원문정보
초록
영어
A hand gesture recognition system for American sign language (ASL) using hierarchical features based on an infrared image is proposed. To reduce the error rate and illumination chage, the infrared image is used in this article. Hierarchical features consist of object extern, Hu-moment invariants, and direction features. First, circularity and eccentricity can be computed from the object extern feature. And then, ASL is classified by K-means using them. Next, the moment invariants features are used to recognize hand gestures by back-propagation (BP). Finally, the direction feature can accurately classify similar gestures like G and Z, I and J, U and H. The goal of this article is to achieve an efficient and effective hand gesture recognition system that meets the high recognition rate of gestures. Through experiments, the recognition rate for the proposed method is 97.15% and it takes 0.046 s to process one frame.
목차
1. Introduction
2. Relevant Theories
2.1. Hu-Moment Invariants
2.2. Back-Propagation
3. The Proposed Method
3.1. Preprocessing for Hand Region
3.2. Hierarchical Features
4. Experimental Results
4.1. Experimental Environment
4.2. Experimental Results
5. Conclusions
Acknowledgments
References