基于数码相机的彩色图像处理研究
|
摘要
与灰度图像相比,彩色图像携带了更多的可视化信息。随着计算机性能的不断增强,机器视觉研究水平的不断提高,多媒体技术和虚拟现实技术的不断完善,特别是彩色成像设备的不断改进,对物体的色彩进行采集、传输和处理必将成为图像处理的重要研究趋势。
彩色图像处理的流程一般包括图像预处理、特征抽取、识别分析三个阶段。图像预处理阶段是彩色图像处理的重要过程,决定了后面处理程序的准确性和难易度,为后面的图像分析奠定了基础。彩色图像分割的目的是将图像中的目标与背景分离,以便于对感兴趣区域进行几何测量和形态评估,分割结果直接影响后续的目标区域的研究结果,能否准确地将目标提取出来决定着整个系统的准确性和可靠性。
结合数码相机图像采集特性和人眼视觉误差,通过理解彩色图像的数据格式,将八叉树量化方法应用于彩色图像的颜色信息量化,采用矢量中值滤波对彩色图像进行噪声消除,以达到对彩色图像进行合理的预处理,并结合实验对矢量中值滤波法的滤波器窗口参数进行讨论分析,随后结合颜色信息相似度理论提出彩色图像预处理效果的评价方法;针对K均值颜色聚类分割方法对分割目标数、图像噪声、被处理对象信息量大小等因素的敏感性特点,提出了一种可变目标分割区域数目的自适应聚类算法,在RGB色彩空间内设计一套彩色图像分割系统。实验获得了合理的颜色量化方法和滤波器窗口参数,处理得到的图像最大色差变化控制在3个CIELAB色差单位;分别对目标区域数是4和8、图像位数在8位和24位的图像进行对比分割实验,随后对实际的工件图进行目标区域数为3的对比处理。结果表明,可通过八叉树结构量化和矢量中值滤波对数码相机采集到的彩色图像进行预处理,然后对经过预处理获得的8位图片进行可变目标区域数的自适应K均值彩色分割,具有分割速度快、分割区域合理、得到的区域边界连通性较好的优点,对尺寸是1022×656的图像分割目标数最高可达到8。
With the continuous increase of computer performance, advancement of machine vision research, development of multimedia technology and virtual reality technology, in particular color imaging devices continue to improve, the collection, transmission and processing of objects’color will become important research trends of image project. Color image processing is the color of specialized information processing technology about color information in pictures. A series of operation technology of color image to achieve desired objectives is known as the color image processing. Color image processing system includes color image segmentation, target identification, feature extraction, and other image processing projects. Image preprocessing decides the accuracy and difficulty of process behind. The purpose of color image segmentation is separate interested object from background, so that is easy to the geometric measurement and configuration evaluation.
Octree arithmetic would be applied in color quantization, Vector Median Filter would be used to eliminate noise, this paper give some common methods of color image preprocessing, then to discuss about window parameters of Vector Median Filter, obtained effect evaluation methods through color information similarity theory at last. An adaptive clustering algorithm with variable number of the target area is designed in RGB color space. The reasonable structures of the processing were found for digital camera, the chromatism will be controlled within 3ΔE units. Pretreated and un-pretreated color images were segmented respectively, then a workpiece was experimented within the methods designed above. The experiments results showed that Octree Color Quantization and Vector Median Filter perform all well in preprocessing of color image, and adaptive K-means color segmentation is a faster, reasonable regional segmentation and the regional border connectivity color image segmentation tool, the segmentation areas of the highest number of goals can be achieved 8 for 1022*686 color picture pretreated.
