Recognition of Suspension Liquid Based on Speckle Patterns Using Deep Learning

Jinhua Yan,Hang Zhang,Ziheng Zhu,Lei Chen,Ming Jin,Zhousu Xu

doi:10.1109/jphot.2020.3044912

Abstract

We presented a machine learning-based method to recognize suspension by distinguishing dispersoid-dependent speckle patterns using a convolutional neural network. The dispersoid size and concentration-related transmissive speckle patterns were recorded by a lensless camera when a coherent He-Ne laser irradiated the suspension. Firstly we realized the recognition of the polystyrene microspheres-dispersed suspensions with different particle sizes and the recognition of several common suspensions including protein powder and milk powder with similar concentration. Further recognition from three different food suspensions with unknown concentration was achieved with high accuracy of 99%. The experimental results confirm that this non-contact method could find applications in the measurement and classification of suspension liquid containing micrometers-sized particles.

Highlights

Measurement of the suspension may find many applications in water pollution monitoring [1], [2], protein particles analysis [3] and cell-rich blood glucose concentration detection [4], in which cases a large number of insoluble dispersoids with the size of the order of micrometer are evenly dispersed in the suspension
We presented a machine learning-based method to recognize suspension by distinguishing dispersoid-dependent speckle patterns using a convolutional neural network
The intensity distribution of speckle pattern is significantly affected by the amplitude distribution of the scattered wavelets, the characteristic of speckle patterns differs from types of suspension, which could be used to suspension recognition

Summary

Introduction

Measurement of the suspension may find many applications in water pollution monitoring [1], [2], protein particles analysis [3] and cell-rich blood glucose concentration detection [4], in which cases a large number of insoluble dispersoids with the size of the order of micrometer are evenly dispersed in the suspension. Many methods were developed to determine the dispersoid size of the suspension, such as microscopic observation [7], electrical impedance analysis technology [8], light scattering-based technology [9] and microfluidic chip-combined 3D fluid focusing technology [10], etc. Due to the random distribution of dispersoids in the suspension, optical speckle patterns appear when the suspension is irradiated by laser light.

Methods

Results

Conclusion