Explanipedia

The PARES Database: Information Extraction over Historical Parish Records Open

José Onofre Montesa Andrés, C. Edward Wall, Solène Tarride, Mickaël Coustaty, Alejandro H. Toselli , et al. · 2025

Historical census records convey information that is key to perform genealogical research and demographic studies. Given the large number of documents of this type that exist, it is crucial to research methods that allow the automatic extr…

What distinguishes conspiracy from critical narratives? A computational analysis of oppositional discourse Open

Damir Korenčić, Berta Chulvi, Xavier Bonet Casals, Alejandro H. Toselli, Mariona Taulé , et al. · 2024

The current prevalence of conspiracy theories on the internet is a significant issue, tackled by many computational approaches. However, these approaches fail to recognize the relevance of distinguishing between texts which contain a consp…

Segmenting large historical notarial manuscripts into multi-page deeds Open

José Ramón Fernández Prieto, David Becerra, Alejandro H. Toselli, Carlos J. Alonso, Enrique Vidal · 2024

Data Augmentation for Offline Handwritten Text Recognition: A Systematic Literature Review Open

Arthur Flor de Sousa Neto, Byron Leite Dantas Bezerra, Gabriel Moura, Alejandro H. Toselli · 2024

Open set classification of untranscribed handwritten text image documents Open

José Ramón Fernández Prieto, Juan José Flores, Enrique Vidal, Alejandro H. Toselli · 2023

End-to-End page-Level assessment of handwritten text recognition Open

Enrique Vidal, Alejandro H. Toselli, Antonio Ríos-Vila, Jorge Calvo-Zaragoza · 2023

[EN] The evaluation of Handwritten Text Recognition (HTR) systems has traditionally used metrics based on the edit distance between HTR and ground truth (GT) transcripts, at both the character and word levels. This is very adequate when th…

Lexicon-based probabilistic indexing of handwritten text images Open

Enrique Vidal, Alejandro H. Toselli, Joan Puigcerver · 2023

End-to-End Page-Level Assessment of Handwritten Text Recognition Open

Enrique Vidal, Alejandro H. Toselli, Antonio Ríos-Vila, Jorge Calvo-Zaragoza · 2023

The evaluation of Handwritten Text Recognition (HTR) systems has traditionally used metrics based on the edit distance between HTR and ground truth (GT) transcripts, at both the character and word levels. This is very adequate when the exp…

Revisiting Bag-of-Word Metrics to Assess End-To-End Text Image Recognition Results Open

Alejandro H. Toselli, Enrique Vidal · 2023

End-to-End Page-Level Assessment Of Handwritten Text Recognition Open

Enrique Vidal, Alejandro H. Toselli, Antonio Ríos-Vila, Jorge Calvo-Zaragoza · 2023

Fake News and Hate Speech: Language in Common Open

Berta Chulvi, Alejandro H. Toselli, Paolo Rosso · 2022

In this paper we raise the research question of whether fake news and hate speech spreaders share common patterns in language. We compute a novel index, the ingroup vs outgroup index, in three different datasets and we show that both pheno…

Open Set Classification of Untranscribed Handwritten Documents Open

José Ramón Fernández Prieto, Juan José Flores, Enrique Vidal, Alejandro H. Toselli, David Garrido Romero , et al. · 2022

Huge amounts of digital page images of important manuscripts are preserved in archives worldwide. The amounts are so large that it is generally unfeasible for archivists to adequately tag most of the documents with the required metadata so…

PLANTAS Dataset Open

Alejandro H. Toselli, Enrique Vidal · 2022

The dataset "PLANTAS" (“Historia de las plantas”, Vol.1) were written using a quill-pen by Bernardo de Cienfuegos, one of the most outstanding Spanish botanists in the XVII century. The book was writing mainly in Spanish, but a significant…

PLANTAS Dataset Open

Alejandro H. Toselli, Enrique Vidal · 2022

The dataset "PLANTAS" (“Historia de las plantas”, Vol.1) were written using a quill-pen by Bernardo de Cienfuegos, one of the most outstanding Spanish botanists in the XVII century. The book was writing mainly in Spanish, but a significant…

A robust handwritten recognition system for learning on different data restriction scenarios Open

Arthur Flor de Sousa Neto, Byron Leite Dantas Bezerra, Alejandro H. Toselli, Estanislau Lima · 2022

ICDAR 2021 Competition on Components Segmentation Task of Document Photos Open

Celso A. M. Lopes, Ricardo Batista das Neves, Byron Leite Dantas Bezerra, Alejandro H. Toselli, Donato Impedovo · 2021

This paper describes the short-term competition on the Components Segmentation Task of Document Photos that was prepared in the context of the 16th International Conference on Document Analysis and Recognition (ICDAR 2021). This competitio…

A Probabilistic Framework for Lexicon-based Keyword Spotting in Handwritten Text Images Open

