1 April 2011 Image colorization using Bayesian nonlocal inference
Author Affiliations +
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)
Chen Yao, Chen Yao, Xiaokang Yang, Xiaokang Yang, Li Chen, Li Chen, Yi Xu, 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 . Submission:
JOURNAL ARTICLE
7 PAGES


SHARE
RELATED CONTENT

Content-aware automatic cropping for consumer photos
Proceedings of SPIE (March 20 2013)
A stereo matching handling model in low-texture region
Proceedings of SPIE (October 07 2015)
Image quality metrics for degraded visual environments
Proceedings of SPIE (May 04 2017)
Facades structure detection by geometric moment
Proceedings of SPIE (June 18 2017)

Back to Top