Multi-objective nature-inspired clustering techniques for image segmentation

Image segmentation aims to partition an image into several disjointed regions that are homogeneous with regards to some measures so that subsequent higher level computer vision processing, such as object recognition, image understanding and scene description can be performed. Multi-objective formulations are realistic models for image segmentation because objectives under consideration conflict with each other, and optimizing a particular solution with respect to a single objective can result in unacceptable results with respect to the other objectives. In this paper, we present the current multi-objective nature-inspired clustering (MoNiC) techniques for image segmentation. We are able to diagnose the requirements and issues for modelling this specific technique in the image segmentation problem. Three identified important phases include intelligence, design and choice with respect to the issues of clustering problem of image segmentation and multi-objective clustering algorithm design.