臺灣博碩士論文加值系統

色彩轉換是一門有趣的研究領域，主要目標是藉由顏色上的改變轉換原始影像的色彩風格。目前大多數已存在的相關方法是根據一張參考影像的顏色資訊對來源影像做色彩轉換，也有少部分方法是讓使用者選擇或提供一些顏色資訊，直接在影像顏色上做修改。
市面上已有許多應用軟體可對影像進行各式各樣的顏色轉換，不過這些工具對初學者來說，若是沒有進行長期間的使用與學習，則難以在短時間內完成理想的轉換結果。
本論文提出一個靈活的以範例為基礎之色彩轉換系統，操作方式從最簡單的全自動模式至進階的選項模式，提供初學者或更高專業等級使用者使用。不只讓初學者能在短期間內熟悉並掌握色彩轉換的基本操作模式，也讓想使用進階功能的使用者，經由多功能的選項得到更細部合意的色彩轉換效果。
實驗結果表明本篇所提出的色彩轉換系統，不只能讓初次操作的使用者以簡單的操作，得到自然的結果，也能讓經由短期學習操作方式的使用者以便捷的操作得到令人滿意的結果。

Color transfer is an interesting topic for research in the field of image processing, whose main task is to automatically alert image’ colors and so to change image’s style as well. Most current methods of color transfer are example-based. Some methods allow the user to provide color information and edit image colors directly on the image. There have been many tools for color transfer available, however most of which are difficult for novices to use and introduce desired results in a short period of time. This paper proposes a flexible example-based color transfer system, which provides two operating modes, an automatic mode and an advanced mode, for novices and expert users, respectively. The experimental results show that the proposed color transfer system not only can introduce natural results with simple operation by novices in the first use, but also can produce various desired results by users with short-term learning.

目錄
第一章 緒論 1
1.1 色彩轉換 1
1.2 研究動機與目的 2
1.3 論文架構 2
第二章 相關研究 3
2.1色彩空間 3
2.1.1 RGB色彩空間 3
2.1.2 Lab色彩空間 4
2.1.3 HSI色彩空間 5
2.2 相關技術 6
2.2.1 全域色彩轉換 6
2.2.2 區域色彩轉換 7
2.2.3 基於學習的色彩轉換 9
第三章 研究方法 10
3.1色彩調色盤建構 10
3.1.1 直方圖分割 11
3.1.2 顏色分割 16
3.1.3 調色盤建構 17
3.2 色板顏色配對 19
3.2.1 自動顏色配對 19
3.2.2 使用者設定 20
3.3 色彩轉換 21
3.4 僞像抑制 23
第四章 色彩轉換系統 26
4.1 系統流程 26
4.2 使用者介面 28
第五章 實驗結果 30
5.1 調色盤細緻程度比較 30
5.2 自動與使用者配對比較 33
第六章 結論與未來研究 36
參考文獻 37
附錄：英文論文 40

圖目錄
圖一 基於範例之色彩轉換 (A) 來源影像 (B) 參考影像 (C) 結果影像 1
圖二 RGB色彩空間 3
圖三 CIELab色彩空間 4
圖四 HSI色彩空間 5
圖五 (A) 原直方圖 H 之分割結果 (B) 平滑化直方圖 H'' 之分割結果 (C) 利用直方圖平滑化簡化分割結果 12
圖六 (A) 分割位置移除前 (B) 分割位置移除後 13
圖七 (A)(B)第一個判斷條件之區間合併，(C)(D)第二個判斷條件之區間合併 14
圖八 初始調色盤 16
圖九 來源影像調色盤與參考影像調色盤之配對結果 20
圖十 使用者指定之調色盤配對 21
圖十一 結果影像之偽像區域 (A) 來源影像，(B) 參考影像，(C) 轉換結果 24
圖十二 圖八結果影像之偽像抑制 25
圖十三 系統流程圖 27
圖十四 使用者介 28
圖十五 使用者介面呼叫MATCH TOOL 29
圖十六 自動轉換結果（一） (A) 來源影像，(B) 參考影像，(C) ~ (K) 各尺寸調色盤配對之轉換結果 31
圖十七 自動轉換結果（二） (A) 來源影像，(B) 參考影像，(C) ~ (K) 各尺寸調色盤配對之轉換結果 32
圖十八 自動配對與使用者配對比較 (A) ~ (C) 來源影像，(D) ~ (F) 參考影像，(G) ~ (I) 自動配對之轉換結果，(J) ~ (L) 使用者配對之影像結果 33
圖十九 自動配對與使用者配對比較 (A) ~ (F) 來源影像，(G) ~ (L) 參考影像，(M) ~ (R) 自動配對之轉換結果，(S) ~ (X) 使用者配對之影像結果 34
圖二十 使用者配對 (A) 來源影像，(B) 參考影像，(C)(D) 不同配對之轉換結果 35
圖二十一 使用者配對 (A) 來源影像，(B) 參考影像，(C)(D) 不同配對之轉換結果 35

