Fish Image Segmentation Using Salp Swarm Algorithm

Abdelhameed Ibrahim, ali ahmed, S. Hussein, and A. E. Hassanien, "Fish Image Segmentation Using Salp Swarm Algorithm", Download book PDF EPUB International Conference on Advanced Machine Learning Technologies and Applications, Cairo, 23 Feb, 2018.

Date Presented:

23 Feb


Fish image segmentation can be considered an essential process in developing a system for fish recognition. This task is challenging as different specimens, rotations, positions, illuminations, and backgrounds exist in fish images. In this research, a segmentation model is proposed for fish images using Salp Swarm Algorithm (SSA). The segmentation is formulated using Simple Linear Iterative Clustering (SLIC) method with initial parameters optimized by the SSA. The SLIC method is used to cluster image pixels to generate compact and nearly uniform superpixels. Finally, a thresholding using Otsu’s method helped to produce satisfactory results of extracted fishes from the original images under different conditions. A fish dataset consisting of real-world images was tested. In experiments, the proposed model shows robustness for different cases compared to conventional work.

Related External Link