水表及远程集中抄表的现状及发展趋势.技术导讯,2003.
[2]郭远刚.水表自动抄收系统现状及发展趋势.行业应用,2007.
[3]王三武,戴亚文.多指针水表自动识别系统.仪器仪表学报,Vol.26,No.11,2005.
[4]郗润平,赵荣椿,岳思聪,易飞.一个基于DSP与图像处理的水表读识系统.全国第十届信号与信息处理、第四届DSP应用技术联合学术会议论文集,2006.
[5]苑玮琦,刘慧.指针式水表数据远传系统的研究.现代电子技术,2008.
[6]吴梦麟.图像式水表读数识别方法研究.南京理工大学,2006.
[7]于聪颖.水表盘字轮号码读取装置.沈阳工业大学,2007.
[8]王旭智,向长波,宋建中,乔双.实时字符识别在视频读表系统中的应用.电子器件,Vol.29,No.4,2006.
[9]葛慧,陈平.BP算法在智能水表抄表系统的应用.工业计量,Vol.17,No.6,2007.
[10]何斌,马天予,王运坚,朱红莲.Visual C++数字图像处理.人民邮电出版社,2001.
[11]W.K.Pratt.Digital Image Processing.New York:John wiley & Sons,inc.,1978.
[12]刘中合,王瑞雪.数字图像处理技术现状与展望.计算机时代,2005.
[13]R.C Gonzalez,R.E.Woods.数字图像处理(第二版).阮秋琦,阮宇智译.电子工业出版社,2003.
[14]陈书海,傅录祥.实用数字图像处理.科学出版社,2005.
[15]庄天戈.CT原理与算法.上海交通大学出版社.1992.
[16]杨枝灵,王开.Visual C++数字图像获取、处理及实践应用.人民邮电出版社,2003.
[17]翟磊,董守平,马红莲.数字图像处理技术的发展现状与展望.计算机技术与进展,2008.
[18]Sergios Theodoridis,Konstantinos Koutroumbas.Pattern Recognition,Third Edition.李晶皎等译.电子工业出版社,2006.
[19]求是科技,张宏林.Visual C++数字图像模式识别技术及工程实践.人民邮电出版社,2003.
[20]中国物品编码中心,中国自动识别技术协会.自动识别技术导论.武汉大学出版社,2007.
[21]熊承义,李玉海.统计模式识别及其发展现状综述.科技进步与对策,2003.
[22]Nagy G.Chinese Character recognition:a twenty-five-year retrospective.ICPR 88',1988.
[23]Govindan V K,Shivaprasad A P.Chinese recognition-a review.Pattern Rcognition,1990.
[24]李峰.一种基于K-L变换和Otsu 阈值选择的彩色图像分割算法.计算机应用,2007.
[25]四维科技,胡小锋,赵辉.Visual C++/MATLAB图像处理与识别实用案例精选.人民邮电出版社,2004.
[26]张晓芸.彩色图像分割算法的研究与实现.重庆大学,2005.
[27]田巍,庄镇泉.基于HSV色彩空间的自适应肤色检测.计算机工程与应用,2004.
[28]李庆峰,付忠良,刘琴.一种高效的倾斜图像校正方法.计算机工程,2006.
[29]Le D S,Thoma G R,Wechsler H.Automated Page Orientation and Skew Angle Detection for Binary Document Images[J].Pattern Recognition,1997,27(10):1325-1344.
[30]Perantonis S J,Gatos B,Papamarkos N.B lock decomposition and segmentation for fast Hough transform evaluation.Pattern Recognition,1999,32(5):811-824.
[31]周冠玮,平西建,程娟.基于改进Hough变换的文本图像倾斜校正方法.计算机应用,2007.
[32]Ciardiello G,Scafuro G,Degrandim.An experimental system for office document handling and text recognition.Proceedings of 9th International Conference on Pattern Recognition,1988,739-743.
[33]Gatos B,Papermarkos N,Chamzas C.Skew Detection and Text Line Position Determination in Digitized Documents[J].Pattern Recognition,1997,30(9):1505-1519.
[34]Chen M,Ding X.A Robust Skew Detection Algorithm for Grayscale Document Image[C].Proceedings of International Conference on Document Analysis and Recognition,Bangalore,India:1999,617-620.
