A new reference-based measure for objective edge map evaluation

Abstract

Edge detection is an important preprocessing task which has been used extensively in image processing. As many applications heavily rely on edge detection, effective and objective edge detection evaluation is crucial. Objective edge map evaluation measures are an important means of assessing the performance of edge detectors under various circumstances and in determining the most suitable edge detector or edge detector parameters. Quantifiable criteria for objective edge map evaluation are established relative to a ground truth, and the weaknesses and limitations in the Pratt's Figure of Merit (FOM), the objective reference-based edge map evaluation standard, are discussed. Based on the established criteria, a new reference-based measure for objective edge map evaluation is presented. Experimental results using synthetic images and their ground truths show that the new measure for objective edge map evaluation outperforms Pratt's FOM visually as it takes into account more features in its evaluation.