彩色图像处理的流程一般包括图像预处理、特征抽取、识别分析三个阶段。图像预处理阶段是彩色图像处理的重要过程,决定了后面处理程序的准确性和难易度,为后面的图像分析奠定了基础。彩色图像分割的目的是将图像中的目标与背景分离,以便于对感兴趣区域进行几何测量和形态评估,分割结果直接影响后续的目标区域的研究结果,能否准确地将目标提取出来决定着整个系统的准确性和可靠性。
结合数码相机图像采集特性和人眼视觉误差,通过理解彩色图像的数据格式,将八叉树量化方法应用于彩色图像的颜色信息量化,采用矢量中值滤波对彩色图像进行噪声消除,以达到对彩色图像进行合理的预处理,并结合实验对矢量中值滤波法的滤波器窗口参数进行讨论分析,随后结合颜色信息相似度理论提出彩色图像预处理效果的评价方法;针对K均值颜色聚类分割方法对分割目标数、图像噪声、被处理对象信息量大小等因素的敏感性特点,提出了一种可变目标分割区域数目的自适应聚类算法,在RGB色彩空间内设计一套彩色图像分割系统。实验获得了合理的颜色量化方法和滤波器窗口参数,处理得到的图像最大色差变化控制在3个CIELAB色差单位;分别对目标区域数是4和8、图像位数在8位和24位的图像进行对比分割实验,随后对实际的工件图进行目标区域数为3的对比处理。结果表明,可通过八叉树结构量化和矢量中值滤波对数码相机采集到的彩色图像进行预处理,然后对经过预处理获得的8位图片进行可变目标区域数的自适应K均值彩色分割,具有分割速度快、分割区域合理、得到的区域边界连通性较好的优点,对尺寸是1022×656的图像分割目标数最高可达到8。
With the continuous increase of computer performance, advancement of machine vision research, development of multimedia technology and virtual reality technology, in particular color imaging devices continue to improve, the collection, transmission and processing of objects’color will become important research trends of image project. Color image processing is the color of specialized information processing technology about color information in pictures. A series of operation technology of color image to achieve desired objectives is known as the color image processing. Color image processing system includes color image segmentation, target identification, feature extraction, and other image processing projects. Image preprocessing decides the accuracy and difficulty of process behind. The purpose of color image segmentation is separate interested object from background, so that is easy to the geometric measurement and configuration evaluation.
Octree arithmetic would be applied in color quantization, Vector Median Filter would be used to eliminate noise, this paper give some common methods of color image preprocessing, then to discuss about window parameters of Vector Median Filter, obtained effect evaluation methods through color information similarity theory at last. An adaptive clustering algorithm with variable number of the target area is designed in RGB color space. The reasonable structures of the processing were found for digital camera, the chromatism will be controlled within 3ΔE units. Pretreated and un-pretreated color images were segmented respectively, then a workpiece was experimented within the methods designed above. The experiments results showed that Octree Color Quantization and Vector Median Filter perform all well in preprocessing of color image, and adaptive K-means color segmentation is a faster, reasonable regional segmentation and the regional border connectivity color image segmentation tool, the segmentation areas of the highest number of goals can be achieved 8 for 1022*686 color picture pretreated.
引文
[1]Hertzmann A,Jacobs C E,Oliver N,et al..Image analogies.In: Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques,ACM Press,2001:327~340
[2]徐红,朱正芳,主观评价法在颜色研究中的应用,光学技术,1995,1:13~32
[3]CIE.Colorimetry:2nd ed.CIE publications No.15.2, Vienna:Central Bureau of the CIE,1986
[4]何东健,耿楠,张义宽,数字图像处理,西安:西安电子科技大学出版社,2004:2~7 30~32
[5]Gudrun Klinker,Steven Shafer,Takeo Kanade.A physical approach to color image understanding.International Journal of Computer Vision,1990,21(4):7~38
[6]阮秋琦,数字图像处理学,北京:电子工业出版社,2001
