边缘检测技术在PVC型材产品检测中的应用研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
计算机视觉检测理论的发展,给自动测量带来新的解决方法。边缘检测技术是计算机自动检测技术的一个重要方面。图象边缘包含了图象的绝大部分有用信息,所以边缘检测在模式识别、计算机视觉、图象分析和图象编码等领域都有重要的研究价值。本文对国内外边缘检测方法的现状和发展进行了综述。
     边缘检测有很多方法,根据课题实际背景,选择了几种比较经典的边缘检测方法,即一阶算子(Roberts算子、Sobel算子、Prewitt算子)、二阶算子(Laplacian算子和Kirsch算子)、LOG算子和Canny算子,对他们进行理论和实际应用研究。
     近几年来迅速发展起来的小波分析,由于其具有时频局部变换的特性及多尺度性,能敏感地反映突变信号及良好的去噪效果,因此能准确、有效地确定图象边缘位置,因此是一种理想的边缘检测方法。本文用B—样条双正交小波构造滤波器组,探索基于多尺度分析的小波变换边缘检测方法的应用。
     本文设计了在Visual C++6.0平台下的图象边缘检测软件。对于输入系统的图象首先进行预处理:灰度转换和滤波去噪;并用几种经典的边缘检测方法对PVC型材产品图象进行边缘检测。用多尺度小波变换的方法在Matlab中对PVC型材产品进行边缘检测,并把检测结果与前面几种经典的边缘检测方法进行比较,认为多尺度小波变换边缘检测是一种效果较好的检测方法。最后对检测的结果进行定性分析。
Computer visual inspection is rising and advancing. It brings a new way to auto-measure. And edge detection is one of great important parts in computer auto visual inspection. Image edge contains much useful information, and it is very important to pattern recognition, computer vision, image analysis and image code. This thesis summarized the current state and development of edge detection in china and abroad.
    There are many methods of edge detection. According to practical task, we choose some classical methods of edge detection including first differential(Roberts operator, Sobel operator and Prewitt operator), second differential(Laplacian operator and Kirsch operator), LOG filter and Canny operator. They are studied in theory and practice applying.
    Wavelet transform is a kind of time-frequency analysis method in signal processing and is becoming more and more popular during these years. Its multi-scale property, localization both in time and frequency domain, sensitivity to the abrupt change of signals, and good to denoising make it an ideal way for edge detection. We use B-spline biorthogonal wavelet to form filter groups, and explore application of edge detection based on multi-scale wavelet transform.
    A analytical and processing software is designed under the environment of Visual C++6.0. Firstly, color intensity is transformed to gray intensity and image is filtered out some noise. Secondly, we use some above classical methods of edge detection. And we use multi-scale wavelet transform to measure the edge of PVC product in Matlab. After comparing these methods, we draw a conclusion: multi-scale wavelet transform is a better method in detecting edge of PVC product. Finally, we make the qualitative analysis of edge detection.
引文
1 D.H.巴拉德,C.M.布朗,计算机视觉,北京,科学出版社,1987
    2 马颂德,张正友,计算机视觉,北京,科学出版社,1998
    3 贾云得,机器视觉,北京,科学出版社,2000
    4 田村秀行,计算机图像处理技术,北京,北京师范大学出版社,1986
    5 孙龙祥,程义民,王以孝,孙启彬,深度图像分析,北京,电子工业出版社,1996
    6 荆仁杰,叶秀清等,计算机图像处理,杭州,浙江大学出版社,1990
    7 K.R.Castlemen,朱志刚,林学訚,石定机等译,数字图像处理,北京,电子工业出版社,1998
    8 Marr D., Hildreth E, Theory of edge detection, Proceedings of the Royal Society of London B, 1976, B207, 483-524
    9 应俊,叶秀清,顾伟康,一个基于知识的边缘提取算法,中国图象图形学报,4A(3),239-242.
