Underwater Image Segmentation with Maximum Entropy based on Particle Swarm Optimization (PSO)

The contrast of the underwater images is often extraordinarily low due to the ray, assimilating of water, illuminating condition and so on. It is not good for the pretreatment like edge detection and image segmentation. The theory of entropy has been widely used in the pre-process of under water images. However the time-consuming computation is often an obstacle in real time application systems. In this paper, the image thresholding approach with the index of entropy maximization of the grayscale histogram based on a new optimization algorithm, namely, the particle swarm optimization (PSO) algorithm is proposed to deal with underwater image. The experiments of segmenting the underwater images are illustrated to show that the proposed method can get ideal segmentation result with less computation cost