Image contextual representation and matching through hierarchies and higher order graphs

Abstract : We present a region matching algorithm which establishes correspondences between regions from two segmented images. An abstract graph-based representation conceals the image in a hierarchical graph, exploiting the scene properties at two levels. First, the similarity and spatial consistency of the image semantic objects is encoded in a graph of commute times. Second, the cluttered regions of the semantic objects are represented with a shape descriptor. Many-to-many matching of regions is specially challenging due to the instability of the segmentation under slight image changes, and we explicitly handle it through high order potentials. We demonstrate the matching approach applied to images of world famous buildings, captured under different conditions, showing the robustness of our method to large variations in illumination and viewpoint.
Type de document :
Communication dans un congrès
21st International Conference on Pattern Recognition - ICPR 2012, Nov 2012, Tsukuba, Japan. pp.2664 - 2667, 2012
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00856295
Contributeur : Enzo Ferrante <>
Soumis le : vendredi 30 août 2013 - 17:29:31
Dernière modification le : mardi 5 février 2019 - 13:52:14

Identifiants

  • HAL Id : hal-00856295, version 1

Collections

Citation

Jose Rubio, Joan Serrat, Antonio López, Nikos Paragios. Image contextual representation and matching through hierarchies and higher order graphs. 21st International Conference on Pattern Recognition - ICPR 2012, Nov 2012, Tsukuba, Japan. pp.2664 - 2667, 2012. 〈hal-00856295〉

Partager

Métriques

Consultations de la notice

165