Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Choosing the number of labels in image segmentation

Liu, Y., Draper, J. H., Gay, A. P., Howarth, C. N. and Martin, Ralph Robert 2011. Choosing the number of labels in image segmentation. Presented at: 2011 IEEE 16th International Conference on Emerging Technologies & Factory Automation, Toulouse, France, 5-9 Sept. 2011. Published in: Mammeri, Z. ed. 2011 IEEE 16th Conference on Emerging Technologies & Factory Automation (ETFA), 5-9 Sept. 2011, Toulouse, France. Los Alamitos, CA: IEEE, 10.1109/ETFA.2011.6059090

Full text not available from this repository.


Image segmentation is a fundamental yet challenging step during image analysis. In this paper we propose a novel method for choosing the number of labels during automatic image segmentation. It minimizes an objective function based on the number of labels, the segmentation errors, and consistency of labels between neighboring pixels. An experimental study on representative data shows encouraging results.

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: 9781457700170
Last Modified: 04 Jun 2017 02:53

Actions (repository staff only)

Edit Item Edit Item