Face Recognition Using Ordinal Features

Shengcai Liao, Zhen Lei, XiangXin Zhu, Zhenan Sun, Stan Z. Li, Tieniu Tan

Abstract: In this paper, we present an ordinal feature based method for face recognition. Ordinal features are used to represent faces. Hamming distance of many local sub-windows is computed to evaluate differences of two ordinal faces. AdaBoost learning is finally applied to select most effective hamming distance based weak classifiers and build a powerful classifier. Experiments demonstrate good results for face recognition on the FERET database, and the power of learning ordinal features for face recognition.