An Optimum Shift-and-Weighted brightness mapping for low-illumination image restoration

ABSTRACT

Images captured under low-illumination environments often impose difficulties in revealing objects of interest. An effective approach, Optimum Shift-and-Weighted Brightness Mapping, is here proposed that can optimally enhance the image for higher brightness, information content, and colour vividness. Specifically, the input-output brightness mapping is determined by a shifted spline curve and a larger amplification is allowed for low-brightness pixels. A weighting function is further applied such that high brightness pixels are preserved. The final enhanced image is obtained by inserting the extracted high frequency components from the original input to the brightness boosted image. The algorithm is adaptive to image contents where parameters are optimized using the efficient golden section search instead of relying on user specified coefficients. Experimental results, from a large set of test images, showed that better quality images could be obtained on a variety of low-illumination scenarios as compared to several recent approaches.

KEYWORDS:

• Image processing
• low-illumination
• brightness mapping
• optimum parameters

Acknowledgements

This work is supported by Natural Science Foundation of Guangdong Province, China (Grant No. 2018A030310522), Shenzhen Science and Technology Planning Project, China (Grant No. JCYJ20170818100522101), Natural Science Foundation of Shenzhen University, China (Grant No. 2017032), and National Natural Science Foundation of China (Grant No. 61603258).

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes on contributors

Yeping Peng received the B.Sc. degree in mechanical design, manufacture, and automation from Harbin Engineering University, China, in 2011, and the M.Sc. and Ph.D. degrees in mechanical engineering from Xi’an Jiaotong University, China, in 2014 and 2017, respectively. She is currently an Assistant Professor with the Shenzhen Key Laboratory of Electromagnetic Control, College of Mechatronics and Control Engineering, Shenzhen University, China. Her main research interests include machine vision, image processing, and signal processing.

Haiyan Shi obtained the M.Sc. degree and the Ph.D. degree in control theory and control engineering from Zhejiang University of Technology, Hangzhou, China in 2010 and 2013, respectively. She is with the School of Mechanical and Electrical Engineering, Shaoxing University. Her research interests include wireless sensor networks, image processing and intelligent computation.

Hongkun Wu received his Bachelor and Master degree in Mechanical Engineering from Xi'an Jiaotong University, China, in 2012 and 2015. He is now a Ph.D. student in the School of Mechanical and Manufacturing Engineering at the University of New South Wales, Australia. His main research interests include image processing and machine condition monitoring.

Ruowei Li received her BEng degree in Mechatronics Engineering, in 2016, from the University of New South Wales, Australia, where she is currently working towards the Ph.D. degree. Her research interests include computer vision, image processing and machine learning.

Ngaiming Kwok received the MPhil degree from Hong Kong Polytechnic University, China, in 1997 and Ph.D. degree from University of Technology Sydney, Australia, in 2007. He is now a lecturer with the University of New South Wales, Australia. His research interests include image processing, intelligent computation and automatic control.

San chi Liu is a Ph.D. candidate in the School of Mechanical and Manufacturing Engineering, University of New South Wales, Australia. He received his BEng in Mechatronic Engineering from the same university. His research interest includes machine learning and image process, with a focus on shadow removal in images.

Shilong Liu received his Ph.D. in 2018 from the University of New South Wales, Australia, the Master degree in Mechatronic Engineering at Beijing Institute of Technology, China, in 2014. His main research interests are image processing, computer vision and applied mathematics.

Md Arifur Rahman received his Ph.D. in 2017 from the University of New South Wales, Australia, the B.Sc. degree in Electrical and Electronic Engineering from Bangladesh University of Engineering and Technology, Bangladesh in 2007. He had worked as a professional engineer in Ericsson. His major research interests include machine vision, robotics and control system.

ORCID

Yeping Peng http://orcid.org/0000-0003-3509-1152

Ngaiming Kwok http://orcid.org/0000-0002-5430-6860

Additional information

Funding

This work is supported by Natural Science Foundation of Guangdong Province, China (Grant No. 2018A030310522), Shenzhen Science and Technology Planning Project, China (Grant No. JCYJ20170818100522101), Natural Science Foundation of Shenzhen University, China (Grant No. 2017032), and National Natural Science Foundation of China (Grant No. 61603258).