User profiles for F. Jug
Florian JugFondatione Human Technopole Verified email at fht.org Cited by 5519 |
[HTML][HTML] Cell segmentation methods for label-free contrast microscopy: review and comprehensive comparison
… where d is PSF (in general a directional first-derivative-of-Gaussian kernel, but simple
difference without Gaussian is used for simplification), g is acquired image and f is original image. …
difference without Gaussian is used for simplification), g is acquired image and f is original image. …
[HTML][HTML] Democratising deep learning for microscopy with ZeroCostDL4Mic
Deep Learning (DL) methods are powerful analytical tools for microscopy and can outperform
conventional image processing pipelines. Despite the enthusiasm and innovations fuelled …
conventional image processing pipelines. Despite the enthusiasm and innovations fuelled …
Content-aware image restoration: pushing the limits of fluorescence microscopy
Fluorescence microscopy is a key driver of discoveries in the life sciences, with observable
phenomena being limited by the optics of the microscope, the chemistry of the fluorophores, …
phenomena being limited by the optics of the microscope, the chemistry of the fluorophores, …
Noise2void-learning denoising from single noisy images
… (f) Result of our N2V trained network. Both networks are not able to preserve the grainy
structure of the image, but the N2V trained network loses more high-frequency detail. …
structure of the image, but the N2V trained network loses more high-frequency detail. …
An objective comparison of cell-tracking algorithms
… The final CT value for a particular video is computed as the F 1 score of completely … The
final BC(i) value for a particular video is computed as the F 1 score of correctly reconstructed …
final BC(i) value for a particular video is computed as the F 1 score of correctly reconstructed …
Content-aware image restoration for electron microscopy
Multiple approaches to use deep neural networks for image restoration have recently been
proposed. Training such networks requires well registered pairs of high and low-quality …
proposed. Training such networks requires well registered pairs of high and low-quality …
[HTML][HTML] LABKIT: labeling and segmentation toolkit for big image data
We present Labkit, a user-friendly Fiji plugin for the segmentation of microscopy image data.
It offers easy to use manual and automated image segmentation routines that can be rapidly …
It offers easy to use manual and automated image segmentation routines that can be rapidly …
ClearVolume: open-source live 3D visualization for light-sheet microscopy
To the Editor: Current state-of-the-art light-sheet microscopes rely on sophisticated control
software to perform the acquisition of gigabytes of image data per second over the course of …
software to perform the acquisition of gigabytes of image data per second over the course of …
[HTML][HTML] Probabilistic noise2void: Unsupervised content-aware denoising
… FCN based image denoising in fact implements f(x) by producing independent predictions
s ^ i = g ( x RF ( i ) ; θ ) ≈ s i for each pixel i, depending only on x RF(i) instead of on the entire …
s ^ i = g ( x RF ( i ) ; θ ) ≈ s i for each pixel i, depending only on x RF(i) instead of on the entire …
[HTML][HTML] Differential lateral and basal tension drive folding of Drosophila wing discs through two distinct mechanisms
… We then quantified the cross correlation between changes in F-actin intensity and cell height,
and found a negative peak for a time lag around 22 s, indicating that an increase in lateral F…
and found a negative peak for a time lag around 22 s, indicating that an increase in lateral F…