Progress in Automated Computer Recognition of Sign Language

This paper reviews the extensive state of the art in automated recognition of continuous signs, from different languages, based on the data sets used, features computed, technique used, and recognition rates achieved. We find that, in the past, most work has been done in finger-spelled words and isolated sign recognition, however recently, there has been significant progress in the recognition of signs embedded in short continuous sentences. We also find that researchers are starting to address the important problem of extracting and integrating non-manual information that is present in face and head movement. We present results from our own experiments integrating non-manual features.