A representation of contextual relationships knowledge in images
Résumé
This report is focused on the study of methods for image retrieval in collection of heterogeneous contents. The spatial relationships between entities in an image allow creating the global description of the image that we call the image context. Taking into account the contextual spatial relationships in the similarity search of images can allow improving the retrieval quality by limiting false alarms. We defined the context of image as the presence of entity categories and their spatial relationships in the image. By studying statistically the relationships between different entity categories on LabelMe, symbolic images databases of heterogeneous content, we create a cartography of their spatial relationships that can be integrated in a graph-based model of the contextual relationships, the principal contribution of this report. This graph describes the general knowledge of every entity categories. Spatial reasoning on this knowledge graph can help improving tasks of image processing such as detection and localization of an entity category by using the presence of another one. Further, this model can be applied to represent the context of an image. The similarity search based on context can be achieved by comparing the graphs, then, contextual similarity between two images is evaluated by the similarity between their graphs. This work was evaluated on the symbolic image database of LabalMe. The experiments showed its relevance for image retrieval by context.
Origine : Fichiers produits par l'(les) auteur(s)