图像式水表读数识别方法研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
随着信息社会的发展,图像处理和机器视觉技术在各行各业的应用越来越广泛。各行业的管理手段正在从人工管理向自动或半自动方向转化。本文提出图像式水表读数的自动识别方法,就是用计算机读数来代替过去抄表员的人工抄表,以达到提高效率和降低人工成本的目的,具有广泛的理论和应用价值。
     本文的主要工作包括:
     (1) 从图像预处理入手,首先针对光照造成的图像灰度不均匀,经典的阈值分割方法如Ostu、Bernsen算法不能很好提取目标的问题,采用了利用梯度点信息插值的S.D.Yanowitz算法,能够很好的分割目标和背景;再利用水平和竖直投影提取水表表框信息;然后再利用改进的Hough变换提取表框范围内直线,对结果进行统计分析,求出水表的倾斜角度;最后采用逆仿射变换的方法,对表框图像进行双线性插值旋转,得到表框的矫正图像。
     (2) 针对水表图像的读数特点,提出逐步求精的策略进行数字字符的精确定位。先采用先验知识对字符进行粗定位;再采用形态学的方法对图像进行增强,并对连通域筛选,以提高精确定位的精度;最后利用投影的方法,求出字符的外接矩形的切线位置,并按照半字和整字的不同方法定位,取得良好的定位效果。
     (3) 采用基于改进Hausdorff距离的滑动模板匹配进行数字字符识别。利用了分形理论中的Hausdorff距离来计算字符与模版的相似程度,并且采用了改进的Hausdorff距离以提高算法的稳定性。在识别半字的过程中研究了滑动模板匹配的方法,解决了半字模版不唯一的问题。实验证明,算法获得较好的识别率。
With the development of information society, image processing and machine vision is widely applied to all walks of life. All trades and professions management tool converts to automation or semi- automation from manual work. In this paper, we propose a method for water meter reading recognition, that is to say, computer reading substituting for manual reading in the past, can improve efficiency and save labor cost, and it has extensive academic and utility value.
    The work including:
    (1) This paper introduces arithmetic for image pre-processing. First, because of illumination, the image intensity is not uniform. The classic binarization algorithms such as Ostu algorithm and Bersen algorithm can not extract object well, so we use S.D.Yanowitz algorithm which interpolates the image grey by gradient imformation. Then it can get water meter frame information by horizontal and vertical projection, and extract line by improved Hough transform. Finally, the image can be corrected by affine transform.
    (2) This paper presents a step wise refinement strategy for digit character location. First, it can use a priori knowledge for approximate location. Second, morphologic enhancement and connected component filter make location more precisely. At last, the tangent rectangle can be solved by projection method, and can be differentiated between complete character and half character.
    (3) This paper researches on a digit character recognition method that is gliding template matching based on improved Hausdorff distance. Using Hausdorff distance in multi-fractal theory calculates the similarity between image and template, and improves the arithmetic's stability. In the process of the half digit character recognitions, the paper proposes sliding template concept, solves the problem that it has no uniqueness shape. Experiment proves the recognition rate of the arithmetic meets the practical need.