    10 Witkin, Scale Space Filtering, Proc. Int. Joint Conf. Artif. Intell., Karlsruhe, Germany, 1983
    11 A.L.Yuille, T.A.Poggio. Scaling Theorems for zero Crossing, IEEE Trans. PAMI, Vol.PAMI-8 No. 1, Jan, 1986
    12 L.D.Wu, S.H.Xie, Scaling theorem for Zero Crossing, IEEE Trans. PAMI, 1986, Vol.PAMI-8
    13 J.Babaud, A.Witkin and R.Duda, Uniqueness of Gaussian Kernel for Scaling-Space Filtering, IEEE Trans, PAMI, Vol.PAMI-8, 1986
    14 G.Cong, S.D.Ma, Nonlinear Diffusion for Early Vision, Proc. Of 13th ICPR, Vienna, Austria, Aug., 1996
    15 J.F.Canny, Finding Edge and Lines in Image, Technical Report AI-TR 720, Massachusetts Artificial Intelligence Laboratory, June, 1983
    16 J.F.Canny, A Computational Approach to Edge Detection, IEEE Trans, PAMI, Vol PAMI-8, 1986
    17 J.Shen, S.Castan, Fast Filter Transform Theory and Design for Image Processing, Proc.IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, USA, 1985
    18 J.Shen, S.Castan, An Optimal Linear Operator for Step Edge Detection, CVIP: Graphical Models and Images Processing, Vol.54, No.2, 1997
    19 R.Derche, Using Canny's Criteria to Derive a Recursively Implemented Optimal Edge Detector, Int.J.Computer Vision, Vol.6, 1987
    20 S.Sarkar, K.L.Boyer, Optimal Infinite Impulse Response Zero Crossing Based Edge Detection.CVGIP, Image Understanding, Vol.54, No.2, 1991
    21 S.D.Ma, B.C.Li, Derivative Computation by Multiscale Filters, Europe-China Workshop on Germetric Modeling and Invariant, Xi'an, China, 1995
    22 Zhou L.X., Gu W.K, Adaptive Edge Detection: A new Criterion and Its Recursive Implementation. Proc. 3 rd ICSP, Beijing, 1996, 1130-1133
    23 周凌翔,顾伟康,最佳边缘检测的准则与算子,模式识别与人工智能,1998,11(1),54-61
    
    
    24 R.M.Haralick and L.G.Shapiro. Computer and Robot Vision. Addison-Wesley Publishing Company, 1992
    25 James J.Lee, Morphological Edge Detection, IEEE Journal of Robotics and Automation, RA-3(3), 142-156,1987
    26 李向吉,丁润涛,脉冲噪声污染图象中的数学形态学边缘检测器,中国图象图形学报,1998,3(11),903-906
    27 R.M Haralick, L.G.Shapiro, Computer and Robot Vision, Addison-Wesley Publishing Company, 1992
    28 Richard J.Feeohs, Multidimension morphological edge detection, Visual Communications and Image Processing Ⅱ, 1987, SPIE Vol.845, 285-292
    29 Song.Xudong, Robust edge detector Based on morphological filters, Pattern Recognition Letters 14, 1993, 889-894
    30 舒昌献,莫玉龙,基于软化形态学的边缘检测,中国图象图形学报,1999,4A(2),139-142
    31 S.Mallat, Multifrequency channel decompositions of images and wavelet, IEEE Transactions on Acoustic, Speech, and Signal Processing, 1989, 37(12)
    32 杨文杰,刘浩学,马昆,边界探测的小波变换方法,中国图象图形学报,1999,4A(1),38—40
    33 Hueckel M, An operator which locates edge in digital pictures, J.ACM, 18(1), 113-125.
    34 Haralick.R.M, A facet model for image data, CGIP, 22, 28-38, 1983
    35 Haralick.R.M, Ridges and valleys on digital image, CVGIP, 22, 28-38, 1983
    36 Haralick.R.M, Digital step edges for zero-crossing of second directional directional derivatives, IEEE Trans. Pattern Analy. Mach. Intel., 58-68, 1984
    37 程正兴,国外小波及应用的概况,工程数学学报,1992,9(3),125-126.
