Adaptive Pyramid and Semantic Graph: Knowledge Driven Segmentation

A method allowing to integrate syntactic and semantic approaches in an automatic segmentation process is described. This integration is possible thanks to the formalism of graphs. The proposed method checks the relevancy of merging criteria used in an adaptive pyramid by matching the obtained segmentation with a semantic graph describing the objects that we look for. This matching is performed by checking the arcconsistency with bilevel constraints of the chosen semantic graph. The efficiency of this approach is experimented on synthetic and real images. Keywords Segmentation, semantic graph, adaptive pyramid.

• Type: Conference
• Year: 2005
• Where: GBRPR
• Authors: Aline Deruyver, Yann Hodé, Eric Laemmer, Jean-Michel Jolion
• Keywords: Adaptive Pyramid, Automatic Segmentation Process, GBRPR 2005, Semantic Graph