期刊名称：Romanian Conference on Human-Computer Interaction
印刷版ISSN：2344-1690
出版年度：2014
期号：3888
页码：19-24
出版社：Matrix ROM
摘要：The task of hand gesture recognition is actively researched and challenging because of complex backgrounds, different lighting environments and unpredictable hand movements. This paper presents an analysis along with an implementation of a system that can recognize the hand center, the fingers and the hand wrist. Hand center recognition is done by finding the minimum inscribed circle in the hand contour. Fingers are detected using the k-curvature algorithm. The hand’s positions along a trajectory are analyzed and based on those a general direction is inferred. Tracking of the features is performed using Kalman filtering in order to achieve stability and robustness. The hand gestures are composed based on a desired direction and a certain positioning of the fingers. An evaluation is performed with the purpose of: quantifying the robustness of the system, to determine the error rate and the processing rate.