    38 马维祯,殷瑞祥,子波分析与子波变换,广州,华南理工大学出版社,1996
    39 李建平,小波分析与信号处理——理论、应用及其软件实现,重庆,重庆出版社,1997
    40 程正兴,林永平,小波分析在图像处理中的应用,工程数学学报,2001,18,57-86
    41 傅德胜,寿益禾,图形图像处理学,南京,东南大学出版社,2002
    42 赵凯,王宗花,小波变换及其在分析化学中的应用,北京,地质出版社,2001
    43 J.Beltran,J.Lucia,J.Navarro,Edge detection and classfication using Mallat's wavelet,Proc.IEEE Trans,Conf.Acoust.,Speech and Signal Processing,VI: 293-297,1994
    44 张雅兰,杨浩,图像边缘检测的一种简化算法,广西工学院学报,1999,10(1),50-53
    45 徐琼,一种基于小波变换的边缘检测方法,四川轻化工学院学报,2000,13(2),13-16
    46 皮明红,李德仁,一种多尺度边缘检测的方法,信号处理,2000,16(1),5-8
    47 吴秀清,徐云翔,周蓉,一种基于数据融合和小波变换的图像边缘检测方法,中国科学技术大学学报,2001,31(4),482-487
    48 唐良瑞,基于小波高频分量的边缘检测方法,北方工业大学学报,2002,14(1),13-16
    49 夏平,李小玲,罗晓曙,基于多尺度小波算子的图象边缘检测,广西大学学报(自然科学版),2002,27(3),264-267
    50 郭丽,闫萍,匡东权,王永臣,基于小波变换多尺度的边缘检测,沈阳工业学院学报,2003,22(1),85-87
    51 解梅,马争,顾德仁,小波变换在有噪图像边缘检测中的应用,系统工程与电子技术,2000,22(1),26-27,46
    
    
    52 刘薇,马争鸣,基于边缘检测的图像小波阈值去噪方法,中国图象图形学报,2002,7A(8),788-793
    53 聂汉军,沈永增,基于小波变换和模糊中值滤波的图像边缘检测,计算机工程与应用,2002,13,91-92,128
    54 李永忠,B样条小波在图像边缘检测中的应用研究,西北民族学院学宝(自然科学版),1999,20(3),10-14
    55 崔冰辉,员卫国,小波变换的多尺度方法在边缘检测中的应用,西安建筑科技大学学报,2000,32(4),367-370
    56 赵罡,朱心雄,基于小波的B样条曲线多分辨率表示及编辑,计算机辅助设计与图形学学报,2001,13(4),328-332
    57 常辉,胡荣强,基于B样条小波的图像边缘检测,武汉理工大学学报·信息与管理工程版,2002,24(3),31-33
    58 李勇,付小莉,基于小波变换的人体图像边缘检测,中原工学院学报,2002,13(3),5-6,46
    59 金鑫,郑兆瑞,韩焱,基于小波变换的X-射线图像边缘检测,太原理工大学学报,2003,34(2),190-192
    60 赵西安,李德仁,2维对称小波与多尺度影像边缘特征提取,测绘学报,2003,32(4),313-319
    61 马振国,李鹏,杨以涵,李和明,基于小波多分辨率分析法的电能质量检测,华北电力大学学报,2003,30(3),13-16
    62 赵育良,赵宏强,杨波,基于小波变换的航空红外图象目标的多尺度识别,激光与红外,2003,33(4),290-293
    63 潘迅宇,潘树陆,王相海,潘金贵,基于多分别率级小波变换的图象压缩方法,中国图象图形学报,2003,8A(9),1089-1094
    64 杨晓强,王保保,丁斌,一种基于小波多分辨率的数字水印方法,计算机仿真,2003,20(12),96-97,37
    65 陈增强,任东,袁著祉,杜升之,基于多分辨率学校的正交基小波神经网络设计,系统工程学报,2003,18(3),218-222
    66 何宁,基于小波多尺度分析的图象特征点提取方法,微机发展,2003,1(4),61-63
    67 张旸,程建政,超声图像的小波去噪及多尺度边缘提取,无损检测,2003,25(6),279-286
