Analysis on Hand Gesture Spotting using Sign Language through Computer Interfacing

Sign Language is the most natural and expressive way for the hearing impaired. A hybrid feature descriptor, which combines the advantages of SURF & Hu Moment Invariant methods, is used as a combined feature set to achieve a good recognition rate along with a low time complexity. To further increase the recognition rate and make the recognition system resilient to view-point variations, the concept of derived features from the available feature set is introduced. K-Nearest Neighbour (KNN) and Support Vector Machine (SVM) are used for hybrid classification of single signed letter. This paper presents a methodology which recognizes the Indian Sign Language (ISL) and translates into a normal text. The methodology consists of three stages, namely a training phase, a testing phase and a recognition phase. Combinational parameters of Hu invariant moment and structural shape descriptors are created to form a new feature vector to recognize sign. Experimental results demonstrate that the proposed system can successfully recognize hand gesture with 96% recognition rate.