Color image segmentation using parallel OptiMUSIG activation function

► We focus on the segmentation of true color test images, based on all possible combination of color intensity features. ► This article proposes a parallel version of the OptiMUSIG (ParaOptiMUSIG) activation function. ► This function is generated with the optimized class responses for the individual features of the true color images. ► This function is applied on a parallel self-organizing neural network architecture to segment true color images. ► The optimized class responses are generated in parallel using a genetic algorithm based optimization technique.