Perceptive Vision for Headline Localisation in Bangla Handwritten Text Recognition

Aurélie Lemaitre 1 B.B. Chaudhuri 2 Bertrand Coüasnon 1
1 IMADOC - Interprétation et Reconnaissance d’Images et de Documents
UR1 - Université de Rennes 1, INSA Rennes - Institut National des Sciences Appliquées - Rennes, CNRS - Centre National de la Recherche Scientifique : UMR6074
Abstract : In this paper, we propose to give tools for Bangla handwriting recognition. We present a mechanism to segment documents into text lines and words, and more specifically to detect headline position in each word. Indeed, this headline is an horizontal line on the upper part of most of characters, which is characteristic of Bangla writing. Its localisation is a new approach that can improve text recognition quality. This headline is detected into words inside text lines thanks to a notion of perceptive vision: at a certain distance, text lines appear as line-segments that give the global orientation of words. Watching closer may help to give the exact position of the headline. Consequently, this work is mainly based on applying a segment extractor at different image resolutions and combining extracted information in order to compute the headlines. Our line-segment extractor is based on Kalman filtering.
Complete list of metadatas

Cited literature [6 references]  Display  Hide  Download

https://hal.inria.fr/inria-00308561
Contributor : Aurélie Lemaitre <>
Submitted on : Thursday, July 31, 2008 - 9:54:15 AM
Last modification on : Friday, November 16, 2018 - 1:23:40 AM
Long-term archiving on : Thursday, June 3, 2010 - 5:10:01 PM

File

04376988.pdf
Files produced by the author(s)

Identifiers

Citation

Aurélie Lemaitre, B.B. Chaudhuri, Bertrand Coüasnon. Perceptive Vision for Headline Localisation in Bangla Handwritten Text Recognition. ICDAR 2007, Sep 2007, Curitiba, Brazil. ⟨10.1109/ICDAR.2007.4376988⟩. ⟨inria-00308561⟩

Share

Metrics

Record views

216

Files downloads

186