A Wireframe-Based Approach for Classifying and Acquiring Proficiency in the American Sign Language

Abstract

We describe our methodology for classifying American Sign Language (ASL) gestures. Rather than operate directly on raw images of hand gestures, we extract coordinates and render wireframes from individual images to construct a curated training dataset. We also explore distilling wireframe representations as joint angles. Because we construct wireframes that contain information about several angles in the joints that comprise hands, our methodology is amenable to training those interested in learning ASL by identifying targeted errors in their hand gestures.