[35]Pstl W.Detection of Linear Oblique Structure and Skew Scan in Digitized Documents.Proceedings of the 8th International Conference on Pattern Recognition,Paris,France:1986,487-489.
[36]Goman L O.The Document Spectrum for Page Layout Analysis[J].IEEE Transaction on PAMI,1993,15(11):1162-1173.
[37]何希平,李云峰,朱庆生.彩色文档图像的倾斜自动校正算法.中国图象图形学报,2006.
[38]Gooch,A.A.,Olsen,S.C.,Tumblin,J.and Gooch,B.Colour2Gray:Salience-Preserving Colour Removal.Proc.ACM Siggraph,2005.
[39]章卫祥,周秉锋.一种基于梯度域的彩色图像转灰度图像的方法.2006中国科协年会——数字成像技术及影像材料科学学术交流会论文集,2006.
[40]张艳群,孟凡荣.MATLAB在图像边缘检测中的应用.计算机应用研究,2004.
[41]Roberts L G.Machine perception of three-dimensional solids,in J.T.Tippett,ed.,Optical and Electro-Optical Information Processing.MIT Press,Cambridge,MA,1965.
[42]Prewitt J.Object enhancement and extraction,in B.Lipkin and A.,Rosenfeld,eds.,Picture Processing and Psychopictorics.Academic Press,New York,1970.
[43]L.S.Davis.A survey of edge detection techniques.Computer Graphics Image Process,1975,4(3):248-270.
[44]李小红.基于LOG滤波器的图像边缘检测算法的研究.计算机应用与软件,2005.
[45]Canny J.A computational approach to edge detection.IEEE Trans Pattern Analysis and Machine Intelligence,1986,8(6):679-698.
[46]曾爱群,张烈平,陈婷.基于MATLAB的芒果边缘检测的研究.微计算机信息,2007.
[47]曹菲,杨小冈,缪栋,张云鹏.一种通用的边缘特征检测方法及其实现.计算机工程,2005.
[48]王植,贺赛先.一种基于Canny理论的自适应边缘检测方法.中国图象图形学报,2004.
[49]隋东坡,周焰,肖志坚.基于粗糙度的改进Canny边缘检测方法.计算机工程与应用.2005.
[50]Ballard D.H..Generalizing the hough transform to detect arbitrary shapes.Pattern Recognition,1981,13(4):111-122.
[51]郭臻,谢晖.现代彩色图像分割技术综述.计算机与信息技术,2007.
[52]H D Cheng,X H Jiang,Y Sun,Jingh Wang.Color image segmentation:advance and prospects.Pattern Recognition,2001,34:2259-2281.
[53]龚巍.示温漆彩色图像分割与温度识别系统.西南科技大学,2007.
[54]石巍.基于人类视觉特征的彩色图像分割技术研究.中国海洋大学,2006.
[55]张晓萌,付燕.图像分割技术研究.科技情报开发与经济,2007.
[56]谭志明.基于图论的图像分割及其嵌入式应用研究.上海交通大学,2007.
[57]Sankur B,Sezgin M.A survey over image thresholding techniques and quantitative performance evaluation.Journal of Electronic Imaging,2004,13(1):146-165.
[58]Otsu N A.Threshold selection method from grey-level histograms.IEEE Trans Syst,Man,Cybern,1979,8:62-66.
[59]Trier O D,Jain A K.Goal-directed evaluation of binarization methods.IEEE Trans Pattern Anal Machine Intell,1995,17:1191-1201.
[60]Trier O D,Taxt T.Evaluation of binarization methods for document images.IEEE Trans Pattern Anal Machine Intell,1995,17:312-315.
[61]Pal N R,Pal S A.Review on image segmentation techniques.Pattern Recognition,1993,26:1277-1294.
[62]Sahoo P K,Sotlani S,Wang A K C,etal.A survey of thresholding techniques.Comput Vis Graph ImageProcess,1988,41:233-260.
[63]Johnson S.C..Hierarchical clustering schemes.Psychometrika,Vol.32,1967,pp:241-254.
[64]Wallace C.S.,Boulton D.M.An information measure for classification.Computer Journal,Vol.11,1968,pp:185-194.
[65]Everitt B.,Landau S.,Leesse M.Cluster Analysis,Arnold,2001.
[66]孙吉贵,刘杰,赵连宇.聚类算法研究.软件学报,2008.
[67]王晓丹.基于模糊聚类及神经网络的纹理分割方法研究.西北工业大学,2000.
