Title :
Hand gesture recognition using input-output hidden Markov models
Author :
Marcel, Sebastien ; Bernier, Olivier ; Viallet, Jean Emmanuel ; Collobert, Daniel
Author_Institution :
France Telecom CNET, Lannion, France
Abstract :
A new hand gesture recognition method based on input-output hidden Markov models is presented. This method deals with the dynamic aspects of gestures. Gestures are extracted from a sequence of video images by tracking the skin-color blobs corresponding to the hand into a body-face space centered on the face of the user. Our goal is to recognize two classes of gestures: deictic and symbolic
Keywords :
feature extraction; gesture recognition; hidden Markov models; image colour analysis; image sequences; tracking; body-face space; deictic gestures; dynamic gestures; gesture extraction; hand gesture recognition; input-output hidden Markov models; skin-color blobs; symbolic gestures; tracking; video image sequences; Computer vision; Face detection; Face recognition; Hidden Markov models; Image segmentation; Neural networks; Pixel; Recurrent neural networks; Skin; Telecommunications;
Conference_Titel :
Automatic Face and Gesture Recognition, 2000. Proceedings. Fourth IEEE International Conference on
Conference_Location :
Grenoble
Print_ISBN :
0-7695-0580-5
DOI :
10.1109/AFGR.2000.840674
