Article
Environmental Sciences
Alexandru Isar, Corina Nafornita, Georgiana Magu
Summary: This paper addresses the issue of noise in image acquisition systems, particularly in relation to edge detection algorithms. By introducing a new denoising system before the Canny edge detector, the robustness of edge detection against Gaussian and speckle noise is improved, surpassing existing state-of-the-art results.
Article
Automation & Control Systems
Ashish Kumar, Harshit Tomar, Virender Kumar Mehla, Rama Komaragiri, Manjeet Kumar
Summary: This paper studies various denoising techniques for removing noise from ECG signals, and proposes a denoising technique based on stationary wavelet transform, which outperforms other methods by preserving more ECG signal components.
Article
Environmental Sciences
Bingzhe Dai, Jie Li, Jiahao Zhou, Yingting Zeng, Wenhao Hou, Junchao Zhang, Yao Wang, Qilin Zhang
Summary: In this paper, a modified empirical wavelet transform (MEWT) method was proposed to process natural lightning signal data. The experimental results demonstrated the adaptive processing capability of the method for lightning signals with different frequencies as well as the noise reduction effect for VLF lightning signals.
Article
Engineering, Biomedical
Mahesh Chandra, Pankaj Goel, Ankita Anand, Asutosh Kar
Summary: The improved high-speed adaptive filter-based denoising architectures proposed in this paper outperform existing adaptive filter architectures and wavelet-based architectures, offering design flexibility and efficiency in denoising ECG signals in noisy environments for low-cost high-performance applications in the medical field. These architectures also require significantly less hardware compared to state-of-the-art wavelet-based architectures.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Computer Science, Artificial Intelligence
Jun-Jie Huang, Pier Luigi Dragotti
Summary: The proposed WINNet method combines the advantages of wavelet-based methods and learning methods for image denoising, containing LINNs, sparse coding denoising, noise estimation networks, etc. By implementing nonlinear redundant transforms, sparse coding, and adaptively adjusting soft thresholds, WINNet method demonstrates strong generalization ability across different noise levels.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2022)
Article
Computer Science, Information Systems
Caixia Liu, Li Zhang
Summary: Denoising is essential in image processing and plays a crucial role in image preprocessing. It helps to enhance image quality, which contributes to subsequent image processing tasks such as image segmentation and feature extraction. In this paper, a novel denoising method based on wavelet transform and nonlocal moment mean filtering approach (NMM) is proposed.
Article
Engineering, Multidisciplinary
Hassan M. Aljohani
Summary: The paper presents a wavelet shrinkage model with noise variance estimated using exponential distribution, involving an epsilon-contamination prior distribution for robust priors in Bayesian analysis. The proposed method computes posterior mean, applies wavelet methods for signal reconstruction, and compares different approaches through extensive simulation and application on a real-life data set. The main focus is on comparing two different likelihoods - normal distribution and double exponential distribution.
ALEXANDRIA ENGINEERING JOURNAL
(2022)
Article
Geochemistry & Geophysics
Peng Wang, Yulan Wang, Bo Huang, Liguo Wang, Xiwang Zhang, Henry Leung, Jocelyn Chanussot
Summary: In this study, a Poissonian blurred HSI denoising method based on variable splitting and penalty technique is proposed under the maximum a posteriori (MAP) model. The method directly removes Poissonian blurred HSI noise without using the Anscombe transform. Experimental results show that the proposed method effectively removes Poisson noise in HSI contaminated by blurs during the imaging procedure.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Multidisciplinary Sciences
Ankita Mishra, Sitanshu Sekhar Sahu, Rajeev Sharma, Sudhansu Kumar Mishra
Summary: In this paper, an automated denoising technique based on time-frequency filtering approach is proposed for ECG signals. Experimental results demonstrate that this technique significantly reduces error and improves signal-to-noise ratio.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2021)
Article
Chemistry, Analytical
Lijing Bu, Jiayu Zhang, Zhengpeng Zhang, Yin Yang, Mingjun Deng
Summary: This paper proposes an enhanced framework for despeckling multi-temporal SAR images, which effectively removes speckle noise, reduces false details, and achieves the fusion of multi-temporal information.
Article
Chemistry, Multidisciplinary
Teresa Kwamboka Abuya, Richard Maina Rimiru, George Onyango Okeyo
Summary: Eliminating noise in CT scan images is crucial for preserving and restoring medical image information. This paper proposes an ensemble approach that integrates anisotropic Gaussian filter and wavelet transform in the preprocessing stage, and a deep learning denoising convolutional neural network in the post-processing stage to eliminate noise. Experimental results show that the proposed approach achieves exceptional performance in maintaining image quality and preserving fine details.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Artificial Intelligence
Chunwei Tian, Menghua Zheng, Wangmeng Zuo, Bob Zhang, Yanning Zhang, David Zhang
Summary: This paper proposes a multi-stage image denoising CNN with wavelet transform, using dynamic convolution, wavelet transform and enhancement, and residual block to improve denoising performance. Experimental results show that the proposed method outperforms popular denoising methods.
