In early days computers are operated by various interface devices, which are developed by the humans to interact with computers. Starting from Punch-cards to touch screens man has changed the human life into an unimaginable state. In this paper, a novel method for dynamic hand gesture recognition based on human computer interface intelligent system is proposed. The main objective is to interact with computers without using mouse clicks and keystrokes. An architecture for hand posture, gesture modelling and recognition system is introduced, which is used as an interface to make possible communication with the sensory challenged (hearing impairment and gustatory impairment) people by simple hand gestures. This proposed system first transforms the pre-processed data of the detected hand into a fu/zy hand-posture feature model by using fuzzy neural networks. Second with the proposed model, the developed system determines the actual hand posture by applying fuzzy inference. Finally, from the sequence of detected hand postures, the system will recognizc the hand gesture of the user. Moreover, the computer vision techniques are developed to recognize a dynamic hand gestures that make interpretations in the form of commands or actions. © 2012 Published by Elsevier Ltd.