Shape measures for image retrieval

Gagaudakis, George and Rosin, Paul L. ORCID: https://orcid.org/0000-0002-4965-3884 2001. Shape measures for image retrieval. Presented at: 2001 International Conference on Image Processing, Thessaloniki, Greece, 7-10 October 2001. Proceedings of the 2001 International Conference on Image Processing. , vol.2 IEEE, pp. 757-760. 10.1109/ICIP.2001.958604

Full text not available from this repository.

Abstract

One of the main goals in content based image retrieval (CBIR) is to incorporate shape into the process in a reliable manner. In order to overcome the difficulties of directly obtaining shape information (in particular avoiding region segmentation) we develop several shape measures that tackle the problem in an indirect manner, requiring only a minimal amount of segmentation. A histogram-based scheme is then used, maintaining low complexity with high efficiency and robustness. The obtained results showed that the synergy of the shape measures worked out providing an improvement over the colour histogram.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Publisher:	IEEE
ISBN:	0780367251
Related URLs:	Publisher
Last Modified:	18 Oct 2022 13:38
URI:	https://orca.cardiff.ac.uk/id/eprint/14694

Citation Data

Actions (repository staff only)

Edit Item