.png){kind=icon}
返回
Deep face recognition for dim images
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2022.108580.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The performance of many state-of-the-art deep face recognition models deteriorates significantly for im-ages captured under low illumination, mainly because the features of dim probe face images cannot match well with those of normal-illumination gallery images. The issue cannot be satisfactorily addressed by enhancing the illumination of face images and performing face recognition on the resulted images alone. We propose a novel deep face recognition framework that consists of a feature restoration net -work, a feature extraction network, and an embedding matching module. The feature restoration network adopts a two-branch structure based on the convolutional neural network to generate a feature image from the raw image and the illumination-enhanced image. The feature extraction network encodes the feature image into an embedding, which is then used by the embedding matching module for face verifi-cation and identification. The overall verification accuracy is improved from 1.1% to 6.7% when tested on the Specs on Faces (SoF) dataset. For face identification, the rank-1 identification accuracy is improved by 2.8%. (c) 2022 Published by Elsevier Ltd.
Keyword:
Face recognition
Dim image
Rank-1 identification accuracy
Two-branch network
Convolutional neural network
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
分享收藏Deep eigen-filters for face recognition: Feature representation via unsupervised multi-structure filter learning.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏分享收藏Learning features from covariance matrix of gabor wavelet for face recognition under adverse conditionsPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Spectrum-aware discriminative deep feature learning for multi-spectral face recognitionPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容