U-Net based particle localization in granular experiments: Accuracy limits and optimization

TL;DR

This paper demonstrates that a U-Net deep neural network can accurately localize particles in complex granular images, surpassing traditional methods, with high detection rates and subpixel precision, while analyzing the influence of training mask design.

Contribution

The study introduces a U-Net based approach for particle localization in challenging images, highlighting the importance of mask design and human labeling biases for optimal performance.

Findings

97.7% particle detection accuracy

2.7% false positives on test images

3.7% of particle diameter localization error

Abstract

Identifying the positions of granular particles from experimental images is often complicated by their partial overlap in two dimensional projections. Uneven backgrounds and inhomogeneous illuminations can add to the challenge. Conventional image-processing methods are often unable to analyze such images. We show that a deep neural network with an U-Net architecture can provide precise particle positions with a high detection rate. For our challenging test image the network correctly identifies 97.7\% of the particles while only creating 2.7 \% of false positives. The training of the U-Net requires a number of target images where the position of all particles have been identified by humans. Those positions are then indicated in the target images by setting a small number of mask pixels to white in an otherwise black image. We demonstrate that the design of these masks critically determines performance: mask size controls the resolution of overlapping particles, anti-aliased masks enable subpixel accuracy, and systematic human labeling biases set a measurable lower bound on achievable precision. Our final network achieves an accuracy of the particle coordinate of 3.7\% of the particle diameter.