Affiliation:
1. Menofia University, Egypt & Scientific Research Group in Egypt (SRGE), Egypt
Abstract
Image colorization is a new image processing topic to recolor gray images to look as like the original color images as possible. Different methods have appeared in the literature to solve this problem, the way that leads to thinking about decolorization, eliminating the colors of color images to just small color keys, aid in the colorization process. Due to this idea, decolorization is considered as a color image encoding mechanism. In this chapter, the authors propose a new decolorization system depends on extracting the color seeds (Representative Pixels [RP]) using morphology operations. Different decolorization methods are studied and compared to the system results using different quality metrics.
Reference22 articles.
1. Arther, D., & Vassilvitskii, S. (2007). k-means++: The advantages of careful seeding. Eighteenth annual ACM-SIAM symposium on Discrete algorithms. (pp. 1027-1035). Astor Crowne Plaza, New Orleans, Louisiana: Society for Industrial and Applied Mathematics.
2. Brooks, S., Saunders, I., & Dodgson, N. A. (February 2007). Image compression using sparse colour sampling combined with nonlinear image processin. The 19th Symposium on Electronic Imaging (SPIE) (pp. 64920F-64920F). San Jose, California, USA: International Society for Optics and Photonics.
3. Chaumont, M., & Puech, W. (2009). Protecting the color information by hiding it. Recent Advances in Signal Processing, 22.
4. Cheng, L., & Vishwanathan, S. V. (2007). Learning to compress images and videos. The 24th international conference on Machine learning (pp. 161-168). Oregon State University, Oregon, USA: ACM.
5. Mean shift: a robust approach toward feature space analysis