摘要
纹理分析是计算机视觉和数字图像处理中的一个重要的研究课题,而如何获得纹理特征是其中的重要环节。本文主要围绕图像特征提取、BP神经网络技术和遗传算法在图像分类与检索中的应用展开,首先介绍了图像检索技术的发展概况、关键技术和研究现状,在系统讨论纹理特征提取的过程中,采用了基于纹理灰度共生矩阵作为图像特征。其次,为了提高图像检索效率,本文将基于遗传算法改进的BP神经网络引入到图像分类中,结合纹理特征进行图像分类识别,并用于图像检索中。本文的主要工作和创新如下:
1.综述了基于纹理分类的图像检索技术,介绍了纹理的定义、分类、分析方法和纹理分析的应用。鉴于纹理的分析是基于纹理的图像检索技术的重点,论文分别分析总结了统计分析、结构分析、模型分析和频谱分析四类纹理分析方法。
2.提出了一种新的图像分类算法,首先利用灰度共生矩阵方法提取出图像的纹理特征,然后结合遗传算法优化的BP神经网络进行网络训练和样本分类。本算法避免了无关样本图像进行图像特征匹配的过程,有效地节省了图像检索的时间开销。实验结果表明,将图像的纹理特征和改进的BP神经网络相结合,有效准确地实现了对给定图像的分类,缩小了查找图像的范围,提高了图像的查准率,并且很大程度上减少了图像检索的匹配时间。
Texture analysis is an important research topic of computer vision and image processing. How to get the texture feature is the most important step. The exploratory research begins with the application of the texture feature extraction, BP neural network and genetic algorithm in image retrieval. Firstly, the development, key technology and research status of image retrieval technology are introduced. Gray level co-occurrence matrix is adopted as the image characteristics while discussing texture feature extraction. Secondly, in order to improve the efficiency of image retrieval, BP neural network is presented for image retrieval, which is also optimized by genetic algorithm.
The main research work and innovation of this thesis are given as follows.
1. Retrieval technology based on texture feature is summarized, the definition, classification, analytical method and application of texture are introduced and analyzed. The statistical analysis, structural analysis, model analysis and spectrum analysis for texture are also discussed in detail in the paper are researched and summarized.
2. A new image classification algorithm is proposed. Firstly, the GLCM is adopted to describe texture feature of an image, combine the neural network optimized by the genetic algorithm for network training and sample classification. It avoids the image feature matching process of the independent image, and ruduces the time complexity for image retrieval. Experiment results show that it can classify the image effectively and accurately combining texture characteristics and the improved BP neural network. It shows that the proposed algorithm is effective and feasible in image classification and image retrieval.
引文
[1]孙君顶.基于内容的图像检索技术研究[D].西安电子科技大学,2005.
[2] Rui Y., Huang T. S., Chang S. F.. Image retrieval: current techniques, Promising directions, and open issues. Journal of visual communication and image representation, 1999, 10: 39-62.
[3]戴丛蕊,徐虹,金燕.卫星遥感资料在云南大雾检测中的应用.云南地理环境研究,2008,20(6):51-54.
[4]王淑华.基于纹理特征的气象云图云雾自动分离算法研究.上海交通大学,2002.
[5] Yokoyama R., Robert M. Haralick. Texture Pattern Image Generation by Regular Markov Chain. Pattern Recognition, 1979,11:225-234.
[6] Jain A K., Farrokhnia F.. Unsupervised texture segmentation using Gabor filter. Pattern Recognition ,1991,24(12):1167-1186.
[7] Vande Wouwer G., Scheunders P., Van Dyck D.. Statistical texture characterization from discrete wavelet representation. IEEE Transaction on Image Processing,1999,8(4): 592-598.
[8] Lu C. S., Chung P.C., Chen C. F.. Unsupervised Texture Segmentation Via Wavelet Transform. Pattern Recognition,1997,30(5):729-742.
[9] Crouse M. S., Nowak R. D., Baraniuk R. G... Wavelet-based statistical signal processing using hidden Markov models. IEEE Transaction on Signal Processing,1998,46:886-902.
[10]罗晓晖,李见为.基于特征尺度及多尺度分解的纹理分割.计算机工程,2003,29(3):124- 168.
