Evaluation of segmentation quality for the geometrical active contour method

Abstract

A new measure of quality is proposed for evaluating the performance of geometrical active segmentation based on level-set method's. The technique is intended for the evaluation of the segmented image and features objective assessment of discrepancy with the theoretical contours, in tandem with subjective visual evaluation using F-measure criteria. The proposed mathematical model is extremely simple, even from the perspective of computational cost. Encouraging results were obtained for a selection of test images, especially in relation to other recently proposed and/or currently employed quality measures in medical image segmentation area.