Abstract
Building human-friendly robots which are able to interact and cooperate with humans has been an active research field in recent years. A major challenge in this field is to develop robots that can interact and cooperate with humans by understanding human communication modalities. Nonetheless, human face is a dynamic object and has a high degree of variability in its appearance, which makes face detection a difficult problem. In this paper, we present a real-time vision-based framework to detect human face and analysis of the human face direction in window area to interact with robot. A cascade of feature detectors trained with boosting technique has been employed. Experimental results using servo motors connect to SD21 and PIC16F887A microcontroller; and the MIABOT Pro have validated our approach. Our future work is to build an intelligent wheelchair whose motion can be controlled by the user’s face direction.