Direct Sparse Nearest Feature Classifier for Face Recognition

Sparse signal representation proposes a novel insight to solve face recognition problem. Based on the sparse assumption that a new object can be sparsely represented by other objects, we propose a simple yet efficient direct sparse nearest feature classifier to deal with the problem of automatically real-time face recognition. Firstly, we present a new method, which calculates an approximate sparse code to alleviate the extrapolation and interpolation inaccuracy in nearest feature classifier. Secondly, a sparse score normalization method is developed to normalize the calculated scores and to achieve a high receiver operator characteristic (ROC) curve. Experiments on FRGC and PIE face databases show that our method can get comparable results against sparse representation-based classification on both recognition rate and ROC curve.