A proposed graph matching technique for Arabic sign language continuous sentences recognition

Many previous systems were developed for recognizing sign languages in general and Arabic sign language specifically. They achieved good results for isolated gestures but none of them was exposed to connected sequence of gestures. This paper focuses on how to recognize connected sequence of gestures using graph-matching technique, and how the continuous input gestures are segmented and classified. Graphs are a general and powerful data structure useful for the representation of various objects and concepts. This work is a component of a real-time Arabic Sign Language Recognition system that applied Pulse Coupled Neural Network for static posture recognition in its first phase.