Content based image retrieval for computed tomography images using Support Vector Machine classifier

Content based image retrieval is used as an important tool by a radiologist, as it is very useful to diagnosis a patient. A set of interested images are retrieved from a large database, which helps to narrow down the problem under examination. Database consisting various images of organs like brain, lungs, neck, and colon. Haar like features are extracted and supplied to Support Vector Machine classifier, to decide that image belongs to which organ of a body. Once, it has been classified, process enters in a next phase of retrieval. In the phase of retrieval, where two different approaches are used for feature extraction, one based on intensity and other based on Statistical moments. Images are retrieved using a similarity measure for both approaches and a comparative analysis is shown in this paper.