(3.238.130.97) 您好!臺灣時間:2021/05/18 10:56
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:賴俊良
研究生(外文):Lai Jiun-Liang
論文名稱:以歸一化切割為基礎的紋理分割系統
論文名稱(外文):Normalized Cut Based Texture Segmentation System
指導教授:辛錫進
指導教授(外文):His-Chin Hsin
學位類別:碩士
校院名稱:中華大學
系所名稱:電機工程學系碩士班
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2001
畢業學年度:89
語文別:中文
論文頁數:55
中文關鍵詞:歸一化切割紋理分割
外文關鍵詞:normalized cuttexture segmentation
相關次數:
  • 被引用被引用:3
  • 點閱點閱:142
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
影像分割,是將一張影像中同質性的部分群組化,這在許多影像分析工作及電腦視覺應用上是一項相當困難而又重要的工作。影像分割以灰階或是色彩的不同來區分總是不夠明顯,但經由紋理的定義,有關影像分割的問題我們可以求助於紋理分割;也就是利用鄰近像素的灰階值在空間排列上的不同(亦即紋理上的不同)來作解釋。紋理內含高頻低頻的不同成份,所以對於紋理分析來說,可以擷取近似成分的賈柏濾波器(Gabor Filters)是吸引人去了解的,因為它允許我們對不同紋理的頻率成分,來擷取不同的頻率與方向的特徵,因而更能解析出紋理的不同。影像分割的要點是充分利用特徵的全面資訊,所以本論文利用圖形分割理論(Graph Partition Theory)發展出來歸一化切割(Normalized Cut)作分割處理。歸一化切割以群聚的相似性考量再加上切割的特性,使分割部分不相似處最小化且群聚部分相似處最大化,達到好的切割。最後本論文以轉換賈柏濾波器得到的特徵向量空間到以解一般特徵值系統得到多重特徵向量的特徵向量空間,並且以此特徵向量空間做分割,實驗證明我們的方法可以得到較好的分割結果。
Image segmentation, which partitions images into homogeneous regions, is an important task in many computer vision applications. Typically, differences in gray levels and/or colors alone are not sufficient for segmenting images of interest. This problem may be solved to a certain degree by taking account of the texture information. One of the commonly used approaches to extracting texture features is the frequency approach. In this thesis, we used Gabor filters to extract texture features in various frequency bands. Based on these features, the Normalized cut measure of similarity between pixels are used to partition images such that the disassociation between different textures and the association within similar texture are to be maximized simultaneously. We also developed a texture segmentation system in which the Gabor filter based feature space is transformed into the Normalized cut based feature space by solving the associated generalized eigen-system efficiently. The performance improvement can be demonstrated by the experimental results on segmentation of some Brodatz textures.
目 錄
摘要……………………………………………………………………..i
Abstract………………………….…………………………………….. ii
誌謝…………………………………………………………………. iii
目錄………………………………………………………………. iv
圖目錄…………………………………………………………………vi
表目錄…………………………………………………………………viii
第一章 緒 論…………………………………………………1
1-1引言………………………………………………………….1
1-2問題的陳述………………………………………………….3
第二章 理論背景……………………………………………6
2-1多重通道近似的分析………………………………………6
2-1-1介紹……………………………………………………….6
2-1-2 賈柏濾波器的特性……………………………………….8
2-2分割方法簡介……………………………………………10
2-2-1區域的分割………………………………………………10
2-2-2模糊c平均值的分割……………………………………11
2-2-3類神經網路的分割………………………………………11
第三章 圖形分割理論與歸一化切割………………………19
3-1介紹……………………………………………………19
3-2與影像分割相關的圖形理論…………………………21
3-3圖形分割……………………………………………..23
3-4計算歸一化切割的最佳分割…………………………24
第四章 以歸一化切割發展的分割系統……………………28
4-1系統一:以 Gabor 濾波器輸出做歸一化二分切割的方法.…28
4-2系統二:以(歸一化切割)多維特徵向量做k-means分割的方法..……………………………………………………30
4-3系統三:以多維特徵向量做歸一化K-way切割的方法..……31
4-3-1 Greedy approach…………………………………………32
4-3-2 Iterative approach….…………………………………32
第五章 驗證過程…………………………………………34
5-1賈柏濾波器的驗證過程……………………………………34
5-2以歸一化切割發展的分割系統的驗證過程………………36
5-2-1系統一的驗證過程…………………………………37
5-2-2系統二的驗證過程…………………………………37
5-2-3系統三的驗證過程…………………………………37
5-2-3-1 Greedy approach的驗證過程………………..38
5-2-3-2 Iterative approach的驗證過程……………38
第六章 結論……………………………………………..52
參考文獻……………………………………………………53
參 考 文 獻
[1]Jianbo Shi and Jitendra Malik. “Normalized Cuts and Image Segmentation.” To appear IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000.
[2]Jianbo Shi; Malik, J. “Normalized cuts and image segmentation.” In Proc. IEEE Conf. Computer Vision and Pattern Recognition, pages 731-737, 1997.
[3]Z. Wu and R. Leahy. “An optimal graph theoretic approach to data clustering: Theory and its application to image segmentation.” PAMI, 11:1101-1113, November 1993
[4]Anil K. Jain and F. Farrokhnia, “Unsupervised Texture Segmentation Using Gabor Filters.” Pattern Recognition, vol. 24, no. 12, pp. 1167-1186, 1991.
