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

Search

Browse

My Space

SIA: semantic image annotation using ontologies and image content analysis

Petrakis Evripidis, Pyrros Koletsis

Full record


URI: http://purl.tuc.gr/dl/dias/7FAA2A4C-376E-40CF-BF29-D82199DCF084
Year 2010
Type of Item Conference Full Paper
License
Details
Bibliographic Citation Pyrros Koletsis, Euripides G.M. Petrakis, "SIA: Semantic Image Annotation using Ontologies and Image Content Analysis" , in 7th Intern. Conference on Image Analysis and Recognition (ICIAR' 2010), 2010, pp. 373-384. doi: 10.1007/978-3-642-13772-3_38 https://doi.org/10.1007/978-3-642-13772-3_38
Appears in Collections

Summary

We introduce SIA, a framework for annotating images automatically using ontologies. An ontology is constructed holding characteristics from multiple information sources including text descriptions and low-level image features. Image annotation is implemented as a retrieval process by comparing an input (query) image with representative images of all classes. Handling uncertainty in class descriptions is a distinctive feature of SIA. Average Retrieval Rank (AVR) is applied to compute the likelihood of the input image to belong to each one of the ontology classes. Evaluation results of the method are realized using images of 30 dog breeds collected from the Web. The results demonstrated that almost 89% of the test images are correctly annotated (i.e., the method identified their class correctly).

Services

Statistics