SNR Maximization Hashing

We propose a novel robust hashing algorithm based on signal-to-noise ratio (SNR) maximization to learn compact binary codes, where the SNR metric is used to select a set of projection directions, and one hash bit is extracted from each projection direction. We first motivate this approach under a Gaussian model for the underlying signals, in which case maximizing SNR is equivalent to minimizing the robust hashing error probability. A globally optimal solution can be obtained by solving a generalized eigenvalue problem. We also develop a multibit per projection algorithm to learn longer hash codes when the number of high-SNR projections is limited. The proposed algorithms are tested on both synthetic and real data sets, showing significant performance gains over existing hashing algorithms.