Skip to Main content Skip to Navigation
New interface
Conference papers

Text/graphic separation using a sparse representation with multi-learned dictionaries

Thanh Ha Do 1, * Salvatore Tabbone 1 Oriol Ramos Terrades 2 
* Corresponding author
1 QGAR - Querying Graphics through Analysis and Recognition
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : In this paper, we propose a new approach to extract text regions from graphical documents. In our method, we first empirically construct two sequences of learned dictionaries for the text and graphical parts respectively. Then, we compute the sparse representations of all different sizes and non-overlapped document patches in these learned dictionaries. Based on these representations, each patch can be classified into the text or graphic category by comparing its reconstruction errors. Same-sized patches in one category are then merged together to define the corresponding text or graphic layers which are combined to createfinal text/graphic layer. Finally, in a post-processing step, text regions are further filtered out by using some learned thresholds.
Document type :
Conference papers
Complete list of metadata

Cited literature [8 references]  Display  Hide  Download
Contributor : Thanh Ha Do Connect in order to contact the contributor
Submitted on : Tuesday, December 4, 2012 - 9:15:57 AM
Last modification on : Saturday, October 16, 2021 - 11:26:09 AM
Long-term archiving on: : Tuesday, March 5, 2013 - 3:49:25 AM


Files produced by the author(s)


  • HAL Id : hal-00759554, version 1



Thanh Ha Do, Salvatore Tabbone, Oriol Ramos Terrades. Text/graphic separation using a sparse representation with multi-learned dictionaries. 21st International Conference on Pattern Recognition - ICPR 2012, Nov 2012, Tsukuba, Japan. ⟨hal-00759554⟩



Record views


Files downloads