在本論文研究計畫中，我們針對彩色圖像提出一項以人類對顏色及顏色組合之情緒感受為基礎，進而在彩色圖像中重新標記顏色或進行圖像間顏色置換之技術及其相關之應用。為此我們開發了一種針對彩色圖像之色彩重新配置及於圖像間色彩轉移的新系統架構，此架構能依據人類的情緒感受或是直接運用一組事先被定義的彩色-情感模組，來執行彩色圖像中的顏色重新標記及彩色圖像間的顏色置換或轉移，進而達成彩色圖像本身的情境轉換或是彩色圖像間之情境轉移。在此研究當中，我們還提出了一種新技術，它可以根據圖像內容的複雜度，去調整和決定圖像的主要顏色總數。因此，本方法可以針對彩色圖像內容實際的配色情況，採用動態可調整之主要顏色數來實現彩色圖像之色彩置換或進行彩色圖像間之色彩轉移，如此可改進以前他人研究此領域所發表之論文，僅採用單一主要顏色或固定數量主要顏色組合的方法來重新呈現彩色圖像，我們的方法將可更有效、更精確地做到針對彩色圖像中的顏色重新標記以及和人類的情緒感受的連結。此外，本論文更將前述我們所提的方法應用在壁紙和紡織布的挑選，使用者可以透過想要的一張參考彩色圖像或是一項已定義好的人類的情感關鍵字(對應一組被事先定義的彩色組合)，運用第三章及第四章節所提技術，可在已建好的資料庫中，搜尋並獲得使用者想要之相似的壁紙或紡織品的彩色圖像。本論文的其他貢獻還有我們在第三章節所提出的演算法Touch Four Sides (TFS) 和 Touch Up Sides (TUS)，它們可以提高從彩色圖像中辨識出背景和前景，以及其他有效主要顏色的識別度。本論文中所提的圖像範疇主要是聚焦在彩色圖像上，如風景照，靜物圖，繪畫，壁紙等。所提出的方法可以幫助非專業人士更客觀，更精確地操作和描述彩色圖像中色彩與情感之間的連結。其潛在的應用，包括商業設計中的廣告設計、封面設計、服裝之顏色匹配、室內設計等，另外還有藝術創作之顏色選擇、藝術作品之色彩置換及灰階圖像之彩色著色、照相機上的照片之色彩再改變等等。

In this research project of dissertation, we propose an applicable technique in regard of tagging and replacing colors in colorful images based on human reaction towards color and the combination of colors. For this purpose, a new framework of colorful relocation for colorful image and colorful transferring between colorful images was developed. Based on human emotional feelings and a pre-defined emotional module, this new framework is able to conduct scheme-changing or scheme-transferring upon colorful images. In this research, a new technique was introduced, and it enables adjusting and deciding the total number of colors in an image according to its complicity. Therefore, it is possible to improve previous studies, where only single or fixed amount of main colors are used to represent colorful images, by adopting the new technique, which is able to dynamically adjust the amount of main colors in a colorful image to execute color changing and transferring, introduced in this study. Furthermore, this study adopted the technique mentioned earlier for wallpaper and textile selection. By searching in the database that uses a colorful image or a pre-defined human emotional keyword (in correspondence with a pre-defined combination of colors) as a reference, the user is able to acquire the similar colorful images that they desired on wallpaper or textile through this new technique. Other significance that this research has offered including the two algorithms introduced in this study, Touch Four Sides (TFS) and Touch Up Sides (TUS), in which they are able to further enhance the identification ability when extracting the main colors from the background and foreground of an image. The main focus of this study should be on colorful images. For instance, scenic pictures, still images, paintings, and wallpapers. The mentioned technique is able to assist non-professional users to describe and connect emotion and color more precisely and objectively. The potential fields applicable to this technique can be in commercial design, cover design, clothing color-matching, interior design, tinting of gray scale images, emotional change on camera taken pictures, and colorful choice or colorful changing in artistic creation…etc.

[1] Yang C-K. and Peng L-K., “Automatic mood-transferring between color images,” IEEE Computer Graphics and Applications 28, 52–61,March 2008.
[2] Michela Dellagiacoma, Pamela Zontone and Giulia Boato, “Emotion Based Classification of Natural Images,” DETECT’11, Glasgow, Scotland, UK. Copyright 2011 ACM 978-1-4503-0962-2/11/10, October 28, 2011.
[3] Li He • Hairong Qi and Russell Zaretzki, “Image color transfer to evoke different emotions based on color combinations,” Springer, SIViP, 9:1965–1973, 2015.
[4] Simon McArdle, “Psychology of Color in Logo Design,” internet: www.huffingtonpost.com/brian-honigman/psychology-color-design-infographic_ b_2516608.html , accessed January 2016.
[5] Amara, “The Complete Guide to Colour Psychology,” Internet : www.amara.com /luxpad/inspiration /colour-psychology/, accessed Feb 2016.