[7] Zhao J.,Tow J.,Katupitiya J..On-tree Fruit Recognition Using Texture Properties and Color Data.Intelligent Robots and Systems,2005:263~268
[8] Sammouda, M.,Sammouda, R.,Niki, N.,et al..Segmentation and analysis of liver cancer pathological color images based on artificial neural networks.Med Imaging Technol,1999,17(4):453~454
[9]Eun Yi Kim , Se Hyun park.Automatic video segmentation using genetic algorithms.Evolutionary computer vision and image understanding,2006:27(11),1252~1265
[10]Lucchese L, Mitra SK.Unsupervised segmentation of color mages based on K-means clustering in the chromaticity plane. In: Collins F, ed. Proc. of the Content-Based Access of Image and Video Libraries. Los Alamitos, IEEE Computer Society Press,1999:74~78
[11]李晨,车牌识别技术的研究及其在智能交通系统中的应用:[硕士学位论文],西安,西北工业大学,2006
[12]顾丹丹,复杂背景下自动人脸检测方法的研究:[硕士学位论文],大连理工大学,2005
[13]徐惠荣,叶尊忠,应义斌,基于彩色信息的树上柑橘识别研究,农业工程学报,2005,21[5]:98~101
[14]罗玮,彭复员,彩色瓷砖的自动分类系统,华中科技大学学报,2001,29(3):79~81
[15]沈兰荪,蔡轶珩,刘长江,等,中医舌象信息采集与分析新进展,世界科学技术:中医药现代化,2007,9(5):97~101
[16]高朝晖,黄卫,基于彩色图像车牌分割研究,公路交通科技,2004,21(6):114~117
[17]Guo Feng,Cao Qixin,Study on Color Image Processing Based Intelligent Fruit Sorting System,In: Proceedings of the 2004. Fifth World Congress on Intelligent Control and Automation (WCICA),2004,6:4802~4805
[18]章毓晋,图象处理和分析,北京:清华大学出版社,1999
[19]Deutsch M,Garcia J,Mandlovic D,Multi-chnnel signal output color pattern recognition by use of a joint transforms correlation,Applied Optics,1996,35(35):6976~6982
[20]Castleman K R.Digital image processing,Prentice Hall Inc.,1996
[21]赵君,王乘,图像格式分析与图像显示实现,计算机与数字工程,2004
[22]张维谷,林福宗,图像文件格式(上)——Windows编程,北京:清华大学出版社,1996
[23]董士海,郑全战,徐曦,等,图像格式编程指南,北京:清华大学出版社,1994
[24]汤顺青,色度学,北京:北京理工大学出版社,1990
[25]冯斌,计算机视觉信息处理方法与水果分级检测研究技术:[博士学位论文],中国农业大学,2002:3~4 59~65
[26]黄国祥,RGB颜色空间以及应用研究,[博士学位论文],长沙:中南大学,2002:8~9
[27]韩晓薇,彩色图像处理技术,[博士学位论文],沈阳,东北大学,2005
[28]何国兴,颜色科学,上海,东华大学出版社,2004
[29]郑建烨,郝重阳,雷方元,等,用色彩直方图特征进行偏色图像的自动检测和校正,中国图像图形学报,2003,8(9):1001~1007
[30]周世生,高等色彩学,北京:印刷工业出版社,1997
[31]方志杰,GretagMacbeth在线颜色测量系统在造纸纸页颜色测量中的应用,西南造纸,2005,34(1):56~58
[32]韩丽,航空数码相机图像处理研究,[硕士学位论文],西安:西北工业大学,2007
[33]Guoxin Jia, Xinghua Qu, Hui Gong, Shenghua Ye. A Research on the Colorimetric Characterization of Digital Camera. In:Conference Committee of the 8th International Symposium on Measurement Technology and Intelligent Instruments (ISMTII 2007)
[34]G.Joy,Zhigang Xiang,Reducing false contours in quantized color images,Computers and Graphics,1996,20(2):231~242
[35]Zhigang Xiang,G.Joy,Color image quantization by agglomerative clusting,IEEE computer graphics an applications,1991,14(1):44~48
[36]Heckbert P.Color image quantization for frame buffer display, Computer Graphics,1982,16(2): 297~307
[37]Orchard M T,Bouman C A. Color quantization of image,IEEE Trans Signal Processing,1991,39(12): 2677~2690.
[38]Andreadis I, Browne M A, Swift J A. Image pixel classification by chromaticity analysis,Pattern Recognition Letters, 1990, 11(1): 52~58.
[39]周长发,Visual C++图像处理编程,北京:电子工业出版社,2006
[40]李云飞,李敏杰,司国良,等,TDI-CCD图像传感器的噪声分析与处理,光学精密工程,2007,15(8):1196~1202
[41]王明佳,张旭光,韩广良,等,自适应权值滤波消除图像椒盐噪声的方法,光学精密工程,2007,15(5):779~783
[42]吴玉莲,图像处理的中值滤波方法及其应用, [硕士学位论文],西安:西安电子科技大学,2006
[43]Trahanias P E, Karakos D G ,Venetsan0p0ul0s A N. Directional processing of color images:theory and experimental results[J].IEEE Transactions on Image Processing,l996,5(6):868～880.
