Self-organizing neural networks for unsupervised color image recognition

Presents a new self-organizing neural network system for color image recognition for any given image data set without a priori information about the number of clusters or cluster centers. The system has a self-organizing feature that utilizes multiple valued information in the process of updating weights between the input layer and distance layer. This model has the shape of a one dimensional ring-structure, with every neuron influencing its two nearest neighbors. Input vectors are distributed to each neuron in parallel. The model showed good convergence properties for several test data sets. Comparisons with original color images and reconstructed images are also presented