End-to-End Handwritten Paragraph Text Recognition Using a Vertical Attention Network
IEEE Transactions on Pattern Analysis and Machine Intelligence · 01.01.2023 · 45 (1) · 508-524
DOI: 10.1109/tpami.2022.3144899 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, erschienen am 01.01.2023. Verfasst von Denis Coquenet und 2 weiteren Autor:innen. Die Arbeit wurde bisher 159-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: Regional HPC Center, Normandy, France, HPC resources from GENCI-IDRIS, French Defense Innovation Agency.
Abstract (Originalsprache)
Unconstrained handwritten text recognition remains challenging for computer vision systems. Paragraph text recognition is traditionally achieved by two models: the first one for line segmentation and the second one for text line recognition. We propose a unified end-to-end model using hybrid attention to tackle this task. This model is designed to iteratively process a paragraph image line by line. It can be split into three modules. An encoder generates feature maps from the whole paragraph image. Then, an attention module recurrently generates a vertical weighted mask enabling to focus on the current text line features. This way, it performs a kind of implicit line segmentation. For each text line features, a decoder module recognizes the character sequence associated, leading to the recognition of a whole paragraph. We achieve state-of-the-art character error rate at paragraph level on three popular datasets: 1.91% for RIMES, 4.45% for IAM and 3.59% for READ 2016. Our code and trained model weights are available at https://github.com/FactoDeepLearning/VerticalAttentionOCR.
Förderung
- Regional HPC Center, Normandy, France
- HPC resources from GENCI-IDRIS
- French Defense Innovation Agency
- Normandy
Zitieren
APA
Coquenet, D., Chatelain, C., & Paquet, T. (2023). End-to-End Handwritten Paragraph Text Recognition Using a Vertical Attention Network. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(1), 508-524. https://doi.org/10.1109/tpami.2022.3144899
Vancouver
Coquenet D, Chatelain C, Paquet T. End-to-End Handwritten Paragraph Text Recognition Using a Vertical Attention Network. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(1):508-524. doi:10.1109/tpami.2022.3144899
BibTeX
@article{Coquenet2023,
author = {Coquenet, Denis and Chatelain, Clement and Paquet, Thierry},
title = {End-to-End Handwritten Paragraph Text Recognition Using a Vertical Attention Network},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2023},
volume = {45},
number = {1},
pages = {508--524},
doi = {10.1109/tpami.2022.3144899}
}
EUVIMED