Hol, M. and Kalsbeek F.E. (2005) Cortina 2005. Master's Thesis / Essay, Computing Science.
|
Text
Infor_Ma_2005_FKalsbeek.CV.pdf - Published Version Download (3MB) | Preview |
Abstract
Searching for images in a large scale database with nothing but keywords might not be optimal. Images are better described by their visual content rather than by keywords. Currently, the majority of the existing content based image retrieval systems rely on small, sometimes artificial, image databases. We propose a large scale content based image retrieval system with an initial keyword based image search. The visual information is extracted from images based on three features: shape, color and texture. To cope with the scalability, several measures have been taken like clustering and the use of categories. The result is a scalable system that works well for images which are distinct in one or more of the three features. For more complex images, future work should involve image segmentation
| Item Type: | Thesis (Master's Thesis / Essay) |
|---|---|
| Degree programme: | Computing Science |
| Thesis type: | Master's Thesis / Essay |
| Language: | English |
| Date Deposited: | 15 Feb 2018 07:30 |
| Last Modified: | 15 Feb 2018 07:30 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/8911 |
Actions (login required)
 |
View Item |