臺灣博碩士論文加值系統

本篇論文提出三個影像色彩轉換演算法（color transfer algorithm）。第一個演算法（簡稱ACT演算法）是一個自動、針對單張靜態影像（still image）且以區塊為基礎(swatch-based)的色彩轉換演算法。此演算法提供將目標影像（target image）色彩特性轉換至來源影像（source image）上的功能。此ACT演算法包含三個處理程序，分別為區塊產生程序（swatch generation process）、區塊配對與色彩轉換程序（swatch matching and color transfer process）、與區塊邊緣修復程序（swatch boundary transition process）。此區塊色彩轉換演算法可自動轉換目標影像色彩至來源影像，無須使用者介入，並產生合理結果影像。蒐集的實驗結果顯示此ACT演算法優於先前由Reinhard等人所提出之需要使用者介入的演算法。
第二個演算法（簡稱ISCT演算法）是一個針對影像序列（image sequence）新奇且自動的之色彩轉換演算法。ISCT演算法可提供將三張使用者所提供之目標影像之色彩特性轉換並產生一影像序列。此演算法藉由三個步驟來完成此目標，分別是前置色彩空間轉換處理步驟（forward color space conversion process）、影像序列步驟（image sequence process）與影像序列動畫處理步驟（image sequence animation process）。給定一張輸入影像（input image）I1與三張目標影像T1、 T2、 T3當成輸入資料，此演算法可產生一具有色調變化（color mood variations）之輸出影像序列{Si}。ISCT演算法執行迅速，它只需幾秒就可成功產生一個影像序列。此外，透過使用者介面，可在視覺上提供非常便利之介面來觀看所產生之影像序列。ISCT演算法已證明是確實可實現的，只需給定三張目標影像，即可產生一具有視覺真實效果的影像序列。此演算具有自動執行、有效且迅速的特性，並可適用於許多運用上。
最後，我們提出一個通用（generalized）、新奇且自動的影像序列色彩轉換演算法（簡稱GISCT演算法）。GISCT演算法與ISCT演算法主要有兩點差異。第一、GISCT演算運用一個新的色彩轉換技術（簡稱NCT）來避免過度色彩轉換的問題。此問題發生於當來源影像與目標影像色彩內容差異太大。第二、GISCT演算法運用通用色彩變化曲線（簡稱GCVC）技術。GCVC運用B-spline曲線，以自動內插（interpolation）方式，來提供在影像序列中之間隔影像之色彩彈性控制。蒐集的實驗結果顯示，GISCT演算法只需幾秒鐘即可產生一結果影像序列。且此影像序列比ISCT演算法所產生之影像序列更具有視覺真實效果。
總結以上，ACT演算法可成功產生結果影像且具有比以前演算法更好之效果。ISCT演算法與GISCT演算法是新奇且第一個被提出之可產生具有色調變化影像序列之演算法。我們相信我們所提出的這三個演算法：ACT演算法、ISCT演算法與GISCT演算法，對於電腦圖學之色彩轉換領域有著一定的貢獻。

This dissertation presents three color transfer algorithms for images. The first algorithm is an automatic, swatch-based, color transfer (ACT) algorithm for two still images. It modifies colors in the source image by borrowing the color characteristics from the target image. The algorithm consists of three processes: a swatch generation process, a swatch matching and color transfer process, and a swatch boundary transition process. This swatch-based algorithm proceeds on color transfer with no user intervention, and produces visually plausible resultant images. Experimental results demonstrate that the ACT is superior to Reinhard et al.’s original user-intervention color transfer algorithm.
The second algorithm presents a novel automatic color transfer approach for image sequence (ISCT). This ISCT algorithm renders an image sequence with color characteristics borrowed from three user-given target images. The algorithm completes the color transfer task with three processes: a forward color space conversion process, an image sequence process, and an image sequence animation process. Given a single input image (I1) and three target images (T1, T2, T3) as inputs, the algorithm produces an image sequence {Si} with color mood variations. The ISCT algorithm is fast. It achieves the goal of rendering an image sequence in several seconds. In addition, the user interface developed provides much freedom to visualize the rendered image sequence. Given only three target images, the ISCT algorithm demonstrates its feasibility to produce an image sequence with visually plausible effects. This algorithm is automatic, effective, and expeditious, and is appropriate for many applications.