[1]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.
[2]L. Neumann and A. Neumann, “Color style transfer techniques using hue, lightness and saturation histogram matching,” Computational Aesthetics in Graphics, Visualization and Imaging, Girona, Spain, pp. 111-122, 2005.
[3]C. R. Senanayake and D. C. Alexander, “Colour transfer by feature based histogram registration,” British Machine Vision Conference, Malvern, UK, pp. 1-10, 2007.
[4]Y.- H. Huang, P.- C. Wang, C.- C. Chou, and K.- P. Lin, “An automatic selective color transfer algorithm for images,” SAC ''11 Proceedings of the 2011 ACM Symposium on Applied Computing, NY, USA , pp. 66-71, 2011.
[5]W. - S. Chen, M. - L. Huang, and C. - M. Wang “Optimizing color transfer using color similarity measurement,” 2016 IEEE/ACIS 15th International Conference on Computer and Information Science (ICIS), Rome, Italy, pp. 26-29, 2016.
[6]A. Abadpour and S. Kasaei, “A fast and efficient fuzzy color transfer method,” Proceedings of the Fourth IEEE International Symposium on Signal Processing and Information Technology, pp. 18-21, 2004.
[7]Y. - W. Tai, J. Jia, and C. - K. Tang, “Local color transfer via probabilistic segmentation by expectation-maximization,” 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR''05), Washington, DC, USA, vol. 1, pp. 747-754, 2005.
[8]X. Huo, J. Tan, and R. Wang, “Color transfer based on combining subtractive clustering with FCM clustering,” 2007 10th IEEE International Conference on Computer-Aided Design and Computer Graphics, Beijing, China, pp. 15-18, 2007.
[9]X. - Y. Qian, B. - F. Wang, and L. Han, “An efficient fuzzy clustering-based color transfer method,” 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery, Yantai, China, pp. 10-12, 2010.
[10]W. - C. Chiou, Y. - L. Chen, and C. - T. Hsu, “Color transfer for complex content images based on intrinsic component,” 2010 IEEE International Workshop on Multimedia Signal Processing, Saint Malo, France, pp. 4-6, 2010.
[11]X. Yang, Z. Su, and D. Wang, “Local color transfer via color classification,” 2012 International Conference on Audio, Language and Image Processing, Shanghai, China, pp. 16-18, 2012.
[12]H. Chang, O. Fried, Y. Liu, S. DiVerdi, and A. Finkelstein, “Palette-based photo recoloring,” ACM Transactions on Graphics (TOG), vol. 34, pp. no. 4, 2015.
[13]H. Hristova, O. - L. Meur, R. Cozot, and K. Bouatouch, “Style-aware robust color transfer,” CAE ''15 Proceedings of the workshop on Computational Aesthetics, Istanbul, Turkey, pp. 67-77, 2015.
[14]K. Panetta, L. Bao, and S. Agaian, “Novel multi-color transfer algorithms and quality measure,” IEEE Transactions on Consumer Electronics, vol. 62, no. 3, pp. 292-300, 2016.
[15]X. Xiao, L. Ma, “Color transfer in correlated color space,” VRCIA ''06 Proceedings of the 2006 ACM international conference on Virtual reality continuum and its applications, Hong Kong, China, pp. 305-309, 2016.
[16]B. Arbelot, R. Vergne, T. Hurtut, and J. Thollot, “Local texture-based color transfer and colorization,” Computers & Graphics, vol. 62, pp. 15-27, 2017.
[17]F. Wu, W. Dong, Y. Kong, X. Mei, J. - C. Paul, and X. Zhang, “Content-Based Colour Transfer,” Computer Graphics Forum, vol. 32, no. 1, pp. 190-203, 2013.
[18]Z. Su, K. Zeng, and L. Liu, “Corruptive artifacts suppression for example-based color transfer,” IEEE Transactions on Multimedia, vol. 16, no. 4, pp. 988-999, 2014.
[19]Z. Cheng, Q. Yang, and B. Sheng, “Deep colorization,” ICCV ''15 Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), pp. 415-423, 2015.
[20]F. Luan, S. Paris, E. Shechtman, and K. Bala, “Deep photo style transfer,” Computer Vision and Pattern Recognition, arXiv:1703.07511v3, 2017.
[21]J. Delon, A. Desolneux, J. - L. Lisani, and A. - B. Petro, “Automatic color palette,” Inverse Problems and Imaging, vol. 1, no. 2, pp. 265-287, 2007.
[22]O. Frigo, N. Sabater, V. Demoulin, and P. Hellier, “Optimal transportation for example-guided color transfer,” 12th Asian Conference on Computer Vision, Singapore, pp. 655-670, 2014.