臺灣博碩士論文加值系統

彩色影像中存在著許多區塊的訊息，依色彩的特性很容易分割出均勻的區域。然而，不同的色域空間其色彩的轉換是非線性的關係。以往相關的研究中經常直接轉換成灰階影像處理卻忽略色彩的特性。爾來部份的研究已逐漸考慮將彩色影像分割架構在不同的色彩空間中，但其分割的處理過程仍難免侷限於灰階的分割處理方式。本篇論文是針對各種不同色彩空間的色彩影像進行自動分割影像方法，以取代實驗及經驗法則的分割方式。論文中應用小波轉換具有多重解析特性的技術，將色彩影像在不同的色彩空間裡，依其色彩特性作分割，在處理的過程中依色彩空間特性先定義出像素點的色彩，並與鄰近像素點的色彩相互比較以確定彼此是否屬於相同的區域。再依標示後的影像做小波函數之逆轉換至下一層並逐層標示。一直達到原始影像的尺寸，而得到每一區塊明顯的邊界與區域，以達到分割的目的。
希望此研究有助於色彩管理系統的建立，並架設在網際網路上，提供相關產業一個自動化的色彩管理的工具與色彩管理標準。
關鍵字(詞)：Color Image、Segmentation、Wavelets、Multiresolution、Color Space

Color images contain much homogenous regions information which can be divided into uniform regions by color characterization. There is no linear relationship among the color space transformations. In the previous, the color research, we found that most of researchers use gray level image segmentation methods to apply on color images. They totally ignore the color characterization. In recent years, some of them took the advantages of color to do segmentation in some device dependence color spaces. The goal of this research is to investigate an automatic image segmentation method which substitutes the traditional heuristic and intuited methods. We propose a color image segmentation technique using wavelet transform with multi-resolution technique. In accordance with the properties of color, we can segment color images in different color spaces to fulfill the functionality of color management. In segmentation process, we start from the toppest level, define the color of a pixel, and compare with the colors of neighboring pixels to decide the regions. After labeling the regions, we do inverse discrete wavelet to next level and label the regions level by level until reaching equal to original image. Then obtain a segmentation image with obvious boundary to achieve image segmentation. It is hoped that the research is much helpful in building a color management on the Internet, which is able to provide an automatic color management tool and standard for related industries.
Keywords：Color Image、Segmentation、Wavelets、Multiresolution、Color Space

摘要 I
ABSTRACT II
LIST OF FIGURES III
LIST OF TABLES IV
CONTENTS 1
CHAPTER 1 INTRODUCTION 3
1-1 Motivation 3
1-2 Objectives 4
1-3 A novel approached for image segmentation 5
CHAPTER 2 TECHNOLOGY OF IMAGE SEGMENTATION 7
2-1 General Approaches 8
2-2 Multi-resolution Approaches 12
2-2-1 Pyramid Applications 12
2-2-2 Multi-resolution Fourier Transform 13
Chapter 3 PRINCIPLE OF WAVELETS 18
3-1 Preliminaries 18
3-2 Discrete Wavelet Transform 20
3-3 Haar Wavelet Transform 25
3-4 Filter Banks and the Discrete Wavelet Transform 26
CHAPTER 4 CHARACTERISTIC OF COLOR 28
4-1 Colorimetry 30
4-2 Color Spaces 31
4-2-1 RGB model and CMY (CMYK) model 32
4-2-2 X, Y, Z model and x, y, z model 33
4-2-3 L*a*b* model and L*u*v* model 34
4-3 Color Transformation (Color Management System) 34
4-3-1 Characterization and Calibration 36
4-3-2 Gamut Mapping 37
Chapter 5 COLOR IMAGE SEGMENTATION USING WAVELETS 39
5-1 Implement Algorithm 39
5-2 Implement Result 43
Chapter 6 CONCLUSION aND FUTURE WORK 49
6-1 Conclusion and Future Work 49
6-2 Contribution 49
BIBLIOGRAPHY 50

