Semantic image segmentation based on spatial relationships and inexact graph matching - Laboratoire Traitement et Communication de l'Information Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Semantic image segmentation based on spatial relationships and inexact graph matching

Résumé

We propose a method for semantic image segmentation, combining a deep neural network and spatial relationships between image regions, encoded in a graph representation of the scene. Our proposal is based on inexact graph matching, formulated as a quadratic assignment problem applied to the output of the neural network. The proposed method is evaluated on a public dataset used for segmentation of images of faces and compared to the U-Net deep neural network that is widely used for semantic segmentation. Preliminary results show that our approach is promising. In terms of Intersection-over-Union of region bounding boxes, the improvement is of 2.4% in average, compared to U-Net, and up to 24.4% for some regions. Further improvements are observed when reducing the size of the training dataset (up to 8.5% in average).
Fichier principal
Vignette du fichier
2020IPTA.pdf (1.53 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02916165 , version 1 (16-12-2020)

Identifiants

Citer

Jérémy Chopin, Jean-Baptiste Fasquel, Harold Mouchère, R. Dayot, Isabelle Bloch. Semantic image segmentation based on spatial relationships and inexact graph matching. International Conference on Image Processing Theory, Tools and Applications (IPTA), Nov 2020, Paris, France. ⟨10.1109/IPTA50016.2020.9286611⟩. ⟨hal-02916165⟩
257 Consultations
167 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More