New contrast enhancement approach for dark images with non-uniform illumination. (August 2018)

• Record Type: Journal Article
• Authors: Gupta, Bhupendra; Agarwal, Tarun Kumar
• Is Part Of: Computers & electrical engineering. Volume 70(2018)
• Page Start: 616
• Page End: 630
• Publication Date: 2018-08
• Subjects: Image contrast enhancement -- Modified sigmoid function -- Color space model -- Perceptual quality metric; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2017.09.007
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Enhancement of the image using "YCbCr" model and the luminance part Y of the input image. Enhancement of the dark image without affecting the finer details in the brighter region and the color information of the input image. Enhancement without effecting naturalness. Graphical abstract: Abstract: Contrast enhancement of dark images with non-uniform illumination is a difficult task, as these images have both dark and bright regions. Hence, we cannot use many of the widely accepted methods of contrast enhancement, which rely on enhancing the contrast of the both of dark and bright regions at equal level, which results in over enhancement and disappearance of the finer details in brighter regions. This motivated us to design an approach for contrast enhancement of dark images with non-uniformly illumination without affecting the details in the bright regions. We are proposing a method which deals with 'YCbCr' model, as by using this color model we can separately use luminance part 'Y'. Then, we enhance the luminance part 'Y' of the image by using a newly developed sigmoid function.