Edge Detector Evaluation Using Empirical ROC Curves

We demonstrate a method for evaluating edge detector performance based on receiver operating characteristic (ROC) curves. Edge detector output is matched against ground truth to count true positive and false positive edge pixels. A detector's parameter settings are trained to give a best ROC cu...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computer vision and image understanding Jg. 84; H. 1; S. 77 - 103
Hauptverfasser: Bowyer, Kevin, Kranenburg, Christine, Dougherty, Sean
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Inc 01.10.2001
Schlagworte:
performance evaluation
edge detection
experimental computer vision
comparison of algorithms
ISSN:1077-3142, 1090-235X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We demonstrate a method for evaluating edge detector performance based on receiver operating characteristic (ROC) curves. Edge detector output is matched against ground truth to count true positive and false positive edge pixels. A detector's parameter settings are trained to give a best ROC curve on one image and then tested on separate images. We compute aggregate ROC curves based on 1 set of 50 object images and another set of 10 aerial images. We analyze the performance of 11 different edge detectors reported in the literature.
Bibliographie:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:1077-3142
1090-235X
DOI:10.1006/cviu.2001.0931