Hybrid pattern recognition for charged particle tracking: Hough transform and convolutional neural efficiency networks
Abstract
Reconstructing charged-particle tracks in silicon detectors is a central task in high-energy physics experiments and a key component of both offline reconstruction and online event selection. Within the reconstruction chain, the efficient and high-purity formation of track candidates plays a critical role in the overall performance. Among the many approaches developed over the years, the Hough transform (HT) has been widely studied as a fast geometry-driven method for track finding. However, in high-occupancy environments such as those expected at the High-Luminosity LHC (HL-LHC), the HT tends to produce a large number of spurious candidates, leading to increased computational overhead in subsequent reconstruction stages. In this work, we present a hybrid approach in which the HT serves as a first-stage data preparation step, providing its parameters space image as an input to a neural network trained to suppress false track candidates. The method combines the speed of the HT with the discriminative power of machine learning to achieve both efficiency and purity. In addition no data transformations are involved when combining these steps resulting in a simpler and more performant algorithm. Performance studies using the Open Data Detector simulated in the ACTS framework under realistic HL-LHC pileup conditions will be presented.
Versions
Related
- Experimental demonstration of the Quantum Fourier Transform on up to 100 qubits using a convolutional compilation strategy
- Image Compression Using Quantum Wavelet Transform and Quantum Convolutional Networks
- The RUBIK satellite payload concept: a 3D-segmented plastic scintillation-based particle tracking detector
- Direct Trajectory Reconstruction for Fast 3D X-ray Particle Tracking Velocimetry in Porous Media
- Convolutional transformer wave functions
BibTeX
@misc{varni2026hybrid,
title = {{Hybrid pattern recognition for charged particle tracking: Hough transform and convolutional neural efficiency networks}},
author = {Carlo Varni and Krzysztof Ciesla and Marcin Wolter and Radoslaw Karol Mienkowski and Noemi Calace and Tomasz Bold},
howpublished = {arXiv},
year = {2026},
month = jul,
doi = {10.48550/arxiv.2607.04723},
eprint = {2607.04723},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.04723},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Hybrid pattern recognition for charged particle tracking: Hough transform and convolutional neural efficiency networks
AU - Carlo Varni
AU - Krzysztof Ciesla
AU - Marcin Wolter
AU - Radoslaw Karol Mienkowski
AU - Noemi Calace
AU - Tomasz Bold
PY - 2026
DA - 2026/07/07
PB - arXiv
DO - 10.48550/arxiv.2607.04723
UR - https://arxiv.org/abs/2607.04723
AB - Reconstructing charged-particle tracks in silicon detectors is a central task in high-energy physics experiments and a key component of both offline reconstruction and online event selection. Within the reconstruction chain, the efficient and high-purity formation of track candidates plays a critical role in the overall performance. Among the many approaches developed over the years, the Hough transform (HT) has been widely studied as a fast geometry-driven method for track finding. However, in high-occupancy environments such as those expected at the High-Luminosity LHC (HL-LHC), the HT tends to produce a large number of spurious candidates, leading to increased computational overhead in subsequent reconstruction stages. In this work, we present a hybrid approach in which the HT serves as a first-stage data preparation step, providing its parameters space image as an input to a neural network trained to suppress false track candidates. The method combines the speed of the HT with the discriminative power of machine learning to achieve both efficiency and purity. In addition no data transformations are involved when combining these steps resulting in a simpler and more performant algorithm. Performance studies using the Open Data Detector simulated in the ACTS framework under realistic HL-LHC pileup conditions will be presented.
ER -