Every form of human gesture has been recognized in the literature as a means of providing natural and intuitive ways to interact with computers across many computer application domains. In this paper we propose a real time gesture recognition approach which uses a depth sensor to extract the initial human skeleton. Then, robust and significant features have been compared and the most unrelated and representative features have been selected and fed to a set of supervised classifiers trained to recognize different gestures. Different problems concerning the gesture initialization, segmentation, and normalization have been considered. Several experiments have demonstrated that the proposed approach works effectively in real time applications.
A real time gesture recognition system for Human Computer Interaction / Attolico, C; Cicirelli, G; Guaragnella, Cataldo; D’Orazio, T. (LECTURE NOTES IN COMPUTER SCIENCE). - In: Multimodal Pattern Recognition of Social Signals in Human-Computer-Interaction: Third IAPR TC3 Workshop, MPRSS 2014, Stockholm, Sweden, August 24, 2014, Revised Selected Papers / [a cura di] Friedhelm Schwenker, Stefan Scherer, Louis-Philippe Morency. - [s.l] : Springer, 2015. - ISBN 978-3-319-14898-4. - pp. 92-101 (( convegno Third IAPR Workshop on Multimodal Pattern Recognition of Social Signals in Human Computer Interaction (MPRSS 2014), in conjuction with ICPR 2014 tenutosi a Stockholm, Sweden nel August 24, 2014 [10.1007/978-3-319-14899-1_9].
A real time gesture recognition system for Human Computer Interaction
GUARAGNELLA, Cataldo;
2015-01-01
Abstract
Every form of human gesture has been recognized in the literature as a means of providing natural and intuitive ways to interact with computers across many computer application domains. In this paper we propose a real time gesture recognition approach which uses a depth sensor to extract the initial human skeleton. Then, robust and significant features have been compared and the most unrelated and representative features have been selected and fed to a set of supervised classifiers trained to recognize different gestures. Different problems concerning the gesture initialization, segmentation, and normalization have been considered. Several experiments have demonstrated that the proposed approach works effectively in real time applications.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