[11] Haralick R. M.. Statistical and Structural Approaches to Texture[J]. Proc. IEEE,1979,67: 786-804.
[12] Tamura H., et a1. Texture features corresponding to visual perception . IEEE Transactions on Systems, Man, and cybernetics,1978,SMC-8(6):460-473.
[13] Unser M.. Texture classification and segmentation using wavelet frames[J]. IEEE Transaction on Image Processing, 1995,4(11):1549-1560.
[14] Nicolas Vandenbroucke, Ludovic Macaire, Jack-Gerard Postaire. Color Image Segmentation by Supervised Pixel Classification in a Color Texture Feature Space: Application to Soccer Image segmentation[C]. International conference on Pattern Recognition (ICPR’00)[A], Barcelona, Spain,2000,3(09):03-09.
[15] Flickner Metal. Query by Image and Video Content: The QBIC System. IEEE Computer , 1995, 28(9):23-32.
[16] Hsieh J. and Grimson W.,“Spatial template extraction for image retrieval by region matching”, IEEE Trans. On Image Processing, vol.12,2003.
[17] Pentland A., Picard R. W., Sclaroff S. Photobook: Content-Based Manipulation of Image Database. Int. Journal of Computer Vision, 1996.
[18] Smith J. R., Chang S. F.. VisualSeek: A Fully Automated Content-Based Image Query System. ACM Multimedia 96, Boston, MA, Nov.
[19] Sclaroff S., Taycher L., Cascia M. L.. Image-Rover: a content-based image browser for the World Wide Web. In Proc. IEEE Workshop on Content-Based Access of Image and Video Libraries,1997,2-9.
[20]韦娜,耿国华,周明全.基于内容的图像检索系统性能评价.中国图象报,2004,9(11):1271-1276.
[21]周明全,耿国华,韦娜.基于内容图像检索技术.北京:清华大学出版社,2007.
[22]李悦,黄文字,覃团发.综合MREG-7全局及局部主颜色的图像检索方法.计算机应用研究, 2009,26(4):1581-1583.
[23]陈纯.计算机图像处理技术与算法.北京:清华大学出版社,2003,89-125.
[24] Swain M. J., Ballard D. H.. Color indexing. International Journal of Computer Vision,1991, 7(1): ll-32.
[25] Stricker M., Orengo M.. Similarity of Color Image. In Proc. SPIE Storage and Retrieval for Image and Video Database, 1995,V01.2420,381-392.
[26] Huang J.. Image indexing using color correlogram. IEEE Int. Conf on Computer Vision and Pattern Recognition, San Juan, Puerto Rico, June 17-19,1997:762-768.
[27] Hsu W., Chua T., Pung H.. An Integrated Color-Spatial Approach to Content-Based Image Retrieval. Proc. of the ACM MM Conf., San Francisco,CA:Nov.1995,305-313.
[28] Pass G., Zabih R.. Histogram Refinement for Content-Based Image Retrieval. IEEE Workshop on Applications of Computer Vision,1996(12):96-102.
[29] DING Gui-guang , DAI Qiong-hai, XU Wen-li. A methoe for image retrieval technique based on local distribution feature s of interest points [J]. Journal of Optoelectronics·Laser (光电子·激光) ,2005 ,16 (9) :1101-1106.
[30] YANG Yong, ZHENG Chong-xun, LIN Pan, et al. A new algorithm for image segmentation based on modified fuzzy C-means clustering[J].Journal of Optoelectronics·Laser (光电子·激光),2005,16 (9):1118-1122.
[31] Rao A., Srihari R., Zhang Z.. Spatial color histogram for content-based retrieval[A]. In 11thIEEE International Conference on Tools with AI[C] ,1999,183-186.
[32] Lim S., Lu G. J.. Spatial statistics for content based image retrieval[A]. Proceedings of the International Conference on Information Technology: Computers and Communications[C]. 2003,28-30.
[33]孙君顶,毋小省.基于颜色分布特征的图像检索.光电子·激光,2006,17(8):1009-1013.
[34]徐建华.图像处理与分析.北京:科学出版社,1994.
[35]章毓晋.图像分割.北京:科学出版社,2001.
[36]李弼程,彭天强,彭波.智能图像处理技术.北京:电子工业出版社,2004.
[37]向世明.纹理图像统计及其应用研究[D].中科院计算技术研究所,2004.
