臺灣博碩士論文加值系統

本論文的目標是在擷取出紋理影像的主要成分，並且此資訊可被利用來重建出原來的影像，以應用於影像壓縮等方面。我們採用一套監督式與非監督式之基於多頻帶賈柏濾波器組的空間–頻率域分析方法來擷取紋理主頻率成份，然後在系統前端，也就是濾波器輸出之空間頻率域內便依照一些參數之臨界值加以分群，以作為分割或重建等進一步的應用。至於重建部份則應用框架理論，藉由主頻率參數和多頻帶賈柏濾波器組之間的權重關係來重建紋理

The purpose of this thesis is to develop a scheme of texture analysis and reconstruction based on a Gabor filter bank. The peak frequency components of a given texture are extracted from the outputs of the Gabor filter bank in the spatial and spatio-frequency domain. The extraction process could be implemented by either a supervised or non-supervised manner. Grouping the extracted peak frequency components facilitates the texture segmentation procedure. Provided with the parameters of the peak frequency components for a given texture, the texture image is approximately reconstructed by applying the frame theory.

誌 謝 i
摘 要 ii
Abstract iii
目 錄 iv
圖目錄 vii
第 一 章 1
緒 論 1
1.1 背景簡介 1
1.2 研究動機與目的 5
1.3 研究方法 7
1.4 內容大綱 8
第 二 章 9
紋理特徵與重建之相關文獻回顧 9
2.1 空間頻率域分析法 9
2.1.1 短時傅立葉轉換 9
2.1.2 小波轉換 10
2.2 振幅-頻率調變模型(AM-FM model) 12
2.3 框架理論(Frame theory) 14
第 三 章 15
應用賈柏濾波器於紋理特徵擷取 15
3.1 紋理主頻率偵測 16
3.1.1 賈柏濾波器 16
3.1.2 賈柏濾波器組在頻率域上之排列方式 20
3.1.3 主頻率偵測 27
3.2 多解析度整合 32
3.2.1 正規化賈柏濾波器 35
3.2.2 匹配濾波器 36
3.2.3 搜尋法 37
3.3 使用事前頻率資訊於主頻率偵測 38
3.4 主頻率成份之群組化 41
第 四 章 55
紋理分割與重建 55
4.1 紋理分割 55
4.2 紋理重建 60
第 五 章 65
實 驗 結 果 65
5.1 紋理分析系統架構 65
5.2 紋理分割實驗結果 65
5.2.1 非監督式排列 65
5.2.2 監督式排列 82
5.3 紋理重建實驗結果 85
5.3.1 非監督式排列 85
5.3.2 監督式排列 88
第 六 章 90
結論與展望 90
參考文獻 91

【1】C. Blakemore and F. W. Campbell, “On the existence neurons in the human visual system selectively sensitive to the orientation and size of retinal images,” Journal of Physiology, London, vol. 203, pp. 237- 260, 1969.

【2】A. C. Bovik, M. Clark, and W. S. Geisler, “Multichannel texture analysis using localized spatial filters,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 12, no. 1, pp. 55-73, 1990.

【3】P. Brodatz, Textires : A photographic album for artists and designers, New York, Dover publications, 1996.

【4】T. Caelli and P. Bevan, “Probing and spatial frequency spectrum for orientation sensitivity in stochastic textures,” Vision Research, vol. 23, pp. 39-45, 1983.

【5】F. W. Campbell and J. G. Robson, “Applications of Fourier analysis of the visibility of gratings,” Journal of Physiology, London, vol. 197, pp. 551-556, 1968.

【6】C. C. Chen, “Markov random fields in image analysis,” UMI’s Dissertation Abstracts Database, 1988.

【7】S. H. Cheng, Sinusoidal texture analysis and reconstruction based on Gabor frames, Master thesis, Feng Chia University, 2004.

【8】I. Daubechies, “The wavelet transform, time-frequency localization and signal analysis,” Information Theory, IEEE Transactions on, vol.36, no.5, pp. 961-1004, 1990.

【9】H. Derin and W. S. Cole, “Segmentation of textured images using Gibbs random fields,” Computer Vision, Graphics, and Image Processing, vol.35, pp. 72-98, 1986.

【10】D. Gabor, “Theory of communication,” Journal of the IEE, vol. 93, no. 26, pp. 429-457, 1946.

【11】N. Graham and J. Nachmias, “Detecting of grating patterns containing two special frequencies: A comparison of single-channel and multiple-channels mosels,” Vision Research, vol. 11, pp. 251-259, 1971.

【12】K. Grochenig, “Acceleration of the frame algorithm,” Signal Processing, vol. 41, no. 12, pp. 3331-3340, 1993.

【13】R. M. Haralick, “Statistical and structural approaches to texture,” Proceedings of The IEEE, vol. 67, no. 5, pp. 786-804, 1979.

【14】J. P. Havlicek, Am-Fm image models, Doctor of science thesis, The university of Texas at Austin, Dec 1996.

【15】J. P. Havlicek, D. S. Harding, and A. C. Bovik, “Reconstruction from the multi-component AM-FM image representation,” Image Processing, Proceedings., International Conference on, vol. 2, pp. 280 -283, Oct, 1995.

【16】J. P. Havlicek, D. S. Harding, and A. C. Bovik, “The multi- component AM-FM image representation,” Image Processing, IEEE Transactions on, vol. 5, Issue. 6, pp. 1094 -1100, June 1996.

【17】C. Hsin, “Edge Extraction based on a Statistical Decision Theory,” The Second Symposium on Computer and Communication Technology, Taichung, Taiwan, pp. 104-116, 1996.

【18】C. C. Huang, Textured segmentation based on spatial-frequency domain analysis, Master thesis, National Chiao Tung University, 2002.

【19】B. Julesz and E. N. Gilbert, “Inability of humans to discriminate between visual textures that agree in second-order statistics – revisited,” Perception, 2, pp. 391-405, 1973.

【20】B. Julesz, “Experiments in the visual perception of texture,” Scientific American, 232, pp. 34-43, 1975.

【21】M. Kass and A. Witkin, “Analyzing oriented patterns,” Computer Vision, Graphics, and Image Processing, vol. 37, pp. 362-385, 1987.

【22】T. S. Lee, “Image representation using 2d gabor wavelets,” IEEE Signal on Pattern Analysis and Machine Intelligence, vol. 18, no. 10, pp. 959-971, 1996.

【23】S. Marčelja, “Mathematical description of the responses of simple cortical cells,” Journal of the Optical Society of America, vol. 70, no. 11, pp. 1297-1300, 1982.

【24】S. C. Pei and M. H. Yeh, “An introduction to discrete finite frames,” IEEE Signal Processing Magazine, vol. 14, no. 6, pp. 84-96, 1997.

【25】A. R. Rao and B. G. Schunck, “Computing oriented texture fields,” CVGIP. Graphical models and image processing, vol. 53, pp. 157-185, 1991.

【26】W. Richards and A. Polit, “Texture matching,” Kybernetic, vol. 16, no. 3, pp. 155-162, 1974.

【27】A. Teuner, O. Pichler, and B. J. Hosticka, “Unsupervised texture segmentation of images using tuned matched Gabor filters,” Image Processing, IEEE Transactions on, vol. 4, pp. 863-870, 1995.

【28】Y. P. Wang, Analysis and synthesis of stochastic textures, Master thesis, Feng Chia University, 2004.

【29】http://ligwww.epfl.ch/~silic/predocschool/ComputerVision/ cvision.html