Design, Implementation and Evaluation of Two Medical Content based Image Retrieval Systems

Francesco Maiorana and Carmelo Pino

Keywords

Medical Content Based Image Retrieval, Gabor filter, Color coherence vector

Abstract

This paper presents the design and implementation of two Content Based Image Retrieval Systems (CBIR). The first is developed in Matlab from scratch by choosing a combination of feature extraction algorithms, texture, color and shape, and by fine tuning the parameter for optimal performance. The system is also extended by an application of query by sketch. The second is based on the well known and robust Oracle 10^g Data Base Management System by using the Oracle InterMedia module. The evaluation of the two systems is performed in the context of medical image retrieval highlighting advantages and drawbacks of the two approaches

Important Links:

• DOI: 10.2316/P.2012.764-150
• From Proceeding (764) Biomedical Engineering / 765: Telehealth / 766: Assistive Technologies - 2012

Go Back