Results 81 to 90 of about 2,185 (196)

Set Representation Learning: A Framework for Learning Gigapixel Images [PDF]

open access: yes, 2021
In Machine Learning, we often encounter data as a set of instances such Point Clouds (set of x,y, and z coordinates), patches from gigapixel images (Digital Pathology, Satellite Imagery, Astronomical Images, etc.), Weakly Supervised Learning, Multiple ...
Adnan, Mohammed
core  

A self-supervised framework for cross-modal search in histopathology archives using scale harmonization

open access: yesScientific Reports
The exponential growth of data across various medical domains has generated a substantial demand for techniques to analyze multimodal big data. This demand is particularly pronounced in fields such as computational pathology due to the diverse nature of ...
Danial Maleki   +2 more
doaj   +1 more source

Wavelet‐Based Feature Extraction for Efficient High‐Resolution Image Classification

open access: yesEngineering Reports, Volume 7, Issue 2, February 2025.
The paper introduces a novel CNN architecture that uses wavelet‐domain inputs for high‐resolution image processing. A wavelet‐domain efficient channel attention module that dynamically focuses on informative wavelet subbands is also presented. The proposed architecture improves classification accuracy while reducing computational complexity.
Albert Dede   +7 more
wiley   +1 more source

Deep learning-based retrieval system for gigapixel histopathology cases and the open access literature

open access: yesJournal of Pathology Informatics, 2019
Background: The introduction of digital pathology into clinical practice has led to the development of clinical workflows with digital images, in connection with pathology reports.
Roger Schaer   +4 more
doaj   +1 more source

Multiscale 3D displacement field measurement using stereo digital image correlation on a fractal speckle pattern

open access: yesStrain, Volume 61, Issue 1, February 2025.
Abstract Even though the simulations used to predict failure are becoming increasingly predictive, complex multiaxial loading tests are still required to validate the design of structural components in a wide range of industries. Large specimen testing often requires two different scales.
J. Serra   +4 more
wiley   +1 more source

Gigapixel end-to-end training using streaming and attention

open access: yes, 2023
Current hardware limitations make it impossible to train convolutional neural networks on gigapixel image inputs directly. Recent developments in weakly supervised learning, such as attention-gated multiple instance learning, have shown promising results,
Stephan Dooper   +22 more
core   +1 more source

Un monumento in alta definizione: il catalogo digitale della Cappella Sansevero

open access: yesArcheomatica
The online publication of the first digital catalogue of the Cappella Sansevero marks a turning point in the monument’s scholarly understanding and scientific enhancement: the first complete cataloguing of its heritage, the result of a multi-year ...
Eleonora Ligas, Rosario Terranova
doaj   +1 more source

Optical Surface Roughness Estimation Using Artificial Intelligence

open access: yesMaterials and Corrosion, Volume 76, Issue 1, Page 188-196, January 2025.
An artificial intelligence (AI) model has been developed using a data set recorded by a laser triangulation scanner and a digital camera. This model is capable of identifying whether blasted steel surfaces are good or bad, and it can also estimate the roughness of these surfaces in the form of the Rz parameter, based on images alone.
Jacob Maxa, Mathias Nowottnick
wiley   +1 more source

Supplementary_material - Unbiased Population Size Estimation on Still Gigapixel Images

open access: yes, 2018
Supplementary_material for Unbiased Population Size Estimation on Still Gigapixel Images by Marcos Cruz, and Javier González-Villa in Sociological Methods ...
Marcos Cruz (758727)   +1 more
core   +1 more source

Lucrezia Borgia alla luce trasmessa

open access: yesArcheomatica
The article analyses the complex digitisation project of Lucrezia Borgia's letters and registers recently carried out by the tech company Haltadefinizione at the State Archive of Modena.
Maria Chiara Spiezia
doaj  

Home - About - Disclaimer - Privacy