Bat-wing elimination algorithm based on the CNN in white-light interferometry

White Light Scanning Interferometry (WLSI) is a mature and key method of non-contact three-dimensional (3D) morphometry. However, bat-wing is an inherent problem with WLSI, introducing systematic errors to the measurement results. In this paper, we proposed a filtering algorithm based on the convolutional neural networks (CNN) to solve the problem. A 450 nm standard step is tested to verify the effectiveness of the algorithm. The results show that the method can effectively suppress the batwing effect.