期刊名称：IAENG International Journal of Computer Science
印刷版ISSN：1819-656X
电子版ISSN：1819-9224
出版年度：2021
卷号：48
期号：2
语种：English
出版社：IAENG - International Association of Engineers
摘要：Spring is a widely used mechanical equipment. The segmentation of spring images is seriously affected by intensity inhomogeneity. To solve this problem, a two-stage high-precision spring image segmentation algorithm is proposed. First, a spring measurement platform is constructed to obtain images of springs. Then a two-stage spring image contour extraction algorithm is proposed. The first stage combines the global information of the image to construct a histogram fuzzy clustering model to obtain the initial contour of the spring, then, the local information of the spring image is combined to construct a level set model to accurately extract the spring contour in the second stage. Through comparison with existing algorithms and accuracy analysis experiments, the effectiveness of the method is verified. Experimental results show that the algorithm has high accuracy, strong adaptive ability, high running speed, and can effectively suppress the problem of intensity inhomogeneity.
关键词：Spring;image segmentation;clustering methods;level set
