Real-Time Face Identification via Multi-convolutional Neural Network and Boosted Hashing Forest
The family of real-time face representations is obtained via Convolutional 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 Boosted Hashing Forest (BH...
Saved in:
Published in | Deep Learning for Biometrics pp. 33 - 55 |
---|---|
Main Authors | , , , |
Format | Book Chapter |
Language | English |
Published |
Switzerland
Springer International Publishing AG
2017
Springer International Publishing |
Series | Advances in Computer Vision and Pattern Recognition |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The family of real-time face representations is obtained via Convolutional 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 Boosted Hashing Forest (BHF) (BHF) technique. This Boosted Hashing Forest (BHF) generalizes Boosted similarity sensitive coding 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\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\times $$\end{document}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\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$+$$\end{document} fps with CPU Core i7 and 120\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$+$$\end{document} fps with GPU GeForce GTX 650. |
---|---|
ISBN: | 3319616560 9783319616568 |
ISSN: | 2191-6586 2191-6594 |
DOI: | 10.1007/978-3-319-61657-5_2 |