ABSTRACT

In the recent years, there has been a strong growth in the number and the size of image databases. Large image databases typically consist of different types of photographic archives. Also the number of industrial image databases has grown remarkably due to a rapid increase of industrial imaging systems. Image databases often need to organize the images automatically by their content. Clustering operations can be applied for the content based organization of the images. In the present study an efficient method is proposed for the clustering of large image databases. The method is based on hierarchical clustering of the image database using grid. In this paper, the grid-based clustering methods are applied to fast image database browsing and retrieval. Proposed clustering methods are tested using real image databases.

Keywords: image database, clustering, retrieval, browsing