Color edge detection using the minimal spanning tree

Abstract

In this study, the edge detection task in vector-valued images is examined as a clustering problem. Using samples within a data window, the minimal spanning tree (MST) provides the ordering of multivariate observations and facilitates the identification of similar classes. The edge detector parameters like edge strength, type and orientation are subsequently determined from the clustered data. Experiments and comparisons are performed, revealing the enhanced performance of the proposed approach.