Automatic generation of consensus ground truth for the comparison of edge detection techniques

被引：40

作者：

Fernandez-Garcia, N. L. ^{[1
]}

Carmona-Poyato, A. ^{[1
]}

Medina-Carnicer, R. ^{[1
]}

Madrid-Cuevas, F. J. ^{[1
]}

机构：

[1] Univ Cordoba, Dept Informat & Anal Numerico, E-14071 Cordoba, Spain

来源：

IMAGE AND VISION COMPUTING | 2008年 / 26卷 / 04期

关键词：

consensus ground truth; empirical discrepancy measurement; edge detection;

D O I：

10.1016/j.imavis.2007.06.009

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Two new methods are proposed to automatically generate consensus ground truth for real images: Minimean and Minimax methods. These methods and a version of the Yitzhaky and Peli method have been used to provide ground truth for the comparison of edge detection techniques. The developed experiments have revealed that the Minimean consensus method is suitable for the comparison of edge detectors because its results are equivalent to those obtained with artificial or manual ground truth. (C) 2007 Elsevier B.V. All rights reserved.

引用

页码：496 / 511

页数：16

共 45 条

[11] A NOTE ON THE GRADIENT OF A MULTIIMAGE [J].

DIZENZO, S .

COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1986, 33 (01) :116-125

[12]

DOUGHERTY S, 1998, EMPIRICAL EVALUATION, P211

[13] A stereo confidence metric using single view imagery with comparison to five alternative approaches [J].

Egnal, G ;

Mintz, M ;

Wildes, RP .

IMAGE AND VISION COMPUTING, 2004, 22 (12) :943-957

[14] Characterization of empirical discrepancy evaluation measures [J].

Fernández-García, NL ;

Medina-Carnicer, R ;

Carmona-Poyato, A ;

Madrid-Cuevas, FJ ;

Prieto-Villegas, M .

PATTERN RECOGNITION LETTERS, 2004, 25 (01) :35-47

[15]

FORSTNER W, 1996, WORKSH PERFORMANCE C, P59

[16]

GAUCH J, 1992, VISUAL COMMUNICATION, V1818, P1168

[17] The Amsterdam Library of Object Images [J].

Geusebroek, JM ;

Burghouts, GJ ;

Smeulders, AWM .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 2005, 61 (01) :103-112

[18] Contour detection based on nonclassical receptive field inhibition [J].

Grigorescu, C ;

Petkov, N ;

Westenberg, MA .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2003, 12 (07) :729-739

[19]

HARALICK RM, 1994, CVGIP-IMAG UNDERSTAN, V60, P245, DOI 10.1006/cviu.1994.1055

[20] Comparison of edge detectors - A methodology and initial study [J].

Heath, M ;

Sarkar, S ;

Sanocki, T ;

Bowyer, K .

COMPUTER VISION AND IMAGE UNDERSTANDING, 1998, 69 (01) :38-54

← 1 2 3 4 5 →