Re-ranking algorithm using post-retrieval clustering for content-based image retrieval
| Autor: | Yunju Baek, Heung-Kyu Lee, Gunhan Park |
|---|---|
| Rok vydání: | 2005 |
| Předmět: |
Fuzzy clustering
business.industry InformationSystems_INFORMATIONSTORAGEANDRETRIEVAL Correlation clustering ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Pattern recognition Library and Information Sciences Management Science and Operations Research computer.software_genre Content-based image retrieval Computer Science Applications Hierarchical clustering ComputingMethodologies_PATTERNRECOGNITION CURE data clustering algorithm Media Technology Canopy clustering algorithm Data mining Artificial intelligence business Cluster analysis computer Algorithm k-medians clustering Information Systems Mathematics |
| Zdroj: | Information Processing & Management. 41:177-194 |
| ISSN: | 0306-4573 |
| DOI: | 10.1016/j.ipm.2003.08.002 |
| Popis: | In this paper, we propose a re-ranking algorithm using post-retrieval clustering for content-based image retrieval (CBIR). In conventional CBIR systems, it is often observed that images visually dissimilar to a query image are ranked high in retrieval results. To remedy this problem, we utilize the similarity relationship of the retrieved results via post-retrieval clustering. In the first step of our method, images are retrieved using visual features such as color histogram. Next, the retrieved images are analyzed using hierarchical agglomerative clustering methods (HACM) and the rank of the results is adjusted according to the distance of a cluster from a query. In addition, we analyze the effects of clustering methods, querycluster similarity functions, and weighting factors in the proposed method. We conducted a number of experiments using several clustering methods and cluster parameters. Experimental results show that the proposed method achieves an improvement of retrieval effectiveness of over 10% on average in the average normalized modified retrieval rank (ANMRR) measure. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect