Speckle noise
View article: Training Dataset supporting the publication: Single Shot Line-of-Sight Atmospheric Turbulence Profiling with STORM for Laser Satellite Communications
Training Dataset supporting the publication: Single Shot Line-of-Sight Atmospheric Turbulence Profiling with STORM for Laser Satellite Communications Open
This is a training dataset for Speckle-based Turbulence Observation and Reconstruction via Machine Learning (STORM), a technique which aims at estimating atmospheric turbulence profiles from the measurement of a single star or laser beam s…
View article: zea: A Toolbox for Cognitive Ultrasound Imaging
zea: A Toolbox for Cognitive Ultrasound Imaging Open
This release brings several new features along with numerous improvements across documentation, conversion scripts, and core operations 🚀. Some highlighted features: Added speckle tracking algorithms in #170 new zea.ops.Map operation in #1…
View article: Training Dataset supporting the publication: Single Shot Line-of-Sight Atmospheric Turbulence Profiling with STORM for Laser Satellite Communications
Training Dataset supporting the publication: Single Shot Line-of-Sight Atmospheric Turbulence Profiling with STORM for Laser Satellite Communications Open
This is a training dataset for Speckle-based Turbulence Observation and Reconstruction via Machine Learning (STORM), a technique which aims at estimating atmospheric turbulence profiles from the measurement of a single star or laser beam s…
View article: HistoSpeckle-Net: Mutual Information-Guided Deep Learning for high-fidelity reconstruction of complex OrganAMNIST images via perturbed Multimode Fibers
HistoSpeckle-Net: Mutual Information-Guided Deep Learning for high-fidelity reconstruction of complex OrganAMNIST images via perturbed Multimode Fibers Open
Existing deep learning methods in multimode fiber (MMF) imaging often focus on simpler datasets, limiting their applicability to complex, real-world imaging tasks. These models are typically data-intensive, a challenge that becomes more pr…
View article: HistoSpeckle-Net: Mutual Information-Guided Deep Learning for high-fidelity reconstruction of complex OrganAMNIST images via perturbed Multimode Fibers
HistoSpeckle-Net: Mutual Information-Guided Deep Learning for high-fidelity reconstruction of complex OrganAMNIST images via perturbed Multimode Fibers Open
Existing deep learning methods in multimode fiber (MMF) imaging often focus on simpler datasets, limiting their applicability to complex, real-world imaging tasks. These models are typically data-intensive, a challenge that becomes more pr…
View article: Stereoscopic Digital Image Correlation for hydroelastic waves of floating membranes
Stereoscopic Digital Image Correlation for hydroelastic waves of floating membranes Open
Wave-structure interactions of flexible membrane-type materials are an emerging research field, driven by their potential in renewable energy and breakwater concepts. This study proposes stereoscopic Digital Image Correlation (DIC) as a sc…
View article: A feedforward equalizer with selective noise decorrelation for bandwidth-limited signal
A feedforward equalizer with selective noise decorrelation for bandwidth-limited signal Open
View article: Experimental insights into data augmentation techniques for deep learning-based multimode fiber imaging: limitations and success
Experimental insights into data augmentation techniques for deep learning-based multimode fiber imaging: limitations and success Open
Multimode fiber~(MMF) imaging using deep learning has high potential to produce compact, minimally invasive endoscopic systems. Nevertheless, it relies on large, diverse real-world medical data, whose availability is limited by privacy con…
View article: Experimental insights into data augmentation techniques for deep learning-based multimode fiber imaging: limitations and success
Experimental insights into data augmentation techniques for deep learning-based multimode fiber imaging: limitations and success Open
Multimode fiber~(MMF) imaging using deep learning has high potential to produce compact, minimally invasive endoscopic systems. Nevertheless, it relies on large, diverse real-world medical data, whose availability is limited by privacy con…
View article: One Pixel Can Change the Diagnosis: Adversarial andNon-Adversarial Robustness and Uncertainty in BreastUltrasound Classification Model
