Real-time face identification via multi-convolutional neural network and Boosted Hashing Forest

Abstract

The family of real-time face representations is obtained via Convolutional Network with Hashing Forest (CNHF). We learn the CNN, then transform CNN to the multiple convolution architecture and finally learn the output hashing transform via new Boosted Hashing Forest (BHF) technique. This BHF generalizes the Boosted Similarity Sensitive Coding (SSC) approach for hashing learning with joint optimization of face verification and identification. CNHF is trained on CASIA-WebFace dataset and evaluated on LFW dataset. We code the output of single CNN with 97% on LFW. For Hamming embedding we get CBHF-200 bit (25 byte) code with 96.3% and 2,000-bit code with 98.14% on LFW. CNHF with 2,000×7-bit hashing trees achieves 93% rank-1 on LFW relative to basic CNN 89.9% rank-1. CNHF generates templates at the rate of 40+ fps with CPU Core i7 and 120+ fps with GPU GeForce GTX 650.