[6] Chang Y., Saito S., Uchikawa K. and Nakajima M, “Example-based color stylization of images,” ACM Transactions on Applied Perception 2, 3 , 322–345, 2005.
[7] L.-C. Ou, M. R. Luo, A. Woodcock and A. Wright, “Colour emotions for single colours,” in part i of A study of colour emotion and colour preference. Color Research Application 29 232–240 , 2004.
[8] L.-C. Ou, M. R. Luo, A. Woodcock and A. Wright, “Colour emotions for two-colour combinations,” in part ii of A study of colour emotion and colour preference. Color Research Application 29 292–298, 2004.
[9] W. Wei-Ning, Y. Ying-Lin and J. Sheng-ming, “Image retrieval by emotional semantics: A study of emotional space and feature extraction,” in Systems, Man and Cybernetics, SMC ’06. IEEE International Conference on, volume 4, pp. 3534 –3539, 2006.
[10] G. Csurka, S. Skaff, L. Marchesotti and C. Saunders, “Learning moods and emotions from color combinations,” in Proceedings of the Seventh Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP ’10, ACM, New York, NY, USA, pp. 298–305, 2010.
[11] E. Reinhard, M. Ashikhmin, B. Gooch and P. Shirley, “Color transfer between images,” IEEE Comput, Graph, pp. 34–41, Appl. 21, 2001.
[12] Fuzhang Wu, Weiming Dong, Yan Kong, Xing Mei, Jean-Claude Paul and Xiaopeng Zhang, “Content-Based Color Transfer,” Computer Graphics Forum Volume 32, Issue 1, pp. 190–203, February 2013.
[13] T Pouli and E Reinhard, “Progressive histogram reshaping for creative color transfer and tone reproduction,” Computers & Graphics 35 (1), 67-80, 2011.
[14] Y.-W. Tai, J. Jia and C.-K. Tang, “Local color transfer via probabilistic segmentation by expectation-maximization,” Computer Vision and Pattern Recognition, IEEE Computer Society Conference on 1, 747–754, 2005.
[15] F. Pitie, A. Kokaram and R. Dahyot, “N-dimensional probability density function transfer and its application to color transfer,” in Computer Vision, 2005. ICCV, Tenth IEEE International Conference on, volume 2, pp. 1434 –1439 Vol. 2, 2005.
[16] X. Xiao and L. Ma, “Color transfer in correlated color space,” in Proceedings of the 2006 ACM international conference on Virtual reality continuum and its applications, VRCIA ’06, ACM, New York, NY, USA, pp. 305–309, 2006.
[17] Sasank Chilamkurthy, “A 2017 Guide to Semantic Segmentation with Deep Learning”, http://blog.qure.ai/notes/semantic-segmentation-deep-learning-review, July 5, 2017.
[18] Y. Xiang and B. Zou, H. Li, “Selective color transfer with multisource images,” Pattern Recognition Letters 30, pp. 682 – 689, 2009.
[19] W.-C. Chiou, Y.-L. Chen and C.-T. Hsu, “Color transfer for complex content images based on intrinsic component,” in Multimedia Signal Processing (MMSP) IEEE International Workshop on, pp. 156 –161, 2010.
[20] W. Dong, G. Bao, X. Zhang and J.-C. Paul, “Fast local color transfer via dominant colors mapping,” in ACM SIGGRAPH ASIA 2010 Sketches, SA ’10, ACM, New York, NY, USA, pp. 46:1–46:2, 2010.
[21] T. Pouli and E. Reinhard, “Progressive color transfer for images of arbitrary dynamic range,” Computers & Graphics 35, 2011, pp. 67 – 80. Extended Papers from Non-Photorealistic Animation and Rendering (NPAR) 2010.
[22] Ming Zhanga, Ke Zhanga, Qinghe Fenga, Jianzhong Wanga and Jun Konga, Yinghua Lua, “A novel image retrieval method based on hybrid information descriptors,” Journal of Visual Communication and Image Representation, Volume 25, Issue 7, Pages 1574–1587,October 2014.
[23] S. Kobayashi, “Color Image Scale,” Kodansha International, 1992.
[24] L. Eisemann, “Pantone’s Guide to Communicating with Color,” Grafix Press, 2000.
[25] I.R.I., “The Color for Designer,” DrSmart Press Co., Ltd, June 2011.
[26] B. M. Whelan, “Color Harmony 2: A Guide to Creative Color Combinations,” Rockport Publishers, 1994.
[27] G. R. Greenfield and D. H. House, “Image recoloring induced by palette color associations,” Journal of WSCG, Vol.11, No.1., ISSN 1213-6972 WSCG’2003, Plzen, Czech Republic, February 3-7, 2003.
[28] Krishnan, N. and M.S Univ., Washington ; Banu, M.S. ; Callins Christiyana, C, “Content Based Image Retrieval Using Dominant Color Identification Based on Foreground Objects,” Conference on Computational Intelligence and Multimedia Applications. International Conference on (Volume:3 ) , 2007.
