Guardado en:
Detalles Bibliográficos
Autores principales: Bottaioli, Natalia, Tarride, Solène, Anger, Jérémy, Mowlavi, Seginus, Gardella, Marina, Tadros, Antoine, Facciolo, Gabriele, von Gioi, Rafael Grompone, Kermorvant, Christopher, Morel, Jean-Michel, Preciozzi, Javier
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2507.08636
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913938345558016
author Bottaioli, Natalia
Tarride, Solène
Anger, Jérémy
Mowlavi, Seginus
Gardella, Marina
Tadros, Antoine
Facciolo, Gabriele
von Gioi, Rafael Grompone
Kermorvant, Christopher
Morel, Jean-Michel
Preciozzi, Javier
author_facet Bottaioli, Natalia
Tarride, Solène
Anger, Jérémy
Mowlavi, Seginus
Gardella, Marina
Tadros, Antoine
Facciolo, Gabriele
von Gioi, Rafael Grompone
Kermorvant, Christopher
Morel, Jean-Michel
Preciozzi, Javier
contents This study evaluates the recently proposed Document Attention Network (DAN) for extracting key-value information from Uruguayan birth certificates, handwritten in Spanish. We investigate two annotation strategies for automatically transcribing handwritten documents, fine-tuning DAN with minimal training data and annotation effort. Experiments were conducted on two datasets containing the same images (201 scans of birth certificates written by more than 15 different writers) but with different annotation methods. Our findings indicate that normalized annotation is more effective for fields that can be standardized, such as dates and places of birth, whereas diplomatic annotation performs much better for fields containing names and surnames, which can not be standardized.
format Preprint
id arxiv_https___arxiv_org_abs_2507_08636
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Normalized vs Diplomatic Annotation: A Case Study of Automatic Information Extraction from Handwritten Uruguayan Birth Certificates
Bottaioli, Natalia
Tarride, Solène
Anger, Jérémy
Mowlavi, Seginus
Gardella, Marina
Tadros, Antoine
Facciolo, Gabriele
von Gioi, Rafael Grompone
Kermorvant, Christopher
Morel, Jean-Michel
Preciozzi, Javier
Computer Vision and Pattern Recognition
Artificial Intelligence
This study evaluates the recently proposed Document Attention Network (DAN) for extracting key-value information from Uruguayan birth certificates, handwritten in Spanish. We investigate two annotation strategies for automatically transcribing handwritten documents, fine-tuning DAN with minimal training data and annotation effort. Experiments were conducted on two datasets containing the same images (201 scans of birth certificates written by more than 15 different writers) but with different annotation methods. Our findings indicate that normalized annotation is more effective for fields that can be standardized, such as dates and places of birth, whereas diplomatic annotation performs much better for fields containing names and surnames, which can not be standardized.
title Normalized vs Diplomatic Annotation: A Case Study of Automatic Information Extraction from Handwritten Uruguayan Birth Certificates
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2507.08636