Sign language translation system using latent feature values of sign language images

Abstract

This paper proposes a sign language translation system for communication among deaf and common people. It uses an algorithm about hand detection and analysis from previous studies and project assignments. The algorithm performs five steps within the limitations, which is the key that it measures a center of gravity with 4 vertexes from sign language images and sifts the latent features from calculated distance, angle for 5 determined points of hand region through specific experiments. Applying the features, success rate is improved from 23% to 100%. The system can make use of development for human-robot interface.