From Contours to Ground Truth: How to Evaluate Edge Detectors by Filtering

Edge detection remains a crucial stage in numerous image processing applications. Thus, an edge detection technique needs to be assessed before use it in a computer vision task. As dissimilarity evaluations depend strongly of a ground truth edge map, an inaccurate datum in terms of localization could advantage inaccurate precise edge detectors or/and favor inappropriate a dissimilarity evaluation measure. Hence, in this work, we demonstrate how to label these ground truth data in a semi-automatic way. Moreover, several referenced-based boundary detection evaluations are detailed and applied toward an objective assessment. Thus, each measure is compared by varying the threshold of the thin edges. Indeed, theoretically, the minimum score of the measure corresponds to the best edge map, compared to the ground truth. Finally, experiments on many images using six edge detectors show that the new ground truth database allows an objective comparison of numerous dissimilarity measures.