Benefiting from Quantum? A Comparative Study of Q-Seg, Quantum-Inspired Techniques, and U-Net for Crack Segmentation
This work addresses crack segmentation for structural health monitoring, but it is incremental as it benchmarks existing methods without major breakthroughs.
The study compared quantum and quantum-inspired methods against classical models for crack segmentation in concrete images, finding that quantum-based approaches offer a promising alternative, especially for complex patterns.
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.