In this paper, a novel classification algorithm called MRC-Boosting is proposed. Through aggregating Maximal-Rejection-Classifier features under boosting framework, this algorithm can deal with complicated two-class classification problem, especially for the category called target detection problem where a target class should be discriminated from the surrounding clutter class. MRC-Boosting is efficient since unlike many other boosting based algorithms, at each iteration the optimal feature is computed in closed-form, with neither exhaustive search nor time-consuming numerical optimization. Furthermore, a variant of MRC-Boosting is derived and applied to face recognition. This variant MRC-Boosting algorithm is able to utilize large amount of training samples efficiently, overcoming the difficulty faced by other algorithms like AdaBoost. The effectiveness of the proposed algorithm is validated by face recognition experiments on CMU-PIE database.