Srinivasan, AkshayaAkshayaSrinivasanGeng, AlexanderAlexanderGengMacaluso, AntonioAntonioMacalusoKiefer-Emmanouilidis, MaximilianMaximilianKiefer-EmmanouilidisMoghiseh, AliAliMoghiseh2025-08-182025-08-182024-09-24https://publica.fraunhofer.de/handle/publica/49065510.58895/ksp/1000174496-10Exploring the potential of quantum hardware for en hancing classical and real-world applications is an ongoing challenge. This study evaluates the performance of quantum and quantum-inspired methods compared to classical mod els for crack segmentation. Using annotated gray-scale im age 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.enQuantum computingquantum image segmentationquantum optimizationdisordered systems500 Naturwissenschaften und Mathematikconference paper