Image based arabic sign language recognition
Mohamed Ahmed Mohandes, Mohamed A. Deriche · 2006
In this paper we propose an image based system for Arabic Sign Language recognition. The recognition stage is performed using a Hidden Markov Model. We have used a Gaussian skin color model to detect the signer’s face. The detected face region 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. Such features are then used as input to the HMM. The proposed system achieved a recognition accuracy of 98% for a data set of 50 signs.