44 citations · 133 across the 13 of their papers we have counts for
14 papers
Handwritten Text Recognition from Crowdsourced Annotations
Solène Tarride, Tristan Faine, Mélodie Boillet +2
In this paper, we explore different ways of training a model for handwritten text recognition when multiple imperfect or noisy transcriptions are available. We consider various tra…
How to Choose Pretrained Handwriting Recognition Models for Single Writer Fine-Tuning
Vittorio Pippi, Silvia Cascianelli, Christopher Kermorvant +1
Recent advancements in Deep Learning-based Handwritten Text Recognition (HTR) have led to models with remarkable performance on both modern and historical manuscripts in large benc…
Large Scale Genealogical Information Extraction From Handwritten Quebec Parish Records
Solène Tarride, Martin Maarand, Mélodie Boillet +4
This paper presents a complete workflow designed for extracting information from Quebec handwritten parish registers. The acts in these documents contain individual and family info…
SIMARA: a database for key-value information extraction from full pages
Solène Tarride, Mélodie Boillet, Jean-François Moufflet +1
We propose a new database for information extraction from historical handwritten documents. The corpus includes 5,393 finding aids from six different series, dating from the 18th-2…
Key-value information extraction from full handwritten pages
Solène Tarride, Mélodie Boillet, Christopher Kermorvant
We propose a Transformer-based approach for information extraction from digitized handwritten documents. Our approach combines, in a single model, the different steps that were so…
Confidence Estimation for Object Detection in Document Images
Mélodie Boillet, Christopher Kermorvant, Thierry Paquet
Deep neural networks are becoming increasingly powerful and large and always require more labelled data to be trained. However, since annotating data is time-consuming, it is now n…
The LAM Dataset: A Novel Benchmark for Line-Level Handwritten Text Recognition
Silvia Cascianelli, Vittorio Pippi, Martin Maarand +4
Handwritten Text Recognition (HTR) is an open problem at the intersection of Computer Vision and Natural Language Processing. The main challenges, when dealing with historical manu…
Robust Text Line Detection in Historical Documents: Learning and Evaluation Methods
Mélodie Boillet, Christopher Kermorvant, Thierry Paquet
Text line segmentation is one of the key steps in historical document understanding. It is challenging due to the variety of fonts, contents, writing styles and the quality of docu…
Including Keyword Position in Image-based Models for Act Segmentation of Historical Registers
Mélodie Boillet, Martin Maarand, Thierry Paquet +1
The segmentation of complex images into semantic regions has seen a growing interest these last years with the advent of Deep Learning. Until recently, most existing methods for Hi…
Multiple Document Datasets Pre-training Improves Text Line Detection With Deep Neural Networks
Mélodie Boillet, Christopher Kermorvant, Thierry Paquet
In this paper, we introduce a fully convolutional network for the document layout analysis task. While state-of-the-art methods are using models pre-trained on natural scene images…
HORAE: an annotated dataset of books of hours
Mélodie Boillet, Marie-Laurence Bonhomme, Dominique Stutzmann +1
We introduce in this paper a new dataset of annotated pages from books of hours, a type of handwritten prayer books owned and used by rich lay people in the late middle ages. The d…
Learning to detect and localize many objects from few examples
Bastien Moysset, Christoper Kermorvant, Christian Wolf
The current trend in object detection and localization is to learn predictions with high capacity deep neural networks trained on a very large amount of annotated data and using a…
Curriculum Learning for Handwritten Text Line Recognition
Jérôme Louradour, Christopher Kermorvant
Recurrent Neural Networks (RNN) have recently achieved the best performance in off-line Handwriting Text Recognition. At the same time, learning RNN by gradient descent leads to sl…
Dropout improves Recurrent Neural Networks for Handwriting Recognition
Vu Pham, Théodore Bluche, Christopher Kermorvant +1
Recurrent neural networks (RNNs) with Long Short-Term memory cells currently hold the best known results in unconstrained handwriting recognition. We show that their performance ca…