[68]马东,曹陪杰,李斌,程敬之.多信息融合的彩色细胞图像分割方法.北京生物医学工程,2000.
[69]杨军,吴晓娟,彭彰,陈文刚.基于多区域分割的步态表示与识别算法研究研究.计算机学报,2006.
[70]黄春艳,杨国胜,侯艳丽.基于颜色直方图和空间信息融合的图像分割算法.计算机工程与应用,2005.
[71]江西莉,刘芳,焦李成.融合上下文信息的多尺度贝叶斯图像分割.计算机学报,2005.
[72]王枚,房培玉,王国宏.彩色图像特征融合规则及其在车牌定位中的作用.计算机应用研究,2008.
[73]Heutte L,Paquet T,Moreau J V,etal.A structural/statistical feature based vector for handwritten character recognition.Pattern Recognition Letters,1998,19(7):629-641.
[74]胡小锋,陈超,叶庆泰.图书索书号粘连字符的切分.上海交通大学学报,2005.
[75]C.L.Liu,K.Nakashima,H.Sako,H.Fujisawa.Hand written digit recognition:investigation of normalization and feature extraction techniques,Pattern Recognition,2004,37(2):256-279.
[76]Trier,O.D.,Jain,A.K.,Taxt T.Feature extraction methods for character recognition Pattern Recognition,1996,pp:641-662.
[77]林文娅.基于图像神经网络的水表字符识别.南京理工大学,2007.
[78]David A.Forsygh,Jean Ponce.Computer Vision:A Modern Approach.林学訚,王宏等 译.电子工业出版社,2004.
[79]金星姬,贾炜玮.人工神经网络研究概述.林业科技情报,2008.
[80]Vapnik V.The nature of statistieal learning theory.Spring-Verlag New York Inc.,1995.张学工译.统计学习理论的本质.北京:清华大小出版社,1999,234-235.
[81]高隽.人工神经网络原理及仿真实例.机械工业出版社,2003.
[82]韩立群.人工神经网络理论、设计及应用.化学工业出版社,2004.
[83]Ralf Salomon,J Leo van Hemmen.Accelerating Back-propagation through Dynamic Self-Adaptation.Neural Networks,1996.
[2]郭远刚.水表自动抄收系统现状及发展趋势.行业应用,2007.
[3]王三武,戴亚文.多指针水表自动识别系统.仪器仪表学报,Vol.26,No.11,2005.
[4]郗润平,赵荣椿,岳思聪,易飞.一个基于DSP与图像处理的水表读识系统.全国第十届信号与信息处理、第四届DSP应用技术联合学术会议论文集,2006.
[5]苑玮琦,刘慧.指针式水表数据远传系统的研究.现代电子技术,2008.
[6]吴梦麟.图像式水表读数识别方法研究.南京理工大学,2006.
[7]于聪颖.水表盘字轮号码读取装置.沈阳工业大学,2007.
[8]王旭智,向长波,宋建中,乔双.实时字符识别在视频读表系统中的应用.电子器件,Vol.29,No.4,2006.
[9]葛慧,陈平.BP算法在智能水表抄表系统的应用.工业计量,Vol.17,No.6,2007.
[10]何斌,马天予,王运坚,朱红莲.Visual C++数字图像处理.人民邮电出版社,2001.
[11]W.K.Pratt.Digital Image Processing.New York:John wiley & Sons,inc.,1978.
[12]刘中合,王瑞雪.数字图像处理技术现状与展望.计算机时代,2005.
[13]R.C Gonzalez,R.E.Woods.数字图像处理(第二版).阮秋琦,阮宇智译.电子工业出版社,2003.
[14]陈书海,傅录祥.实用数字图像处理.科学出版社,2005.
[15]庄天戈.CT原理与算法.上海交通大学出版社.1992.
[16]杨枝灵,王开.Visual C++数字图像获取、处理及实践应用.人民邮电出版社,2003.
[17]翟磊,董守平,马红莲.数字图像处理技术的发展现状与展望.计算机技术与进展,2008.
[18]Sergios Theodoridis,Konstantinos Koutroumbas.Pattern Recognition,Third Edition.李晶皎等译.电子工业出版社,2006.
[19]求是科技,张宏林.Visual C++数字图像模式识别技术及工程实践.人民邮电出版社,2003.
