Vinod,V.V. , Chaudhury,S., Ghose,S. and Mukherjee,Jayanta (1994):
A connectionist approach for clustering with applications in image analysis, IEEE trans.
on System Man and Cybernetics, vol.24, no.3, pp 365-383, 1994.  Abstract. 
A new neural network strategy for clustering is presented. The network works on the histogram and the process is similar to mode separation. The number of clusters are autonomously detected by the network and it overcomes some major difficulties encountered by mode separation techniques. Clustering is done by first selecting the prototypes and then assigning patterns to one of the prototypes based on its distance from the prototype and the distribution of data. The netwrok does not employ weight learning and is therefore faster than exisiting unsupervised learning networks. The network was apllied to a wide class of problems including gray level image reduction, color segmentation and remotely sensed image segmentation. The experimental results obtained are promising.