    68 于红玉,沈晋惠,陈世华,张旭,基于小波变换的多分辨率医学图象融合,北京生物医学工程,2003,22(1),21-22,13
    69 杜文正,基于小波多尺度边缘检测的液压缸内泄故障诊断,液压与气动,2003.3,52-53
    70 周长发,精通Visual C++图像编程,北京,电子工业出版社,2000
    71 唐良瑞,马全明,景晓军等,图像处理实用技术,北京,化学工业出版社,2002
    72 干耀南,李树涛,毛建旭,计算机图像处理与识别技术,北京,高度教育出版社,2001
    73 章毓晋,图象分割,北京,科学出版社,2001
    74 赵容椿等,数字图像处理导论,西安,西北工业大学出版社,1995
    75 夏良正,数字图像处理,南京,东南大学出版社,1999
    76 竺子比,光电图像处理,武汉,华中理工大学出版社,2000,9
    
    
    77 陆宗骐,梁诚,灰阶边缘的细化,小型微型计算机系统,2003,24(1)
    78 李宏贵,李兴国,一种改进的梯度算子,中国图象图形学报,2003,8A(3),253-255
    79 吕俊白,基于Laplacian算子的一种新的边缘检测方法,小型微型计算机系统,2002,23(9),1133-1135
    80 宋培华,陆宗骐,高敦岳,基于Log_Prewitt算子的边缘检测算法,小型微型计算机系统,2002,23(11),1401-1402
    81 吕晓琪,王洪仁,刘建勋,基于LOG算子的亚像素边缘检测,包头钢铁学院学报,2002,21(2)
    82 S.Mallat, A theory of multiresolution signal decomposition: The wavelet transform, IEEE Trans. PAMI, 11(7), 674-693, 1989
    83 Y.Meyer, Wavelets algorithms and application, Society for Industrial and Applied Mathematics, Philadephia, 1993
    84 程正兴,小波分析算法与应用,西安,两安交通大学出版社,1998
    85 杨福生,小波变换的工程分析与应用,北京,科学出版社,1999
    86 陈武凡,小波分析及其在图像处理中的应用,北京,科学出版社,2002
    87 李弼程,罗建书,小波分析及其应用,北京,电子工业出版社,2003
    88 赵松年,熊小芸,子波变换与子波分析,北京,电子工业出版社,1996
    89 S.Mallat, Singularity detection and processing with wavelets, IEEE Trans on IT, 1992, 38, 617-643
    90 S.Mallat, Multiresolution approximation and wavelet orthonormal bases of L~2, Trans.Amer.Math.Soc., 1989, 315, 69-87
    91 M.Vetterli, Wavelet and filter bank, theory and design, IEEE Trans on SP, 1992, 40(9), 2207-2231
    92 A. Soman, On orthonormal wavelets and paraunitary filter banks, IEEE Trans. on SP,1993, 41(3), 1170-1183
    93 A.Cohen, Biorthogonal wavelets and dual filter, Wavelets in Image Communication, 1994, 1-26
    94 周心明,兰赛,徐燕,图像处理中几种边缘检测算法的比较,现代电力,2000,17(3)
    95 马艳,张治辉,几种边缘检测算子得比较,工矿自动化,2004,1,54-56
    96 张远鹏,董海,周文灵,计算机图象处理技术基础,北京,北京大学出版社,1996
    97 何斌,马天予,王运坚,朱红莲,Visual C++数字图象处理,北京,人民邮电出版社,2002

© 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