Paper Title
The Weight Adjustment of Haar-Like Features In Voila Jones Classifier Using Principal Component Analysis Method For Hand Posture Recognition

Abstract
Hand Posture detection and recognition are important steps in the Hand Gesture Recognition for Human Computer Interaction. This paper presents a novel approach for improving the most familiar Viola Jones classifier to detect and recognize Hand Postures. In the Viola Jones algorithm Haar like features are used for feature extraction and Adaptive Boosted Classifier is used for detection and classification. The proposed scheme includes Principal Component Analysis (PCA) method to adjust the weight of positive training feature samples for the improved performance in the cascaded adaptive boost learning algorithm. By using this method the complexity and time in training phase is reduced. The performance of the proposed scheme is investigated in terms of Recognition accuracy and computation time. Keywords - Hand posture, Haar-Like Features, Boosting, Principal Component Analysis.