[5]Farrokhnia, F.; Jain, A.K. “A Multi-Channel Filtering Approach to Texture Segmentation.” Computer Vision and Pattern Recognition, 1991. Proceedings CVPR ''91., IEEE Computer Society Conference on , 1991 , Page(s): 364 -370
[6]A. C. Bovik, M. Clark, and W. S. Geisler. “Multichannel Texture Analysis Using Localized Spatial Filters.” IEEE Trans. Pattern Anal. Machine Intell. 12(1):55-73, 1990.
[7]J. Malik and P Perona, Preattentive “Texture Discrimination with Early Vision Mechanisms.” J. Opt. Soc. Amer. A, 7(5):923-932, 1990.
[8]H. Tarura, S. Mori, and T, Yamawaki, “Texture Feature Corresponding to Visual Perception” IEEE Trans. Syst., Man, Cybern. Vol. SMC-8, pp. 460-473, june 1978
[9]Rafael C. Gonzalez and Richard E. Woods “Digital Image Processing” 1993
[10]Anil K. Jain and R. C. Dubes. “Algorithms for Clustering Data.” Prentice-Hall, New Jersey, 1988
[11]P. Brodatz, “Texture: A photographic Album for Artists and Designers” , New York: Dover, 1966.
[12]Roberto H. Bamberger and Mark J. T. Smith, ”A filter bank for the directional decomposition of images: theory and design.”, IEEE Trans. Signal Processing, vol. 40, no. 4, pp. 882-893, april 1992
[13]Larry. S. David, Steven A. Johns and J. K. Aggarwal, “Texture analysis using generalized co-occurrence matrices.” IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-1, no.3, pp. 251-259, July 1979.
[14]Mary M. Galloway, “Texture analysis using gray level run length.”, Computer Graphics Image Process., pp. 172-179, 1975.
[15]G. R. Cross and A. K. Jain, “Markov random field texture models.” , IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-5, no. 1, pp. 25-39, January 1983
[16]Jian-Chang Mao and A. K. Jain, “Texture classification and segmentation using multiresolution simultaneous autoregressive models”, Pattern Recognition, vol. 25, no. 2, pp. 173-188, February 1992
[17]Tagliarini, G.A.; Christ, J.F.; Page, E.W. “Optimization using neural networks” Computers, IEEE Transactions on Volume: 40 12 , Dec. 1991 , Page(s): 1347 —1358
[18]Hance, G.A.; Umbaugh, S.E.; Moss, R.H.; Stoecker, W.V. “Unsupervised color image segmentation: with application to skin tumor borders” IEEE Engineering in Medicine and Biology Magazine Volume: 15 1 , Jan.-Feb. 1996 , Page(s): 104 —111
[19]H. Kaizer, :”A quantification of textures on aerial photographs” Boston Mniv. Res. Lab., Tech Note 121, ad 69484,1955.
[20]Julesz, B., Bergen, J.R. “Textons, the fundamental elements in preattentive vision and perceptions of textures” The Bell System Technical Journal, vol. 62 no. 6. pp. 1619-1615, 1983.
[21]Kjell, B.P., Dyer, C.R. :”Segmentation of textured images.” Proc. of the Int. Conf. On Computer vision, and Pattern Recognition, Miami Beach, Florida, 22-26 June, pp 476-481, 1986
[22]M. Nagao, H.Tanabe, and K. Ito, “Agricultural land use classification of aerial photographs by histogram similarity method,” in proc. 3rd int. Joint Conf. Pattern Recognition, pp. 669-672, 1976
[23]S. Z. Selim and M. A. Ismail, “K-means-type algorithm: generalized convergence theorem and characterization of local optimality,” IEEE Trans. Pattern Anal. March. Intell., vol. 6, no. 1, pp. 81-87, 1984.
[24]J. M. Coggins and A. K. Jain, “A spatial filtering approach to texture analysis.” Pattern Recognition Lett. 3 195-203 1985
[25]--------,”Nonlinear neural networks : Principles, Mechanisms, and architecture,” Neural Networks vol. 1 no. 1 pp. 17-61, 1988.
[26]R. Hecht-Nielsen, “Theory of the Backpropogation neural network,” IEEE IJCNN (Washington DC), vol.1, pp. 593-611, 1989
[27]T. Kohonen, “The self-organizing map” Proceedings of the IEEE, vol.78, no.9, pp. 1464-1480,1990.
[28]葉怡成, “應用類神經網路”, 儒林, 1997年7月
[29]J. Canny. ”A Computational Approach to Edge Detection.” IEEE Trans. Pattern Anal. Machine Intell. 8(6):679-698, 1986
[30]J. Cheeger. “A lower bound for the smallest eigenvalue of the laplacian.” In R. C. Gunning, editor, Problems in Analysis, pages 195-199. Princeton Univ. Press, 1970
[31]W.E. Donath and A.J. Hoffman. “Lower bounds for the partitioning of graphs” IBM Journal of Research and Development, pages 420-425, 1973.
[32]M. Fiedler. “A property of eigenvectors of nonnegative symmetric matrices and its applications to graph theory.” Czech. Mathematical Journal, 25(100):619-633, 1975.
[33]I.J. Cox, S.B. Rao, and Y. Zhong. “Ratio regions: a technique for image segmentation.“ In 13th International Conference on Pattern Recognition, 1996.
[34]S. Sarkar and K.L. Boyer. “Quantitative measures of change based on feature organization: eigenvalues and eigenvectors” CVPR ''96, 1996 IEEE Computer Society Conference on , 1996 , Page(s): 478 —483
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top