Contribution à l'interprétation d'images et vérification de la consistance d'un graphe

Abstract : In this thesis we show that symbolic reasoning associated with arc consistency checking is an efficient tool for images interpretation. We first show that this theoretical framework makes it possible to verify the spatial organization of different components of a complex object in an image. We then propose to extend the use of this framework to the selective recognition of shapes described by mathematical equations, thanks to the notion of hyper-arc consistency with bi-levels constraint. The relevance and feasibility of this approach have been validated by multiple tests. In addition, the results obtained on over-segmented images show that the proposed method is noise-resistant, even under conditions where humans (in some cases visual agnosia) may fail. These results support the interest of symbolic reasoning in image understanding.
Complete list of metadatas

Cited literature [97 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-02166274
Contributor : Abes Star <>
Submitted on : Wednesday, June 26, 2019 - 4:30:13 PM
Last modification on : Wednesday, July 10, 2019 - 11:53:35 AM

File

Hode_Yann_2018_ED269.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-02166274, version 1

Citation

Yann Hodé. Contribution à l'interprétation d'images et vérification de la consistance d'un graphe. Intelligence artificielle [cs.AI]. Université de Strasbourg, 2018. Français. ⟨NNT : 2018STRAD041⟩. ⟨tel-02166274⟩

Share

Metrics

Record views

70

Files downloads

21