Comparison of edge detector performance through use in an object recognition task

被引：56

作者：

Shin, MC

Goldgof, DB

Bowyer, KW

机构：

[1] Univ N Carolina, Dept Comp Sci, Charlotte, NC 28223 USA

[2] Univ S Florida, Dept Comp Sci & Engn, Tampa, FL 33620 USA

[3] Univ Notre Dame, Dept Comp Sci & Engn, Notre Dame, IN 46556 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：

Algorithms - Computer vision - Object recognition - Performance;

D O I：

10.1006/cviu.2001.0932

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents an empirical evaluation methodology for edge detectors. Edge detector performance is measured using a particular edge-based object recognition algorithm as a "higher-level" task. A detector's performance is ranked according to the object recognition performance that it generates. We have used a challenging train and test dataset containing 110 images of jeep-like images. Six edge detectors are compared and results suggest that (1) the SUSAN edge detector performs best and (2) the ranking of various edge detectors is different from that found in other evaluations. (C) 2001 Elsevier Science (USA).

引用

页码：160 / 178

页数：19

共 15 条

[1] HUMAN PAPILLOMAVIRUS TYPE-16 IN INTRAEPITHELIAL NEOPLASIA (BOWENOID PAPULOSIS) AND COEXISTENT INVASIVE-CARCINOMA OF THE VULVA [J].

BERGERON, C ;

NAGHASHFAR, Z ;

CANAAN, C ;

SHAH, K ;

FU, Y ;

FERENCZY, A .

INTERNATIONAL JOURNAL OF GYNECOLOGICAL PATHOLOGY, 1987, 6 (01) :1-11

[2]

BLACK M, 1998, IEEE T IMAGE PROCESS, V7

[3]

BOWYER KW, IN PRESS COMPUT VISI

[4] A COMPUTATIONAL APPROACH TO EDGE-DETECTION [J].

CANNY, J .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1986, 8 (06) :679-698

[5]

Chang K. I., 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), P294, DOI 10.1109/CVPR.1999.786954

[6]

CHRISTENSEN H, 1997, MACHINE VISION APPL, V9

[7] A robust visual method for assessing the relative performance of edge-detection algorithms [J].

Heath, MD ;

Sarkar, S ;

Sanocki, T ;

Bowyer, KW .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1997, 19 (12) :1338-1359

[8]

HUTTENLOCHER D, IEEE C CVPR 1993, P705

[9]

PHILLISP PJ, 1999, IEEE T PATTERN ANAL, V21

[10]

ROSENTHALER L, 1992, ECCV 92, P78

← 1 2 →