Randomized intraclass-distance minimizing binary codes for face recognition

Hao Zhang, Bruce Draper, Quanyi Mo, Ross Beveridge, Jonathon Phillips

Abstract: A new algorithm for learning binary codes is pre- sented using randomized initial assignments of bit labels to classes followed by iterative refinement to minimize in- traclass Hamming distance. This Randomized Intraclass- Distance Minimizing Binary Codes (RIDMBC) algorithm is introduced in the context of face recognition, an area of bio- metrics where binary codes have rarely been used (unlike iris recognition). A cross-database experiment is presented training RIDMBC on the Labeled Faces in the Wild (LFW) and testing it on the Point-and-Shoot Challenge (PaSC). The RIDMBC algorithm performs better than both PaSC baselines. RIDMBC is compared with the Predictable Dis- criminative Binary Codes (DBC) algorithm developed by Rastegari et al. The DBC algorithm has an upper bound on the number of bits in a binary code; RIDMBC does not. RIDMBC outperforms DBC when using the same bit code length as DBC’s upper bound and RIDMBC further improves when more bits/features are added.