An Improved MSCNN Method for Underwater Image Defogging

Abstract

Underwater imagery is an important carrier and presentation of underwater information, which plays a vital role in the exploration, exploitation and utilization of marine resources. However, due to the limitations of objective imaging environment and equipment, the quality of underwater images is always poor, with degradation phenomena such as low contrast, blurred details and colour deviation, which seriously restrict the development of related fields. Therefore, how to enhance and recover degraded underwater images through post-production algorithms has received increasing attention from scholars. In recent years, with the rapid development of deep learning technology, great progress has been made in underwater image enhancement and restoration based on deep learning. In this paper, we propose an improved MSCNN underwater image defogging method, which combines Retinex and CLAHE for brightness equalization and contrast enhancement of underwater images, making the method more advantageous for complex situations such as low illumination, uneven illumination and obvious Rayleigh scattering phenomena in underwater environments, and conduct objective analysis and comparison of the recovered images to prove the effectiveness of this algorithm in underwater defogging and colour correction. The effectiveness of the algorithm for underwater defogging and colour correction is demonstrated by objective analysis and comparison of the recovered images.