Feb 25, 2021

AWS releases Amazon Lookout for production anomaly detection

AWS
SmartManufacturing
production
AnomalyDetection
Georgia Wilson
3 min
AWS logo
Amazon Web Services (AWS) has announced its general availability of Amazon Lookout for Vision...

Used by the likes of GE Healthcare, Amazon and Basler, Amazon Web Services (AWS) has announced the general availability of Amazon Lookout for Vision. The solution uses AWS-trained computer vision models to find anomalies and flaws in products or production processes.

The benefits of Amazon Lookout for Vision

Harnessing computer vision and a sophisticated machine learning technique called ‘few-shot learning’, AWS’ latest solution - Amazon Lookout for Vision - spot product or process defects and anomalies in manufactured products.  

AWS explains that, “customers can get started quickly using Amazon Lookout for Vision to detect manufacturing and production defects (e.g. cracks, dents, incorrect color, irregular shape, etc.) in their products and prevent those costly errors from progressing down the operational line and from ever reaching customers.”

By adopting Amazon Lookout for Vision alongside Amazon Lookout for Equipment, Amazon Monitron, and AWS Panorama, manufacturers can benefit from one of the most comprehensive suites for cloud-to-edge industrial machine learning services.

“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. 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,” commented Swami Sivasubramanian, Vice President of Amazon Machine Learning for AWS.

Amazon Lookout for Vision: how does it work?

Amazon Lookout for Vision provides manufacturers with a highly accurate, low cost anomaly detection solution. Amazon Lookout for Vision harnesses computer vision to process thousands of images an hour in order to spot defects and anomalies without the need for experience in machine learning.

By sending camera images to Amazon Lookout for Vision in real time, the solution utilises a machine learning technique called ‘few shot learning’ where the model is able to classify data based on a very small amount of training data. 

Amazon Lookout for Vision requires as little as 30 images of the acceptable and anomalous state to determine a baseline to begin assessing parts or products. Not only is the solution functional with a minimal amount of training data, the solution is adaptable to a wide range of inspection tasks in an industrial environment.

Following analysis, Amazon Lookout for Vision reports images that differ from the baseline via a service dashboard or the ‘DetectAnomalies’ real time API in order for appropriate action to be taken.

“Customers also have the ability to provide feedback on the results (e.g. whether a prediction correctly identified an anomaly or not), and Lookout for Vision will automatically retrain the underlying model so that the service continuously improves. This feature allows the technology to adapt to changes in the manufacturing process and even understand when variations are permissible or not based on customer feedback. This means that customers can be more nimble and adapt their processes based on competitive advantages or external factors impacting their operations,” states AWS. 

For more information on manufacturing topics - please take a look at the latest edition of Manufacturing Global.

Follow us on LinkedIn and Twitter.

Share article