Improvements in Image Segmentation by Applying Hopfield Neural Networks

Hundreds of algorithms for different aspects of image segmentation have been developed. In this paper goals of using segmentation in video and multimedia systems are considered. Thus direction of improvements is towards forming masks and matte signals. The idea is to spread locally dominant segment in already segmented image. This problem is set as optimization problem and solution can be achieved by Hopfield neural network. Presented results are obtained applied to color detected segmentation, performed by mean shift algorithm.