One of the most precious gifts of nature to the human breed is the ability to express himself by responding to the events occurring in his surroundings. Every normal human being sees, listens and then reacts to the situations by speaking himself out. But there are some less fortunate ones who are deprived of this valuable gift. The deaf and the dumb, rely on some sort of sign language for communicating their feelings to others. In the era of advanced technologies, where computers, laptops and other processor-based devices are an integral part of day-to-day life, efforts are required to be done for making the disables more independent in life. This project consists of image processing and machine learning methods for this purpose. Our aim is to design a human computer interface system that can recognize language of the deaf and dumb accurately. In this paper, vision-based hand gesture recognition system has been discussed as hand plays vital communication mode, considering various techniques available for hand tracking, segmentation, feature extraction and classification are referred. Implementation of the project is as; images are captured using webcam and are processed.