Automatic sign language recognition: Vision based feature extraction and probabilistic recognition scheme from multiple cues

Caridakis, G; Diamanti, O; Karpouzis, K; Maragos, P

dc.contributor.author	Caridakis, G	en
dc.contributor.author	Diamanti, O	en
dc.contributor.author	Karpouzis, K	en
dc.contributor.author	Maragos, P	en
dc.date.accessioned	2014-03-01T02:45:10Z
dc.date.available	2014-03-01T02:45:10Z
dc.date.issued	2008	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32174
dc.subject	Feature extraction	en
dc.subject	Geodesic Active Contour models	en
dc.subject	Gesture recognition	en
dc.subject	Hidden Markov Models	en
dc.subject	Image segmentation	en
dc.subject	Markov Models	en
dc.subject	Optical flow	en
dc.subject	Self-organizing maps	en
dc.subject	Sign language recognition	en
dc.subject.other	Computational grammars	en
dc.subject.other	Computer vision	en
dc.subject.other	Conformal mapping	en
dc.subject.other	Decoding	en
dc.subject.other	Digital image storage	en
dc.subject.other	Extractive metallurgy	en
dc.subject.other	Feature extraction	en
dc.subject.other	Geodesy	en
dc.subject.other	Gesture recognition	en
dc.subject.other	Image processing	en
dc.subject.other	Image segmentation	en
dc.subject.other	Linguistics	en
dc.subject.other	Markov processes	en
dc.subject.other	Object recognition	en
dc.subject.other	Optical flows	en
dc.subject.other	Optical projectors	en
dc.subject.other	Self organizing maps	en
dc.subject.other	Skin	en
dc.subject.other	Speech recognition	en
dc.subject.other	Active contours	en
dc.subject.other	Adaptive architectures	en
dc.subject.other	Classification schemes	en
dc.subject.other	Computer vision techniques	en
dc.subject.other	Geodesic Active Contour models	en
dc.subject.other	Hand detections	en
dc.subject.other	Hand shapes	en
dc.subject.other	Markov chains	en
dc.subject.other	Markov Models	en
dc.subject.other	Motion informations	en
dc.subject.other	Optical flow	en
dc.subject.other	Optimal utilizations	en
dc.subject.other	Research problems	en
dc.subject.other	Sign language recognition	en
dc.subject.other	Skin colors	en
dc.subject.other	Vision-based	en
dc.subject.other	Work focus	en
dc.subject.other	Hidden Markov models	en
dc.title	Automatic sign language recognition: Vision based feature extraction and probabilistic recognition scheme from multiple cues	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1145/1389586.1389687	en
heal.identifier.secondary	http://dx.doi.org/10.1145/1389586.1389687	en
heal.identifier.secondary	89	en
heal.publicationDate	2008	en
heal.abstract	This work focuses on two of the research problems comprising automatic sign language recognition, namely robust computer vision techniques for consistent hand detection and tracking, while preserving the hand shape contour which is useful for extraction of features related to the handshape and a novel classification scheme incorporating Self-organizing maps, Markov chains and Hidden Markov Models. Geodesic Active Contours enhanced with skin color and motion information are employed for the hand detection and the extraction of the hand silhouette, while features extracted describe hand trajectory, region and shape. Extracted features are used as input to separate classifiers, forming a robust and adaptive architecture whose main contribution is the optimal utilization of the neighboring characteristic of the SOM during the decoding stage of the Markov chain, representing the sign class. Copyright 2008 ACM.	en
heal.journalName	1st International Conference on Pervasive Technologies Related to Assistive Environments, PETRA 2008	en
dc.identifier.doi	10.1145/1389586.1389687	en