There is an accelerating demand to access and work over the visual content of documents. Because of the insufficiency of text-based techniques for storing this data, content-based image retrieval (CBIR) systems have become a promising field.
Due this fact, in this study a CBIR system is implemented that is Mpeg-7 compliant and ORDBMS based. The database contains images and their content summaries that are parsed from XML files. The summaries describe their dominant colors, color histograms, color spaces and labels, in order to be compliant with Mpeg-7. The query process requires only the summary not the image itself.
Software implementation of the system is based on JSP and servlet technologies using Oracle database and Tomcat web server. It is shown that the usage of these tools in the proposed architecture brings security, portability, and speed.
| Identifer | oai:union.ndltd.org:METU/oai:etd.lib.metu.edu.tr:http://etd.lib.metu.edu.tr/upload/1260247/index.pdf |
| Date | 01 January 2004 |
| Creators | Guner, Kani Kerim |
| Contributors | Bozdagi Akar, Gozde |
| Publisher | METU |
| Source Sets | Middle East Technical Univ. |
| Language | English |
| Detected Language | English |
| Type | M.S. Thesis |
| Format | text/pdf |
| Rights | To liberate the content for public access |
Page generated in 0.0019 seconds