Table of Contents Author Guidelines Submit a Manuscript
International Journal of Digital Multimedia Broadcasting
Volume 2017, Article ID 9029315, 13 pages
Research Article

Low-Light Image Enhancement Based on Guided Image Filtering in Gradient Domain

1School of Computer Engineering and Science, Shanghai University, Shanghai, China
2School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China
3School of Machinery and Automation, Wuhan University of Science and Technology, Wuhan, China
4Earthquake Administration of Shanghai, Shanghai, China

Correspondence should be addressed to Xiankun Sun; nc.ude.seus@nuskx and Jingyuan Yin; moc.qq@2413321601

Received 2 March 2017; Revised 16 June 2017; Accepted 6 August 2017; Published 28 September 2017

Academic Editor: Fabrice Labeau

Copyright © 2017 Xiankun Sun et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


We propose a novel approach for low-light image enhancement. Based on illumination-reflection model, the guided image filter is employed to extract the illumination component of the underlying image. Afterwards, we obtain the reflection component and enhance it by nonlinear functions, sigmoid and gamma, respectively. We use the first-order edge-aware constraint in the gradient domain to achieve good edge preserving features of enhanced images and to eliminate halo artefact effectively. Moreover, the resulting images have high contrast and ample details due to the enhanced illumination and reflection component. We evaluate our method by operating on a large amount of low-light images, with comparison with other popular methods. The experimental results show that our approach outperforms the others in terms of visual perception and objective evaluation.