Low complexity classification system for glove-based arabic sign language recognition

Authors:
Khaled Assaleh;Tamer Shanableh;Mohammed Zourob
Affiliations:
Department of Electrical Engineering, American University of Sharjah, Sharjah, UAE;Department of Computer Science and Engineering, American University of Sharjah, Sharjah, UAE;Department of Electrical Engineering, American University of Sharjah, Sharjah, UAE
Venue:
ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part III
Year:
2012

Citing 4
Cited 0

Telescopic vector composition and polar accumulated motion residuals for feature extraction in Arabic sign language recognition

Journal on Image and Video Processing
Using acceleration measurements for activity recognition: An effective learning algorithm for constructing neural classifiers

Pattern Recognition Letters
Multi-Dimensional Dynamic Time Warping for Image Texture Similarity

SBIA '08 Proceedings of the 19th Brazilian Symposium on Artificial Intelligence: Advances in Artificial Intelligence
uWave: Accelerometer-based personalized gesture recognition and its applications

PERCOM '09 Proceedings of the 2009 IEEE International Conference on Pervasive Computing and Communications

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a low complexity classification approach for sign language recognition using sensor-based gloves. Each glove includes 5 bend sensors and a 3D accelerometer. The classification approach is based on a novel feature extraction method based on accumulated differences (ADs). The ADs approach projects the dynamics of the glove sensor readings into one feature vector. This vector is normally of high dimensionality as it is meant to capture the dynamics of a sign language gesture. As such, dimensionality reduction using stepwise regression is applied to feature vectors before classification. Thereafter, a simple minimum distance classifier is employed. The proposed system is applied to a dataset Arabic sign language gestures and it yielded a recognition rates 92.5% and 95.1% for user dependent and user independent models respectively. Moreover, the computational complexity of the proposed method is O(N) as compared to the classical approach of Dynamic Time Warping (DTW) which is of O(N2) complexity.