Structural and Visual Comparisons for Web Page Archiving - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Structural and Visual Comparisons for Web Page Archiving

Marc Teva Law
  • Fonction : Auteur
  • PersonId : 972375
Nicolas Thome
Stéphane Gançarski
Matthieu Cord

Résumé

In this paper, we propose a Web page archiving system that combines state-of-the-art comparison methods based on the source codes of Web pages, with computer vision techniques. To detect whether successive versions of a Web page are similar or not, our system is based on: (1) a combination of structural and visual comparison methods embedded in a statistical discriminative model, (2) a visual similarity measure designed for Web pages that improves change detection, (3) a supervised feature selection method adapted to Web archiving. We train a Support Vector Machine model with vectors of similarity scores between successive versions of pages. The trained model then determines whether two versions, defined by their vector of similarity scores, are similar or not. Experiments on real archives validate our approach.
Fichier non déposé

Dates et versions

hal-01272800 , version 1 (11-02-2016)

Identifiants

Citer

Marc Teva Law, Nicolas Thome, Stéphane Gançarski, Matthieu Cord. Structural and Visual Comparisons for Web Page Archiving. 12th edition of the ACM Symposium on Document Engineering, DocEng'12, Sep 2012, Paris, France. pp.117-120, ⟨10.1145/2361354.2361380⟩. ⟨hal-01272800⟩
99 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More