CAViz, exploration interactive des résultats de l'analyse factorielle des correspondances pour des images

Khang-Nguyen Pham 1 Annie Morin 2 Patrick Gros 2
2 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : We propose an interactive graphical tool, CAViz, which allows to visualize and to extract knowledge from FCA results on images. Originally the FCA is for the analysis of contingency tables. For adapting FCA on images, we first define the "visual" words in images. These words are constructed from local descriptors (SIFT, Scale Invariant Feature Transform) in images. CAViz projects clouds of points in factorial plans and allows viewing and extracting interesting information such as: characterizing words, important factors using FCA relevant indicators (representation quality and contribution to the inertia). An application to the Caltech4 database shows the interest of CAViz for image mining.
Document type :
Journal articles
Complete list of metadatas

https://hal.inria.fr/inria-00603305
Contributor : Patrick Gros <>
Submitted on : Friday, June 24, 2011 - 3:38:09 PM
Last modification on : Friday, November 16, 2018 - 1:22:21 AM

Links full text

Identifiers

Citation

Khang-Nguyen Pham, Annie Morin, Patrick Gros. CAViz, exploration interactive des résultats de l'analyse factorielle des correspondances pour des images. Revue des sciences et technologies de l'Information (Série visualisation et extraction des connaissances), Hermes, 2008, 22 (2-3), pp.489-502. ⟨10.3166/ria.22.489-502⟩. ⟨inria-00603305⟩

Share

Metrics

Record views

206