Text Recognition in Multimedia Documents: A Study of two Neural-based OCRs Using and Avoiding Character Segmentation

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 : Text embedded in multimedia documents represents an important semantic information that helps to automatically access the content. This paper proposes two neural-based OCRs that handle the text recognition problem in different ways. The first approach segments a text image into individual characters before recognizing them, while the second one avoids the segmentation step by integrating a multi-scale scanning scheme that allows to jointly localize and recognize characters at each position and scale. Some linguistic knowledge is also incorporated into the proposed schemes to remove errors due to recognition confusions. Both OCR systems are applied to caption texts embedded in videos and in natural scene images and provide outstanding results showing that the proposed approaches outperform the state-of-the-art methods.
Complete list of metadatas

Cited literature [49 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00867225
Contributor : Pascale Sébillot <>
Submitted on : Friday, September 27, 2013 - 5:05:09 PM
Last modification on : Tuesday, February 26, 2019 - 11:20:50 AM
Long-term archiving on : Saturday, December 28, 2013 - 4:33:06 AM

File

IJDAR_LastVersion.pdf
Files produced by the author(s)

Identifiers

Citation

Khaoula Elagouni, Christophe Garcia, Franck Mamalet, Pascale Sébillot. Text Recognition in Multimedia Documents: A Study of two Neural-based OCRs Using and Avoiding Character Segmentation. International Journal on Document Analysis and Recognition, Springer Verlag, 2014, 17 (1), pp.19-31. ⟨10.1007/s10032-013-0202-7⟩. ⟨hal-00867225⟩

Share

Metrics

Record views

2124

Files downloads

988