Region-based color image segmentation of fishes with complex background in water

Abstract

Color image segmentation of fishes with complex back ground in water is considered. Unsupervised color equalization in HSV space is used to enhance and correct nonuniform color cast of image underwater. Region-based segmentation algorithm is presented for the aim of accurately and fast identification of fishes. The segmentation operation is applied in the selected region, which can also avoid a large number of computations without considering information of non interested regions. For comparison, we test segmentation algorithm combined with automatic color equalization on different region, including segmentation of single fish in a small area and more than one fishes in an interested region at the same time. Experiments show the result is encouraging and efficient.