Lighting enhancement of underwater image using coronavirus herd immunity optimizer

Recently, the technology of Underwater computer vision has played a vital role by improving the quality of underwater images owing to its significance in different applications in marines, such as military, resource development, biological research, and underwater environmental assessments. Moreover, light is absorbed and scattered while propagating through water, leading to color distortion. Additionally, floating micro-particles in the water contribute to low image contrast, resulting in blurry and poorly lit underwater images with a color cast. Therefore, many researchers have been attracted to developing diverse computer vision-based methods to improve the quality of underwater images, such as restoration, enhancement, and deep-learning techniques to restore and enhance degraded underwater images. Although numerous studies have attempted to address these issues, there is still much room for improvement in the quality of the produced images. To this end, this paper proposes a new enhancement method to improve underwater image quality. The presented approach utilizes the Coronavirus herd immunity optimizer algorithm for underwater image enhancement (CHIO-UIE) and is evaluated using standard measures on public datasets. The empirical results demonstrate that the CHIO-UIE method enhances the quality of images based on qualitative and quantitative evaluations, successfully improving underwater images with low contrast and light by significantly enhancing the visual impact of distorted underwater images across various underwater environments.