Search Results for author:
Found 12 papers, 0 papers with code
Improving Automatic Text Recognition with Language Models in the PyLaia Open-Source Library
PyLaia is one of the most popular open-source software for Automatic Text Recognition (ATR), delivering strong performance in terms of speed and accuracy.
The Socface Project: Large-Scale Collection, Processing, and Analysis of a Century of French Censuses
For this project, we developed a complete processing workflow: large-scale data collection from French departmental archives, collaborative annotation of documents, training of handwritten table text and structure recognition models, and mass processing of millions of images.
Handwritten Text Recognition from Crowdsourced Annotations
However, selecting training samples based on the degree of agreement between annotators introduces a bias in the training data and does not improve the results.
Ranked #1 on
Handwritten Text Recognition
on Belfort
Large Scale Genealogical Information Extraction From Handwritten Quebec Parish Records
Verification of the birth and death acts from this sample shows that 74% of them are considered complete and valid.
Key-value information extraction from full handwritten pages
We propose a Transformer-based approach for information extraction from digitized handwritten documents.
SIMARA: a database for key-value information extraction from full pages
We propose a new database for information extraction from historical handwritten documents.
Ranked #1 on
Key Information Extraction
on SIMARA
Détection d'Objets dans les documents numérisés par réseaux de neurones profonds
For this purpose, we propose confidence estimators from different approaches for object detection.
Confidence Estimation for Object Detection in Document Images
In the active learning framework, the three first estimators show a significant improvement in performance for the detection of document physical pages and text lines compared to a random selection of images.
Robust Text Line Detection in Historical Documents: Learning and Evaluation Methods
We present a study conducted using three state-of-the-art systems Doc-UFCN, dhSegment and ARU-Net and show that it is possible to build generic models trained on a wide variety of historical document datasets that can correctly segment diverse unseen pages.
Including Keyword Position in Image-based Models for Act Segmentation of Historical Registers
However, the segmentation of complex documents into semantic regions is sometimes impossible relying only on visual features and recent models embed both visual and textual information.
Multiple Document Datasets Pre-training Improves Text Line Detection With Deep Neural Networks
In this paper, we introduce a fully convolutional network for the document layout analysis task.
HORAE: an annotated dataset of books of hours
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.