[20]中国物品编码中心,中国自动识别技术协会.自动识别技术导论.武汉大学出版社,2007.
[21]熊承义,李玉海.统计模式识别及其发展现状综述.科技进步与对策,2003.
[22]Nagy G.Chinese Character recognition:a twenty-five-year retrospective.ICPR 88',1988.
[23]Govindan V K,Shivaprasad A P.Chinese recognition-a review.Pattern Rcognition,1990.
[24]李峰.一种基于K-L变换和Otsu 阈值选择的彩色图像分割算法.计算机应用,2007.
[25]四维科技,胡小锋,赵辉.Visual C++/MATLAB图像处理与识别实用案例精选.人民邮电出版社,2004.
[26]张晓芸.彩色图像分割算法的研究与实现.重庆大学,2005.
[27]田巍,庄镇泉.基于HSV色彩空间的自适应肤色检测.计算机工程与应用,2004.
[28]李庆峰,付忠良,刘琴.一种高效的倾斜图像校正方法.计算机工程,2006.
[29]Le D S,Thoma G R,Wechsler H.Automated Page Orientation and Skew Angle Detection for Binary Document Images[J].Pattern Recognition,1997,27(10):1325-1344.
[30]Perantonis S J,Gatos B,Papamarkos N.B lock decomposition and segmentation for fast Hough transform evaluation.Pattern Recognition,1999,32(5):811-824.
[31]周冠玮,平西建,程娟.基于改进Hough变换的文本图像倾斜校正方法.计算机应用,2007.
[32]Ciardiello G,Scafuro G,Degrandim.An experimental system for office document handling and text recognition.Proceedings of 9th International Conference on Pattern Recognition,1988,739-743.
[33]Gatos B,Papermarkos N,Chamzas C.Skew Detection and Text Line Position Determination in Digitized Documents[J].Pattern Recognition,1997,30(9):1505-1519.
[34]Chen M,Ding X.A Robust Skew Detection Algorithm for Grayscale Document Image[C].Proceedings of International Conference on Document Analysis and Recognition,Bangalore,India:1999,617-620.
[35]Pstl W.Detection of Linear Oblique Structure and Skew Scan in Digitized Documents.Proceedings of the 8th International Conference on Pattern Recognition,Paris,France:1986,487-489.
[36]Goman L O.The Document Spectrum for Page Layout Analysis[J].IEEE Transaction on PAMI,1993,15(11):1162-1173.
[37]何希平,李云峰,朱庆生.彩色文档图像的倾斜自动校正算法.中国图象图形学报,2006.
[38]Gooch,A.A.,Olsen,S.C.,Tumblin,J.and Gooch,B.Colour2Gray:Salience-Preserving Colour Removal.Proc.ACM Siggraph,2005.
[39]章卫祥,周秉锋.一种基于梯度域的彩色图像转灰度图像的方法.2006中国科协年会——数字成像技术及影像材料科学学术交流会论文集,2006.
[40]张艳群,孟凡荣.MATLAB在图像边缘检测中的应用.计算机应用研究,2004.
[41]Roberts L G.Machine perception of three-dimensional solids,in J.T.Tippett,ed.,Optical and Electro-Optical Information Processing.MIT Press,Cambridge,MA,1965.
[42]Prewitt J.Object enhancement and extraction,in B.Lipkin and A.,Rosenfeld,eds.,Picture Processing and Psychopictorics.Academic Press,New York,1970.
[43]L.S.Davis.A survey of edge detection techniques.Computer Graphics Image Process,1975,4(3):248-270.
[44]李小红.基于LOG滤波器的图像边缘检测算法的研究.计算机应用与软件,2005.
[45]Canny J.A computational approach to edge detection.IEEE Trans Pattern Analysis and Machine Intelligence,1986,8(6):679-698.
[46]曾爱群,张烈平,陈婷.基于MATLAB的芒果边缘检测的研究.微计算机信息,2007.
[47]曹菲,杨小冈,缪栋,张云鹏.一种通用的边缘特征检测方法及其实现.计算机工程,2005.
[48]王植,贺赛先.一种基于Canny理论的自适应边缘检测方法.中国图象图形学报,2004.
[49]隋东坡,周焰,肖志坚.基于粗糙度的改进Canny边缘检测方法.计算机工程与应用.2005.
[50]Ballard D.H..Generalizing the hough transform to detect arbitrary shapes.Pattern Recognition,1981,13(4):111-122.
