Title :
A New Approach Dedicated to Hand Gesture Recognition
Author :
Binh, Nguyen Dang ; Ejima, Toshiaki
Author_Institution :
Intelligence Media Lab., Kyushu Inst. of Technol., Iizuka
Abstract :
A new pseudo 2-D hidden Markov model (P2DHMM) structure dedicated to the time series recognition, T-ComP2DHMMs, is presented. The T-P2DHMM allows it to do temporal analysis, and to be used in large set of hand gestures movement recognition systems. Our work also present a feature extraction method based on the joint statistics of a subset of DCT coefficients and their position on the hand. Using feature extraction method along with the T-ComP2DHMM structure was used to develop a complete vocabulary of 36 gestures including the America Sign Language (ASL) letter spelling alphabet and digits. The results are effectiveness of the approach
Keywords :
feature extraction; gesture recognition; hidden Markov models; time series; T-ComP2DHMM; feature extraction; hand gestures movement recognition systems; joint statistics; pseudo 2D hidden Markov model; temporal analysis; time series recognition; Classification tree analysis; Detectors; Feature extraction; Handicapped aids; Hidden Markov models; Intelligent structures; Laboratories; Shape; Tree data structures; Video sequences; Gesture recognition; pseudo 2-DHMM; time series recognition;
Conference_Titel :
Cognitive Informatics, 2006. ICCI 2006. 5th IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
1-4244-0475-4
DOI :
10.1109/COGINF.2006.365677
