Skip to Main content Skip to Navigation
Conference papers

Combining Multi-Scale Character Recognition and Linguistic Knowledge for Natural Scene Text OCR

Khaoula Elagouni 1 Christophe Garcia 2 Franck Mamalet 1 Pascale Sébillot 3
2 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
3 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Understanding text captured in real-world scenes is a challenging problem in the field of visual pattern recognition and continues to generate a significant interest in the OCR (Optical Character Recognition) community. This paper proposes a novel method to recognize scene texts avoiding the conventional character segmentation step. The idea is to scan the text image with multi-scale windows and apply a robust recognition model, relying on a neural classification approach, to every window in order to recognize valid characters and identify non valid ones. Recognition results are represented as a graph model in order to determine the best sequence of characters. Some linguistic knowledge is also incorporated to remove errors due to recognition confusions. The designed method is evaluated on the ICDAR 2003 database of scene text images and outperforms state-of-the-art approaches.
Complete list of metadata

Cited literature [15 references]  Display  Hide  Download
Contributor : Pascale Sébillot Connect in order to contact the contributor
Submitted on : Monday, November 19, 2012 - 7:03:27 PM
Last modification on : Wednesday, June 16, 2021 - 3:35:01 AM
Long-term archiving on: : Thursday, February 21, 2013 - 11:45:08 AM


Files produced by the author(s)


  • HAL Id : hal-00753908, version 1


Khaoula Elagouni, Christophe Garcia, Franck Mamalet, Pascale Sébillot. Combining Multi-Scale Character Recognition and Linguistic Knowledge for Natural Scene Text OCR. 10th IAPR International Workshop on Document Analysis Systems, DAS, Mar 2012, Gold Coast, Queensland, Australia. pp.120-124. ⟨hal-00753908⟩



Record views


Files downloads