Segmentation of color images using a two-stage self-organizing network

Abstract

We propose a two-stage hierarchical artificial neural network for the segmentation of color images based on the Kohonen self-organizing map (SOM). The first stage of the network employs a fixed-size two-dimensional feature map that captures the dominant colors of an image in an unsupervised mode. The second stage combines a variable-sized one-dimensional feature map and color merging to control the number of color clusters that is used for segmentation. A post-processing noise-filtering stage is applied to improve segmentation quality. Experiments confirm that the self-learning ability, fault tolerance and adaptability of the two-stage SOM lead to a good segmentation results.