臺灣博碩士論文加值系統

在這篇論文我們將提出一個以特徵分佈為基礎的彩色紋理影像檢索。亦即我們利用顏色和區域性的邊緣樣式資訊來比對兩彩色紋理區塊的同質性。此一同質性比對法，可用於彩色紋理資料庫之檢索。值得一提的是，本論文將色彩和邊緣的紋理特徵作一致性處理，不同於以往之方法僅將灰階紋理分析方法延伸運用於彩色影像的每個頻道，或僅分析色彩之特性，所以所提方法能得較佳檢索效果。另外我們還利用前述之同質性測量比對法，進行影像區塊切割方法，以達到針對自然影像資料庫進行彩色紋理區塊檢索的目的。所提方法之另一特色是因為所提比對特徵皆有抗平移、旋轉及縮放之能力，故本法可用以檢索平移、旋轉及縮放等變形之紋理。由眾多的實驗數據也確實證明我們的方法是有其可行性。

A new method for color texture retrieval using color and edge features is proposed in this study. The proposed method unifies color and edge features rather than simply extend gray-level texture analysis to each channel of the color images, or analyze only color characteristics. More specifically, the distributions of color and local edge patterns are used to derive similarity measure of a pair of textured regions for color texture retrieval. Moreover, a segmentation method based on the similarity measure is employed to extend the retrieval method to natural image database. More important, since the proposed feature distributions are invariant to translation, rotation and scale variations, our method has the ability to retrieve textures which are changed in translation, rotation and scale. The effectiveness and practicability of the proposed method have been proven by various experiments.

ABSTRACT (IN CHINESE)........................................I
ABSTRACT (IN ENGLISH)........................................II
CONTENTS.....................................................III
LIST OF FIGURES..............................................IV
LIST OF TABLES...............................................V
CHAPTER 1 INTRODUCTION.......................................1
1.1. MOTIVATION...........................................1
1.2. SURVEY OF RELATED STUDIES............................1
1.3. PROPOSED APPROACH....................................4
1.4. ORGANIZATION OF THIS THESIS..........................4
CHAPTER 2 COLOR TEXTURE RETRIEVAL BASED ON FEATURE DISTRIBUTIONS................................................5
2.1. EXTRACTION OF FEATURE DISTRIBUTIONS..................5
2.1.1. Color histogram.................................5
2.1.2. Local edge pattern histogram....................6
2.2. SIMILARITY MEASURE BASED ON FEATURE DISTRIBUTIONS....10
CHAPTER 3 COLOR TEXTURE RETRIEVAL FOR NATURAL IMAGES.........14
3.1. DATABASE CREATION....................................14
3.1.1. Hierarchical splitting..........................15
3.1.2. Agglomerative merging...........................16
3.2. QUERY MATCHING.......................................17
CHAPTER 4 EXPERIMENTAL RESULTS...............................20
4.1. COLOR TEXTURE RETRIEVAL FOR TEXTURE IMAGES...........20
4.1.1. Determination of feature weights23
4.1.2. Invariant characteristic of our method..........31
4.1.3. Compare to other existing methods...............33
4.2. COLOR TEXTURE RETRIEVAL FOR NATURAL IMAGES...........43
CHAPTER 5 CONCLUSIONS AND FUTURE WORK.......................53
REFERENCES...................................................54

