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

TL;DR

This paper compares quantum, quantum-inspired, and classical deep learning methods for crack segmentation in concrete images, highlighting the potential of quantum techniques as promising alternatives for complex pattern analysis.

Contribution

It provides a comprehensive benchmarking of quantum and quantum-inspired methods against classical models for crack segmentation.

Findings

Quantum-inspired and quantum methods perform competitively with classical models.

Quantum techniques show promise for complex crack pattern segmentation.

Quantum methods could be viable for near-future practical applications.

Abstract

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.