TY - GEN
T1 - Real time large vocabulary continuous sign language recognition based on OP/Viterbi algorithm
AU - Guilin, Yao
AU - Hongxun, Yao
AU - Xin, Liu
AU - Feng, Jiang
PY - 2006
Y1 - 2006
N2 - Up to now, continuous sign language recognition is mainly based on statistical methods, especially Hidden Markov Models (HMM) and Viterbi-Beam searching. However, the recognition speed often gets unacceptable with an increased vocabulary, which could cause a long time delay that is not fit for the real time recognition system. To speed up the recognition process, we present a method using One-Pass (OP) pre-searching before Viterbi recognition. The experiments are processed in the large vocabulary database. Results show that the average recognition speed of OP/Viterbi approach can get a notable raise comparing with the single frame 's without reducing too much recognition accuracy.
AB - Up to now, continuous sign language recognition is mainly based on statistical methods, especially Hidden Markov Models (HMM) and Viterbi-Beam searching. However, the recognition speed often gets unacceptable with an increased vocabulary, which could cause a long time delay that is not fit for the real time recognition system. To speed up the recognition process, we present a method using One-Pass (OP) pre-searching before Viterbi recognition. The experiments are processed in the large vocabulary database. Results show that the average recognition speed of OP/Viterbi approach can get a notable raise comparing with the single frame 's without reducing too much recognition accuracy.
UR - https://www.scopus.com/pages/publications/34147098996
U2 - 10.1109/ICPR.2006.954
DO - 10.1109/ICPR.2006.954
M3 - 会议稿件
AN - SCOPUS:34147098996
SN - 0769525210
SN - 9780769525211
T3 - Proceedings - International Conference on Pattern Recognition
SP - 312
EP - 315
BT - Track C
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 18th International Conference on Pattern Recognition, ICPR 2006
Y2 - 20 August 2006 through 24 August 2006
ER -