Random Forest-Based Recognition of Isolated Sign Language Subwords Using Data from Accelerometers and Surface Electromyographic Sensors
Open Access
Abstract
Sign language recognition (SLR) has been widely used for communication amongst the hearing-impaired and non-verbal community. This paper proposes an accurate and robust SLR framework using an improved decision tree as the base classifier of random forests. This framework was used to recognize Chinese sign language subwords using recordings from a pair of portable devices worn on both arms consisting of accelerometers (ACC) and surface electromyography (sEMG) sensors. The experimental results demonstrated the validity of the proposed random forest-based method for recognition of Chinese sign language (CSL) subwords. With the proposed method, 98.25% average accuracy was obtained for the classification of a list of 121 frequently used CSL subwords. Moreover, the random forests method demonstrated a superior performance in resisting the impact of bad training samples. When the proportion of bad samples in the training set reached 50%, the recognition error rate of the random forest-based method was only 10.67%, while that of a single decision tree adopted in our previous work was almost 27.5%. Our study offers a practical way of realizing a robust and wearable EMG-ACC-based SLR systems.Keywords
Funding Information
- National Nature Science Foundation of China (61271138)
This publication has 21 references indexed in Scilit:
- Vision-Based Portuguese Sign Language Recognition System2014
- A Sign-Component-Based Framework for Chinese Sign Language Recognition Using Accelerometer and sEMG DataIEEE Transactions on Biomedical Engineering, 2012
- A Combined sEMG and Accelerometer System for Monitoring Functional Activity in StrokeIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2009
- Modelling and recognition of the linguistic components in American Sign LanguageImage and Vision Computing, 2009
- Myoelectric control systems—A surveyBiomedical Signal Processing and Control, 2007
- Teager–Kaiser Energy Operation of Surface EMG Improves Muscle Activity Onset DetectionAnnals of Biomedical Engineering, 2007
- Random Forests for land cover classificationPattern Recognition Letters, 2006
- Large vocabulary sign language recognition based on fuzzy decision treesIEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 2004
- Bagging predictorsMachine Learning, 1996
- Glove-Talk: a neural network interface between a data-glove and a speech synthesizerIEEE Transactions on Neural Networks, 1993