Optimal settings for vision camera calibration

As machine vision system has significant applications in computerized inspection systems, the precise calibration of it is essential to enhance its application potential. The parameters, namely, illumination intensity, length of extender tube, number of control points, and region of interest influence the accuracy and repeatability of calibration. The objective of this study is to determine the optimal settings of the parameters in the operating environment that will maximize the performance of the machine vision system. This paper considers the above-mentioned four factors as the influencing parameters on accuracy and repeatability of calibration and distorted image plane error (DIPE) as a measure of its performance. The Taguchi method-based orthogonal array is applied to evolve the independent optimal settings and the percentage contributions of various parameters on accuracy and repeatability. In addition to the independent optimization, the settings for simultaneous optimization of accuracy and repeatability are evolved with desirability function, total loss function, and Taguchi quality loss function. The optimal settings under independent and simultaneous cases are analyzed and reported. © 2008 Springer-Verlag London Limited.