NOVEL BOOSTING FRAMEWORK FOR SUBUNIT-BASED SIGN LANGUAGE
George Awad1, Junwei Han2, Alistair Sutherland3
National Institute for Standards and Technology1, Dundee University2, Dublin City University3
Recently, a promising research direction has emerged in sign language recognition (SLR) from videos aimed at breaking up signs into manageable subunits. This work presents a novel SL learning technique based on boosted subunits. Three main contributions distinguish the proposed work from traditional approaches: 1) A novel boosting framework is developed to recognize SL. The learning is based on subunits instead of the whole sign, which is more scalable for the recognition task. 2) Feature selection is performed to learn a small set of discriminative combinations of subunits and SL features. 3) A joint learning strategy is adopted to share subunits across sign classes, which leads to a better performance classifiers. Our experiments show that compared to Dynamic Time Warping (DTW) when applied on the whole sign, our proposed technique gives better results.