An Efficient Converging Snake Algorithm for Locating Object Boundaries

Abstract

Active contour are now established as a technique for extracting salient contours from an image. A snake is an active contour for representing object contour. Traditional snake algorithms are often used to represent the contour of a single object. A different contour search algorithm is presented in this paper that provides an efficient convergence to the object contours than both the kass et al and greedy snake algorithm (GSA).Our proposed algorithm provides a straightforward approach for snake contour rapid splitting and connection, which usually cannot be gracefully handle by traditional snakes. This  algorithm compares with other two conventional approaches is faster according to needed execution time. This paper tells us which one is better by comparing each other. The experimental results of various test sequence images with a single object shown good performance, which proved that the proposed algorithm is faster among those.

DOI: http://dx.doi.org/10.11591/telkomnika.v14i1.7467