Underwater image enhancement by color correction and color constancy via Retinex for detail preserving. (May 2022)

• Record Type: Journal Article
• Authors: Muniraj, Manigandan; Dhandapani, Vaithiyanathan
• Is Part Of: Computers & electrical engineering. Volume 100(2022)
• Publication Date: 2022-05
• Subjects: Color constancy -- Color correction -- Underwater image enhancement -- Underwater image restoration -- Multi-scale retinex -- CLAHE -- Degradation -- Non-uniform illumination -- Rolling guidance filter -- Fast local laplacian filter; 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.2022.107909
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: In underwater, light attenuation causes non-uniform illumination that degrades underwater image. To enhance the degraded image, we propose an underwater image enhancement method that includes color correction, color constancy, multi-scale retinex (MSR), edge-aware and texture smoothing filters, and contrast stretching. The formulated color correction compensates the red and blue channels by masking. Color constancy transforms non-uniform illumination into uniform illumination. Furthermore, the gamma correction in the color constancy improves the contrast of the image. The distorted colors are restored using the MSR with contrast limited adaptive histogram equalization (CLAHE). The edges are preserved using a fast local laplacian filter (FLLF), while the detailed texture of the image is smoothed using a rolling guidance filter (RGF) The contrast stretching enhances the image by stretching the pixel values. The qualitative and quantitative evaluation of the proposed algorithm outperforms the existing methods in terms of naturalness, contrast, visibility and enhancement of low-light images. Graphical abstract: Highlights: The formulation of color correction compensates the red and blue channels by masking. The color constancy method reduces the color cast. The Retinex with CLAHE reduces the color distortions and restores image details. The FLLF and RGF filters preserve the details of edge and texture, respectively. The contrast stretching is adapted to enhance the contrast of the image.