Symbol descriptor based on shape context and vector model of information retrieval

Thi Oanh Nguyen (1) , Salvatore Tabbone (1) , Oriol Ramos Terrades (1)

1 QGAR - Querying Graphics through Analysis and Recognition

In this paper we present an adaptative method for graphic symbol representation based on shape contexts. The proposed descriptor is invariant under classical geometric transforms (rotation, scale) and based on interest points. To reduce the complexity of matching a symbol to a large set of candidates we use the popular vector model for information retrieval. In this way, on the set of shape descriptors we build a visual vocabulary where each symbol is retrieved on visual words. Experimental results on complex and occluded symbols show that the approach is very promising.

Mots clés: symbol descriptor; graphic symbol; visual word; vector model

Domaines: Traitement du texte et du document; Traitement des images [eess.IV]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Thi Oanh Nguyen, Salvatore Tabbone, Oriol Ramos Terrades. Symbol descriptor based on shape context and vector model of information retrieval. The 8th IAPR International Workshop on Document Analysis Systems, Sep 2008, Nara, Japan. pp.191-197, ⟨10.1109/DAS.2008.58⟩. ⟨hal-00334432⟩