Quantum Machine Vision Demonstrates Better Defect Detection

New research has demonstrated that quantum artificial vision systems can outperform their classical computer-powered counterparts at image detection and classification.

The study used a quantum-enhanced method for classification on universal gate-based quantum computers and a quantum classification algorithm on a quantum annealer.

The researchers found that both algorithms outperformed common classical methods in the identification of relevant images and the accurate classification of manufacturing defects.

The paper, “Quantum artificial vision for defect detection in manufacturing” was co-authored by quantum technology developer Multiverse Computing and technology transfer center Ikerlan.

“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,” said Ikerlan CEO Ion Etxeberria.

“This collaborative study confirmed the benefits of applying quantum methods to real-world industrial challenges. We strongly believe that quantum computing will play a key role in providing AI-based solutions for particularly complex scenarios.” 

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

“We are pleased to witness the value of early applications of quantum computing today, such as quantum artificial vision, and excited to enter a new era of machine learning alongside forward-thinking partners like Ikerlan as quantum technology continues to advance.”

Multiverse Computing initially became known for its quantum and quantum-inspired solutions for complex financial services problems but also serves companies in the mobility, energy, life sciences and industry 4.0 sectors.

In July, the company announced it was partnering with Bosch to introduce quantum-computing powered digital twin technology at its automotive electronics plant in Madrid.