Improving deaf people accessibility and communication through automatic sign language recognition using novel technologies

Abstract

Communication is a key for human development. Nevertheless, deaf people have difficulty interacting with hearing and hard of hearing people. On the other hand, new technology allows gesture recognition. This work aims to promote the development of tools to take advantage of 3D camera technology for the benefit of the Deaf Community around the world. This research proposes a sign recognition model using 3d cameras (i.e. Leap Motion and Intel RealSense) and support vector machines (SVM). The goal is to support the communication process between deaf and hearing people. Furthermore, we conduct an experiment determining an appropriate amount of training sample signs to ensure satisfactory results using SVMs.