PATTERN RECOGNITION
(2023)
Article
Engineering, Biomedical
Saurabh Khare, Praveen Kaushik
Summary: A hybrid method based on WNNM and NLM is proposed for removing multiplicative speckle noise in medical images. Experimental results show that the proposed method outperforms existing methods in terms of speckle reduction and edge preservation.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Engineering, Multidisciplinary
Nazeer Muhammad, Nargis Bibi, Muhammad Arif Shah, Saira Zainab, Ihsan Ullah, Zahid Mahmood
Summary: A novel sub band replacement and fusion process with adaptive weights is proposed for image denoising and representation in this paper. The method, based on entropy measurement and edge enhancement strategy, improves image quality by removing noise, preserving details, and adapting to non stationary Gaussian noise. Visually and quantitatively validated, the proposed method can enhance edges and denoise images effectively without over-smoothing or over-sharpening.
APPLIED MATHEMATICAL MODELLING
(2021)
Review
Engineering, Biomedical
Syarifah Noor Syakiylla Sayed Daud, Rubita Sudirman
Summary: This review article comprehensively describes the application of the wavelet method in denoising the EEG signal based on recent research. It provides an overview of the basic theory and characteristics of EEG and the wavelet transform method, describes commonly applied wavelet-based methods for EEG dataset denoising, reviews a considerable number of the latest published EEG research works with wavelet applications, discusses challenges in current EEG-based wavelet method research, and recommends alternative solutions to mitigate the issues.
ANNALS OF BIOMEDICAL ENGINEERING
(2022)
Article
Engineering, Electrical & Electronic
Mohamed Amide Ouamri, Marius-Emil Otesteanu, Alexandru Isar, Mohamed Azni
PHYSICAL COMMUNICATION
(2020)
Article
Chemistry, Multidisciplinary
Georgiana Magu, Radu Lucaciu, Alexandru Isar
Summary: A novel post-processing method for Kalman filter with adaptive parameter selection is proposed to improve the accuracy of target trajectory estimation. Simulations show that polynomial fitting can significantly enhance the accuracy of estimated trajectories, especially for single and multiple targets.
APPLIED SCIENCES-BASEL
(2021)
Article
Environmental Sciences
Alexandru Isar, Corina Nafornita, Georgiana Magu
Summary: This paper addresses the issue of noise in image acquisition systems, particularly in relation to edge detection algorithms. By introducing a new denoising system before the Canny edge detector, the robustness of edge detection against Gaussian and speckle noise is improved, surpassing existing state-of-the-art results.
Article
Environmental Sciences
Ciprian David, Corina Nafornita, Vasile Gui, Andrei Campeanu, Guillaume Carrie, Michel Monnerat
Summary: This research proposes a method to improve satellite localization accuracy by fusing existing data with new information extracted using roof-mounted cameras and image processing algorithms. The camera helps exclude Non-Line-of-Sight satellites, providing a probability map to determine which satellites to use for localization.
Article
Health Care Sciences & Services
Beatrice Arvinti, Emil Radu Iacob, Alexandru Isar, Daniela Iacob, Marius Costache
Summary: This study aims to reduce diagnostic errors in neonatal ultrasound by optimizing medical procedures and proposing an algorithm. In practical clinical cases, noise affecting image quality was successfully reduced and contrast was enhanced through denoising and contrast correction methods.
JOURNAL OF PERSONALIZED MEDICINE
(2022)
Article
Chemistry, Analytical
Alexandru Bobaru, Corina Nafornita, George Copacean, Vladimir Cristian Vesa, Michael Skutek
Summary: This research presents an unsupervised online method for compensating for elevation mounting angle error and bumper and environmental error in the radar sensor of the Advanced Driver Assist System (ADAS). The proposed methods eliminate the need for specific calibration jigs and allow ongoing calibration throughout the sensor's lifespan.
Article
Biology
Beatrice Arvinti, Alexandru Isar
Summary: Magnetic resonance angiography is a vital medical procedure that provides imaging of the body's blood vessels and organs. This study proposes and tests a local adaptive contrast-adjustment algorithm using the dual-tree complex wavelet transform to enhance the contrast of cardiac images.
Article
Medicine, General & Internal
Beatrice Arvinti, Emil Radu Iacob, Alexandru Isar, Daniela Iacob, Marius Costache
Summary: This study aimed to develop remote neonatal intensive supervision systems for medical diagnosis and alarm for cardiac abnormalities. The algorithm tailored to infants' ECG characteristics successfully detected bradycardia events. The proposed personalized algorithm improved signal-to-noise ratio of processed ECG data.
MEDICINA-LITHUANIA
(2021)
Proceedings Paper
Computer Science, Information Systems
Teodor Mitrea, Vlad Vasile, Monica Borda, Corina Nafornita, Alexandru Romaniuc
2020 13TH INTERNATIONAL CONFERENCE ON COMMUNICATIONS (COMM)
(2020)
Proceedings Paper
Engineering, Electrical & Electronic
Corina Nafornita, Alexandru Isar, Teodor Dehelean, Ioan Nafornita
2020 14TH INTERNATIONAL SYMPOSIUM ON ELECTRONICS AND TELECOMMUNICATIONS (ISETC)
(2020)
Proceedings Paper
Engineering, Electrical & Electronic
Alexandru Isar, Corina Nafornita, Adrian Macaveiu, Georgiana Magu
2020 14TH INTERNATIONAL SYMPOSIUM ON ELECTRONICS AND TELECOMMUNICATIONS (ISETC)
(2020)
Proceedings Paper
Engineering, Electrical & Electronic
Adrian Savu-Jivanov, Alexandru Isar, Cristina Stolojescu-Crisan, Janos Gal
2020 14TH INTERNATIONAL SYMPOSIUM ON ELECTRONICS AND TELECOMMUNICATIONS (ISETC)
(2020)