Product-HMMS for automatic sign language recognition

Theodorakis, S; Katsamanis, A; Maragos, P

dc.contributor.author	Theodorakis, S	en
dc.contributor.author	Katsamanis, A	en
dc.contributor.author	Maragos, P	en
dc.date.accessioned	2014-03-01T02:46:28Z
dc.date.available	2014-03-01T02:46:28Z
dc.date.issued	2009	en
dc.identifier.issn	15206149	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32663
dc.subject	Asynchrony	en
dc.subject	HMM+	en
dc.subject	Integration	en
dc.subject	Product HMM	en
dc.subject	Sign language recognition	en
dc.subject.other	Alternative approach	en
dc.subject.other	Asynchrony	en
dc.subject.other	Classification performance	en
dc.subject.other	Fusion methods	en
dc.subject.other	Fusion model	en
dc.subject.other	HMM+	en
dc.subject.other	Integration scheme	en
dc.subject.other	Multi-stream	en
dc.subject.other	Multi-stream HMM	en
dc.subject.other	Product HMM	en
dc.subject.other	Shape information	en
dc.subject.other	Shape model	en
dc.subject.other	Sign language	en
dc.subject.other	Sign language recognition	en
dc.subject.other	Sign recognition	en
dc.subject.other	Acoustics	en
dc.subject.other	Linguistics	en
dc.subject.other	Signal processing	en
dc.subject.other	Hidden Markov models	en
dc.title	Product-HMMS for automatic sign language recognition	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICASSP.2009.4959905	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICASSP.2009.4959905	en
heal.identifier.secondary	4959905	en
heal.publicationDate	2009	en
heal.abstract	We address multistream sign language recognition and focus on efficient multistream integration schemes. Alternative approaches are investigated and the application of Product-HMMs (PHMM) is proposed. The PHMM is a variant of the general multistream HMM that also allows for partial asynchrony between the streams. Experiments in classification and isolated sign recognition for the Greek Sign Language using different fusion methods, show that the PHMMs perform the best. Fusing movement and shape information with the PHMMs has increased sign classification performance by 1,2% in comparison to the Parallel HMM fusion model. Isolated sign recognition rate increased by 8,3% over movement only models and by 1,5% over movement-shape models using multistream HMMs. ©2009 IEEE.	en
heal.journalName	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings	en
dc.identifier.doi	10.1109/ICASSP.2009.4959905	en
dc.identifier.spage	1601	en
dc.identifier.epage	1604	en