An Efficient and Accurate Face Verification Method Based on CNN Cascade Architecture
Dangdang Chen, Lanqing He, Shengming Yu, Shengjin Wang
Available Online June 2017.
- https://doi.org/10.2991/caai-17.2017.120How to use a DOI?
- face verification; deep learning; convolution neural network; metric learning
- Unconstrained face verification has been actively studied for decades in computer vision. Recent algorithms rely on Convolution Neural Network to further improve the accuracy. However, such algorithms tend to be time-consuming and computationally complex, which cannot meet the real-time requirements. In this paper, we propose an efficient and accurate face verification method based on Convolution Neural Network Cascade architecture. First, we use a compact network to handle most of the simple samples. Then, we use a complex network to handle a small number of hard samples. Finally, we use an ensemble of multi-patch networks with metric learning. Our method achieves an accuracy of 99.72% on LFW, which performs favorably against the state-of-the-arts. Furthermore, we significantly reduce time cost from 485ms to only 20ms on a single core i7-4790, which has strong practical value for real-time face verification systems.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Dangdang Chen AU - Lanqing He AU - Shengming Yu AU - Shengjin Wang PY - 2017/06 DA - 2017/06 TI - An Efficient and Accurate Face Verification Method Based on CNN Cascade Architecture BT - 2017 2nd International Conference on Control, Automation and Artificial Intelligence (CAAI 2017) PB - Atlantis Press SP - 534 EP - 540 SN - 1951-6851 UR - https://doi.org/10.2991/caai-17.2017.120 DO - https://doi.org/10.2991/caai-17.2017.120 ID - Chen2017/06 ER -