Deep learning-based approaches to Handwritten Text Recognition (HTR) have shown remarkable results on publicly available large datasets, both modern and historical. However, it is often the case that historical manuscripts are preserved in small collections, most of the time with unique characteristics in terms of paper support, author handwriting style, and language. State-of-the-art HTR approaches struggle to obtain good performance on such small manuscript collections, for which few training samples are available. In this paper, we focus on HTR on small historical datasets and propose a new historical dataset, which we call Leopardi, with the typical characteristics of small manuscript collections, consisting of letters by the poet Giacomo Leopardi, and devise strategies to deal with the training data scarcity scenario. In particular, we explore the use of carefully designed but cost-effective synthetic data for pre-training HTR models to be applied to small single-author manuscripts. Extensive experiments validate the suitability of the proposed approach, and both the Leopardi dataset and synthetic data will be available to favor further research in this direction.

Learning to Read L'Infinito: Handwritten Text Recognition with Synthetic Training Data / Cascianelli, Silvia; Cornia, Marcella; Baraldi, Lorenzo; Piazzi, Maria Ludovica; Schiuma, Rosiana; Cucchiara, Rita. - 13053 LNCS:(2021), pp. 340-350. ((Intervento presentato al convegno International Conference on Computer Analysis of Images and Patterns tenutosi a Virtual nel 27 September - 01 October 2021 [10.1007/978-3-030-89131-2_31].

Learning to Read L'Infinito: Handwritten Text Recognition with Synthetic Training Data

Cascianelli, Silvia;Cornia, Marcella;Baraldi, Lorenzo;Piazzi, Maria Ludovica;Schiuma, Rosiana;Cucchiara, Rita
2021

Abstract

Deep learning-based approaches to Handwritten Text Recognition (HTR) have shown remarkable results on publicly available large datasets, both modern and historical. However, it is often the case that historical manuscripts are preserved in small collections, most of the time with unique characteristics in terms of paper support, author handwriting style, and language. State-of-the-art HTR approaches struggle to obtain good performance on such small manuscript collections, for which few training samples are available. In this paper, we focus on HTR on small historical datasets and propose a new historical dataset, which we call Leopardi, with the typical characteristics of small manuscript collections, consisting of letters by the poet Giacomo Leopardi, and devise strategies to deal with the training data scarcity scenario. In particular, we explore the use of carefully designed but cost-effective synthetic data for pre-training HTR models to be applied to small single-author manuscripts. Extensive experiments validate the suitability of the proposed approach, and both the Leopardi dataset and synthetic data will be available to favor further research in this direction.
International Conference on Computer Analysis of Images and Patterns
Virtual
27 September - 01 October 2021
13053 LNCS
340
350
Cascianelli, Silvia; Cornia, Marcella; Baraldi, Lorenzo; Piazzi, Maria Ludovica; Schiuma, Rosiana; Cucchiara, Rita
Learning to Read L'Infinito: Handwritten Text Recognition with Synthetic Training Data / Cascianelli, Silvia; Cornia, Marcella; Baraldi, Lorenzo; Piazzi, Maria Ludovica; Schiuma, Rosiana; Cucchiara, Rita. - 13053 LNCS:(2021), pp. 340-350. ((Intervento presentato al convegno International Conference on Computer Analysis of Images and Patterns tenutosi a Virtual nel 27 September - 01 October 2021 [10.1007/978-3-030-89131-2_31].
File in questo prodotto:
File Dimensione Formato  
2021_CAIP_HTR.pdf

accesso aperto

Tipologia: Post-print dell'autore (bozza post referaggio)
Dimensione 20.22 MB
Formato Adobe PDF
20.22 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1249339
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact