| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 10361516 | Pattern Recognition Letters | 2005 | 11 Pages |
Abstract
A method of determining edge detector performance from tests on synthetic images is presented. The position of a step edge is defined and its shape modified by the acquisition system's measured point spread function. These images contain both accurate positional information and realistic edge profiles. Results for a Canny detector have been presented and its optimum operating parameters determined for the given acquisition system.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Vision and Pattern Recognition
Authors
R.C. Staunton,