Trajectory based hand gesture recognition
Daniel Popa, Georgiana Simion, Vasile Gui, Marius Oteşteanu · 2007
Abstract: The recognition of hand gestures from image sequences is an important and challenging problem. This paper presents a robust solution to track and recognize a list of hand gestures from their trajectory. The CamShift algorithm is used for hand tracking and the resulting trajectory is segmented into strokes. The trajectory of recognized gestures consists of at least 2 strokes. The gestures are classified based on the number of strokes, the strokes ’ angle sequence and, eventually, strokes proportionality. The low computational cost of the algorithm allows implementation on low-cost processing systems. Key-Words: video tracking, CamShift, robust methods, gesture recognition, human machine interface. 1