شماره ركورد كنفرانس :
173
عنوان مقاله :
Hybrid Method for Hand Gesture Recognition Based on Combination of Haar-Like and HOG Features
عنوان به زبان ديگر :
Hybrid Method for Hand Gesture Recognition Based on Combination of Haar-Like and HOG Features
پديدآورندگان :
Ghafouri sudabeh نويسنده , Seyedarabi Hadi نويسنده
كليدواژه :
Adaboost learning algorithm , Histogram Gradient Oriented feature , Multi-class support vector machine , Haar-like feature , Hand posture recognition
عنوان كنفرانس :
بيست و يكمين كنفرانس مهندسي برق ايران
چكيده فارسي :
In this paper a new method is proposed for hand gesture recognition. The proposed method increases hand gesture recognition rate and decreases false positive error rate byusing combination of Haar-like and Histogram of Oriented Gradients (HOG) features. Also some new Haar-like features areproposed proportional to hand posture to solve major Haar-like problem that is high false positive error rate in hand posturerecognition. These features improve recognition rate to 83%. Theexperiments showed that hybrid method can recognize hand gesture by 93.5% accuracy which is 25% higher than previous method, and decrease the false positive error from 92% to 8%.
چكيده لاتين :
In this paper a new method is proposed for hand gesture recognition. The proposed method increases hand gesture recognition rate and decreases false positive error rate byusing combination of Haar-like and Histogram of Oriented Gradients (HOG) features. Also some new Haar-like features areproposed proportional to hand posture to solve major Haar-like problem that is high false positive error rate in hand posturerecognition. These features improve recognition rate to 83%. Theexperiments showed that hybrid method can recognize hand gesture by 93.5% accuracy which is 25% higher than previous method, and decrease the false positive error from 92% to 8%.
شماره مدرك كنفرانس :
4474702
