Print Email Facebook Twitter Sign Language Recognition by Combining Statistical DTW and Independent Classification Title Sign Language Recognition by Combining Statistical DTW and Independent Classification Author Lichtenauer, J.F. Hendriks, E.A Reinders, M.J.T. Faculty Electrical Engineering, Mathematics and Computer Science Department Mediamatics Date 2008-05-13 Abstract To recognize speech, handwriting, or sign language, many hybrid approaches have been proposed that combine Dynamic Time Warping (DTW) or Hidden Markov Models (HMMs) with discriminative classifiers. However, all methods rely directly on the likelihood models of DTW/HMM. We hypothesize that time warping and classification should be separated because of conflicting likelihood modeling demands. To overcome these restrictions, we propose using Statistical DTW (SDTW) only for time warping, while classifying the warped features with a different method. Two novel statistical classifiers are proposed—Combined Discriminative Feature Detectors (CDFDs) and Quadratic Classification on DF Fisher Mapping (Q-DFFM)—both using a selection of discriminative features (DFs), and are shown to outperform HMM and SDTW. However, we have found that combining likelihoods of multiple models in a second classification stage degrades performance of the proposed classifiers, while improving performance with HMM and SDTW. A proof-of-concept experiment, combining DFFM mappings of multiple SDTW models with SDTW likelihoods, shows that, also for model-combining, hybrid classification can provide significant improvement over SDTW. Although recognition is mainly based on 3D hand motion features, these results can be expected to generalize to recognition with more detailed measurements such as hand/body pose and facial expression. Subject time series analysisface and gesture recognition3D/stereo scene analysisstatistical dynamic programmingMarkov processesclassifier design and evaluationreal-time systems To reference this document use: http://resolver.tudelft.nl/uuid:a3e063bf-742b-4a86-b952-93d51be0b775 Publisher IEEE ISSN 0162-8828 Source IEEE Transactions on Pattern Analysis and Machine Intelligence, 30 (11), 2008 Part of collection Institutional Repository Document type journal article Rights (c) 2008 Lichtenauer, J.F. ; Hendriks, E.A. ; Reinders, M.J. ; IEEE Files PDF Lichtenauer_2008.pdf 610.22 KB Close viewer /islandora/object/uuid:a3e063bf-742b-4a86-b952-93d51be0b775/datastream/OBJ/view