[44]Trahanias P E,Venetanopoulos A N.Vector directional filters:a new class of multichannel image processing filters.IEEE Transactions on Image Processing,1993,2(4):528~534
[45]Shepard R N. Toward a universal law of generalization for psychological science.Science,1987,237:1317~1323
[46]K.N.Plataniotis,D.Androutsos,A.N.Venetsanopoulos. Color Image Processing Using Adaptive Vector Directional Filters. IEEE Transactions on Circuits and Systems-II:Analog and Digital Signal Processing,1998,45(10):1414~1419
[47]Karakos D G , Trahanias P E . Generalized multichannel image-filtering structure.IEEE Transactions on Image Processing,1997,6(7):1038~1045
[48]Plataniotis K N, Androutsos D, Venetsanopoulos A N. Content-based color image filters. Electronics Letters, 1997, 33: 203~212
[49]单勇,王润生,彩色图像混合滤波算法,数据采集与处理,2006,21(12):67~70
[50]Jaakko Astola,Petri,Haacisto,Yrjo neuvo.Vector Median Filters.Proceedings of The IEEE,1990,78(4): 678~689
[51]王明佳,张旭光,韩广良,等,自适应权值滤波消除图像椒盐噪声的方法,光学精密工程,2007,15(5): 779~783
[52]王鑫,阎晓东,数码相机CCD噪点的检测,影像技术, 2004,1:30~33
[53]Chen W, Er M J, Wu Sh Q. Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithm domain[J]. IEEE Transactions on Systems, Man, and Cybernetics. Part B:Cybernetics, 2006, 36(2): 458~466
[54]章毓晋,图像分割,北京,科学出版社,2001
[55]R M Haralick,L G Shapro. Image Segmentation. Techniques computer Vision Graphics. Image Process,1985,29: 100~132
[56]B J Schacter,L S Davis,A Rosenfeld. Scene Segmentation by Cluster Detection in Color Spaces.ACM Sigart Bulletin,1976,16~17
[57]R Ohlander, K Price, D R Reddy.Picture Segmentation Using a Recursive Region Splitting Method. Computer Craphics Image Process.1978,8:313~333
[58]Mangin J F,Frouin V,Bloch I,et al.,1995,5(3):297~318
[59]Falcao A X. User-Steered Image Segmentation Paradigms: Live Wire and Live Lane,Graphic Models and Image Processing,1998,50(4):233~260
[60]Klinker G J,Shafer S A. Image Segmentation and Reflection Analysis Through Color. Application of Artifical Intelligence VI,1988
[61]Klunker G J,Shafer S A. A physical Approach to Color Image Understanding International,Journal of Computer Vision,1990,4(1):7-38
[62]Cheng H D.,Chen J R.,Li J G.,Threshold Selection Based on Fuzzy C-partition Entropy Approach. Pattern Recognition,1998,31(7):857~870
[63]Huang L K,Wang M J,Image Thresholding by Minimizing the Measure of Fuzziness Pattern Recognition,1995,28(1):41-51
[64]Blanz W E,Gish S L.A Connextionst Classfier Archtecture Applided to Image Segmentation,In:Proc of 10th Inernational Conference on Parrern Recognition,New Jersey,USA,1990:272~277
[65]Babaguclh N.,Yamada K.,Kisc K.,et al.,In:Connerionist Model Binanzation In Proc of the 10th International Conference on Pattern Recogniton,New Jersey,USA,1990:51~56
[66]Takalp A M. Digital Video Processing Prentree, Prentice Hall Inc.,1995
[67]林开颜,徐立鸿,快速模糊C均值聚类彩色图像分割方法,中国图像图形学报2004,9(2):160~163
[68]H D Cheng, X H Jiang, Y Sun. Color Image Segmentation Advance and Prospects,2001,34:2259~2281
[2]徐红,朱正芳,主观评价法在颜色研究中的应用,光学技术,1995,1:13~32
[3]CIE.Colorimetry:2nd ed.CIE publications No.15.2, Vienna:Central Bureau of the CIE,1986
[4]何东健,耿楠,张义宽,数字图像处理,西安:西安电子科技大学出版社,2004:2~7 30~32
