Image segmentation via self-organising fusion

Abstract

A method called self-organising fusion (SOF) for performing fast image segmentation is presented. The input image is divided into a set of small regions, each associated with a working feature. First, all regions are simultaneously updated and then a statistical process is applied to merge the qualified regions. The contours of objects are obtained by alternating the two processes of updating and merging until convergence. The concurrent updating creates a SOF behaviour that facilitates the identification of regions presumably comprising the same object. The method can save computation cost as both updating and merging are conducted in parallel fashion, and as parameter selection is done for local regions, it is able to deal with fairly complex images.