News

Deep Learning Streamlines Industrial Image Analysis for Material Inspections

OLYMPUS Stream™ software’s AI offers accurate and automated image segmentation

Multiphase analysis of composite materials is a typical industrial image analysis application using deep-learning technology. After deep-learning image segmentation with OLYMPUS Stream software version 2.5, different phases can be distinguished and detected accurately. Combined with the software’s Count and Measure solution, users can easily obtain repeatable and quantitative results. Left: original image of etched copper. Middle: image segmentation using conventional thresholding methods. Right: deep-learning image segmentation.

WALTHAM, Mass., (July 27, 2021)—OLYMPUS Stream™ image analysis software now leverages the power of artificial intelligence to bring next-generation image segmentation to industrial microscope inspections. Software version 2.5 adds Olympus’ TruAI™ deep-learning technology, enabling users to train neural networks to automatically segment and classify objects in microscope images for a range of material inspections. A trained network can be applied to future analyses for a similar application to maximize efficiency.

Accurate Image Segmentation

Image analysis is a critical part of many material science, industrial and quality assurance applications. However, image segmentation using conventional thresholding methods that depend on HSV or RGB color spaces can miss critical information or targets in samples. Olympus’ TruAI technology offers more accurate segmentation based on deep learning for a highly reproducible and robust analysis.

Easily Train and Manage Neural Networks

With the TruAI solution, users can easily train robust neural networks. An easy-to-use interface lets users efficiently label images and run trainings in batches. Networks can be configured with many input channels, trained to identify up to 16 classes, and imported or exported. The solution also offers options to review and edit training details.

Customized User Workflows

The software update also gives all users access to Olympus’ workflow customization services. This team designs tailor-made OLYMPUS Stream workflows to address user-specific application scenarios, challenges, and goals.

Update to OLYMPUS Stream Software Version 2.5

OLYMPUS Stream v. 2.4 customers may use their existing license for a free update to software version 2.5.

About EVIDENT

In 2022, Olympus Corporation spun off its Scientific Solutions Division, which included its life science and industrial solutions businesses, to establish a new company called Evident. Although our name is different, our expertise, manufacturing capabilities, and commitment to our customers, which defined us over the past 100 years, remain unchanged.

At Evident, innovation and exploration are at the heart of what we do. Committed to making people’s lives healthier, safer, and more fulfilling, we support our customers with solutions that solve their challenges and advance their work; whether it’s researching medical breakthroughs, inspecting infrastructure, or exposing hidden toxins in consumer products.

Evident’s industrial solutions range from microscopes and videoscopes to nondestructive testing equipment and X-ray analyzers for maintenance, manufacturing, and environmental applications. Backed by state-of-the-art technologies, Evident products are widely used for quality control, inspection, and measurement.

In life science, Evident empowers scientists and researchers through collaboration and cutting-edge solutions. We’re dedicated to meeting the challenges and supporting the evolving needs of our customers, continuing to advance a comprehensive range of microscopes for pathology, hematology, IVF, and other clinical applications as well as for research and education.

For more information, visit EvidentScientific.com.

Olympus, the Olympus logo, OLYMPUS Stream and TruAI are trademarks of Olympus Corporation or its subsidiaries.

Media Contact:
Michelle Gaynor
michelle.gaynor.ext@evidentscientific.com
+1 609 828 3634