引文
1 申小阳.数字仪表动态显示字符的计算机自动识别 浙江工业大学硕士研究生学位论文.2002
    2 张宏林.Visual C++数字图像模式识别技术及工程实践.第2版.北京:北京人民邮电出版社,2002
    3 敖银辉.神经和模糊技术在车牌识别中的应用.广东工业大学学报.2003.12,20(4):43~47
    4 Fumiaki Takeda, Sigeru Omatu. High speed paper currency recognition by neural networks. IEEE Trans on Neural Network.. 1995, 6(1): 73~77
    5 唐轶峻,申小阳,朱雯兰,隋成华.基于BP神经网络的数显仪表数字字符识别系统.电测与仪表.2005.9,42(477):42~45
    6 严国莉,黄山,李岱璋,尚建华.印刷体数字快速识别算法在身份证编号数字识别中的应用.计算机工程.2003.1,29(1):178~179
    7 芮挺,沈春林,丁健,张金林.基于主分量分析的手写数字字符识别.小型微型计算机系统.2005.2,26(2):289~292
    8 芮挺,沈春林,丁健.基于最佳鉴别变换的HMM 手写数字字符识别.中国图形图像学报.2004.8,9(8):1008~1013
    9 娄震,胡钟山,杨静宇,刘克,孙靖夷.基于轮廓分段特征的手写体阿拉伯数字识别.计算机学报,1999.10,22(10):1065~1073
    10 林晓帆,丁晓青,吴佑寿,陈友斌,刘今晖.字符识别的置信度分析.清华大学学报,1998.8,38(9):47~50
    11 武强,童学锋,季隽.基于人工神经网络的数字字符识别.计算机工程.2003.8,29(14):112~113
    12 章专,仲林国,朱志刚.基于图像采集与处理的自动抄表系统.电测与仪表.2004.10,41(466):63~65
    13 吴炜,余艳梅,刘大宇,何小海.一种基于Hausdorf距离的车牌字符识别算法.计算机应用研究.2004(2)
    14 Milan Sonka, Vaclav Hlavac, Roger Boyle. Image Processing, Analysis, and Machine Vision. 第2版.北京:北京人民邮电出版社.2003.9
    15 Yanowitz, S.D, Bruckstein, A.M. Anew method for image segmentation. Pattern Recognition, 1988., 9th International Conference on 14-17 Nov. 1988(1) Page(s):270-275
    16 陈强,朱立新,夏德深.结合Canny算子的图像二值化.计算机辅助设计与图形学学报.2005.6.17(6):1302~1306
    17 Otsu N. A threshold selection method from gray-level histograms [J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62~66
    18 龙均宇,金连文 一种基于全局均值和局部方差的图像二值化方法.计算机工程.2004.1,30(2):70~72
    19 Bemsen J. Dynamic thersholding of gray-level images [A]. In: Proceedings of the 8th International Conference on Pattern Recognition[C]. Paris: IEEE Computer Society Press, 1986:1251~1255
    20 汪国有,邹玉兰,凌勇.基于显著性的OSTU局部递归分割算法.华中科技大学学报.2002.9,30(9):57~59
    21 A.Rosenfeld and A.C.Kak, Digtal Picture Processing. Academic Press, New York, 1982.
    22 L.S.Davis, A.Rosenfeld and J.S.Weszka, "Region extraction by averaging and thresholding", IEEE Trans. On systems Man and Cybernetics, Vol SMC-5: 383~388, 1975
    23 J.S.Weszka and A.Rosenfeld, "Hystogram modification for threshold selection", IEEE Trans. On Systems Man and Cybernetics, Vol.SMC-9,pp.38~52,1979
    24 J.F.Canny. Finding edges and lines in images. Technical Report AI-TR-720, MIT. Artifical Intelligence Laboratory, Cambridge.MA, 1983
    25 W.E.L. Grimson. "From images to Surface". M.I.T. Press, Cambridge, Massachusetts, 1981,pp. 179~203.
    26 V.R.Southwell, "Relaxation Methods in Theoretical Physics", Oxford University Press, Oxford, 1946.
    27 张艰,赵宇明,陈德权.分时电表表盘数字读数的自动识别系统.计算机工程.2005.3,31(5):178~180
    28 夏德深,傅德胜.第1版.计算机图像处理及应用.南京:东南大学出版社,2004.2
    29 何斌,马天予,王运坚,朱红莲.Visual C++数字图像处理.第1版.人民邮电出版社.2001.
    30 J.F.Canny. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.8, No 6, 679~698, 1986.
    31 芮挺,沈春林,张金林.车牌识别中倾斜牌照的快速矫正算法.计算机工程.2004.7,30(13):122~124
    32 Hough P.V.C. A method and means for recognizing complex patterns. US: Patent 3, 069, 654. 1962.
    33 Ballard D.H. Generalizing the Hough transform to detect arbitary shapes. Pattern Recognition. 1981, Vol.13, No 2, 111~122
    34 Kushnir M, Ahe K, Matsumoto K. Recognition of handprinted Hebrew characters using features selected in the Hough transform space. Pattern Recognition. 1985, Vol. 18, No 2:103~104.
