The Sign Language is a method of communication for deaf-dumb people. Here vision based approach has been used. This paper presents design and implementation of real time Sign Language Recognition system to recognize 26 gestures from the Indian Sign Language using MATLAB .The signs are captured by using web cam. This signs are preprocessed for feature extraction using HSV color model. The obtained features are compared by using Principle Component Analysis (PCA) algorithm. After comparing features of captured sign with testing database minimum Euclidean distance is calculated for sign recognition. Finally, recognized gesture is converted into text and voice format. This system provides an opportunity for a deaf-dumb people to communicate with non-signing people without the need of an interpreter.