Deep learning based single shot multiple phase derivative retrieval method in multi-wave digital holographic interferometry

Abstract

Simultaneous and single shot measurement of multiple phase derivatives is a challenging problem in multi-wave digital holographic interferometry. In this work, we propose a deep learning approach which is capable of direct extraction of the multiple phase derivative information even in the presence of severe noise and without the need of multiple phase-shifted frames, dedicated experimental control related to multiple wavelengths, spatial carrier and polarization, numerical differentiation and phase unwrapping operations. We show both numerical and experimental results to validate the method’s performance in digital holographic interferometry.