AUTOMATIC SIGN LANGUAGE IDENTIFICATION

We propose a Random-Forest based sign language identifica-tion system. The system uses low-level visual features and is based on the hypothesis that sign languages have varying distributions of phonemes (hand-shapes, locations and move-ments). We evaluated the system on two sign languages – British SL and Greek SL, both taken from a publicly avail-able corpus, called Dicta Sign Corpus. Achieved average F1 scores are about 95 % – indicating that sign languages can be identified with high accuracy using only low-level visual fea-tures. Index Terms — Sign language, sign language identifica-tion, language identificatio