[5]Gudrun Klinker,Steven Shafer,Takeo Kanade.A physical approach to color image understanding.International Journal of Computer Vision,1990,21(4):7~38
[6]阮秋琦,数字图像处理学,北京:电子工业出版社,2001
[7] Zhao J.,Tow J.,Katupitiya J..On-tree Fruit Recognition Using Texture Properties and Color Data.Intelligent Robots and Systems,2005:263~268
[8] Sammouda, M.,Sammouda, R.,Niki, N.,et al..Segmentation and analysis of liver cancer pathological color images based on artificial neural networks.Med Imaging Technol,1999,17(4):453~454
[9]Eun Yi Kim , Se Hyun park.Automatic video segmentation using genetic algorithms.Evolutionary computer vision and image understanding,2006:27(11),1252~1265
[10]Lucchese L, Mitra SK.Unsupervised segmentation of color mages based on K-means clustering in the chromaticity plane. In: Collins F, ed. Proc. of the Content-Based Access of Image and Video Libraries. Los Alamitos, IEEE Computer Society Press,1999:74~78
[11]李晨,车牌识别技术的研究及其在智能交通系统中的应用:[硕士学位论文],西安,西北工业大学,2006
[12]顾丹丹,复杂背景下自动人脸检测方法的研究:[硕士学位论文],大连理工大学,2005
[13]徐惠荣,叶尊忠,应义斌,基于彩色信息的树上柑橘识别研究,农业工程学报,2005,21[5]:98~101
[14]罗玮,彭复员,彩色瓷砖的自动分类系统,华中科技大学学报,2001,29(3):79~81
[15]沈兰荪,蔡轶珩,刘长江,等,中医舌象信息采集与分析新进展,世界科学技术:中医药现代化,2007,9(5):97~101
[16]高朝晖,黄卫,基于彩色图像车牌分割研究,公路交通科技,2004,21(6):114~117
[17]Guo Feng,Cao Qixin,Study on Color Image Processing Based Intelligent Fruit Sorting System,In: Proceedings of the 2004. Fifth World Congress on Intelligent Control and Automation (WCICA),2004,6:4802~4805
[18]章毓晋,图象处理和分析,北京:清华大学出版社,1999
[19]Deutsch M,Garcia J,Mandlovic D,Multi-chnnel signal output color pattern recognition by use of a joint transforms correlation,Applied Optics,1996,35(35):6976~6982
[20]Castleman K R.Digital image processing,Prentice Hall Inc.,1996
[21]赵君,王乘,图像格式分析与图像显示实现,计算机与数字工程,2004
[22]张维谷,林福宗,图像文件格式(上)——Windows编程,北京:清华大学出版社,1996
[23]董士海,郑全战,徐曦,等,图像格式编程指南,北京:清华大学出版社,1994
[24]汤顺青,色度学,北京:北京理工大学出版社,1990
[25]冯斌,计算机视觉信息处理方法与水果分级检测研究技术:[博士学位论文],中国农业大学,2002:3~4 59~65
[26]黄国祥,RGB颜色空间以及应用研究,[博士学位论文],长沙:中南大学,2002:8~9
[27]韩晓薇,彩色图像处理技术,[博士学位论文],沈阳,东北大学,2005
[28]何国兴,颜色科学,上海,东华大学出版社,2004
[29]郑建烨,郝重阳,雷方元,等,用色彩直方图特征进行偏色图像的自动检测和校正,中国图像图形学报,2003,8(9):1001~1007
[30]周世生,高等色彩学,北京:印刷工业出版社,1997
[31]方志杰,GretagMacbeth在线颜色测量系统在造纸纸页颜色测量中的应用,西南造纸,2005,34(1):56~58
[32]韩丽,航空数码相机图像处理研究,[硕士学位论文],西安:西北工业大学,2007
[33]Guoxin Jia, Xinghua Qu, Hui Gong, Shenghua Ye. A Research on the Colorimetric Characterization of Digital Camera. In:Conference Committee of the 8th International Symposium on Measurement Technology and Intelligent Instruments (ISMTII 2007)
[34]G.Joy,Zhigang Xiang,Reducing false contours in quantized color images,Computers and Graphics,1996,20(2):231~242
[35]Zhigang Xiang,G.Joy,Color image quantization by agglomerative clusting,IEEE computer graphics an applications,1991,14(1):44~48
[36]Heckbert P.Color image quantization for frame buffer display, Computer Graphics,1982,16(2): 297~307
[37]Orchard M T,Bouman C A. Color quantization of image,IEEE Trans Signal Processing,1991,39(12): 2677~2690.
[38]Andreadis I, Browne M A, Swift J A. Image pixel classification by chromaticity analysis,Pattern Recognition Letters, 1990, 11(1): 52~58.
