American Sign Language Alphabet Recognition using Microsoft Kinect
American Sign Language (ASL) alphabet recognition using marker-less vision sensors is a challenging task due to the complexity of ASL alphabet signs, self-occlusion of the hand, and limited resolution of the sensors. This paper describes a new method for ASL alphabet recognition using a low-cost depth camera, which is Microsoft's Kinect. A segmented hand configuration is first obtained by using a depth contrast feature based per-pixel classification algorithm. Then, a hierarchical mode-seeking method is developed and implemented to localize hand joint positions under kinematic constraints. Finally, a Random Forest (RF) classifier is built to recognize ASL signs using the joint angles. To validate the performance of this method, we used a publicly available dataset from Surrey University. The results have shown that our method can achieve above 90% accuracy in recognizing 24 static ASL alphabet signs, which is significantly higher in comparison to the previous benchmarks.
C. Dong et al., "American Sign Language Alphabet Recognition using Microsoft Kinect," Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (2015, Boston, MA), vol. 2015, pp. 44-52, IEEE Computer Society, Oct 2015.
The definitive version is available at https://doi.org/10.1109/CVPRW.2015.7301347
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (2015: Jun. 7-12, Boston, MA)
Mechanical and Aerospace Engineering
Keywords and Phrases
Computational Linguistics; Computer Vision; Decision Trees; Gesture Recognition; Joints ( Structural Components); Kinematics; Probability Distributions; Accuracy; Alphabet Recognition; American Sign Language; Hand Configuration; Kinematic Constraints; Microsoft's Kinect; Pixel Classification; Thumb; Pattern Recognition
International Standard Book Number (ISBN)
International Standard Serial Number (ISSN)
Article - Conference proceedings
© 2015 IEEE Computer Society, All rights reserved.
01 Oct 2015