Choosing the number of labels in image segmentation
Yansong Liu, John H. Draper, Alan P. Gay, Catherine J. Howarth, R. R. Martin · 2011
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.