Paper
U-Net based particle localization in granular experiments: Accuracy limits and optimization
Authors
Fahad Puthalath, Matthias Schröter, Nicoletta Sanvitale, Matthias Sperl, Peidong Yu
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.
Metadata
Related papers
Fractal universe and quantum gravity made simple
Fabio Briscese, Gianluca Calcagni • 2026-03-25
POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan
Marta Moscati, Muhammad Saad Saeed, Marina Zanoni, Mubashir Noman, Rohan Kuma... • 2026-03-25
LensWalk: Agentic Video Understanding by Planning How You See in Videos
Keliang Li, Yansong Li, Hongze Shen, Mengdi Liu, Hong Chang, Shiguang Shan • 2026-03-25
Orientation Reconstruction of Proteins using Coulomb Explosions
Tomas André, Alfredo Bellisario, Nicusor Timneanu, Carl Caleman • 2026-03-25
The role of spatial context and multitask learning in the detection of organic and conventional farming systems based on Sentinel-2 time series
Jan Hemmerling, Marcel Schwieder, Philippe Rufin, Leon-Friedrich Thomas, Mire... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.01753v1</id>\n <title>U-Net based particle localization in granular experiments: Accuracy limits and optimization</title>\n <updated>2026-03-02T11:22:49Z</updated>\n <link href='https://arxiv.org/abs/2603.01753v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.01753v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>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.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cond-mat.stat-mech'/>\n <published>2026-03-02T11:22:49Z</published>\n <arxiv:comment>14 pages, 14 figures</arxiv:comment>\n <arxiv:primary_category term='cond-mat.stat-mech'/>\n <author>\n <name>Fahad Puthalath</name>\n </author>\n <author>\n <name>Matthias Schröter</name>\n </author>\n <author>\n <name>Nicoletta Sanvitale</name>\n </author>\n <author>\n <name>Matthias Sperl</name>\n </author>\n <author>\n <name>Peidong Yu</name>\n </author>\n </entry>"
}