An indexing method for graphical documents

Salvatore Tabbone (1) , Daniel Zuwala (1)

1 QGAR - Querying Graphics through Analysis and Recognition

In this paper, a method to browse symbols into graphi- cal documents is presented. More precisely, we propose a combined filtering and indexing mechanism that retrieves in an efficient way the most similar symbols to a given input query. For a database of 200000 symbols the retrieval time has been divided by a factor of 4, 5 compared to a linear search.

Mots clés: indexing; graphical documents; document processing

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Salvatore Tabbone, Daniel Zuwala. An indexing method for graphical documents. 9th International Conference on Document Analysis and Recognition - ICDAR'07, IAPR, Sep 2007, Curitiba, Brazil. pp.789 - 793, ⟨10.1109/ICDAR.2007.4377023⟩. ⟨inria-00204098⟩