An approach of color recognition based on SVM

This paper presented an intelligent approach of color recognition with support vector machine (SVM) in the HSI color space, which is in accord with human visual perception characteristics. Based on the structural risk minimization principle, SVM can solve small-sample learning problems and avoid the over-learning as well as easily falling into local minima problems during the training process. Experimental results show that the proposed method can be used to recognize typical colors effectively.