Automatic player detection and recognition in images using AdaBoost

In this work we developed an augmented reality sports broadcasting application for enhanced end-user experience. The proposed system consists of three major steps. In the first step each player is detected using AdaBoost Algorithm. In second step, same algorithm is used to detect face in each player image. In third step, a robust face recognition algorithm is applied to match face of each player with an online database of players face images which also stores statistics of each player. The application can be used to show the users the statistics of players captured in still image using camera or smart phone. Useful statistics can be name of the player, height, age, sports record etc in specific game. For player and subsequent face detection we use Haar-like features and AdaBoost algorithm for both feature selection and classification. The employed face recognition system uses AdaBoost algorithm with Liner Discriminant Analysis as a week learner for feature selection in LDA subspace while classification is performed using a classic nearest center classifier. Detailed experimental results are shown on general player face database as well as on real baseball game images containing different number of players at various poses and lighting conditions.