Learning iteration-wise generalized shrinkage–thresholding operators for blind deconvolution
Salient edge selection and time-varying regularization are two crucial techniques to
guarantee the success of maximum a posteriori (MAP)-based blind deconvolution. However …
guarantee the success of maximum a posteriori (MAP)-based blind deconvolution. However …
Uncertainty-aware unsupervised image deblurring with deep residual prior
Non-blind deblurring methods achieve decent performance under the accurate blur kernel
assumption. Since the kernel uncertainty (ie kernel error) is inevitable in practice, semi-blind …
assumption. Since the kernel uncertainty (ie kernel error) is inevitable in practice, semi-blind …
An ℓ0-overlapping group sparse total variation for impulse noise image restoration
Total variation (TV) based methods are effective models in image restoration. For eliminating
impulse noise, an effective way is to use the ℓ 1-norm total variation model. However, the TV …
impulse noise, an effective way is to use the ℓ 1-norm total variation model. However, the TV …
Sparsity-based signal extraction using dual Q-factors for gearbox fault detection
Early detection of faults developed in gearboxes is of great importance to prevent
catastrophic accidents. In this paper, a sparsity-based feature extraction method using the …
catastrophic accidents. In this paper, a sparsity-based feature extraction method using the …
Combined higher order non-convex total variation with overlapping group sparsity for impulse noise removal
T Adam, R Paramesran, Y Mingming… - Multimedia Tools and …, 2021 - Springer
A typical approach to eliminate impulse noise is to use the ℓ 1-norm for both the data fidelity
term and the regularization terms. However, the ℓ 1-norm tends to over penalize signal …
term and the regularization terms. However, the ℓ 1-norm tends to over penalize signal …
Image deconvolution using hybrid threshold based on modified L1-clipped penalty in EM framework
Image deconvolution remains a challenging task due to its inherent ill-posedness. While
existing algorithms show strong numerical performance, their complexity often complicates …
existing algorithms show strong numerical performance, their complexity often complicates …
Image processing and deep normalized CNN for the location measurement and reading distance prediction of RFID multi-tags
X Zhuang, D Zhou, J Cai, H Zuo, X Zhao… - IEEE Sensors …, 2023 - ieeexplore.ieee.org
In the field of radio frequency identification (RFID) application, the locations of RFID
multitags have a great influence on the reading distance of RFID system. In order to improve …
multitags have a great influence on the reading distance of RFID system. In order to improve …
A nonblind deconvolution method by bias correction for inaccurate blur kernel estimation in image deblurring
J Han, S Zhang, Z Ye - IEEE Transactions on Geoscience and …, 2022 - ieeexplore.ieee.org
The blur kernel estimated by a blind deblurring algorithm is hardly to be error-free. The blur
kernel error is usually ignored in the nonblind deconvolution stage and may result in severe …
kernel error is usually ignored in the nonblind deconvolution stage and may result in severe …
Non-blind image deblurring method by the total variation deep network
There are a lot of non-blind image deblurring methods, especially with the total variation
(TV) model-based method. However, how to choose the parameters adaptively for …
(TV) model-based method. However, how to choose the parameters adaptively for …
Compressive sensing via nonlocal low-rank tensor regularization
The aim of Compressing sensing (CS) is to acquire an original signal, when it is sampled at
a lower rate than Nyquist rate previously. In the framework of CS, the original signal is often …
a lower rate than Nyquist rate previously. In the framework of CS, the original signal is often …