Edge detector evaluation using empirical ROC curves

被引：224
作者：
Bowyer, K
Kranenburg, C
Dougherty, S
机构：
[1] Univ Notre Dame, Dept Comp Sci & Engn, Notre Dame, IN 46556 USA
[2] Univ S Florida, Dept Comp Sci & Engn, Tampa, FL 33620 USA
来源：
COMPUTER VISION AND IMAGE UNDERSTANDING | 2001年 / 84卷 / 01期
基金：
美国国家科学基金会;
关键词：
performance evaluation; experimental computer vision; edge detection; comparison of algorithms;
D O I：
10.1006/cviu.2001.0931
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
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. (C) 2001 Elsevier Science (USA).
引用
收藏
页码：77 / 103
页数：27
相关论文
共 41 条
[1]   QUANTITATIVE DESIGN AND EVALUATION OF ENHANCEMENT-THRESHOLDING EDGE DETECTORS [J].
ABDOU, IE ;
PRATT, WK .
PROCEEDINGS OF THE IEEE, 1979, 67 (05) :753-763
[2]  
[Anonymous], SPIE APPL ARTIFICIAL
[3]   EDGE FOCUSING [J].
BERGHOLM, F .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1987, 9 (06) :726-741
[4]   A geometric approach to edge detection [J].
Bezdek, JC ;
Chandrasekhar, R ;
Attikiouzel, Y .
IEEE TRANSACTIONS ON FUZZY SYSTEMS, 1998, 6 (01) :52-75
[5]   Robust anisotropic diffusion [J].
Black, MJ ;
Sapiro, G ;
Marimont, DH ;
Heeger, D .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 1998, 7 (03) :421-432
[6]  
BLAND M, 1995, MED STAT
[7]   Edge detector evaluation using empirical ROC curves [J].
Bowyer, K ;
Kranenburg, C ;
Dougherty, S .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2001, 84 (01) :77-103
[8]  
Bowyer K., 1998, EMPIRICAL EVALUATION
[9]  
Bryant D. J., 1979, Proceedings of the 1979 IEEE Computer Society Conference on Pattern Recognition and Image Processing, P138
[10]   A COMPUTATIONAL APPROACH TO EDGE-DETECTION [J].
CANNY, J .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1986, 8 (06) :679-698
12345