An HMM-based approach for gesture segmentation and recognition
- 11 November 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 679-682
- https://doi.org/10.1109/icpr.2000.903636
Abstract
Gesture, as a 驴natural驴 mean, provides an alternative way for human-computer interaction. The recognition of continuous gestures suffers greatly from the existences of non-gesture hand motions. The given gestures can start at any moment in an input sequence. Hidden Markov Model (HMM) is used to tackle this problem. This paper proposes a novel method for the spotting and recognition of continuous spatio-temporal features. Without sliding the input temporal patterns past the trained models, the algorithm makes use of accumulation scores for evaluation. Therefore, it is an exhaustive evaluation method but only a sum operation is needed in each input frame. The method is demonstrated with real experiments on the recognition of some spatio-temporal trajectories. Results of the experiments show that the proposed method is very effective and fast in extracting given gestures from a continuous trajectory containing non-gestures.Keywords
This publication has 8 references indexed in Scilit:
- Application of hidden Markov models for recognition of a limited set of words in unconstrained speechPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- ASL recognition based on a coupling between HMMs and 3D motion analysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A state-based technique for the summarization and recognition of gesturePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Learning visual behavior for gesture analysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Real-time American sign language recognition using desk and wearable computer based videoPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1998
- Visual interpretation of hand gestures for human-computer interaction: a reviewPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1997
- Phonetic training and language modeling for word spottingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- Automatic recognition of keywords in unconstrained speech using hidden Markov modelsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1990