INDIAN SIGN LANGUAGE RECOGNITION WITH IMPLEMENTATION OF SPEEDED UP ROBUST FEATURES ALGORITHM

In This paper automatic gesture recognition is used for Indian Sign Language (ISL). In Indian sign language for representing alphabet we use both hands. We suggest an a method used in dealing with addresses local-global ambiguity which increases the range of possible interpretations of natural language, and a computer has to find a way to deal with this identification, inter-class variability increases for each hand gesture. Hand parts are firstly separated and then detected by skin color model reference i.e. HSI. In this system the well-built points are removing out for recognition process using Speeded Up Robust Features algorithm of each hand posture. The multi class linear support vector machines (SVM) is used to arrange each hand posture, because of it for the system a identification rate of 93.3% is achieved. The performance of this suggested approach is analyzed with well-known classifiers like SVM and experimental results are differentiated with the conventional and existing algorithms which indicate the better efficiency of the proposed approach