A review of the autoencoder and its variants: A comparative perspective from target recognition in synthetic-aperture radar images

G Dong, G Liao, H Liu, G Kuang - IEEE Geoscience and …, 2018 - ieeexplore.ieee.org
In recent years, unsupervised feature learning based on a neural network architecture has
become a hot new topic for research [1]-[4]. The revival of interest in such deep networks can …

Space-efficient optical computing with an integrated chip diffractive neural network

HH Zhu, J Zou, H Zhang, YZ Shi, SB Luo… - Nature …, 2022 - nature.com
Large-scale, highly integrated and low-power-consuming hardware is becoming
progressively more important for realizing optical neural networks (ONNs) capable of …

Low-resolution face recognition: a review

Z Wang, Z Miao, QM Jonathan Wu, Y Wan, Z Tang - The Visual Computer, 2014 - Springer
Low-resolution face recognition (LR FR) aims to recognize faces from small size or poor
quality images with varying pose, illumination, expression, etc. It has received much …

Histogram of oriented lines for palmprint recognition

W Jia, RX Hu, YK Lei, Y Zhao… - IEEE Transactions on …, 2013 - ieeexplore.ieee.org
Subspace learning methods are very sensitive to the illumination, translation, and rotation
variances in image recognition. Thus, they have not obtained promising performance for …

Simultaneous super-resolution and feature extraction for recognition of low-resolution faces

PH Hennings-Yeomans, S Baker… - 2008 IEEE Conference …, 2008 - ieeexplore.ieee.org
Face recognition degrades when faces are of very low resolution since many details about
the difference between one person and another can only be captured in images of sufficient …

Learning support correlation filters for visual tracking

W Zuo, X Wu, L Lin, L Zhang… - IEEE transactions on …, 2018 - ieeexplore.ieee.org
For visual tracking methods based on kernel support vector machines (SVMs), data
sampling is usually adopted to reduce the computational cost in training. In addition …

FVFSNet: Frequency-spatial coupling network for finger vein authentication

J Huang, A Zheng, MS Shakeel… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Finger vein biometrics is becoming an important source of human authentication due to its
advantages in terms of liveness detection, high security, and user convenience. Although …

Face relighting from a single image under arbitrary unknown lighting conditions

Y Wang, L Zhang, Z Liu, G Hua, Z Wen… - IEEE transactions on …, 2008 - ieeexplore.ieee.org
In this paper, we present a new method to modify the appearance of a face image by
manipulating the illumination condition, when the face geometry and albedo information is …

Spartans: Single-Sample Periocular-Based Alignment-Robust Recognition Technique Applied to Non-Frontal Scenarios

F Juefei-Xu, K Luu, M Savvides - IEEE Transactions on Image …, 2015 - ieeexplore.ieee.org
In this paper, we investigate a single-sample periocular-based alignment-robust face
recognition technique that is pose-tolerant under unconstrained face matching scenarios …

A regularized correntropy framework for robust pattern recognition

R He, WS Zheng, BG Hu, XW Kong - Neural computation, 2011 - ieeexplore.ieee.org
This letter proposes a new multiple linear regression model using regularized correntropy
for robust pattern recognition. First, we motivate the use of correntropy to improve the …