Research Article
A learning approach to semantic image analysis
@INPROCEEDINGS{10.1145/1374296.1374327, author={G. Th. Papadopoulos and P. Panagi and S. Dasiopoulou}, title={A learning approach to semantic image analysis}, proceedings={2nd International ICST Conference on Mobile Multimedia Communications}, publisher={ACM}, proceedings_a={MOBIMEDIA}, year={2006}, month={9}, keywords={Semantic Image Analysis Support Vector Machines (SVMs) Genetic Algorithms (GAs) Fuzzy Directional Relations Ontologies Object Recognition}, doi={10.1145/1374296.1374327} }- G. Th. Papadopoulos
P. Panagi
S. Dasiopoulou
Year: 2006
A learning approach to semantic image analysis
MOBIMEDIA
ACM
DOI: 10.1145/1374296.1374327
Abstract
In this paper, a learning approach coupling Support Vector Machines (SVMs) and a Genetic Algorithm (GA) is presented for knowledge-assisted semantic image analysis in specific domains. Explicitly defined domain knowledge under the proposed approach includes objects of the domain of interest and their spatial relations. SVMs are employed using low-level features to extract implicit information for each object of interest via training in order to provide an initial annotation of the image regions based solely on visual features. To account for the inherent visual information ambiguity, fuzzy spatial relations along with the previously computed initial annotations are supplied to a genetic algorithm, which decides on the globally most plausible annotation. Experiments with images of the beach vacation domain demonstrate the performance of the proposed approach.
