A New Approach for Clustering of X-ray Images
Medical image databases are a key component in future diagnosis
and preventive medicine. Automatic clustering of medical images
plays an important role for structuring of a given medical database
as well as for searching and retrieval of biomedical images. This
paper introduces a new approach for efficient clustering of x-ray
images based on various levels of image features. Initially, for each
given x-ray image, features have been extracted from three
different levels, namely, global, local and pixel. Finally, a new
approach, a combination of k-means and hierarchical clustering
techniques, has been applied in order to cluster x-ray images. The
experimental results are also presented at the end of this paper.
Keywords: Biomedical Images, Image Clustering, Image
Databases, X-ray Images
Download Full-Text
