Reading text in the wild is gaining attention in the computer vision community. Images captured in the wild are almost always compressed to varying degrees, depending on application context, and this compression introduces artifacts that distort image content into the captured images. In this paper we investigate the impact these compression artifacts have on text localization and recognition in the wild. We also propose a deep Convolutional Neural Network (CNN) that can eliminate text-specific compression artifacts and which leads to an improvement in text recognition. Experimental results on the ICDAR-Challenge4 dataset demonstrate that compression artifacts have a significant impact on text localization and recognition and that our approach yields an improvement in both – especially at high compression rates.

Reading Text in the Wild from Compressed Images / Galteri, Leonardo; Bazazian, Dena; Seidenari, Lorenzo; Bertini, Marco; Andrew D Bagdanov, ; Nicolau, Anguelos; Karatzas, Dimosthenis; Del Bimbo, Alberto. - ELETTRONICO. - (2017), pp. 0-0. (Intervento presentato al convegno International Conference on Computer Vision Workshops tenutosi a Venezia) [10.1109/ICCVW.2017.283].

Reading Text in the Wild from Compressed Images

GALTERI, LEONARDO;SEIDENARI, LORENZO;BERTINI, MARCO;BAGDANOV, ANDREW DAVID;DEL BIMBO, ALBERTO
2017

Abstract

Reading text in the wild is gaining attention in the computer vision community. Images captured in the wild are almost always compressed to varying degrees, depending on application context, and this compression introduces artifacts that distort image content into the captured images. In this paper we investigate the impact these compression artifacts have on text localization and recognition in the wild. We also propose a deep Convolutional Neural Network (CNN) that can eliminate text-specific compression artifacts and which leads to an improvement in text recognition. Experimental results on the ICDAR-Challenge4 dataset demonstrate that compression artifacts have a significant impact on text localization and recognition and that our approach yields an improvement in both – especially at high compression rates.
2017
Proc. of International Conference on Computer Vision Workshops
International Conference on Computer Vision Workshops
Venezia
Galteri, Leonardo; Bazazian, Dena; Seidenari, Lorenzo; Bertini, Marco; Andrew D Bagdanov, ; Nicolau, Anguelos; Karatzas, Dimosthenis; Del Bimbo, Alber...espandi
File in questo prodotto:
File Dimensione Formato  
PID4947981-epic2017.pdf

Accesso chiuso

Descrizione: Articolo principale
Tipologia: Pdf editoriale (Version of record)
Licenza: Tutti i diritti riservati
Dimensione 1.01 MB
Formato Adobe PDF
1.01 MB Adobe PDF   Richiedi una copia

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1094987
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 2
social impact