Image Calibration for Machine Vision Inspection System

Abstract:

Machine vision system has been widely used for a variety of applications in industrial testing and measurements. However, image distortion caused by optical system and system re-positioning will bring errors to the machine vision detection system. This paper addresses on three types of image distortions including optical distortion and perspective deformation, image translation and rotation, and image scale change. To rectify optical distortion and perspective deformation, a black and white grid pattern is used as a standard template for finding the multiple matching points between distorted image points and ideal image points, and then a polynomial mathematical model simulating the geometric distortion is established. The distortion coefficients are calculated from the least square method. Image translation and rotation are compensated by using a floating fixture origin as the reference point. Image scale change is remedied by using a standard scale factor to shrink or enlarge an actual image to its standard size. The experimental results have demonstrated the effectiveness of the approach proposed.

• Periodical: Applied Mechanics and Materials (Volumes 556-562)
• Pages: 2841-2845
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.556-562.2841
• Online since: May 2014
• Authors: Liang Shan Feng*, Ying Ping Huang, Zhu Kai Xu, Yong Zhang
• Keywords: Deformation, Distortion, Image Calibration, Machine Vision, Positioning Error

References

[1] C. Ricolfe-Viala, A. J. Sanchez-Salmeron: Robust Metric Calibration of Non-linear Lens Distortion [J]. Pattern Recognition, 43(4): 1688-1699, (2010).

DOI: 10.1016/j.patcog.2009.10.003

[2] W. Wang, Y. L. Zhong, J. K. Wu: Real Time System Designed for Distortion Correction in Wide Angle Lens [J]. Optical Technique, 30(4): 489-490, (2004).

[3] T. Lin, S. Sheng, Y. Chen: Error Analysis of Euclidean Reconstruction from Translational Motion [C]. 2009 Iternational Conference on Artificial Intelligence and Computztional Intelligence, 3: 219-223, (2009).

DOI: 10.1109/aici.2009.343

[4] Z. Zhang: A Flexible new technique for camera calibration, IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(11): 1330-1334, (2000).

DOI: 10.1109/34.888718

[5] H. Y. Jia, Y. Zhang, J. Wei: Radial Distortion Correction and Its Performance Evaluation [J]. Journal of University of Jinan, 27(01): 38-41, (2013).

[6] J. M. Lin, M. L. Xing, D. G. Sha, et al: Distortion Measurement of CCD Imaging System with Short Focal Length and Large Field Objective [J]. Optics and Lasers in Engineering, 43(6): 1137-1144, (2005).

DOI: 10.1016/j.optlaseng.2004.07.006

[7] L. Alvarez, L. Gomez, P. Henfiquez: Zoom Dependent Lens Distortion Mathematical Models [J]. Journal of Mathematical Imaging and Vision, 44(3): 480-490, (2012).

DOI: 10.1007/s10851-012-0339-x