Choosing the number of labels in image segmentation

Yonghuai Liu, J. H. Draper, Alan Philip Gay, Catherine Howarth, R. R. Martin

Research output: Contribution to conferencePaper


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.
Original languageEnglish
Publication statusPublished - 2011
EventEmerging Technologies and Factory Automation - Toulouse, France
Duration: 05 Sept 201109 Sept 2011
Conference number: 16


ConferenceEmerging Technologies and Factory Automation
Abbreviated titleETFA-2011
Period05 Sept 201109 Sept 2011


Dive into the research topics of 'Choosing the number of labels in image segmentation'. Together they form a unique fingerprint.

Cite this