Head gestures recognition
Pei Chi Ng, L.C. De Silva · 2002
We describe a system that automatically detects and recognizes human head gestures such as nodding and shaking in complex background conditions using a cheap Web camera under uncontrolled conditions. The images of the head, captured at 20 frames per second, are very noisy and are of a low resolution. The invariant moments of each image captured is extracted and is fed into a recognition system that uses discrete hidden Markov models (HMMs) to classify the head gestures. The system achieves an average success rate of 87%. The system can successfully run on any low to high end PC connected to a USB Web camera without any manual initialization.