Benefiting from Quantum? A Comparative Study of Q-Seg, Quantum-Inspired Techniques, and U-Net for Crack Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Srinivasan, Akshaya, Geng, Alexander, Macaluso, Antonio, Kiefer-Emmanouilidis, Maximilian, Moghiseh, Ali
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929541356716032
author Srinivasan, Akshaya
Geng, Alexander
Macaluso, Antonio
Kiefer-Emmanouilidis, Maximilian
Moghiseh, Ali
author_facet Srinivasan, Akshaya
Geng, Alexander
Macaluso, Antonio
Kiefer-Emmanouilidis, Maximilian
Moghiseh, Ali
contents Exploring the potential of quantum hardware for enhancing classical and real-world applications is an ongoing challenge. This study evaluates the performance of quantum and quantum-inspired methods compared to classical models for crack segmentation. Using annotated gray-scale image patches of concrete samples, we benchmark a classical mean Gaussian mixture technique, a quantum-inspired fermion-based method, Q-Seg a quantum annealing-based method, and a U-Net deep learning architecture. Our results indicate that quantum-inspired and quantum methods offer a promising alternative for image segmentation, particularly for complex crack patterns, and could be applied in near-future applications.
format Preprint
id arxiv_https___arxiv_org_abs_2410_10713
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Benefiting from Quantum? A Comparative Study of Q-Seg, Quantum-Inspired Techniques, and U-Net for Crack Segmentation
Srinivasan, Akshaya
Geng, Alexander
Macaluso, Antonio
Kiefer-Emmanouilidis, Maximilian
Moghiseh, Ali
Computer Vision and Pattern Recognition
Disordered Systems and Neural Networks
Image and Video Processing
Exploring the potential of quantum hardware for enhancing classical and real-world applications is an ongoing challenge. This study evaluates the performance of quantum and quantum-inspired methods compared to classical models for crack segmentation. Using annotated gray-scale image patches of concrete samples, we benchmark a classical mean Gaussian mixture technique, a quantum-inspired fermion-based method, Q-Seg a quantum annealing-based method, and a U-Net deep learning architecture. Our results indicate that quantum-inspired and quantum methods offer a promising alternative for image segmentation, particularly for complex crack patterns, and could be applied in near-future applications.
title Benefiting from Quantum? A Comparative Study of Q-Seg, Quantum-Inspired Techniques, and U-Net for Crack Segmentation
topic Computer Vision and Pattern Recognition
Disordered Systems and Neural Networks
Image and Video Processing
url https://arxiv.org/abs/2410.10713