Image colorization using Bayesian nonlocal inference

Chen Yao; Xiaokang Yang; Li Chen; Yi Xu

doi:10.1117/1.3582139

Translator Disclaimer

1 April 2011 Image colorization using Bayesian nonlocal inference

Chen Yao, Xiaokang Yang, Li Chen, Yi Xu

Author Affiliations +

J. of Electronic Imaging, 20(2), 023008 (2011). https://doi.org/10.1117/1.3582139

Abstract

Colorization is the process of adding colors to monochrome images. State-of-the-art colorization methods can be generally categorized into example-based colorization and scribble-based algorithms. In this paper, we present a new scribble-based colorization algorithm based on Bayesian inference and nonlocal likelihood computation. We convert the process of image colorization to a probability optimization problem in this Bayesian framework, where we use nonlocal-mean likelihood computation and Markov random field prior's. The expectation maximization method is used to solve an optimization object function. Finally, experimental results demonstrate the effectiveness of the proposed algorithm

©(2011) Society of Photo-Optical Instrumentation Engineers (SPIE)

Citation Download Citation

Chen Yao, Xiaokang Yang, Li Chen, and Yi Xu "Image colorization using Bayesian nonlocal inference," Journal of Electronic Imaging 20(2), 023008 (1 April 2011). https://doi.org/10.1117/1.3582139

Published: 1 April 2011

ACCESS THE FULL ARTICLE