1 April 2011 Image colorization using Bayesian nonlocal inference
Author Affiliations +
J. of Electronic Imaging, 20(2), 023008 (2011). doi:10.1117/1.3582139
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
Chen Yao, Xiaokang Yang, Li Chen, 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


Content-aware automatic cropping for consumer photos
Proceedings of SPIE (March 21 2013)
Image quality metrics for degraded visual environments
Proceedings of SPIE (May 05 2017)
Facades structure detection by geometric moment
Proceedings of SPIE (June 19 2017)

Back to Top