Consulter le flux RSS

Publications

Cette page présente les publications du Centre Borelli déposées sur le serveur HAL.

Affichage des publications 151 à 160 sur 1555 au total

Image Processing

Improving OCR Using Internal Document Redundancy

Current OCR systems are based on deep learning models trained on large amounts of data. Although they have shown some ability to generalize to unseen data, especially in detection tasks, they can struggle with recognizing low-quality data. This is…

Diego Belzarena, Seginus Mowlavi, Aitor Artola, Camilo Mariño, Marina Gardella, Ignacio Ramírez, Antoine Tadros, Roy He, Natalia Bottaioli, Boshra Rajaei, Gregory Randall, Jean-Michel Morel

International Conference on Document Analysis and Recognition -

Gender studies

Sparking Interest: An Experience with Machine Learning and micro:bit on Girls in ICT Day

The participation of women in Science, Technology, Engineering, and Mathematics (STEM) fields -and particularly in Information and Communication Technologies (ICT)-continues to be affected by structural and cultural factors that limit their…

Alejandra Armendariz, Julia Azziz, Isabel Briozzo, Rocío Cabral, Ximena Caporale, Mariana del Castillo, Romina García Camargo, Marina Gardella, Josefina Lema, Lara Raad, Claudina Rattaro, Carmen Salinas, Mariana Siniscalchi, Julieta Umpierrez

XVII Congress of Latin American Women in Computing 2025 (LAWCC) -

Mathematics

Time Series Representations with Hard-Coded Invariances

Automatically extracting robust representations from large and complex time series data is becoming imperative for several real-world applications. Unfortunately, the potential of common neural network architectures in capturing invariant properties…

Thibaut Germain, Chrysoula Kosma, Laurent Oudre

42nd International Conference on Machine Learning -

Cardiology and cardiovascular system

Localization of arrhythmogenic sites in post-ischemic ventricular tachycardia using Network Granger Causality

Detecting abnormal electrical wave propagation in Sinus Rhythm (SR) in patient with Ventricular Tachycardia (VT) can enhance treatment strategies. However, traditional methods, like activation maps, often produce biased results due to the difficulty…

Lucas Zoroddu, Pierre Humbert, Laurent Oudre, Thomas Demarcy, Laurent Launay, Francis Bessière

47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2025) -

Signal and Image processing

SPOP: Time Series Compression with Quadratic Splines

Time series compression is an important topic, enabling long signals to be represented in a small number of parameters while denoising. Change-point detection methods offer a relevant framework for tackling this task. In this paper, we propose a new…

Nicolás Enrique Cecchi, Vincent Runge, Charles Truong, Laurent Oudre

33rd European Signal Processing Conference (EUSIPCO 2025) -

Computer Vision and Pattern Recognition

Scanned Documents Forensics: Detecting Inserted Characters Through Noise and Chromatic Artifacts

Document forgery detection plays a crucial role in safeguarding the integrity of various sectors, including accounting, insurance, finance, law enforcement, and national security. The ability to distinguish between authentic and counterfeit…

Marina Gardella, Julieta Umpierrez, Antoine Tadros, Seginus Mowlavi, Natalia Bottaioli, Diego Belzarena, Gabriele Facciolo, Roy He, Jean-Michel Morel, Rafael Grompone von Gioi

2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW 2025) -