Multiverse Computing, a developer of quantum computing solutions, and IKERLAN, a Spain-based center supporting the transfer of technology, developed a quantum-enhanced kernel method for classification on universal gate-based quantum computers, as well as a quantum classification algorithm on a quantum annealer.

Results of the joint research study showed detected defects in manufactured car pieces via image classification by quantum artificial vision systems. The researchers found that both algorithms used in the kernel classification method outperformed common classical methods in the identification of relevant images and the accurate classification of manufacturing defects.

Ion Etxeberria, CEO of IKERLAN, said that the study confirmed the benefits of applying quantum methods to real-world industrial challenges.

“To the best of our knowledge, this research represents the first implementation of quantum computer vision for a relevant problem in a manufacturing production line,” Etxeberria said.

In the researchers’ paper, the team said it considered several algorithms for quantum computer vision using noisy intermediate-scale quantum devices. It then measured, or benchmarked, its quantum-based vision system against classical approaches, such as those structured on neural networks.

The quantum algorithms outperformed their classical counterparts in several ways, the researchers said. The researchers performed experiments that relied on data set images requiring the vision systems to detect the car part defects.

Etxeberria said that the team believes that quantum computing will continue to play a key role in providing AI-based solutions to particularly complex scenarios.

“Quantum machine learning will significantly disrupt the automotive and manufacturing industries,” said Roman Orus, chief scientific officer at Multiverse Computing.

The research was submitted Aug. 9 to the journal Quantum Physics (www.doi.org/10.48550/arXiv.2208.04988).