Skip to Main Content
The performance of structured light profilometers is significantly hindered by the generation of distorted sinusoid fringe images, particularly, for multi-channel applications. In this paper we investigate the application of neural network fringe calibration for the multi-channel approach. We analytically review the nature of the major error sources associated with the multi-channel approach and propose a fringe calibration technique with emphasis on minimal photometric calibration. The performance of the calibration technique is gauged through both simulation and experimentation.