Supporting Arabic Sign Language Recognition with Facial Expressions

this paper presents an automatic translation model forth combination official expressions of user and gestures of manual alphabets in the Arabic sign language. The part of facial expression depends on locations of user's mouth, nose and eyes. The part of gestures of manual alphabets in the Arabic sign language does not rely on using any gloves or visual markings to accomplish the recognition job. As an alternative, it deals with images of signer's hands. Two parts enable the user to interact with the environment in a natural way. First part in the model deals with signs and consists of three phases preprocessing phase, skin detection phase and feature extraction phase. Second part in the model that deals with facial expressions consists of two phases face detection and tracking facial expression. Proposed model has an accuracy 90% using minimum distance classifier (MDC) and absolute difference classifier in case of facial expressions and 99% in case of signer's hands.