Textural Features for Scribble-Based Image Colorization
In this paper we propose how to exploit image textural features to improve scribble-based image colorization. The existing techniques work by propagating color from the user-added scribbles over the whole image. The color propagation paths are determined so as to minimize the luminance changes integrated along the path. In our method, at first linear discriminant analysis is performed over the scribble pixels to extract discriminative textural features (DTF). Our contribution to image colorization lies in using DTF for the path optimization instead of the luminance. The colorization results presented in the paper explain and confirm the method’s robustness compared with the alternative existing techniques.
KeywordsTextural Feature Linear Discriminant Analysis Propagation Path Local Binary Pattern Color Propagation
Unable to display preview. Download preview PDF.
- 1.Levin, A., Lischinski, D., Weiss, Y.: Colorization using optimization. In: SIGGRAPH, pp. 689–694 (2004)Google Scholar
- 4.Kim, T., Lee, K., Lee, S.: Edge-preserving colorization using data-driven random walks with restart. In: IEEE ICIP, pp. 1661–1664 (2009)Google Scholar
- 7.Heu, J., Hyun, D., Kim, C., Lee, S.: Image and video colorization based on prioritized source propagation. In: IEEE ICIP, pp. 465–468 (2009)Google Scholar