Title: | From contours to ground truth: how to evaluate edge detectors by filtering |
Authors: | Abdulrahman, Hasan Magnier, Baptiste Montesinos, Philippe |
Citation: | Journal of WSCG. 2017, vol. 25, no. 2, p. 133-142. |
Issue Date: | 2017 |
Publisher: | Václav Skala - UNION Agency |
Document type: | článek article |
URI: | wscg.zcu.cz/WSCG2017/!_2017_Journal_WSCG-No-2.pdf http://hdl.handle.net/11025/26291 |
ISSN: | 1213-6972 (print) 1213-6980 (CD-ROM) 1213-6964 (on-line) |
Keywords: | detekce hran;zemní skutečnost;kontrolované hodnocení;měřená vzdálenost;objektivní hodnocení |
Keywords in different language: | edge detection;ground truth;supervised evaluation;distance measure;objective evaluation |
Abstract in different language: | 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. |
Rights: | © Václav Skala - UNION Agency |
Appears in Collections: | Volume 25, Number 2 (2017) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Abdulrahman.pdf | Plný text | 2,19 MB | Adobe PDF | View/Open |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/26291
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.