[1]C. Carson, S. Belongie, H. Greenspan, and J. Malik, “Region-based image querying,” CVPR’97 Workshop on Content-Based Access of Image and Video Libraries, 1997
[2]K.M. Chen and S.Y.Chen, “Color texture segmentation using feature distributions,” CVGIP, pp. 198-205, 2000.
[3]P. Chetverikov, “Experiments in the rotation-invariant texture discrimination using anisotropy features,” Proceedings of the 16th International Conference on Pattern Recognition, pp. 1071-1073, Munich, Germany, 1982.
[4]F.S. Cohen, Z. Fan and M.A. Patel, “Classification of rotated and scale textured images using Gaussian Markov random field models,” IEEE Transactions Pattern Analysis Machine Intelligence, vol. 13, pp. 192-202, 1991.
[5]L.S. Davis, “Polarograms: a new tool for texture analysis,” Pattern Recognition, vol. 13, pp. 219-223, 1981.
[6]L.S. Davis, S.A. Johns and J.K. Aggarwal, “Texture analysis using generalized co-occurrence matrices,” IEEE Transactions Pattern Analysis Machine Intelligence, vol. 1, pp. 251-259, 1979.
[7]C. Faloutsos, R. Barber, M. Flickner, J. Hafner, W. Niblack, D. Petkovic and W. Equitz, “Efficient and Effective Querying by Image Content,” Journal of Intelligent Information Systems, vol. 3, pp. 231-262, 1994.
[8]L.V. Gool, P. Dewaele and A. Oosterlinck, “Texture analysis announce 1983,” Computer Vision Graphics Image Processing, vol. 29, no. 3, pp. 336-357, 1985.
[9]H. Greenspan, S. Belingie, R. Goodman and P. Perona, “Rotation invariant texture recognition using a steerable pyramid,” Proceedings of the 12th International Conference on Pattern Recognition, vol. 2, pp. 162-167, Jerusalem, Israel, 1994.
[10]G.M. Haley and B.S. Manjunath, “Rotation-invariant texture classification using modified Gabor filter,” Proceedings of the IEEE Conference on Image Processing, pp. 655-659, Austin, TX, 1994.
[11]R.M. Haralick and L. Shapiro, Computer and Robot Vision. vol. 1, Addison-Wesley, New York, 1992.
[12]D. Harwood, T. Ojala, M. Pietiläinen, S. Kelman and L.S. Davism, “Texture classification by center-symmetric auto-correlation using Kullback discrimination of distributions,” Pattern Recognition Letters, vol. 16, pp. 1-10, 1995.
[13]C.L. Huang, T.Y. Cheng, C.C. Chen, “Color images’ segmentation using scale space filter and Markov random field,” Pattern Recognition, vol. 25, no. 10, pp. 1217-1229, 1992.
[14]R.L. Kashyap and A. Khotanzad, “A model-based method for rotation invariant texture classification,” IEEE Transactions Pattern Analysis Machine Intelligence, vol. 8, pp. 472-481, 1986.
[15]M.M. Keung and A.M. Peterson, “Scale and rotation invariant texture classification,” Proceedings of the 26th Asilomar Conference in Signals, Systems and Computers, Pacific Grove, CA, 1992.
[16]H.C. Lin, L.L. Wang, S.N. Yang, “Regular-texture image retrieval based on texture-primitive extraction,” Image and Vision Computing, vol. 17, pp. 51-63, 1999.
[17]F. Liu and R.W. Picard, “Periodicity, directionality, and randomness: wold features for image modeling and retrieval,” IEEE Transactions on Pattern Analysis and Machine Intelligence vol. 18, no. 7, pp. 722-733, 1996.
[18]S.V.R. Madiraju and C.C. Liu, “Rotation invariant texture classification using covariance,” Proceedings of the IEEE Conference on Image Processing, vol. 1, pp. 262-265, Washington, DC, 1995.
[19]B.S. Manjunath and W.Y. ma, “Texture features for browsing and retrieval of image data,” IEEE Transactions on Pattern Analysis and machine Intelligence, vol. 18, no. 8, 1996.
[20]J. Mao and A.K. Jain, “Texture classification and segmentation using multiresolution simultaneous autoregressive models,” Pattern Recognition, vol. 25 pp. 173-188, 1992.
[21]M. Nadler and E.P. Smith, Pattern Recognition Engineering, Wiley, New York, 1993.
[22]T. Ojala, M. Pietikäinen, “Unsupervised texture segmentation using feature distributions,” Pattern Recognition, vol. 32, no. 9, pp. 477-486, 1999.
[23]G. Paschos, “Fast color texture recognition using chromaticity moments,” Pattern Recognition Letters, vol. 21, pp. 837-841, 2000.
[24]A. Pentland et al., “Photobook: tools for content-based manipulation of image databases,” International Journal Computer Vision, vol. 18, pp.233-254, 1996.
[25]M. Pietikäinen, T. Ojala, Z. Xu, “Rotation-invariant texture classification using feature distributions,” Pattern Recognition, vol. 33, pp. 43-52, 2000.
[26]M. Porat and Y. Zeevi, “Localized texture processing in vision: analysis and synthesis in the Gaborian space,” IEEE Transactions Biomedical Engineering, vol. 36, pp. 115-129, 1989.
[27]M.A. Stricker, “Color and Geometry as cues for indexing,” Technical Report, University of Chicago, 1992.
[28]G.V.D. Wouwer, P. Scheunders, S. Livens, and D.V. Dyck, “Wavelet correlation signatures for color texture characterization,” Pattern Recognition, vol. 32, pp. 443-451, 1999.
[29]J. You and H.A. Cohen, “Classification and segmentation of rotated and scaled textured images using texture “tuned” masks,” Pattern Recognition, vol. 26, pp. 245-258, 1993.
[30]Y. Zhong and A.K. Jain, “Object localization using color, texture and shape,” pattern Recognition, vol. 33, pp. 671-684, 2000.