[51]郭臻,谢晖.现代彩色图像分割技术综述.计算机与信息技术,2007.
[52]H D Cheng,X H Jiang,Y Sun,Jingh Wang.Color image segmentation:advance and prospects.Pattern Recognition,2001,34:2259-2281.
[53]龚巍.示温漆彩色图像分割与温度识别系统.西南科技大学,2007.
[54]石巍.基于人类视觉特征的彩色图像分割技术研究.中国海洋大学,2006.
[55]张晓萌,付燕.图像分割技术研究.科技情报开发与经济,2007.
[56]谭志明.基于图论的图像分割及其嵌入式应用研究.上海交通大学,2007.
[57]Sankur B,Sezgin M.A survey over image thresholding techniques and quantitative performance evaluation.Journal of Electronic Imaging,2004,13(1):146-165.
[58]Otsu N A.Threshold selection method from grey-level histograms.IEEE Trans Syst,Man,Cybern,1979,8:62-66.
[59]Trier O D,Jain A K.Goal-directed evaluation of binarization methods.IEEE Trans Pattern Anal Machine Intell,1995,17:1191-1201.
[60]Trier O D,Taxt T.Evaluation of binarization methods for document images.IEEE Trans Pattern Anal Machine Intell,1995,17:312-315.
[61]Pal N R,Pal S A.Review on image segmentation techniques.Pattern Recognition,1993,26:1277-1294.
[62]Sahoo P K,Sotlani S,Wang A K C,etal.A survey of thresholding techniques.Comput Vis Graph ImageProcess,1988,41:233-260.
[63]Johnson S.C..Hierarchical clustering schemes.Psychometrika,Vol.32,1967,pp:241-254.
[64]Wallace C.S.,Boulton D.M.An information measure for classification.Computer Journal,Vol.11,1968,pp:185-194.
[65]Everitt B.,Landau S.,Leesse M.Cluster Analysis,Arnold,2001.
[66]孙吉贵,刘杰,赵连宇.聚类算法研究.软件学报,2008.
[67]王晓丹.基于模糊聚类及神经网络的纹理分割方法研究.西北工业大学,2000.
[68]马东,曹陪杰,李斌,程敬之.多信息融合的彩色细胞图像分割方法.北京生物医学工程,2000.
[69]杨军,吴晓娟,彭彰,陈文刚.基于多区域分割的步态表示与识别算法研究研究.计算机学报,2006.
[70]黄春艳,杨国胜,侯艳丽.基于颜色直方图和空间信息融合的图像分割算法.计算机工程与应用,2005.
[71]江西莉,刘芳,焦李成.融合上下文信息的多尺度贝叶斯图像分割.计算机学报,2005.
[72]王枚,房培玉,王国宏.彩色图像特征融合规则及其在车牌定位中的作用.计算机应用研究,2008.
[73]Heutte L,Paquet T,Moreau J V,etal.A structural/statistical feature based vector for handwritten character recognition.Pattern Recognition Letters,1998,19(7):629-641.
[74]胡小锋,陈超,叶庆泰.图书索书号粘连字符的切分.上海交通大学学报,2005.
[75]C.L.Liu,K.Nakashima,H.Sako,H.Fujisawa.Hand written digit recognition:investigation of normalization and feature extraction techniques,Pattern Recognition,2004,37(2):256-279.
[76]Trier,O.D.,Jain,A.K.,Taxt T.Feature extraction methods for character recognition Pattern Recognition,1996,pp:641-662.
[77]林文娅.基于图像神经网络的水表字符识别.南京理工大学,2007.
[78]David A.Forsygh,Jean Ponce.Computer Vision:A Modern Approach.林学訚,王宏等 译.电子工业出版社,2004.
[79]金星姬,贾炜玮.人工神经网络研究概述.林业科技情报,2008.
[80]Vapnik V.The nature of statistieal learning theory.Spring-Verlag New York Inc.,1995.张学工译.统计学习理论的本质.北京:清华大小出版社,1999,234-235.
[81]高隽.人工神经网络原理及仿真实例.机械工业出版社,2003.
[82]韩立群.人工神经网络理论、设计及应用.化学工业出版社,2004.
[83]Ralf Salomon,J Leo van Hemmen.Accelerating Back-propagation through Dynamic Self-Adaptation.Neural Networks,1996.