1 November 1992 Edge location error for local maximum and zero-crossing edge detectors
Author Affiliations +
Proceedings Volume 1830, Curves and Surfaces in Computer Vision and Graphics III; (1992); doi: 10.1117/12.131759
Event: Applications in Optical Science and Engineering, 1992, Boston, MA, United States
Abstract
In this paper we examine the localization criterion for edge detection and determine the density function describing the edge location error, i.e. the displacement of the detected edge position from the true edge location. Canny defines the measure of localization as the reciprocal of the root-mean-square edge location error and formulates an expression of this measure for local maximum detectors. However, Tagare and deFigueiredo point out that an incorrect assumption is made in the calculation. The same procedure is used by Sarkar and Boyer for their localization measure for zero-crossing detectors. We modify the analysis and obtain a closed form solution of the probability density function of the edge location error. Examination of the density function indicates the variance of the edge location error does not exist, and hence can not be used as a measure of localization. A new localization measure is proposed, characterized by a percentile level on the absolute value of the edge location error.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Vito J. Greco, Jack Koplowitz, "Edge location error for local maximum and zero-crossing edge detectors", Proc. SPIE 1830, Curves and Surfaces in Computer Vision and Graphics III, (1 November 1992); doi: 10.1117/12.131759; https://doi.org/10.1117/12.131759
PROCEEDINGS
12 PAGES


SHARE
KEYWORDS
Sensors

Edge detection

Machine vision

Computer graphics

Computer vision technology

Visualization

Error analysis

RELATED CONTENT

Performance of visual tasks from contour information
Proceedings of SPIE (September 07 2010)
CAD/CAM in the French automobile industry
Proceedings of SPIE (August 01 1990)
Robust computational vision
Proceedings of SPIE (August 20 1993)
Image smoothing and differentiation with regularized filters
Proceedings of SPIE (February 01 1992)
Fast adaptive threshold for the Canny edge detector
Proceedings of SPIE (November 03 2005)
Hierarchical object boundary detection and description
Proceedings of SPIE (August 01 1990)

Back to Top