Document, Image and Video Analysis (DIVA) Research Group

Welcome to the website of the DIVA research group at the University of Fribourg. Our reserach involves many different fields dealing with multimedia engineering, machine learning and data analysis.

Profil

PUBLICATION
Labeling, Cutting, Grouping: an Efficient Text Line Segmentation Method for Medieval Manuscripts

To be published at the ICDAR 2019 conference.

CONFERENCE TUTORIAL
Creating a Reproducible Research Environment

Tutorial at the ICDAR 2019 conference.

PAPER AWARD
Reproducibility Award at SDS Conference 2019

Award for the paper on "Improving Reproducible Deep Learning Workflows with DeepDIVA".

CONFERENCE WORKSHOP
2nd International Workshop on Open Services and Tools for Document Analysis (ICDAR-OST)

Workshop at the ICDAR 2019 conference.

PUBLICATION
A Comprehensive Study of ImageNet Pre-Training for Historical Document Image Analysis

To be published at the ICDAR 2019 conference.

CONFERENCE
ICDAR 2021

We are happy to announce that our proposal to host ICDAR 2021 in Lausanne, Switzerland has been accepted by the ICDAR committee.