An Adaptive Clonal Selection Algorithm for Edge Linking Problem

Edges produced by existing edge detection algorithms often contain discontinuities. Edge linking as a post-processing step is very important for computer vision and pattern recognition. Nevertheless, subject to the lacking of information in the image, difficulties arise when it is tackled. The clonal selection algorithm (CSA), inspired by the basic features of adaptive immune response to antigenic stimulus, can exploit and explore the solution space parallelly and effectively. In this paper, by introducing receptor editing and making the proportions of receptor editing and hypermutation change adaptively, we propose an improved CSA for edge linking of images. The algorithm is tested on a set of artificial images devised with the aim of demonstrating the sort of features that may occur in real images. For all problems, the algorithm produced smooth contours while the details of the object shape are preserved.