A pair-mode model for underwater single image enhancement

Enhancing underwater images is a challenging problem owing to light scattering and absorption in underwater environments. Such environments provoke several combined degradations in images including color attenuation, blurring and low contrast. Using image processing techniques to enhance this kind of image remains very attractive because of its low-cost of implementation and typically its small number of parameters when compared to more complex learning techniques. This paper proposes an image processing model which first, analyses the color characteristics of the degraded image. Second, decides about the suitable enhancement steps (i.e., mode of operation) to be performed. It operates in two modes (mode-1 and mode-2), both of which investigate a combination of contrast and chromaticity enhancement techniques. The proposed model was tested on 5141 images collected from various, well-known datasets. It was evaluated using eight different measures, some of which are reference-based, and the rest are blind-based. A set of qualitative and quantitative comparisons was conducted, applying more than 20 methods varying between image processing and deep learning. Besides its efficiency and simplicity, the proposed model demonstrates an ability to achieve good contrast ranges, natural-looking colors, and superior or equivalent quality enhancements when compared to other methods.