A review of the autoencoder and its variants: A comparative perspective from target recognition in synthetic-aperture radar images
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 …
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
Large-scale, highly integrated and low-power-consuming hardware is becoming
progressively more important for realizing optical neural networks (ONNs) capable of …
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 …
quality images with varying pose, illumination, expression, etc. It has received much …
Histogram of oriented lines for palmprint recognition
Subspace learning methods are very sensitive to the illumination, translation, and rotation
variances in image recognition. Thus, they have not obtained promising performance for …
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 …
the difference between one person and another can only be captured in images of sufficient …
Learning support correlation filters for visual tracking
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 …
sampling is usually adopted to reduce the computational cost in training. In addition …
FVFSNet: Frequency-spatial coupling network for finger vein authentication
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 …
advantages in terms of liveness detection, high security, and user convenience. Although …
Face relighting from a single image under arbitrary unknown lighting conditions
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 …
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
In this paper, we investigate a single-sample periocular-based alignment-robust face
recognition technique that is pose-tolerant under unconstrained face matching scenarios …
recognition technique that is pose-tolerant under unconstrained face matching scenarios …
A regularized correntropy framework for robust pattern recognition
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 …
for robust pattern recognition. First, we motivate the use of correntropy to improve the …