BIBLIOGRAPHY
[1].Calway, A. and R. Wilson “Curve extraction in images using the multi-resolution Fourier transform,” Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on page(s): 2129-2132 vol.4 3-6 Apr 1990
[2]Joblove G. H., Donald Greenberg “Color spaces for computer graphics” .Computer Graphics (Proceedings of SIGGRAPH 78). 12(3), pp. 20-25, 1978.
[3]Kehtarnavaz, N. Monaco, J. Nimtschek, J. and Weeks, A. “Color image segmentation using multi-scale clustering,” Image Analysis and Interpretation, 1998 IEEE Southwest Symposium on On page(s): 142-147 1998
[4]Kenneth R. Castleman, “Digital image processing”
Prentice-Hall,New Jersey,1996
[5]Konstantinos N. Plataniotis, Anastasios N. Ventsanopoulos “Color Image Processing and Applications”, Springer-Verlag, New York, 2000.
[6]Ledley, R.S., Buas, M.,Golab, T.J. “Fundamentals of true-color image processing” 10th International Conference Pattern Recognition, Proceedings, pp. 791-795 vol.1 16-21 Jun 1990
[7]Lee Kuen-Long and Ling Hwei Chen “Unsupervised texture segmentation by determining the interior of texture region base on wavelet transform, ”International Journal of Pattern Recognition and Artificial Intelligence on pp. 1231-1250 vol. 5, No. 8 (2001).
[8]Li Chang-Tsun and R. Wilson “Image segmentation based on a multi-resolution Bayesian framework,” Image Processing, 1998. ICIP 98, Proceedings. 1998 International Conference on page(s): 761-765 vol.3 4-7 Oct 1998.
[9]Lu Chun S., Pau C. Chung and Chih F. Chen “Unsupervised Texture Segmentation Via Wavelet Transform”, Patt. Recogn. 30, 5 (1997) 729-742.
[10]Olkkonen, H and P. Pesola “Note Gaussian Pyramid Wavelet Transform for Multi-resolution analysis of Images”
[11]Peter J. Burt and Edward H. Adelson “The Laplacian Pyramid as a Compact Image Code,” IEEE Transaction on Communication, COM-31:532-540, 1983.
[12]Phil Green, Lindsay MacDonald “Color Engineering” John Wiley and Son, West Sussex, England, 2002
[13]Rafael C. Gonzalez and Richard E. Woods “Digital Image Processing“, 2nd edition, Prentice Hall, New Jersey, 2002
[14]Saeed, M. Karl, W.C. Nguyen, T.Q. Rabiee, and H.R. “A new multiresolution algorithm for image segmentation,” on the Proceedings of the1998 IEEE International Conference of Acoustics, Speech, and Signal Processing, (ICASSP '98), on page(s): 2753-2756 vol.5, 1998
[15]Sideny Burrus C.,Ramesh A. Gopinath and Haitao Guo, “Introduction to Wavelet Transforms” Prentice-Hall,New Jersey,1998
[16]Smith A. R. “Color gamut transform pairs” Computer Graphics (Proceedings of SIGGRAPH 78). 12(3), pp. 12-19, 1978
[17]Vannoorenberghe, P. Colot, O. de Brucq, D. “Color image segmentation using Dempster-Shafer's theory,” on the 1999 International Conference of Image Processing (ICIP `99). On page(s): 300-304 Vol.4 1999
[18]Wilson, R “Multi-resolution image modelling” Electronics & Communication Engineering Journal. On page(s): 90-96 April 1997
[19]Yining Deng Kenney, C. Moore, M.S. and Manjunath, B.S. “Peer group filtering and perceptual color image quantization” on the 1999 IEEE International Symposium Circuits and Systems (ISCAS '99). Proceedings of the on page(s): 21-24 Vol.4, Jul 1999
[20]Yining Deng Manjunath, B.S. “Content-based search of video using color, texture, and motion” on the 1997 International Conference of Image Processing. Proceedings on page(s): 534-537 vol.2 26-29 Oct 1997
[21]Yining Deng Manjunath, and B.S. Shin, H. “Color image segmentation,” on the 1999 IEEE Computer Society Conference of Computer Vision and Pattern Recognition, on page(s): -451 Vol. 2 1999
[22]Yui-Liang Chen, Mei-Chun Lo, and Chih-Chieh Yu, Applying UML on creating a Color Management System, TAGA 2003 55th Annual Technical Conference, Montreal, Quebec, Canada, April 6-9, 2003.
[23]單維彰, “凌波初步”, 1990 台北：全華。
[24]羅梅君, "彩色影像色彩管理與色彩校正技術”財團法人印刷技術研究中心