Face Recognition Using Smoothed High-Dimensional Representation

Recent studies have underlined the significance of high-dimensional features and their compression for face recognition. Partly motivated by these findings, we propose a novel method for building unsupervised face representations based on binarized descriptors and efficient compression by soft assignment and unsupervised dimensionality reduction. For binarized descriptors, we consider Binarized Statistical Image Features (BSIF) which is a learning based descriptor computing a binary code for each pixel by thresholding the outputs of a linear projection between a local image patch and a set of independent basis vectors estimated from a training data set using independent component analysis. In this work, we propose application specific learning to train a separate BSIF descriptor for each of the local face regions. Then, our method constructs a high-dimensional representation from an input face by collecting histograms of BSIF codes in a blockwise manner. Before dropping the dimension to get a more compressed representation, an important step in the pipeline of our method is soft feature assignment where the region histograms of the binarized codes are smoothed using kernel density estimation achieved by a simple and fast matrix-vector product. In detail, we provide a thorough evaluation on FERET and LFW benchmarks comparing our face representation method to the state-of-the-art in face recognition showing enhanced performance on FERET and promising results on LFW.