本篇論文提出一個以本質元件（intrinsic component）及圖形理論之區塊對應分析（graph-theoretic region correspondence estimation）來達到自動化色彩轉移，主要處理對象為擁有複雜內容的影像。假設有多張可用的參考影像，我們希望藉由加入本質元件的概念來加強表示影像中區域的連接性，並決定出一組最佳的參考顏色集合來轉移顏色特徵。另一方面，我們也將本質元件當作色彩轉移程序中輔助的資訊，以減少原本可能於複雜區塊中顏色溢出（color-bleeding）的情形。首先，我們以區塊為單位來表示各張影像，提出以結合區塊特性（region attributes）和區塊之間的空間相鄰關係（spatially adjacent relationships）的區塊對應基準，來決定出每個目標區塊所對應的最佳匹配參考區塊。最後，我們根據最佳匹配的區塊對應組合於去相關的色彩空間作色彩轉移，並針對複雜區塊的部分像素點採取權重式的色彩轉移技術。實驗結果顯示，不論於主觀和客觀的評估上，我們所提出的方法都可以得到比過去的方法更優越的結果。

[1] A. Levin, D. Lischinski and Y. Weiss, “Colorization using Optimization,” Proc. of SIGGRAPH, July 2004.
[2] H. Siddiqui and C. A. Bouman, “Hierarchical Color Correction for Camera Cell Phone Images,” IEEE Trans. on Image Processing, vol. 17, no. 11, Nov. 2008.
2, Feb. 2007.
[3] Y. Chang, S. Saito, and M. Nakajima, “Example-Based Color Transformation of Image and Video Using Color Categories,” IEEE Trans. Image Processing, vol. 16, no. 2, Feb. 2007.
[4] Z. Liu, C. Zhang and Z. Zhang, “Learning-Based Perceptual Image Quality Improvement for Video Conferencing,” Proc. ICME, pp. 1035-1038, 2007.
[5] 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.
[6] Y.W. Tai, J. Jia and C.K Tang, “Local Color Transfer via Probabilistic Segmentation by Expectation-Maximization,” Proc. CVPR, 2005.
[7] Y. Chang, S. Saito, K. Uchikawa, and M. Nakajima, “Example-based color stylization of images,” ACM Trans. Appl. Percept., vol. 2, pp. 322–345, 2005.
[8] T. Welsh, M. Ashikhmin and K. Mueller, “Transferring Color to Greyscale Images,” Proc. of SIGGRAPH, July 2002.
[9] A. Abadpour and S. Kasaei, ”An Efficient PCA–Based Color Transfer Method,” Visual Communication and Image Representation, Vol. 18, no. 1, pp.15-34, Feb. 2007.
[10] Y. Xiang, B. Zou, H. Wang, H. Li and Z. Xie, “Multi-Reference Color Transfer for Natural Images,” Proc. ICIP, 2008.
[11] D.L. Ruderman, T.W. Cronin, and C.C. Chiao, “Statistics of Cone Responses to Natural Images: Implications for Visual Coding,” J. Optical Soc. of America, vol. 15, no. 8, pp. 2036-2045, 1998.
[12] http://en.wikipedia.org/wiki/LMS_color_space
[13] G. D. Finlayson, M. S. Drew and C. Lu, “Intrinsic Images by Entropy Minimization,” Proc. ECCV, 2004.
[14] D. Comaniciu and P. Meer, “Mean shift: a robust approach toward feature space analysis,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 5, pp. 603-619, May 2002.
[15] W.C. Chiou and C.T. Hsu, “Region-Based Color Transfer from Multi-Reference with Graph-Theoretic Correspondence Estimation,” Proc. ICIP, 2009.
[16] C.Y. Li and C.T. Hsu, “Image Retrieval with Relevance Feedback Based on Graph-Theoretic Correspondence Estimation,” IEEE Trans. Multimedia, vol. 10, no. 2, pp. 447-456, April 2008.
[17] D. Hasler and S. Suesstrunk, “Measuring colourfulness for natural images,” Proc. IS&T/SPIE Electronic Imaging 2003: Human Vision and Electronic Imaging VIII, SPIE, 87-95, 2003.
[18] W.C. Chiou and C.T. Hsu, “Color Transfer for Complex Images Based on Intrinsic Component,” accepted by Proc. MMSP, 2009.