Adhesive image segmentation based on watershed algorithm

Xiaoyu Zhang, Ning Liu 

Department of Computer Science and Application, Zhengzhou Institute of Aeronautical Industry Management, Zhengzhou, Henan, 450015, China

Since adhesive image has a deficiency of over-segmentation, the work applied watershed algorithm, whose merits include quick computing speed, closed outline and accurate location, to adhesive image segmentation. In the first few sessions, the basic principle and arithmetic steps of watershed algorithm were illustrated in detail. On this basis, following sessions correspondingly introduced the MATLAB simulation analysis and verification. Through simulation and contrast of the segmentation results by different algorithms, it could be concluded that watershed algorithm, the most effective method, could help split adhesive objects into single ones, while greatly reducing or even eliminating the over-segmentation phenomenon.