Boosted subunits: a framework for recognising sign language from videos. Issue 1 (1st February 2013)

• Record Type: Journal Article
• Authors: Han, Junwei; Awad, George; Sutherland, Alistair
• Is Part Of: IET image processing. Volume 7:Issue 1(2013)
• Page Start: 70
• Page End: 80
• Publication Date: 2013-02-01
• Subjects: computer vision -- feature extraction -- language translation -- natural language processing -- pattern clustering -- video signal processing -- sign language recognition; boosted subunit -- vision‐based sign language recognition -- English -- spatiotemporal descriptor extraction -- feature vector -- subunit clustering -- joint learning strategy -- hand gesture video; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2012.0273
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : This study addresses the problem of vision‐based sign language recognition, which is to translate signs to English. The authors propose a fully automatic system that starts with breaking up signs into manageable subunits. A variety of spatiotemporal descriptors are extracted to form a feature vector for each subunit. Based on the obtained features, subunits are clustered to yield codebooks. A boosting algorithm is then applied to learn a subset of weak classifiers representing discriminative combinations of features and subunits, and to combine them into a strong classifier for each sign. A joint learning strategy is also adopted to share subunits across sign classes, which leads to a more efficient classification. Experimental results on real‐world hand gesture videos demonstrate the proposed approach is promising to build an effective and scalable system.