Matching for Shape Defect Detection
The problem of defect detection in 2D and 3D shapes is analyzed. A shape is represented by a set of its contour, or surface, points. Mathematically, the problem is formulated as a specific matching of two sets of points, a reference one and a measured one. Modified Hausdorff distance between these two point sets is used to induce the matching. Based on a distance transform, a 2D algorithm is proposed that implements the matching in a computationally efficient way. The method is applied to visual inspection and dimensional measurement of ferrite cores. Alternative approaches to the problem are also discussed.
KeywordsDefect Detection Robust Regression Distance Transform Reference Shape Ferrite Core
Unable to display preview. Download preview PDF.
- 3.P.J. Rousseeuw and A.M. Leroy. Robust Regression and Outlier Detection. Wiley Series in Probability and Mathematical Statistics, 1987.Google Scholar
- 5.The SQUASH Consortium. Standard-compliant Quality Control System for High-level Ceramic Material manufacturing. Technical report, EU INCO-COPERNICUS Programme, Project IC15 CT 96-0742, 1998.Google Scholar
- 6.J. Verestoy and D. Chetverikov. Shape defect detection in ferrite cores. Machine Graphics and Vision, 6(2):25–236, 1997.Google Scholar