One Pixel Can Change the Diagnosis: Adversarial andNon-Adversarial Robustness and Uncertainty in BreastUltrasound Classification Model Open
Deep learning models have strong potential for automating breast ultrasound (BUS) image classification to support early cancer detection. However, their vulnerability to small input perturbations poses a challenge for clinical reliability.…
View article: Dihedral Corner Region Camouflage in Radar Vision by Super-Dispersion Encoded Surfaces
Dihedral Corner Region Camouflage in Radar Vision by Super-Dispersion Encoded Surfaces Open
Right-angle dihedral structures produce strong, highly correlated returns that dominate radar cross-section (RCS) and image signatures. Conventional absorbers or random coding metasurfaces often lose effectiveness across wide frequency ban…
View article: DiCAF: A Dual-Input Co-Attention Fusion Network with NMS Ensemble for Underwater Debris Detection
DiCAF: A Dual-Input Co-Attention Fusion Network with NMS Ensemble for Underwater Debris Detection Open
Underwater debris poses a significant threat to marine ecosystems, fisheries, and the tourism industry, necessitating the development of automated vision-based detection systems. Although recent studies have sought to enhance detection per…
View article: Tailoring surface wettability through laser speckle patterning
Tailoring surface wettability through laser speckle patterning Open
View article: Towards a Safer and Sustainable Manufacturing Process: Material classification in Laser Cutting Using Deep Learning
Towards a Safer and Sustainable Manufacturing Process: Material classification in Laser Cutting Using Deep Learning Open
Laser cutting is a widely adopted technology in material processing across various industries, but it generates a significant amount of dust, smoke, and aerosols during operation, posing a risk to both the environment and workers' health. …
View article: Automatic Target Recognition in SAR Using Deep Learning
Automatic Target Recognition in SAR Using Deep Learning Open
- The project uses many useful deep learning methods to automatically recognize targets in SAR images and relies on the well-known MSTAR dataset. In defense and surveillance, radar systems in many sectors are valuable and important because…
View article: Towards a Safer and Sustainable Manufacturing Process: Material classification in Laser Cutting Using Deep Learning
Towards a Safer and Sustainable Manufacturing Process: Material classification in Laser Cutting Using Deep Learning Open
Laser cutting is a widely adopted technology in material processing across various industries, but it generates a significant amount of dust, smoke, and aerosols during operation, posing a risk to both the environment and workers' health. …
View article: On the phase aberration estimation using common mid-angle correlations
On the phase aberration estimation using common mid-angle correlations Open
Phase aberrations, despite degrading ultrasound images, also encode valuable information about the spatial distribution of the speed of sound in tissue. In pulse-echo ultrasound, we can quantify them by exploiting speckle correlations. Amo…
View article: On the phase aberration estimation using common mid-angle correlations
On the phase aberration estimation using common mid-angle correlations Open
Phase aberrations, despite degrading ultrasound images, also encode valuable information about the spatial distribution of the speed of sound in tissue. In pulse-echo ultrasound, we can quantify them by exploiting speckle correlations. Amo…
View article: Despeckling of Ultrasound Images Using Non-subsampled Shearlet Transform and Enhanced Gradient Domain Guided Filter
Despeckling of Ultrasound Images Using Non-subsampled Shearlet Transform and Enhanced Gradient Domain Guided Filter Open
View article: MSP-Net: Multi-Scale Spectrum Pyramid Network for Robust Synthetic Aperture Radar Automatic Target Recognition
MSP-Net: Multi-Scale Spectrum Pyramid Network for Robust Synthetic Aperture Radar Automatic Target Recognition Open
Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) remains challenging due to speckle noise, aspect-angle variation, and the loss of fine scattering cues in conven-tional deep-learning pipelines. Spatial-domain CNNs primaril…
View article: Multimodal Optical Imaging Platform for Quantitative Burn Assessment