[38] Chen D., Wang L.. Texture features based on texture. Spectrum PR,1991,24:391-399.
[39] Falontsos C., Barber R., Flickner M., et al. Efficient and effective querying by image content. Journal of intelligent information systems,1994,3(1):231-262.
[40] Huang X. L., Shen L S.. A method of shape encoding and retrieval. Journal of Electronics, 2002, 19(3):302-306.
[41] Malki J., Boujemaa N., Nastar C., et a1. Region Queries Without Sementation for Image Retrieval by Content. Proc. of Visual Information and Information System. London, UK: Springer-Verlag,1999,115-122.
[42]戴声扬,章毓晋.图像检索中的两层描述和非对称区域匹配.电子学报.2005,4.
[43]曾智勇,张学军,崔江涛,周利华.基于显著兴趣点颜色及空间分布的图像检索新方法.光子学报,2006,35(2):308-311.
[44] Zhang D.S., Lu G.J.. Evaluation of similarity measurement for image retrieval, IEEE Int. Conf. Neural Networks & Signal Processing, Nan Jing, China, 2003, 928-931.
[45] Swain M. J., Ballard D. H... Color indexing. Intl. J. on Computer Vision,1991, 7(1):11-32.
[46] Hafner J., Sawhney H., Equitz W., et al, Efficient color histogram indexing for quadratic form distance functions. IEEE Trans. On Pattern Analysis and Machine Intelligence, 1995, 17(7): 729-736.
[47] Arnold W.M., Marcel W., Simone S., et al. Content-based image retrieval at the end of the early years. IEEE Trans. On PAMI, 2000, 22(12):1349-1379.
[48] Manjunath B.S., Phillipe S., Thomas S.. Introduction to MPEG-7: Multimedia Content Description Interface, John Wiley & Sons, Inc., New York, NY, 2002.
[49] Mehtre B.M., Kankallllalli M.S., Narasimhalu A.D.. Color matching for image retrieval. PatternRecognition Letters, 1995, 16:325-331.
[50] Hsieh I.S., Fan K. C.. Multiple classifiers for color flag and trademark image retrieval. IEEE Trans. On Image Processing, 2001,10(6):938-950.
[51] Jain A.K., Vailaya A.. Shape-based retrieval: a case study with trademark image databases. Pattern Recognition, 1998, 31(9):1369-1390.
[52] Lee H.Y., Lee H.K., Ha Y.H.. Spatial color descriptor for image retrieval and video segmentation. IEEE Trans. On Multimedia, 2003, 5(3):358-367.
[53]茹立云,彭潇,苏中等.基于内容图像检索中的特征性能评价.计算机研究与发展, 2003, 40(11):1566-1570.
[54]孙君顶,赵珊.图像低层特征提取与检索技术.北京:电子工业出版社,2009.
[55] Coggins JM, Jain AK. A spatial filtering approach to texture analysis. Pattern Recognition, 1985,3:195-203.
[56] Castleman K R著.朱志刚等译.数字图像处理.北京:电子工业出版社,2002.
[57] Sklansky J. Image segmentation and feature extraction. IEEE Transactions on Systems, Man, and Cybernetics,1978,8(5): 237-247.
[58] Haralick R.M., Shanmugam K. and Its hak Dinstein. Texture Features for Image Classification. IEEE Trans. On Systems, Man, and Cybernetics,1973,SMC-3(6): 610-621.
[59] Weszka J. S., Dyer C.R., Resenfeid A.. A comparative study of texture measures for terrain classification. IEEE Transaction on Systems, Man, and Cybernetics.1976,6(4): 269-285.
[60]洪继光.灰度-梯度共生矩阵纹理分析方法.自动化学报, 1984,10(1):22-25.
[61]盛文,杨江平,柳建,吴新建.一种基于纹理元灰度模式统计的图像纹理分析方法.电子学报,2000,28(4).
[62] Ojala T., Pietikainen M., Maenpaa T.. Multiresolution gray scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24: 971-987.
[63] Xie X. and Mirmehdi M.. TEXEM: Texture exemplars for defect detection on random textured surfaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(8): 1454- 1464.
[64] Beck J.. Effect of orientation and of shape similarity on perceptual grouping. Perceptual psychophysics,1966,1(7):300-302.
