Automatic semantic indexing of medical images using a web ontology language for case-based image retrieval

Authors:
Gowri Allampalli-Nagaraj;Isabelle Bichindaritz
Affiliations:
University of Washington, Institute of Technology, 1900 Commerce Street, Box 358426, Tacoma, WA 98402, USA;University of Washington, Institute of Technology, 1900 Commerce Street, Box 358426, Tacoma, WA 98402, USA
Venue:
Engineering Applications of Artificial Intelligence
Year:
2009

Citing 2
Cited 2

Case-based reasoning in the health sciences: What's next?

Artificial Intelligence in Medicine
Retrieval of multimedia objects by combining semantic information from visual and textual descriptors

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II

Combinations of case-based reasoning with other intelligent methods

International Journal of Hybrid Intelligent Systems - CIMA-08
Learning semantic concepts from image database with hybrid generative/discriminative approach

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a system implemented to evaluate the retrieval efficiency of images when they are semantically indexed using a combination of a web ontology language and the low-level features of the image. Finding a similarity measure algorithm to retrieve images based on the semantic metadata can be very challenging due to diverse image content and inadequate domain-specific ontologies describing the content. The existing methods for indexing images are primarily based on text. While these methods are widely used due to their simplicity, they are not very efficient as they require a domain expert and the textual interpretations of image content vary from person to person. In our approach, we leverage sophisticated image-processing techniques to automatically extract image content information into MPEG-7 format and associate them to the existing domain ontologies developed by experts, thereby, bridging the gap between low-level features and high-level semantics. This implementation and validation experiments show that a high retrieval accuracy rate is obtained when all the image descriptors are combined with an ontology while building the semantic metadata for indexing images.