An improved K-means clustering algorithm for fish image segmentation

• Published in: Mathematical and computer modelling Vol. 58; no. 3-4; pp. 784 - 792
• Main Authors: Yao, Hong, Duan, Qingling, Li, Daoliang, Wang, Jianping
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.08.2013
• Subjects: [formula omitted]-means clustering; algorithms; animal behavior; computer techniques; Contour extraction; decision making; diagnostic techniques; fish; Image segmentation; mathematical models; Mathematical morphology; Image segmentation; Contour extraction; Mathematical morphology; K-means clustering
• ISSN: 0895-7177; 1872-9479
• DOI: 10.1016/j.mcm.2012.12.025

Fish contour extraction from images is the foundation of many fish image applications such as disease early warning and diagnostics, animal behavior, aquatic product processing, etc. In order to improve the accuracy and stability of fish image segmentation, we propose a new fish images segmentation method which is the combination of the K-means clustering segmentation algorithm and mathematical morphology. Firstly, the traditional K-means clustering segmentation algorithm has been improved for fish images. The best number of clusters is determined by the number of gray histogram peaks, and the cluster centers data is filtered by comparing the mean with the threshold decided by Otsu. Secondly, the opening and closing operations of mathematical morphology are used to get the contour of the fish body. The experimental results show that the algorithm realized the separation between the fish image and the background in the condition of complex backgrounds. Compared with Otsu and other segmentation algorithms, our algorithm is more accurate and stable.