Title :
Choosing the number of labels in image segmentation
Author :
Liu, Y. ; Draper, J.H. ; Gay, A.P. ; Howarth, C.N. ; Martin, R.R.
Author_Institution :
Aberystwyth Univ., Aberystwyth, UK
Abstract :
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.
Keywords :
image segmentation; automatic image segmentation; image analysis; objective function; segmentation errors; Databases; Histograms; Image color analysis; Image segmentation; Labeling; Markov processes; Optimization;
Conference_Titel :
Emerging Technologies & Factory Automation (ETFA), 2011 IEEE 16th Conference on
Conference_Location :
Toulouse
Print_ISBN :
978-1-4577-0017-0
Electronic_ISBN :
1946-0740
DOI :
10.1109/ETFA.2011.6059090