Finally, we recommend a generalized color transfer algorithm for image sequences (GISCT). There are two major differences between the GISCT algorithm and the ISCT algorithm. The first major difference is that the GISCT algorithm proposes a new color transfer approach (NCT) to eliminate the appearance of over-transformation, which occurs when the source and target image are not compatible. The second difference is that we present a generalized color variation curve (GCVC) in the GISCT algorithm. Specifically, a B-spline curve is automatically generated to interpolate color statistics, which provides more flexible control over in-between images. Experimental results show that the GISCT algorithm generates results in several seconds. It renders an image sequence with versatile color variations, producing more visually plausible appearance than those generated by the ISCT algorithm.
In conclusion, the ACT algorithm produces results that are superior to its closest competitor. The novel ISCT and the GISCT algorithms generate an image sequence with color mood variation. These algorithms contribute significantly to the topic of color transfer in the computer graphics community.

Acknowledgement　 i
摘要　 ii
Abstract　 iv
Contents　 vi
List of Figures　 viii
List of Tables　 xi
1. Introduction　 1
　　1.1 Introduction　 1
　　1.2 Problem Statements　 2
　　1.3 Thesis Contribution　 5
　　1.4 Structures of the Thesis　 7
2. A Survey of Light, Color Vision and Color Spaces　 9
　　2.1 The Light and the Color　 9
　　2.2 Color Vision　 12
　　　　2.2.1 The Structures of the Human Eye　 13
　　　　2.2.2 The Retina　 14
　　　　2.2.3 The Visual Pathways into the Brain　 21
　　2.3 The Color Spaces　 23
3. A Novel Automatic Color Transfer Algorithm for Still Images　 38
　　3.1 Introduction　 38
　　3.2 Related Works　 40
　　3.3 An Automatic Color Transfer Algorithm　 47
　　　　3.3.1 Swatch Generation　 48
　　　　3.3.2 Swatch Matching and Color Transfer　 49
　　　　3.3.3 Swatch Boundary Transition　 51
　　3.4 Experimental Results　 54
　　3.5 Summary　 67
4. A Novel Color Transfer Algorithm for Image Sequences　 68
　　4.1 Introduction　 68
　　4.2 Related Works　 70
　　4.3 An Image Sequence Color Transfer Algorithm　 72
　　　　4.3.1 The Forward Color Space Conversion　 73
　　　　4.3.2 The Image Sequence Process　 75
　　　　4.3.3 The Image Sequence Animation　 77
　　4.4 Experimental Results 78
　　　　4.4.1 The User Interface　 79
　　　　4.4.2 The Canyon Test Model　 81
　　　　4.4.3 The Green Tunnel Test Model　 85
　　4.5 Summary　 89
5. A Generalized Algorithm for Image Sequence Color Transfer　 91
　　5.1 Introduction　 91
　　5.2 Related Works　 93
　　5.3 A Generalized Algorithm for Image Sequence Color Transfer　 95
　　　　5.3.1 The Static Color Transfer Algorithm　 95
　　　　5.3.2 The Movie Clip Approach　 99
　　5.4 Experimental Results　 103
　　　　5.4.1 The Mount Model　 104
　　　　5.4.2 The Banana Model　 109
　　　　5.4.3 The Africa Model　 113
　　　　5.4.4 The Rocky Mountain Model　 118
　　　　5.4.5 The Multi-Layers Model　 120
　　5.5 Summary　 124
6. Conclusions and Future Works　 125
　　6.1 Conclusions　 125
　　6.2 Future Works　 127
Bibliography　 128
Index　 133

[Abad2004]A. Abadpour, and S. Kasaei, “A Fast and Efficient Fuzzy Color Transfer Method,” Proceedings of the 4th IEEE International Symposium on Signal Processing and Information Technology, pp. 491-494, 2004.
[Arth1992]C. Arthur, and M. D. Guyton, Human Physiology and Mechanisms of Disease. London: Harcourt Brace, 1992.
[Berl1969]B. Berlin, and P. Kay, Basic Color Terms: Their Universality and Evolution. Berkeley: University of California Press, 1969.
[Buch1983]G. Buchsbaum, and A. Gottschalk, “Trichromacy, Opponent Colour Coding and Optimum Colour Information Transmission in the Retina,” Proceedings of Royal Society, London, pp. 89-113, 1983.
