Bag-of-Bags of Words - Irregular Graph Pyramids vs Spatial Pyramid Matching for Image Retrieval

Abstract : This paper presents a novel approach, named bag-of-bags of words (BBoW), to address the problem of Content-Based Image Retrieval (CBIR) from image databases. The proposed bag-of-bags of words model extends the classical bag-of-words (BoW) model. An image is represented as a connected graph of local features on a regular grid. Then irregular partitions (subgraphs) of images are further built via Normalized Cuts. Each subgraph in the partition is then represented by its own signature. Compared to existing methods for image retrieval, such as Spatial Pyramid Matching (SPM), the BBoW model does not assume that similar parts of a scene always appear at the same location in images of the same category. The extension of the proposed model to pyramid gives rise to a method we name irregular pyramid matching (IPM). The experiments demonstrate the strength of our method for image retrieval when the partitions are stable across an image category. The statistical analysis of subgraphs is discussed in the paper.
Type de document :
Communication dans un congrès
4th International Conference on Image Processing Theory, Tools and Applications, Oct 2014, Paris, France. paper 470, 2014
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01002837
Contributeur : Yi Ren <>
Soumis le : vendredi 6 juin 2014 - 18:38:24
Dernière modification le : mardi 28 octobre 2014 - 18:57:30

Identifiants

  • HAL Id : hal-01002837, version 1

Collections

Citation

Yi Ren, Aurélie Bugeau, Jenny Benois-Pineau. Bag-of-Bags of Words - Irregular Graph Pyramids vs Spatial Pyramid Matching for Image Retrieval. 4th International Conference on Image Processing Theory, Tools and Applications, Oct 2014, Paris, France. paper 470, 2014. 〈hal-01002837〉

Partager

Métriques

Consultations de la notice

198