[65] Bergen J.R., Julesz B.. Parallel versus serial processing in rapid pattern discrimination. Natural,1983,303(7):696-698.
[66] Bergen J. R., Adelson E. H.. Early vision and texture perception using feature distribution. Pattern Recognition, 1999,32(3):447-486.
[67] Tuceryan M., Jain A.K.. Texture segmentation using Voronoi Polygons. IEEE Trans on PAMI, 1990,12:211-216.
[68] Shapiro L., Stockman G.. Computer Vision. Prentice Hall, 2001.
[69] Carlucci L..A formal system for texture languages. Pattern Recognition,1972,5(1):53-72
[70] Lu S.Y., Fu K.S.. A Syntactic Approach to Texture. Analysis. CGIP, 1978,7:303-330.
[71] Ma W. T., Zhang H. J.. Benchmarking of image features for content-based retrieval. Signals, Systems & Computers. Conference Record of the Thirty-Second Asilomar Conference, Pacific Grove, USA, 1998,1:253-257.
[72] Cross G. R., Jain A. K.. Markov random field texture models. IEEE Transactions on Pattern Analysis and Machine intelligence, 1983, 5(1):25-38.
[73] Francos J. M., Meiri A. Z., Porat. B.A.. Unified texture model based on a 2D wold-like decomposition. IEEE Trans. on Signal Processing, 1993,41(8):2665-2678.
[74] Timo O., Matti Pietikainen, Topi M.. Multisolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,7:971-987.
[75] Geman S., Geman D.. Stochastic relaxation Gibbs distribution and the Bayesian restoration of images. IEEE Trans Pattern Anal Machine Intell,1984,16:721-741.
[76] Cohen F., Fan Z., Attali S.. Automated inspection of textile fabrics using textural models. IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(8): 803-809.
[77] Mao J., Jain A.K.. Texture classification and segmentation using multiresolution simultaneous autoregressive models. Pattern Recognition,1992,25(2):173-188.
[78] Luo J., Savakis A. E.. Self-supervised texture segmentation using complementary types of features. Pattern Recognition,2001,34(11):2071-2082.
[79] Bennett J., Khotanzad A.. Modeling textured images using Generalized Long Correlation Models. IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(12):1365- 1375.
[80] Kapan L. M., Kuo C. C.. Extending self-similarity for fractional brownian motion. IEEE Transactions on Signal Processing,1994, 42(12):3526-3530.
[81]吴均,赵忠明.利用基于小波的尺度共生矩阵进行纹理分析.遥感学报,2001,5(2):100-103.
[82] Scharcanski J.. Stochastic texture analysis for monitoring stochastic processes in industry. Pattern Recognition Letters, 2005,26:1701-1709.
[83]安志勇,王晓华,赵珊等.一种图像纹理特征检索算法.西安电子科技大学学报(自然科学版), 2007,34(3): 409-413.
[84]安志勇,曾智勇,赵珊等.基于纹理特征的图像检索.光电子激光,2008,19(2):230-232.
[85] Lin H.. Automated visual inspection of ripple defects using wavelet characteristics based multivariate statistical approach. Image and Vision Computing. 2007,25:1785-1801.
[86] Truchetet F. and Laligant O.. A review on industrial applications of wavelet and multiresolution based signal-image processing. Journal Electronic Imaging, 2008.
[87] Alexandrov A.D., Ma W., Abbadi A., et al. Adaptive filtering and indexing for image databases, SPIE,1995,2420:12-23.
[88] Manjunath B. S , Ma W. Y.. Texture features for browsing and retrieval of image data. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1996,18(8):837-842.
[89]范一群,战荫伟.基于方向滤波器组和Gabor滤波器的指纹增强方法.第十四届全国图象图形学学术会议论文集, 2008.
[90]杜吉祥,翟传敏.基于GABOR纹理特征的植物图像识别方法研究.第十四届全国图象图形学学术会议论文集, 2008.
[91]靳宏磊,张振华,李立源等.基于纹理分析的表面粗糙度等级识别.中国图象图形学报,2000, 5(6):612-615.
[92]芦亚亚,丁维龙,王杰,张维统.自然场景下果实目标的识别和定位.浙江工业大学学报,2007, 35(3):267-273.
