Hand Region Extraction and Gesture Recognition using entropy analysis

In this paper, we propose the gesture recognition system using motion information from extracted hand region in complex background image. First, we measure entropy for the difference image between continuous frames. Using color information that is similar to a skin color in candidate region which has high value, we extract hand region only from background image. Chain code has been applied to acquire outline detection from the extracted hand region and hand gestures recognition is carried out by improved centroidal profile. In the experiment results for 6 kinds of hand gesture, unlike existing methods, we can stably recognize hand gesture in complex background and illumination changes without marker. Also, it shows the recognition rate with more than 95% for person and 90~100% for each gesture at 15 fps.