Gestures conversion to Arabic letters

Abstract

Gestures is one of the best  ways of communication between dumb and blind people depend on  the expression of signs. In this paper we suggest an algorithm to recognizing hand gestures of Arabic latters to communicate between the dumb (through signs) and blind (hear the voice corresponding to sings).The proposed algorithm used the  video of gesture from the dumb  then convert the  video into frames ( images) and calculate the distance to recognition the letters by  using  k-mean , k- medoid and artificial neural network,  calculate the distance by using Euclidean distance and slop .There are sixteen features (8-features from Euclidean distance and 8-features from slop ). The results were (93.3% For k-mean),(93.1% for k-medoid ) and(92.9% for ANN).We create our data base (from 5- videos with 308 frames).