Enrique Vidal, Alejandro H. Toselli, Joan Puigcerver · 2021

Query by String Keyword Spotting (KWS) is here considered as a key technology for indexing large collections of handwritten text images to allow fast textual access to the contents of these collections. Under this perspective, a probabilis…

Digital Editions as Distant Supervision for Layout Analysis of Printed Books Open

Alejandro H. Toselli, Si Wu, David A. Smith · 2021

HU‐PageScan: a fully convolutional neural network for document page crop Open

Ricardo Batista das Neves, Estanislau Lima, Byron Leite Dantas Bezerra, Cleber Zanchettin, Alejandro H. Toselli · 2020

November The offer of online, automated, and impersonal services demand users to upload scanned copies of their documents to the organisations. As a consequence of this decentralisation, the documents present more challenges to the already…

Towards the Natural Language Processing as Spelling Correction for Offline Handwritten Text Recognition Systems Open

Arthur Flor de Sousa Neto, Byron Leite Dantas Bezerra, Alejandro H. Toselli · 2020

The increasing portability of physical manuscripts to the digital environment makes it common for systems to offer automatic mechanisms for offline Handwritten Text Recognition (HTR). However, several scenarios and writing variations bring…

HDSR-Flor: A Robust End-to-End System to Solve the Handwritten Digit String Recognition Problem in Real Complex Scenarios Open

Arthur Flor de Sousa Neto, Byron Leite Dantas Bezerra, Estanislau Lima, Alejandro H. Toselli · 2020

Automatic handwriting recognition systems are of interest for academic research fields and for commercial applications. Recent advances in deep learning techniques have shown dramatic improvement in relation to classic computer vision prob…

Handwritten Music Recognition for Mensural notation with convolutional recurrent neural networks Open

Jorge Calvo-Zaragoza, Alejandro H. Toselli, Enrique Vidal · 2019

Transforming scholarship in the archives through handwritten text recognition Open

Guenter Muehlberger, Louise Seaward, Melissa Terras, Sofia Ares Oliveira, V. Herrero , et al. · 2019

Purpose An overview of the current use of handwritten text recognition (HTR) on archival manuscript material, as provided by the EU H2020 funded Transkribus platform. It explains HTR, demonstrates Transkribus , gives examples of use cases,…

A set of benchmarks for Handwritten Text Recognition on historical documents Open

Joan Andreu Sánchez, Verónica Romero, Alejandro H. Toselli, Mauricio Villegas, Enrique Vidal · 2019

Multi-task Layout Analysis of Handwritten Musical Scores Open

Lorenzo Quirós, Alejandro H. Toselli, Enrique Vidal · 2019

Probabilistic multi-word spotting in handwritten text images Open

Alejandro H. Toselli, Enrique Vidal, Joan Puigcerver, Ernesto Noya-García · 2018

Oficio De Hipotecas De Girona. A Dataset Of Spanish Notarial Deeds (18Th Century) For Handwritten Text Recognition And Layout Analysis Of Historical Documents. Open

Lorenzo Quirós, Lluís Serrano, V. Herrero, Alejandro H. Toselli, Rosa Congost , et al. · 2018

This dataset is a subset of 596 documents from the Registre d'Hipoteques de Girona of 1769 collection, guarded by the Arxiu Històric de Girona. This collection, is composed by hundreds of thousands of notarial deeds from …

Oficio De Hipotecas De Girona. A Dataset Of Spanish Notarial Deeds (18Th Century) For Handwritten Text Recognition And Layout Analysis Of Historical Documents. Open

Lorenzo Quirós, Lluís Serrano, V. Herrero, Alejandro H. Toselli, Rosa Congost , et al. · 2018

This dataset is a subset of 596 documents from the Registre d'Hipoteques de Girona of 1769 collection, guarded by the Arxiu Històric de Girona. This collection, is composed by hundreds of thousands of notarial deeds from …

Icdar 2015 Competition Htrts: Handwritten Text Recognition On The Transcriptorium Dataset Rerelease Open

Mauricio Villegas, Joan Andreu Sánchez, Alejandro H. Toselli, Verónica Romero, Enrique Vidal · 2018

A new release of the dataset used in the ICDAR 2015 HTR competition in which all Page XML files are based on the same 2013-07-15 schema. It only contains page level images, Page XML files for train and test (including the ground truth tran…

Icdar 2015 Competition Htrts: Handwritten Text Recognition On The Transcriptorium Dataset Rerelease Open

Mauricio Villegas, Joan Andreu Sánchez, Alejandro H. Toselli, Verónica Romero, Enrique Vidal · 2018

A new release of the dataset used in the ICDAR 2015 HTR competition in which all Page XML files are based on the same 2013-07-15 schema. It only contains page level images, Page XML files for train and test (including the ground truth tran…

Alejandro H. Toselli YOU? Author Swipe