Handwritten Text Recognition (HTR) in free-layout pages is a valuable yet challenging task which aims to automatically understand handwritten texts. State-of-the-art approaches in this field usually encode input images with Convolutional Neural Networks, whose kernels are typically defined on a fixed grid and focus on all input pixels independently. However, this is in contrast with the sparse nature of handwritten pages, in which only pixels representing the ink of the writing are useful for the recognition task. Furthermore, the standard convolution operator is not explicitly designed to take into account the great variability in shape, scale, and orientation of handwritten characters. To overcome these limitations, we investigate the use of deformable convolutions for handwriting recognition. This type of convolution deform the convolution kernel according to the content of the neighborhood, and can therefore be more adaptable to geometric variations and other deformations of the text. Experiments conducted on the IAM and RIMES datasets demonstrate that the use of deformable convolutions is a promising direction for the design of novel architectures for handwritten text recognition.

Watch Your Strokes: Improving Handwritten Text Recognition with Deformable Convolutions / Cojocaru, Iulian; Cascianelli, Silvia; Baraldi, Lorenzo; Corsini, Massimiliano; Cucchiara, Rita. - (2020), pp. 6096-6103. ((Intervento presentato al convegno 25th International Conference on Pattern Recognition tenutosi a Milan, Italy nel 10-15 January 2021 [10.1109/ICPR48806.2021.9412392].

Watch Your Strokes: Improving Handwritten Text Recognition with Deformable Convolutions

Iulian Cojocaru;Silvia Cascianelli;Lorenzo Baraldi;Massimiliano Corsini;Rita Cucchiara
2020

Abstract

Handwritten Text Recognition (HTR) in free-layout pages is a valuable yet challenging task which aims to automatically understand handwritten texts. State-of-the-art approaches in this field usually encode input images with Convolutional Neural Networks, whose kernels are typically defined on a fixed grid and focus on all input pixels independently. However, this is in contrast with the sparse nature of handwritten pages, in which only pixels representing the ink of the writing are useful for the recognition task. Furthermore, the standard convolution operator is not explicitly designed to take into account the great variability in shape, scale, and orientation of handwritten characters. To overcome these limitations, we investigate the use of deformable convolutions for handwriting recognition. This type of convolution deform the convolution kernel according to the content of the neighborhood, and can therefore be more adaptable to geometric variations and other deformations of the text. Experiments conducted on the IAM and RIMES datasets demonstrate that the use of deformable convolutions is a promising direction for the design of novel architectures for handwritten text recognition.
25th International Conference on Pattern Recognition
Milan, Italy
10-15 January 2021
6096
6103
Cojocaru, Iulian; Cascianelli, Silvia; Baraldi, Lorenzo; Corsini, Massimiliano; Cucchiara, Rita
Watch Your Strokes: Improving Handwritten Text Recognition with Deformable Convolutions / Cojocaru, Iulian; Cascianelli, Silvia; Baraldi, Lorenzo; Corsini, Massimiliano; Cucchiara, Rita. - (2020), pp. 6096-6103. ((Intervento presentato al convegno 25th International Conference on Pattern Recognition tenutosi a Milan, Italy nel 10-15 January 2021 [10.1109/ICPR48806.2021.9412392].
File in questo prodotto:
File Dimensione Formato  
2020_ICPR_HTR_CR.pdf

accesso aperto

Tipologia: Pre-print dell'autore (bozza pre referaggio)
Dimensione 2.17 MB
Formato Adobe PDF
2.17 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/11380/1204119
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 3
social impact