    35 胡占义,杨长江,马颂德.Hough变换的新定义.计算机学报.1997(8):744~752
    36 包明,路小波 基于Hough变换的车牌倾斜检测方法.交通与计算机.2004,22(2)
    37 曾文锋,李树山,王江安.基于仿射变换模型的图像配准中的平移、旋转和缩放.红外与激光 工程,2001.2,30(1):18~20
    38 Heam D et al.计算机图形学[M].第1版.北京:电子工业出版社,1998
    39 Brown L. A Survey of Image Registration Techniques[J]. ACM Computing Surveys, 1992, Vol. 24, No 12: 325~376.
    40 田捷等.使用图像分析与处理技术[M].第1版.北京:电子工业出版社,2000
    41 李闯,丁晓清,吴佑寿.基于边缘的字符串定位算法.清华大学学报,2005,45(10):1335~1338
    42 Jain A K, Yu B. Automatic text location in images and video frames[J]. Pattern Recognition, 1998, 31(12): 2055~2076.
    43 卢雅琴,邬凌超.基于数学形态学的车牌定位方法.计算机工程.2005.2,31(3):224~225
    44 ZhongY. ZhangH. Jain A K. Automatic caption localization in compressed videos[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2000, 22(4): 385~392
    45 Shin C S, Kim K I,Park M H, et al. Support vector machine based text detection in digital video[A]. Proceedings of the IEEE Signal Processing Society Workshop on Neural Networks for Signal Processing X[C]. Sydney, Australia: IEEE, 2000. 634~641
    46 沈瑛,范俊波.身份证识别的文字定位算法研究.计算机应用与软件.2004.3,21(3):80~82
    47 范瑞彬.遥感图像中机场识别与毁伤分析研究.南京理工大学硕士研究生学位论文,2004.6
    48 章毓晋.图像处理和分析.第2版.北京:清华大学出版社.1999.
    49 Serra. J. Image Analysis and mathematical morphology[M]. 1982
    50 Maragos. P. Tutorial on advances in morphological image processing and analysis[J]. Optical Engineering, 1987, Vol.26, No7, 623~632
    51 Wegman E. J. Nonpararnetric probability density estimation. A summary of available methods, Techno metrics[M], 1986
    52 王铁生,施鹏飞.二值图像的快速标记方法及其应用.微型电脑应用.2004,20(6):6~9
    53 M.B.Dillencourt et al. A general approach to connected component labeling for arbitrary image representations[J], Vol.39, No 2,1996, 253~280
    54 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.2003.8:173~175
    55 王晓华,高庆吉,赵卫平.利用模糊统计识别货下车号的研究[J].中国图像图形学报.2000,5(11):963~967
    56 陈友仁.基于隐马尔科夫模型的车牌自动识别技术[J].微型电脑应用.2001,30(2):102~107
    57 臧辉.遗传算法及其应用.武汉科技学院学报.2005.4,18(4):55~57
    58 郑朝辉,裘聿皇,陈峻峰.一种印刷体字符识别的新方法:基于遗传算法的(0,1,*)-矩阵法.控制与决策.2001.5,16(3):296~298.
    59 孙俊,李正明,杨继昌.遗传神经网络在汽车轮胎号识别中的应用.农业机械学报.2005.9,9(36):157~159
    60 吴小艳,王维庆,杨春祥,何山,王小龙.几种基于模版匹配法的数字图像识别算法分析.计量技术.2005(6):27~29
    61 焦李成.神经网络系统理论.第1版.西安电子科技大学出版社,1996
    62 王刚,刘立柱 基于神经网络的模糊模式识别算法研究.信息工程大学学报.2006.3,7(1):54~56
    63 Pentland A P. Fractal-based description of natural scenes[J]. IEEE France Pattern Analysis and Machine Intelligence, 1984, 6(6): 661~671.
    64 肖旺新,张雪,黄卫.采用分形分段维数识别车牌字符.交通运输工程学报.2004.6,4(2):107~110
    65 滕书华,孙即祥,邵晓芳.一种鲁棒性的印刷体数字识别算法.光学与光电技术.2005.12,3(6):12~15.
    66 申小阳,唐轶峻,姜柏军,朱文兰,隋成华.仪表的数字字符识别系统.仪表技术与传感器.2005(6):54~57
    67 张昊,徐刚.基于四邻域的二值图像细化算法.信号处理与模式识别.2004(6):24~27.
    68 叶建栲,刘宏林.基于模板匹配的点状符号分离方法[J].测绘工程,1999,8(4):32~34.
    69 Ding Ren, Li Yingzi. A Note on Hausdorff Distance[j]. Mathematical Research and Exposition, 2000, 20(4): 511~514
    70 Huttenlocher D P, Klanderman G A, Ruchlidge W J. Comparing image using the Hausdorff distance. IEEE Tran PAMI. 1993, 15(9): 850~863

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700