期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2008
卷号：8
期号：1
页码：54-63
出版社：International Journal of Computer Science and Network Security
摘要：The paper focuses on a low-dimensional color-based indexing technique for achieving efficient and effective retrieval performance. We have implemented the technique of retrieval of images from databases based on color feature extracted from each region/regions of an image represented by dominant or representative color descriptor. Each image is segmented using Mean Shift algorithm, a robust clustering technique to extract color feature of a region of interest. Image databases have been designed and the image region features are ingested into them. Indexing data structures are designed to support basic operations on image databases such as search, insertion, and deletion. Search efficiency is considered as the most important aspect because search is normally carried out on-line. The new algorithm cluster-based R*-tree indexing is proposed and compared the efficiency with R* -tree and sequential search. The accuracy of the retrieval system is measured and compared the results. Experimental results show the high performance of the proposed method. The toolbox is developed in JAVA to incorporate all these modules and retrieve images based on query-by-example.
