Skip to Main content Skip to Navigation
Conference papers

Modèle de langue visuel pour la reconnaissance de scènes

Abstract : We describe here a method to use a graph language modeling approach for imageretrieval and image categorization. Since photographic images are 2D data, we first use im- age regions (mapped to automatically induced concepts) and then spatial relationships between these regions to build a complete image graph representation. Our method deals with different scenarios, where isolated images or groups of images are used for training or testing. The results obtained on an image categorization problem show (a) that the procedure to automatically induce concepts from an image is effective, and (b) that the use of spatial relationships, in addition to concepts, for representing an image content helps improve the classifier accuracy. This approach extends the language modeling approach to information retrieval to the problem of graph-based image retrieval and categorization, without considering image annotations.
Document type :
Conference papers
Complete list of metadata

Cited literature [16 references]  Display  Hide  Download

https://hal.inria.fr/hal-00954023
Contributor : Marie-Christine Fauvet <>
Submitted on : Monday, March 3, 2014 - 12:22:34 PM
Last modification on : Tuesday, June 1, 2021 - 2:08:07 PM
Long-term archiving on: : Saturday, May 31, 2014 - 10:52:25 AM

File

99.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00954023, version 1

Citation

Trong-Ton Pham, Loic Maisonnasse, Philippe Mulhem, Eric Gaussier. Modèle de langue visuel pour la reconnaissance de scènes. CORIA, 2009, Giens, France. pp.99-112. ⟨hal-00954023⟩

Share

Metrics

Record views

483

Files downloads

157