This paper explains the task of segmenting any given colour image using competitive neural network. Image segmentation refers to the division pixels into homogeneous classes or clusters so that items in the same class are as similar as  possible and items in different classes are as dissimilar as possible. . The most basic attribute for segmentation is image luminance amplitude for a monochrome image and color components for a color image. Since there are more than 16 million colours available in any given image and it is difficult to analyse the image on all of its colours, the likely colours are grouped together by image segmentation. For that purpose competitive neural network has been used. Competitive Neural Networks are groups of neurons compete for the right to become active. The activation of the node with the largest net is set equal to 1, and the remaining nodes are set equal to 0. It works on the principle of “Winner Takes All”. First, the color image of interest is read as a three dimensional matrix. It is then converted into a two-dimensional matrix.Weight matrix is randomly initialized. Competitive neural network is then created. Then the neural network is trained using the two-dimensional image matrix. This weight matrix is reconstructed to form the segmented image. Quality of the reconstructed image is determined by calculating the Peak Signal to Noise Ratio and found to be reasonable. This work finds vast applications in medical imaging, satellite imaging, military applications and non destructive testing of products in industries.

Key words: Neural Network, Image processing, Image Segmentation.