[Chan2005a]Y. Chang, S. Stato, K. Uchikawa, and M. Nakajima, “Example-based Color Stylization of Images,” ACM Transactions on Applied Perception, vol. 2, no. 3, pp. 322-345, 2005.
[Chan2005b]Y. Chang, S. Saito, and M. Nakajima, “Example-based Color Transformation for Image and Video,” Proceedings of the 3rd International Conference on Computer Graphics and Interactive Techniques in Australasia and South East Asia, pp. 347-353, 2005.
[Chan2004]Y. Chang, S. Saito, K. Uchikawa, and M, Nakajima, “Example-based Color Stylization Based on Categorical Perception,” Proceedings of the 1st Symposium on Applied Perception in Graphics and Visualization, pp. 91-99, 2004.
[Chan2003]Y. Chang, S. Saito, and M. Nakajima, “A Framework for Transfer Colors Based on the Basic Color Categories,” Proceedings of the Computer Graphics International, pp. 176-181, 2003.
[Chen2004]T. Chen, Y. Wang, V. Schillings, and C. Meinel, “Grayscale Image Matting and Colorization,” Proceedings of Asian Conference on Computer Vision, pp. 1164-1169, 2004.
[Coma2002]D. Comaniciu, and P. Meer, “Mean shift: A Robust Approach toward Feature Space Analysis,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 5, pp. 603-619, 2002.
[DiBl2003]G. Di Blasi, and D. R. Recupero, “Fast Colorization of Gray Images,” Proceedings of Eurographics Italian Chapter, 2003.
[Ferw2001]J. A. Ferwerda, “Elements of Early Vision for Computer Graphics,” IEEE Computer Graphics and Application, vol. 21, no. 5, pp. 22-33, 2001.
[Frie1999]M. Friedman, and A. Kandel, Introduction to Pattern Recognition Statistical, Structural, Neural and Fuzzy Logic Approaches. London: Imperial College Press, 1999.
[Gonz2002]R. Gonzalez, and R. Woods, Digital Image Processing, 2nd ed. New Jersey: Prentice Hall, 2002.
[Gree2005]G. R. Greenfield, and D. H. House, “A Palette-Driven Approach to Image Color Transfer,” Proceedings of Computational Aesthetics in Graphics, Visualization and Imaging, pp. 111-122, 2005.
[Gree2003]G. R. Greenfield, and D. H. House, “Image Recoloring Induced by Palette Color Associations,” Journal of WSCG, vol. 11, no. 1, pp. 189-196, 2003.
[Gupt2005]M. R. Gupta, S. Upton, and J. Bowen, “Simulating the Effect of Illumination Using Color Transformations,” Proceedings of the SPIE Conference on Computational Imaging III 5674, pp. 248-258, 2005.
[Hear1994]D. Hearn, and M. P. Baker, Computer Graphics, 2nd ed. New Jersey: Prentice Hall, 1994.
[Hert2001]A. Hertzmann, C. E. Jacobs, N. Oliver, B. Curless, and D. H. Salesin, “Image Analogies,” Proceedings of ACM SIGGRAPH 2001, California, USA, pp. 327-340, 2001.
[Kote2005]H. Kotera, “A Scene-Referred Color Transfer for Pleasant Imaging on Display,” Proceedings of IEEE International Conference on Image Processing, vol. 2, pp. 5-8, 2005.
[Lafo1996]E. Lafortune, “Mathematical Model and Monte Carlo Algorithm for Physically Based Rendering,” Ph. D. Dissertation, Department of Computer Science, Katholieke Universiteit Leuven, Belgium, 1996.
[Neum2005]L. Neumann, and A. Neumann, “Color Style Transfer Techniques using Hue, Lightness and Saturation Histogram Matching,” Proceedings of Computational Aesthetics in Graphics, Visualization and Imaging 2005, pp. 111-122, 2005.
[Pets2004]G. Petschnigg, R. Szeliski, M. Agrawala, M. Cohen, H. Hoppe, and K. Toyama. "Digital Photography with Flash and No-flash Image Pairs". ACM Transactions on Graphics, vol. 23, no. 3, pp. 664–672, 2004.
[Pham1995]B. Pham, and G. Pringle, “Color Correction for an Image Sequence”, IEEE Computer Graphics and Applications, vol. 15, no. 3, pp. 38-42, 1995.
