Automated surface feature detection using fringe projection: An autoregressive modeling-based approach

Abstract

An automatic surface defect detection algorithm is proposed in a fringe projection profilometry setup. An exponential phase field associated with the fringe projected surface image is analyzed using two-dimensional auto-regressive (AR) model. The AR model coefficients capture the local fringe frequency information. The variation in the fringe frequency from the defect-free to defective surface region is utilized as a signature for defect identification and localization. The fringe frequency threshold required for the image segmentation into defective and defect free regions is derived from the mean frequency computed over the same image which obviates the need for the reference image. In order to enhance the computation efficiency of the algorithm the image is divided into small patches and analysis is performed patch-wise. The simulation and experimental results demonstrate the advantages of the proposed phase based surface evaluation method over the commonly used intensity based methods.