Amazon launches computer vision service to detect defects in manufactured products

Amazon today announced the general availability of Amazon Lookout for Vision, a cloud service that analyzes images using computer vision to spot product or process defects and anomalies in manufactured goods. Amazon says Lookout for Vision, which is available in select Amazon Web Services (AWS) regions via the AWS console and supporting partners, is able to train an AI model using as few as 30 baseline images.

Tasks in manufacturing can be error-prone when humans are in the loop. A study from Vanson Bourne found that 23% of all unplanned downtime in manufacturing is the result of human error, compared with rates as low as 9% in other segments. The $327.6 million Mars Climate Orbiter spacecraft was destroyed because of a failure to properly convert between units of measurement. And one pharma company reported a misunderstanding that resulted in an alert ticket being overridden, which cost four days on the production line at £200,000 ($253,946) per day.

Lookout for Vision aims to combat this by injecting a bit of AI into the mix, detecting manufacturing and production defects in products — including cracks, dents, incorrect colors, and irregular shapes — from their appearance. The service can process thousands of images an hour and requires no upfront commitment or minimum fee, Amazon says. Customers pay by the hour for usage to train the model and detect anomalies or defects using the service.

After analyzing the data, Lookout for Vision reports images that differ from the baseline via the service dashboard or a real-time API. Amazon claims Lookout for Vision is sophisticated enough to maintain accuracy with variances in camera angle, pose, and lighting arising from changes in work environments. But customers have the ability to provide feedback on the results and whether a prediction correctly identified an anomaly. Lookout for Vision will automatically retrain the underlying model so the service continuously improves.

Customers using Lookout for Vision include GE Healthcare, Basler, and Sweden-based Dafgards. (Lookout for Vision launched in preview with customers beginning in December 2020 after being unveiled during Amazon’s virtual re:Invent conference.) Dafgards is using the service to automate the inspection of its production lines and detect whether pizzas, hamburgers, and quiches have the correct toppings. And Amazon’s own Print-On-Demand facility, which prints books to fulfill customer orders, is tapping Lookout for Vision to automate and scale visual inspection at each step of book manufacturing.

“Whether a customer is placing toppings on a frozen pizza or manufacturing finely calibrated parts for an airplane, what we’ve heard unequivocally is that guaranteeing only high-quality products reach end users is fundamental to their business. While this may seem obvious, ensuring such quality control in industrial pipelines can in fact be very challenging,” AWS Amazon machine learning VP Swami Sivasubramanian said in a press release. “We’re excited to deliver Amazon Lookout for Vision to customers of all sizes and across all industries to help them quickly and cost-effectively detect defects at scale to save time and money while maintaining the quality their consumers rely on — with no machine learning experience required.”