[93]韩彦芳,施鹏飞.基于多层小波和共生矩阵的纹理表面缺损检测.上海交通大学学报,2006, 40(3):425-430.
[94]陈玲,沈红标,李咸伟,刘其真.改进的图像纹理检索方法在矿石识别中的应用.中国图象图形学报,2006,11(11): 1700-1703.
[95] Coda G., Interrante V., Sapiro G.. Texture synthesis for 3D shape representation. IEEE Transactions on Visualization and Computer Graphics,2003,9(4):512-524.
[96] Pei S. C., Zeng Y. C., Chang C. H.. Virtual restoration of ancient Chinese paintings using color contrast enhancement and lacuna texture synthesis. IEEE Transactions on Image Processing, 2004, 13(3): 416-429.
[97]谢薇娜,周昌乐,徐丹,许家佗.基于颜色纹理的图像多特征检索技术在中医舌诊中的应用研究.中国图象图形学报, 2005,10(8):992-998.
[98] Ngo C. W., Pong T. C., Zhang H. J.. Motion analysis and segmentation through spatio-temporal slices processing. IEEE Transactions on Image Processing, 2003, 12(3):341- 355.
[99]刘晓民.基于纹理的视觉伺服研究.沈阳:中国科学院沈阳自动化研究所,2007.
[100]尚燕.纹理图像分类算法的研究[D].燕山大学,2007.
[101]王令.基于内容的图像检索技术分析和研究[D].江南大学,2008,6.
[102]余冰.基于统计的人脸识别方法[D].杭州:浙江大学,2002.5.
[103]孟志刚.人脸识别的关键技术研究[D].西南科技大学,2005.
[104]贾渊,姬长英,罗霞,陈念年.用基于遗传算法的BP神经网络识别牛肉肌肉与脂肪.农业工程学报,2007,23(11):216-219.
[105]孙焱.基于BP神经网络的图像检索方法研究[D].东北师范大学,2008.
[106]甘井中.基于BP神经网络图像识别的研究[D].大连理工学,2008,12.
[107]秦钟.基于图像不变矩特征和BP神经网络的车型分类.华南理工大学学报(自然科学版),2009,37(2):87-91.
[108]华媛媛.纹理信息在遥感图像分类中的应用与研究[D].西安科技大学,2009.
[109]童小华,张学,刘妙龙.基于多光谱遥感影像分类的城镇用地变化研究.光谱学与光谱分析,2009,29(8):2131-2135.
[110]魏景汗,罗跃嘉.认知事件相关脑电位教程[M].北京:经济日报出版社,2002.
[111]吴仕勇.基于数值计算方法的BP神经网络及遗传算法的优化研究[D].云南师范大学,2006.
[112]王小平等.遗传算法.西安交通大学出版社,2005,7.
[113]许振伟. BP神经网络分类器在储粮害虫图像检索中的应用研究.中国粮油学报, 2010, 25(1): 103-106.
[114]杨建刚.人工神经网络实用教程[M].杭州:浙江大学出版社,2001.
[115]方勇.遥感图像分析中的多源数据融合技术研究[D].解放军测绘学院, 1998.
[116]蒋宗礼.人工神经网络导论.北京:高等教育出版社, 2003.
[117]黄建国,罗航,王厚军,龙兵.运用GA-BP神经网络研究时间序列的预测.电子科技大学学报, 2009,38(9):387-392.
[118]骆成风.利用BP算法进行新疆MODIS数据土地利用分类研究.干早区地理,2005,28(2): 258- 262.
[119]刘国东,丁晶. BP网络用于水文预测的几个问题的探讨[J].水利学报,2002,4: 60-63.
[120]章宏林. Visual C++数字图像模式识别技术与工程实践.人民邮电出版社,2003.
[121]阮若林.利用遗传算法优化人工神经网络权值.咸宁学院学报,2005,25(6):49-51.
[122]骆成凤,刘正军,王长耀,牛铮.基于遗传算法优化的BP神经网络遥感数据土地覆盖分类.农业工程学报,2006,22(12):133-137.
[123]雷英杰,张善文等. MATLAB遗传算法工具箱及应用[M].西安:电子科技大学出版社, 2005,56-97.
[124]孙志强,葛哲学.神经网络理论与MATLAB7实现[M].北京:电子工业出版社,2005.