[39]周长发,Visual C++图像处理编程,北京:电子工业出版社,2006
[40]李云飞,李敏杰,司国良,等,TDI-CCD图像传感器的噪声分析与处理,光学精密工程,2007,15(8):1196~1202
[41]王明佳,张旭光,韩广良,等,自适应权值滤波消除图像椒盐噪声的方法,光学精密工程,2007,15(5):779~783
[42]吴玉莲,图像处理的中值滤波方法及其应用, [硕士学位论文],西安:西安电子科技大学,2006
[43]Trahanias P E, Karakos D G ,Venetsan0p0ul0s A N. Directional processing of color images:theory and experimental results[J].IEEE Transactions on Image Processing,l996,5(6):868～880.
[44]Trahanias P E,Venetanopoulos A N.Vector directional filters:a new class of multichannel image processing filters.IEEE Transactions on Image Processing,1993,2(4):528~534
[45]Shepard R N. Toward a universal law of generalization for psychological science.Science,1987,237:1317~1323
[46]K.N.Plataniotis,D.Androutsos,A.N.Venetsanopoulos. Color Image Processing Using Adaptive Vector Directional Filters. IEEE Transactions on Circuits and Systems-II:Analog and Digital Signal Processing,1998,45(10):1414~1419
[47]Karakos D G , Trahanias P E . Generalized multichannel image-filtering structure.IEEE Transactions on Image Processing,1997,6(7):1038~1045
[48]Plataniotis K N, Androutsos D, Venetsanopoulos A N. Content-based color image filters. Electronics Letters, 1997, 33: 203~212
[49]单勇,王润生,彩色图像混合滤波算法,数据采集与处理,2006,21(12):67~70
[50]Jaakko Astola,Petri,Haacisto,Yrjo neuvo.Vector Median Filters.Proceedings of The IEEE,1990,78(4): 678~689
[51]王明佳,张旭光,韩广良,等,自适应权值滤波消除图像椒盐噪声的方法,光学精密工程,2007,15(5): 779~783
[52]王鑫,阎晓东,数码相机CCD噪点的检测,影像技术, 2004,1:30~33
[53]Chen W, Er M J, Wu Sh Q. Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithm domain[J]. IEEE Transactions on Systems, Man, and Cybernetics. Part B:Cybernetics, 2006, 36(2): 458~466
[54]章毓晋,图像分割,北京,科学出版社,2001
[55]R M Haralick,L G Shapro. Image Segmentation. Techniques computer Vision Graphics. Image Process,1985,29: 100~132
[56]B J Schacter,L S Davis,A Rosenfeld. Scene Segmentation by Cluster Detection in Color Spaces.ACM Sigart Bulletin,1976,16~17
[57]R Ohlander, K Price, D R Reddy.Picture Segmentation Using a Recursive Region Splitting Method. Computer Craphics Image Process.1978,8:313~333
[58]Mangin J F,Frouin V,Bloch I,et al.,1995,5(3):297~318
[59]Falcao A X. User-Steered Image Segmentation Paradigms: Live Wire and Live Lane,Graphic Models and Image Processing,1998,50(4):233~260
[60]Klinker G J,Shafer S A. Image Segmentation and Reflection Analysis Through Color. Application of Artifical Intelligence VI,1988
[61]Klunker G J,Shafer S A. A physical Approach to Color Image Understanding International,Journal of Computer Vision,1990,4(1):7-38
[62]Cheng H D.,Chen J R.,Li J G.,Threshold Selection Based on Fuzzy C-partition Entropy Approach. Pattern Recognition,1998,31(7):857~870
[63]Huang L K,Wang M J,Image Thresholding by Minimizing the Measure of Fuzziness Pattern Recognition,1995,28(1):41-51
[64]Blanz W E,Gish S L.A Connextionst Classfier Archtecture Applided to Image Segmentation,In:Proc of 10th Inernational Conference on Parrern Recognition,New Jersey,USA,1990:272~277
[65]Babaguclh N.,Yamada K.,Kisc K.,et al.,In:Connerionist Model Binanzation In Proc of the 10th International Conference on Pattern Recogniton,New Jersey,USA,1990:51~56
[66]Takalp A M. Digital Video Processing Prentree, Prentice Hall Inc.,1995
[67]林开颜,徐立鸿,快速模糊C均值聚类彩色图像分割方法,中国图像图形学报2004,9(2):160~163
[68]H D Cheng, X H Jiang, Y Sun. Color Image Segmentation Advance and Prospects,2001,34:2259~2281