Image Colorization with an Affective Word

详细信息    查看全文

• 作者：Xiaohui Wang (18)
  Jia Jia (18)
  Hanyu Liao (18)
  Lianhong Cai (18)
  
• 关键词：Image colorization ; affective word ; color theme
• 刊名：Lecture Notes in Computer Science
• 出版年：2012
• 出版时间：2012
• 年：2012
• 卷：7633
• 期：1
• 页码：59-66
• 全文大小：1047KB
• 参考文献：1. Levin, A., Lischinski, D., Weiss, Y.: Colorization using optimization. ACM Transactions on Graphics聽23, 689 (2004) CrossRef
  2. Welsh, T., Ashikhmin, M., Mueller, K.: Transferring color to greyscale images. ACM Transactions on Graphics聽21(3), 277鈥?80 (2002) CrossRef
  3. Ironi, R., Cohen-Or, D., Lischinski, D.: Colorization by example. In: Rendering Techniques, pp. 201鈥?10 (2005)
  4. Charpiat, G., Hofmann, M., Sch枚lkopf, B.: Automatic Image Colorization Via Multimodal Predictions. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol.聽5304, pp. 126鈥?39. Springer, Heidelberg (2008) CrossRef
  5. Tai, Y.W., Jia, J., Tang, C.K.: Local color transfer via probabilistic segmentation by expectation-maximization. In: Computer Vision and Pattern Recognition, vol.聽1, pp. 747鈥?54. IEEE (2005)
  6. Chia, A.Y.S., Zhuo, S., Gupta, R.K., Tai, Y.W., Cho, S.Y., Tan, P., Lin, S.: Semantic colorization with internet images. ACM Transactions on Graphics聽30(6), 1鈥? (2011) CrossRef
  7. Arnheim, R.: Art and visual perception: A psychology of the creative eye. University of California Press (1954)
  8. Kobayashi, S.: Color image scale. Kosdansha International (1991)
  9. Kobayashi, S.: Art of Color Combinations. Kosdansha International (1995)
  10. Reinhard, E., Adhikhmin, M., Gooch, B., Shirley, P.: Color transfer between images. IEEE Computer Graphics and Applications聽21(5), 34鈥?1 (2001) CrossRef
  11. Chen, T., Cheng, M.M., Tan, P., Shamir, A., Hu, S.M.: Sketch2photo: internet image montage. ACM Transactions on Graphics聽28(5), 124:1鈥?24:10 (2009)
  12. Cohen-Or, D., Sorkine, O., Gal, R., Leyvand, T., Xu, Y.Q.: Color harmonization. ACM Transactions on Graphics聽25(3), 624鈥?30 (2006) CrossRef
  13. O鈥橠onovan, P., Agarwala, A., Hertzmann, A.: Color compatibility from large datasets. ACM Transactions on Graphics聽30(4), 63:1鈥?3:12 (2011) CrossRef
  14. Rother, C., Kolmogorov, V., Blake, A.: 鈥滸rabCut鈥? interactive foreground extraction using iterated graph cuts. ACM Transactions on Graphics聽23(3), 309鈥?14 (2004) CrossRef
  15. Cheng, M.M., Zhang, F.L., Mitra, N.J., Huang, X., Hu, S.M.: Repfinder: finding approximately repeated scene elements for image editing. ACM Transactions on Graphics聽29, 83:1鈥?3:8 (2010) CrossRef
  16. Cheng, M.M., Zhang, G.X., Mitra, N.J., Huang, X., Hu, S.M.: Global contrast based salient region detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 409鈥?16. IEEE (June 2011)
  17. Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE Transactions on Pattern Analysis and Machine Intelligence聽24(4), 509鈥?22 (2002) CrossRef
  18. Wang, X.H., Jia, J., Cai, L.H.: Affective image adjustment with a single word. To apper in The Visual Computer
  19. Dong, Z., Dong, Q.: HowNet and the Computation of Meaning. World Scientific (2006)
  20. Barnes, C., Shechtman, E., Finkelstein, A., Goldman, D.B.: Patchmatch: a randomized correspondence algorithm for structural image editing. ACM Transactions on Graphics聽28(3), 24:1鈥?4:11 (2009) CrossRef
  
• 作者单位：Xiaohui Wang (18)
  Jia Jia (18)
  Hanyu Liao (18)
  Lianhong Cai (18)
  
  18. Key Laboratory of Pervasive Computing, Ministry of Education, Tsinghua National Laboratory for Information Science and Technology (TNList), Department of Computer Science and Technology, Tsinghua University, China
  

文摘

An important role of image color is the conveyer of emotions (through color themes). The colorization is less useful with an undesired color theme, even semantically correct, which has been rarely considered previously. In this paper, we propose a complete system for the image colorization with an affective word. We only need users to assist object segmentation along with text labels and give an affective word. First, the text labels along with other object characters are jointly used to filter the internet images to give each object a set of semantically correct reference images. Second, we select a set of color themes according to the affective word based on art theories. With these themes, a generic algorithm is adopted to select the best reference for each object. Finally, we propose a hybrid texture synthesis approach to colorize each object. Our experiments show that the results of our system have both the correct semantics and the desired emotions.