Learning-based Correlation Analysis Between Laser Speckle and Surface Size Distribution

Abstract

Extracting quantitative information about highly scattering surfaces from an imaging system is challenging because the phase of the scattered light undergoes multiple folds upon propagation, resulting in complex speckle patterns. One specific application is the drying of wet powders in the pharmaceutical industry, where quantifying the particle size distribution (PSD) is of particular interest. A non-invasive and real-time monitoring probe in the drying process is required, but there is no suitable candidate for this purpose. In this thesis, we develop a theoretical relationship from the PSD to the speckle image and describe a physics-enhanced autocorrelation-based estimator (PEACE) machine learning algorithm for speckle analysis to measure the PSD of a powder surface. This method solves both the forward and inverse problems together and enjoys increased interpretability, since the machine learning approximator is regularized by the physical law. Moreover, we utilized an engineered intensity pupil to boost the sidelobe intensity more than 30 times and proposed a learning-based model to estimate the particle sizes from a single snapshot. It reduces the data collection time from 15 sec to 0.25 sec, broadening its application to many manufacturing industries which require a real-time refresh rate.