Active region segmentation of color images by a competition of regions

Abstract

An active region segmentation algorithm based on a regularization approach using the Hopfield neural network was proposed by us. The objective function to be minimized by the network was defined based on the criteria that integrate region growing and edge detection for the image segmentation. In this report, the algorithm is extended to divide the image into more than three regions. As a result, the segmentation is improved by a competition of regions.