[29] J. D. Foley, A. V. Dam, S. k. Feiner, and J. F. Hughes, “Comput. Graphics: Principles and Practice,” Ma Addison-Wesley, 1990.
[30] H. J. Eysenck, “A critical and experimental study of colour preferences,” The American Journal of Psychology 54, pp. 385–394, 1941.
[31] R. D. Norman, W. A. Scott, “Colour and affect: a review and semantic evaluation,” Journal of General Psychology 46, pp. 185–233, 1952.
[32] Chou Chien-Kuo, “Color Scheme Bible Compact Edition,” Grandtech information Co., Ltd, 2011.
[33] Y.Y.Su and C.C.Chang , “A Dynamic Color Palette for Color Images Coding,” Third IEEE Pacific Rim Conference on Multimedia Hsinchu, Taiwan, pp. 369-376, December 2002..
[34] Y. Linde, A. Buzo, and R. M. Gray, “An Algorithm for Vector Quantizer Design,” IEEE Transactions on Communications, vol. 28, pp. 84-95, January 1980.
[35] Sato T, Kajiwara K, Hoshino H and Nakamura T, “Quantitative evaluation and categorizing of human emotion induced by colour,” Advances in Colour Science and Technology 3, pp. 53–59 ,2000.
[36] Cohn, J. “Experimentelle Untersuchunger uber Gefuhlsbetonung Farben, helligkeiten und ihre Combinationen”. Philos. Stud., 10, 562–603, 1894.
[37] J. Lee, Y.-M. Cheon, S.-Y. Kim and E.-J. Park, “Emotional evaluation of color patterns based on rough sets,” in Natural Computation, 2007. Third International Conference on, volume 1, pp. 140 –144. ICNC 2007.
[38] S. Tanaka, Y. Iwadate and S. Inokuchi, “An attractiveness evaluation model based on the physical features of image regions,” in Pattern Recognition, Proceedings. 15th International Conference on, 2000.
[39] R. Gray, “Vector Quantization,” IEEE ASSP Mag., vol. 1, pp. 4-29, April 1984.
[40] J. Itten, “Art of Colour,” Van Nostrand Reinhold, 1962.
[41] X. Mao, B. Chen and I. Muta, “Affective property of image and fractal dimension,” ELSEVIER, Chaos, Solitons & Fractals Volume 15, Issue 5, Pages 905–910, March 2003.
[42] CIELAB, “CIELab - Color Models - Technical Guides,” internet: dba.med.sc.edu /price/irf/Adobe_tg/models/ cielab.html, accessed Feb 2016.
[43] L. Neumann and A. Neumann, “Color style transfer techniques using hue, lightness and saturation histogram matching,” in Computational Aesthetics in Graphics, Visualization and Imaging 2005, pages 111-122. May 2005.
[44] M.-T. Li, M.-L. Huang and C.-M. Wang, “Example-based color alternation for images,” in Computer Engineering and Technology (ICCET), 2nd International Conference on, volume 7, pp. V7–316 –V7–320, 2010.
[45] M. Grundland and N. A. Dodgson, “Decolorize: Fast, contrast enhancing, color to grayscale conversion,” ELSEVIER, Pattern Recognition, Volume 40, Issue 11, Pages 2891–2896, November 2007.
[46] T.-W. Huang and H.-T. Chen, “Landmark-based sparse color representations for color transfer,” in Computer Vision, IEEE 12th International Conference, 2009.
[47] X. An and F. Pellacini, “User-controllable color transfer,” Wiley-Blackwell, Computer Graphics Forum, Volume 29, Number 2, pp. 263-271(9) , May 2010.
[48] H. Huang and Y. Zang, C.-F. Li, “Example-based painting guided by colorfeatures,” Springer, The Visual Computer, Volume 26, Issue 6-8, pp. 933-942, June 2010.
[49] Hartigan, J. A., Wong and M. A., “Algorithm AS 136: A K-Means Clustering Algorithm,” Journal of the Royal Statistical Society, Series C 28 (1): 100-108. JSTOR 2346830, 1979.
[50] Kobayashi, S. The Aim and Method of the Color Image Scale. Color Res, 6, pp. 93–107, Appl. 1981.
[51] Zhang, D. and Lu, G. “Evaluation of Similarity Measurement for Image Retrieval.” In Proceedings of the IEEE International Conference Neural Networks & Signal Processing, Nanjing, China, 14–17 December 2003.
[52] Ravishankar K.C., Prasad B.G., Gupta S.K. and Biswas K.K. “Dominant color region based indexing for CBIR.” In Proceedings of the International conference on Image analysis and processing, Venice, Italy, 27–29, pp. 887–892 September 1999.
[53] Talib A., Mahmuddin M., Husni H. and George L.E. “Dominant Color-Based Indexing Method for Fast Content-Based Image Retrieval.” J. Vis. Commun. Image Representat, 24, pp. 345–360, 2013.