Sparsely encoded local descriptor for face verification

Abstract

A novel Sparsely Encoded Local Descriptor (SELD) is proposed for face verification. Different from traditional hard or soft quantization methods, we exploit linear regression (LR) model with sparsity and non-negativity constraints to extract more discriminative features (i.e. sparse codes) from local image patches sampled pixel-wisely. Sum-pooling is then imposed to integrate all the sparse codes within each block partitioned from the whole face image. Whitened Principal Component Analysis (WPCA) is finally used to suppress noises and reduce the dimensionality of the pooled features, which thus results in the so-called SELD. To validate the proposed method, comprehensive experiments are conducted on face verification task to compare SELD with the existing related methods in terms of three variable component modules: K-means or K-SVD for dictionary learning, hard/soft assignment or regression model for encoding, as well as sum-pooling or max-pooling for pooling. Experimental results show that our method achieves a competitive accuracy compared with the state-of-the-art methods on the challenging Labeled Faces in the Wild (LFW) database.