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
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
收藏
页码:160 / 178
页数:19
相关论文
共 15 条
  • [1] HUMAN PAPILLOMAVIRUS TYPE-16 IN INTRAEPITHELIAL NEOPLASIA (BOWENOID PAPULOSIS) AND COEXISTENT INVASIVE-CARCINOMA OF THE VULVA
    BERGERON, C
    NAGHASHFAR, Z
    CANAAN, C
    SHAH, K
    FU, Y
    FERENCZY, A
    [J]. 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
  • [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
    Heath, MD
    Sarkar, S
    Sanocki, T
    Bowyer, KW
    [J]. 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