A Fusion Recognition Method Based on Multifeature Hidden Markov Model for Dynamic Hand Gesture.

Guoliang Chen,Kaikai Ge

doi:10.1155/2020/8871605

Guoliang Chen, Kaikai Ge

Open Access

https://doi.org/10.1155/2020/8871605

Copy DOI

Abstract

In this paper, a fusion method based on multiple features and hidden Markov model (HMM) is proposed for recognizing dynamic hand gestures corresponding to an operator's instructions in robot teleoperation. In the first place, a valid dynamic hand gesture from continuously obtained data according to the velocity of the moving hand needs to be separated. Secondly, a feature set is introduced for dynamic hand gesture expression, which includes four sorts of features: palm posture, bending angle, the opening angle of the fingers, and gesture trajectory. Finally, HMM classifiers based on these features are built, and a weighted calculation model fusing the probabilities of four sorts of features is presented. The proposed method is evaluated by recognizing dynamic hand gestures acquired by leap motion (LM), and it reaches recognition rates of about 90.63% for LM-Gesture3D dataset created by the paper and 93.3% for Letter-gesture dataset, respectively.

Highlights

Dynamic hand gesture recognition is a very intriguing problem in recent years that, if efficiently solved, could be the wealthiest means of communication that can be used
Five main classifying methods of hand gesture based on 3D vision can be identified: support vector machines (SVMs), artificial neural network (ANN), template matching (TM), hidden Markov model (HMM), and dynamic time warping (DTW) [4]. e SVM is a popular classifier for hand gesture recognition, in which support vectors are used to determine the hyperplane to realize the maximum separation of the hand gesture classes [6]
Avola et al [22] propose a long short-term memory (LSTM) and recurrent neural networks (RNNs) combined with an effective set of discriminative features based on both joint angles and fingertip positions to recognize sign language and semaphoric hand gestures, which achieves an accuracy of over 96%

Summary

Introduction

Dynamic hand gesture recognition is a very intriguing problem in recent years that, if efficiently solved, could be the wealthiest means of communication that can be used. Five main classifying methods of hand gesture based on 3D vision can be identified: support vector machines (SVMs), artificial neural network (ANN), template matching (TM), HMM, and dynamic time warping (DTW) [4]. Zhou et al [12] use HMM to model the different information sequences of dynamic hand gestures and use BP neural network (BPNN) as a classifier to process the resulting hand gestures modeled by HMM, which achieves a satisfactory real-time performance and an accuracy above 84%. Avola et al [22] propose a long short-term memory (LSTM) and recurrent neural networks (RNNs) combined with an effective set of discriminative features based on both joint angles and fingertip positions to recognize sign language and semaphoric hand gestures, which achieves an accuracy of over 96%.

Prophase Work of Gesture Recognition

Feature Extraction

Gesture Modeling and Recognition

Experiments

Findings

Conclusion