Abstract
Video segmentation has been and is likely to be an important component of the content-based video acquisition and retrieval systems. In this paper, we have proposed an video segmentation technique that uses Kohonan's Self Organizing map (SOM) neural network for segmentation of color videos. It has been observed that, SOM training if performed on the wavelet-transformed video, not only reduces the training time of the SOM but also make more compact segments. Our experiments have shown better results produced by our proposed technique than the previous approaches in practice.