Cognitive Environment for Pervasive Learners

Abstract

We present a novel approach for taking the ordinary classroom teaching to a new level, by creating a cognitive environment which includes the use of an image sensing device, number of client/student systems and a master/faculty system connected over a network. An automatic face detector and recognizer are activated on all the client systems for taking the attendance. The detection process is based on the adaboost algorithm, which is a cascade of binary features to rapidly locate and detect faces; recognition is achieved using principle component analysis. Hand gesture detection for students to raise doubts is achieved using adaboost algorithm. The system can also detect whether the students are asleep by extracting the eye region alone and applying principle component analysis to classify whether eyes are closed or open. Kalman filter is used to track the detected eye in consecutive frames. Experimental results show that our system is a viable approach and achieves good detection and recognition rates across wide range of head poses with different lighting conditions.