Phase Unwrapping Method Using Adaptive AI Model for the Application of Industrialization and Precision Metrology Field

Abstract

Phase unwrapping method based on Residual Auto Encoder Network is proposed in this chapter. Phase unwrapping is regarded as a multiple classification problem, and it will be solved by the trained network model. Through training and validation stages, optimal network models can be served as predictors of wrap count distribution map of wrapped phase. Then merge the wrapped phase and count together to complete unwrapping. Software simulation and hardware acquisition are the sources of training dataset. To further improve accuracy of unwrapping, image analysis-based optimization method is designed that can remove misclassification and noise points in initial result. In addition, phase data stitching by Iterative Closest Point is adopted to realize dynamic resolution and enhance the flexibility of method. Point diffraction interferometer and multi-step phase extraction technique is the foundation of proposed method. It can be concluded from experiments that the proposed method is superior to state-of-art ones in accuracy, time efficiency, anti-noise ability, and flexibility.