Color image segmentation using semi-supervised self-organization feature map

Abstract

Image segmentation is one of the fundamental steps in digital image processing, and is an essential part of image analysis. This paper presents an image segmentation of color images by semi-supervised clustering method based on modal analysis and mutational agglomeration algorithm in combination with the self-organization feature map (SOM) neural network. The modal analysis and mutational agglomeration is used for initial segmentation of the images. Subsequently, the sampled image pixels of the segmented image are used to train the network through SOM. Results are compared with four different state of the art image segmentation algorithms and are found to be encouraging for a set of natural images. © Springer International Publishing Switzerland 2014.