شماره ركورد كنفرانس :
3926
عنوان مقاله :
Continuous Hidden Markov Model Based Dynamic Persian Sign Language Recognition
پديدآورندگان :
Ghanbari Azar Saeideh ghanbariazar91@ms.tabrizu.ac.ir Graduate Student Faculty of Electrical and Computer Engineering University of Tabriz Tabriz, Iran , Seyedarabi Hadi seyedarabi@tabrizu.ac.ir Associate Professor Faculty of Electrical and Computer Engineering University of Tabriz Tabriz, Iran
كليدواژه :
Persian sign language , trajectory , hidden Markov model , spline interpolation
عنوان كنفرانس :
بيست و چهارمين كنفرانس مهندسي برق ايران
چكيده فارسي :
This study proposes a vision based Persian Sign Language (PSL) recognition system. Continuous Hidden Markov Model (HMM) with Gaussian mixture state observation densities is used to classify 15 dynamic signs. The proposed feature extraction approach is based on the spline interpolation of the sign trajectories. The efficiency of the system was assessed with a large set of videos collected by the authors. The system achieved the recognition rate of 98%. For signer-dependent and signerindependent experiments, the accuracy rates of 95.3% and 78% were obtained, respectively.
