Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

DOG I : An annotation system for images of dog breeds

Petrakis Evripidis, Pyrros Koletsis, Antonios Dimas

Full record


URI: http://purl.tuc.gr/dl/dias/E89F4241-EAB0-460E-8456-E618895B2434
Year 2012
Type of Item Conference Paper Abstract
License
Details
Bibliographic Citation Antonios Dimas, Pyrros Koletsis, Euripides G.M. Petrakis, "DOGI: An Annotation System for Images of Dog Breeds", in 9th International Conference on Image Analysis and Recognition (ICIAR'2012), 2012, pp. 410-417. doi:10.1007/978-3-642-31295-3_48 https://doi.org/10.1007/978-3-642-31295-3_48
Appears in Collections

Summary

DOG I (Dog OntoloGy Image annotator) is a complete and fully automated semantic annotation system for images of dog breeds. Annotation relies on feature extraction and on associating low-level features with image concepts in an ontology. Because general purpose ontologies for all image types are not yet available, we choose the problem of annotating images of dog breeds as a case study and for the evaluation of our methodology. Nevertheless, DOG I can be adapted to more image types provided that an ontology for a new image domain becomes available. Therefore, DOG I offers an ideal test-bed for experimentation and sets the grounds for the annotation and evaluation of virtually any image type. Evaluation results are realized using images collected from the Web. Almost 95% of the test images is correctly annotated (i.e., DOG I identified their class correctly). DOG I is accessible on the Internet.

Services

Statistics