Bayesian retinex underwater image enhancement. (May 2021)

• Record Type: Journal Article
• Authors: Zhuang, Peixian; Li, Chongyi; Wu, Jiamin
• Is Part Of: Engineering applications of artificial intelligence. Volume 101(2021)
• Publication Date: 2021-05
• Subjects: Underwater image enhancement -- Retinex decomposition -- Multiorder gradients -- Maximum a posteriori -- Alternative optimization; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2021.104171
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: This paper develops a Bayesian retinex algorithm for enhancing single underwater image with multiorder gradient priors of reflectance and illumination. First, a simple yet effective color correction approach is adopted to remove color casts and recover naturalness. Then a maximum a posteriori formulation for underwater image enhancement is established on the color-corrected image by imposing multiorder gradient priors on reflectance and illumination. The l 1 norm is appropriately used to model piecewise and piecewise linear approximations on the reflectance, and the l 2 norm is used to enforce spatial smoothness and spatial linear smoothness on the illumination. Meanwhile, a complex underwater image enhancement issue is turned into two simple denoising subproblems where their convergence analyses are mathematically provided, and their solutions can be derived by an efficient optimization algorithm. Besides, the proposed model is fast implemented on pixelwise operations while not requiring additional prior knowledge about underwater imaging conditions. Final experiments demonstrate the effectiveness of the proposed method in color correction, naturalness preservation, structures and details promotion, artifacts or noise suppression. Compared with several traditional and leading enhancement approaches, the proposed method yields better results on qualitative and quantitative assessments. The superiority of the proposed method can be extended to several challenging applications. Highlights: We develop a Bayesian retinex algorithm for enhancing single underwater image. We impose multiorder gradient priors on reflectance and illumination. We adopt an effective color correction to address color casts and restoration. We derive an efficient optimization scheme for proposed objective function. We perform a variety of experiments and applications to verify the proposed method.