A genetic algorithm approach to ontology-driven semantic image analysis
P. Panagi, Stamatia Dasiopoulou, Georgios Th. Papadopoulos, Ioannis Yiannis Kompatsiaris, Michael Gerassimos Strintzis · 2006
In this paper, a hybrid approach coupling ontologies and a genetic algorithm is presented for realizing knowledge-assisted semantic image analysis. The employed domain knowledge considers both high-level information referring to objects of the domain of interest and their spatial relations, and low-level information in terms of prototypical low-level visual descriptors. To account for the inherent in visual information ambiguity, fuzzy spatial relations have been employed and the corresponding domain ontology definitions are obtained though training. A genetic algorithm is applied to decide the most plausible annotation. Experiments with images from the beach vacation domain demonstrate the performance of the proposed approach.