Arabic Sign Language Recognition an Image-Based Approach
Mohamed Ahmed Mohandes, S.I. Quadri, Mohamed A. Deriche · 2007
In this paper we propose an image based system for Arabic sign language recognition. A Gaussian skin color model is used to detect the signer's face. The centroid of the detected face is then used as a reference to track the hands movement using region growing from the sequence of images comprising the signs. A number of features are then selected from the detected hand regions across the sequence of images. The recognition stage is performed using a hidden Markov model. The proposed system achieved a recognition accuracy of about 93% for a data set of 300 signs with leave one out method.