Skip to Main Content
Geometric distortion of an image is one of the most important parameters affecting the accuracy of optical inspection systems. We propose a new image distortion correction method to increase the accuracy of printed circuit board (PCB) inspection systems. Our model-free method is applied to correct the randomly distorted images that cannot be represented by a mathematical model. To reduce the correction time of the inspection system, we propose a control area-merging algorithm that minimizes the number of control areas using the quad-tree approach. We apply the proposed method to a PCB inspection system, and verify its usefulness through experiments using actual inspection images.