[Pine2003]J. M. Pinel, and H. Nicolas, “Cast Shadows Detection on Lambertian Surfaces in Video Sequences,” Proceedings of SPIE 5150, Visual Communications and Image Processing 2003, pp. 378-384, 2003.
[Piti2005]F. Pitie, A. C. Kokaram, and R. Dahyot, “N-Dimensional Probability Density Function Transfer and Its Application to Color Transfer,” Proceedings of IEEE International Conference on Computer Vision, pp. 1434-1439, 2005.
[Reed2001]T. R. Reed, The Computer Engineering Handbook. CRC Press, 2001.
[Rein2004]E. Reinhard, A. O. Akuyz, M. Colbert, C. E. Hughes, and M. O’Connor, “Real-time Color Blending of Rendered and Captured Video,” Proceedings of the Interservice/Industry Training, Simulation, and Education Conference, Florida, USA, 2004.
[Rein2001]E. Reinhard, M. Ashikhmin, B. Gooch, and P. Shirley, “Color Transfer between Images,” IEEE Computer Graphics and Applications, vol. 21, no. 5, pp. 34-41, 2001.
[Rude1998]D. L. Ruderman, T. W. Cronin, and C. C. Chiao, “Statistics of Cone Responses to Natural Images: Implications for Visual Coding,” Journal of Optical Society of America, vol. 15, no. 8, pp. 2036-2045, 1998.
[Shap2001]L. G. Shapiro, and G. C. Stockman, Computer Vision. New Jersey: Prentice Hall, 2001.
[Syko2004]D. Sykora, J. Burianek, and J. Zara, “Unsupervised Colorization of Black-and White Cartoons,” Proceedings of the 3rd International Symposium on Non-Photorealistic Animation and Rendering, pp. 121-127, 2004.
[Tai2005]Y. W. Tai, J. Jia, and C. K. Tang, “Local Color Transfer via Probabilistic Segmentation by Expectation-Maximization,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 747-754, 2005.
[Umba1998]S. E. Umbaugh, Computer Vision and Image Processing. New Jersey: Prentice Hall, 1998.
[Wang2007]C. M. Wang, and Y. H. Huang, “A Novel Automatic Color Transfer Algorithm between Images,” Journal of the Chinese Institute of Engineers, 2007, to appear.
[Wang2006]C. M. Wang, Y. H. Huang, and M. L. Huang, “An Effective Algorithm for Image Sequence Color Transfer,” Journal of Mathematical and Computer Modelling, vol. 44, no. 7-8, pp. 608-627, 2006.
[Wang2004]C. M. Wang, and Y. H. Huang, “A Novel Color Transfer Algorithm for Image Sequences,” Journal of Information Science and Engineering, vol. 20, no. 6, pp. 1039-1056, 2004.
[Wels2002]T. Welsh, M. Ashikhmin, and K. Mueller, “Transferring Color to Greyscale Images,” ACM Transactions on Graphics, vol. 21, no. 3, pp. 277-280, 2002.
[Wu1999]G. K. Wu, and T. R. Reed, “Image Sequence Processing using Spatiotemporal Segmentation,” IEEE Transaction on Circuits and Systems for Video Technology, vol. 9, no. 5, pp. 798-807, 1999.
[Wysz2000]G. Wyszecki, and W. S. Stiles, Color Science Concepts and Methods, Quantitative Data and Formulae, 2nd ed. Canada: Wiley, 2000.
[Xu2005]S. Xu, S. Zhejiang, S. Zhang, and X. Ye, “Uniform Color Transfer,” Proceedings of IEEE International Conference on Image Processing, pp. 940-943, 2005.
[Yin2004]L. Yin, J. Jia, and J. Morrissey, “Towards Race-Related Face Identification: Research on Skin Color Transfer,” Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition, pp. 362-368, 2004.
[Ying2005]J. Ying, and L. Ji, “Pattern Recognition Based Color Transfer,” Proceedings of the International Conference on Computer Graphics, Imaging and Visualization, pp. 55-60, 2005.
[Zhan2004]M. Zhang, and N. D. Georganas, “Fast Color Correction using Principal Regions Mapping in Different Color Spaces,” Real-Time Imaging, vol. 10, no. 1, pp. 23-30, 2004.