Adaptive gesture recognition in human computer interaction

Caridakis, G; Karpouzis, K; Drosopoulos, N; Kollias, S

dc.contributor.author	Caridakis, G	en
dc.contributor.author	Karpouzis, K	en
dc.contributor.author	Drosopoulos, N	en
dc.contributor.author	Kollias, S	en
dc.date.accessioned	2014-03-01T02:45:56Z
dc.date.available	2014-03-01T02:45:56Z
dc.date.issued	2009	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32470
dc.subject	Feature Extraction	en
dc.subject	Gesture Recognition	en
dc.subject	Human Computer Interaction	en
dc.subject	Large Scale	en
dc.subject	levenshtein distance	en
dc.subject	Processing Speed	en
dc.subject	Self Organized Map	en
dc.subject	Markov Model	en
dc.subject.other	Hand positions	en
dc.subject.other	Input signal	en
dc.subject.other	Levenshtein distance	en
dc.subject.other	Markov model	en
dc.subject.other	Multiple modalities	en
dc.subject.other	Optimal trajectories	en
dc.subject.other	Processing speed	en
dc.subject.other	Real time	en
dc.subject.other	Recognition process	en
dc.subject.other	User performance	en
dc.subject.other	Weak classifiers	en
dc.subject.other	Weight assignment	en
dc.subject.other	Classifiers	en
dc.subject.other	Feature extraction	en
dc.subject.other	Human computer interaction	en
dc.subject.other	Image analysis	en
dc.subject.other	Learning systems	en
dc.subject.other	Markov processes	en
dc.subject.other	Multimedia services	en
dc.subject.other	Multimedia systems	en
dc.subject.other	Self organizing maps	en
dc.subject.other	Gesture recognition	en
dc.title	Adaptive gesture recognition in human computer interaction	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/WIAMIS.2009.5031485	en
heal.identifier.secondary	http://dx.doi.org/10.1109/WIAMIS.2009.5031485	en
heal.identifier.secondary	5031485	en
heal.publicationDate	2009	en
heal.abstract	An adaptive, invariant to user performance fluctuation or noisy input signal, gesture recognition scheme is presented based on Self Organizing Maps, Markov Models and Levenshtein sequence distance. Multiple modalities, all based on the hand position during gesturing, train different classifiers which are then fused in a weak classifier boosting-like setup by weight assignment to each stream. The adaptability of the proposed approach consists of the incorporation of Self Organizing Maps during training, the exploitation of neighboring relations between states of the Markov models and the modified Levenshtein distance algorithm. The main focus of current work is to tackle intra and inter user variability during gesture performance by adding flexibility to the decoding procedure and allowing the algorithm to perform an optimal trajectory search while the processing speed of both the feature extraction and the recognition process indicate that the proposed architectureis appropriate for real time and large scale lexicon applications. © 2009 IEEE.	en
heal.journalName	2009 10th International Workshop on Image Analysis for Multimedia Interactive Services, WIAMIS 2009	en
dc.identifier.doi	10.1109/WIAMIS.2009.5031485	en
dc.identifier.spage	270	en
dc.identifier.epage	274	en