Fringe pattern analysis using deep learning

TL;DR

This paper introduces a deep learning approach for fringe pattern analysis in optical metrology, significantly improving phase demodulation accuracy from a single fringe pattern compared to traditional methods.

Contribution

It is the first to demonstrate deep neural networks effectively perform fringe analysis, enhancing accuracy and edge preservation in phase recovery from minimal data.

Findings

Deep neural networks outperform traditional methods in phase accuracy.

The method preserves edges better than Fourier-based techniques.

Experimental validation confirms superior performance in fringe projection profilometry.

Abstract

In many optical metrology techniques, fringe pattern analysis is the central algorithm for recovering the underlying phase distribution from the recorded fringe patterns. Despite extensive research efforts for decades, how to extract the desired phase information, with the highest possible accuracy, from the minimum number of fringe patterns remains one of the most challenging open problems. Inspired by recent successes of deep learning techniques for computer vision and other applications, here, we demonstrate for the first time, to our knowledge, that the deep neural networks can be trained to perform fringe analysis, which substantially enhances the accuracy of phase demodulation from a single fringe pattern. The effectiveness of the proposed method is experimentally verified using carrier fringe patterns under the scenario of fringe projection profilometry. Experimental results demonstrate its superior performance in terms of high accuracy and edge-preserving over two representative single-frame techniques: Fourier transform profilometry and Windowed Fourier profilometry.