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. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1145/1374296.1374327 | MobiMedia |
Keywords | Field | DocType |
initial annotation,image region,fuzzy spatial relation,specific domain,approach coupling support vector,genetic algorithm,beach vacation domain,domain knowledge,image analysis,implicit information,ontologies,spatial relation,object recognition,support vector machine | Spatial relation,Annotation,Pattern recognition,Domain knowledge,Computer science,Support vector machine,Fuzzy logic,Artificial intelligence,Ambiguity,Genetic algorithm,Cognitive neuroscience of visual object recognition | Conference |
ISBN | Citations | PageRank |
1-59593-517-7 | 1 | 0.38 |
References | Authors | |
13 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
G. Th. Papadopoulos | 1 | 43 | 2.42 |
P. Panagi | 2 | 1 | 0.38 |
S. Dasiopoulou | 3 | 277 | 18.37 |