Method for segmentation of overlapping fish images in aquaculture

• DOI: 10.25165/j.ijabe.20191206.3217
• Publication Date: 2020-03-09T04:02:23Z
• Authors: Chao Zhou; ; Kai Lin; Daming Xu; Jintao Liu; Song Zhang; Chuanheng Sun; Xinting Yang
• Keywords: Feature (linguistics); Segmentation-based object categorization

Individual fish segmentation is a prerequisite for feature extraction and object identification in any machine vision system. In this paper, method of overlapping images aquaculture was proposed. First, the shape factor used to determine whether an overlap exists picture. Then, corner points were extracted using curvature scale space algorithm, skeleton obtained by improved Zhang-Suen thinning algorithm. Finally, intersecting obtained, overlapped region segmented. The results show that average error rate efficiency 10% 90%, respectively. Compared with traditional watershed method, separation point accurate, accuracy high. Thus, proposed achieves better performance effectiveness. This can be applied multi-target behavior analysis systems, it effectively improve recognition precision. Keywords: aquaculture, image processing, segmentation, detection, algorithm DOI: 10.25165/j.ijabe.20191206.3217 Citation: Zhou C, Lin K, Xu D M, Liu J T, Zhang S, Sun C H, et al. Method aquaculture. Int Agric & Biol Eng, 2019; 12(6): 135–142.