Combining highlight removal and low‐light image enhancement technique for HDR‐like image generation. Issue 9 (9th June 2020)

• Record Type: Journal Article
• Authors: Saha, Rappy; Pratim Banik, Partha; Sen Gupta, Shantanu; Kim, Ki‐Doo
• Is Part Of: IET image processing. Volume 14:Issue 9(2020)
• Page Start: 1851
• Page End: 1861
• Publication Date: 2020-06-09
• Subjects: image enhancement -- image colour analysis -- image recognition -- image sensors -- image processing; actual colour -- low‐light enhancement technique -- HDR‐like -- highlight removal -- low‐light image enhancement technique -- low dynamic range image -- highlight areas -- conventional image sensors -- highlight phenomena limit colour richness -- image recognition -- high dynamic range‐like images -- rich colours -- single LDR image -- highlight pixels; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2019.1099
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Low dynamic range (LDR) image may contain low‐light and highlight areas due to the limitations of the dynamic range of conventional image sensors. Low‐light and highlight phenomena limit colour richness and visibility of objects in an image. Therefore, it can cause a reduction in the quality of images and a loss in accuracy in the application of image recognition. To overcome this, high dynamic range (HDR)‐like images have been developed with rich colours such as those seen by the human eye. In this study, the authors propose a method to obtain an HDR‐like image from a single LDR image by removing the specular component from highlight pixels as well as strengthening the actual colour. Next, they select low‐light image enhancement via illumination map estimation as a low‐light enhancement technique by showing the comparison with gamma‐based expansion operator. They evaluate their HDR‐like output images with non‐reference and full‐reference metrics. They show the comparison of their proposed method with six other methods. Besides, visually, their proposed method delivers more pleasing output than the output of other competitive methods.