Multimodal Optical Imaging Platform for Quantitative Burn Assessment Open
Accurate assessment of burn severity at injury onset remains a major clinical challenge due to the lack of objective methods for detecting subsurface tissue damage. This limitation is critical in battlefield and mass-casualty settings, whe…
View article: Multimodal Optical Imaging Platform for Quantitative Burn Assessment
Multimodal Optical Imaging Platform for Quantitative Burn Assessment Open
Accurate assessment of burn severity at injury onset remains a major clinical challenge due to the lack of objective methods for detecting subsurface tissue damage. This limitation is critical in battlefield and mass-casualty settings, whe…
View article: Estimating differential pistons for the Extremely Large Telescope using focal plane imaging and a residual network
Estimating differential pistons for the Extremely Large Telescope using focal plane imaging and a residual network Open
As the Extremely Large Telescope (ELT) approaches operational status, optimising its imaging performance is critical. A differential piston, arising from either the adaptive optics (AO) control loop, thermomechanical effects, or other sour…
View article: Estimating differential pistons for the Extremely Large Telescope using focal plane imaging and a residual network
Estimating differential pistons for the Extremely Large Telescope using focal plane imaging and a residual network Open
As the Extremely Large Telescope (ELT) approaches operational status, optimising its imaging performance is critical. A differential piston, arising from either the adaptive optics (AO) control loop, thermomechanical effects, or other sour…
View article: Mathematical Modelling of Remote Sensing Time Series: A Case Study of Hurst Castle
Mathematical Modelling of Remote Sensing Time Series: A Case Study of Hurst Castle Open
This study presents a multi-temporal analysis of displacement data from Sentinel-1 Synthetic Aperture Radar data at Hurst Castle with datasets sourced from the European Ground Motion Service, and temperature records from Ventnor Park and O…
View article: Graph-Based Multi-Resolution Cosegmentation for Coarse-to-Fine Object-Level SAR Image Change Detection
Graph-Based Multi-Resolution Cosegmentation for Coarse-to-Fine Object-Level SAR Image Change Detection Open
The ongoing launch of high-resolution satellites has led to a significant increase in the volume of synthetic aperture radar data, resulting in a high-resolution and high-revisit Earth observation that efficiently supports subsequent high-…
View article: pyspeckle: a python module for creation and analysis of laser speckle
pyspeckle: a python module for creation and analysis of laser speckle Open
No new features but you can now run the notebooks in your browser using JupyterLite 0.6.0 jupyterlite support modernize packaging modernize github actions use pyproject.toml only improve docstrings use ruff for linting add requirements-dev…
View article: 100 Mfps ghost imaging with wavelength division multiplexing
100 Mfps ghost imaging with wavelength division multiplexing Open
Ghost imaging (GI) and single-pixel imaging (SPI) techniques enable image reconstruction without spatially resolved detectors, offering unique access to wide spectral ranges and challenging imaging environments. Yet, their adoption has bee…
View article: Recursive Threshold Median Filter and Autoencoder for Salt-and-Pepper Denoising: SSIM analysis of Images and Entropy Maps
Recursive Threshold Median Filter and Autoencoder for Salt-and-Pepper Denoising: SSIM analysis of Images and Entropy Maps Open
This paper studies the removal of salt-and-pepper noise from images using median filter (MF) and simple three-layer autoencoder (AE) within recursive threshold algorithm. The performance of denoising is assessed with two metrics: the stand…
View article: Recursive Threshold Median Filter and Autoencoder for Salt-and-Pepper Denoising: SSIM analysis of Images and Entropy Maps
Recursive Threshold Median Filter and Autoencoder for Salt-and-Pepper Denoising: SSIM analysis of Images and Entropy Maps Open
This paper studies the removal of salt-and-pepper noise from images using median filter (MF) and simple three-layer autoencoder (AE) within recursive threshold algorithm. The performance of denoising is assessed with two metrics: the stand…