Join or Sign in

Register for your free membership or if you are already a member,
sign in using your preferred method below.

To check your latest product inquiries, manage newsletter preference, update personal / company profile, or download member-exclusive reports, log in to your account now!
Login asmag.comMember Registration

Vision technologies that enable smart cameras in manufacturing

Vision technologies that enable smart cameras in manufacturing
What makes machine vision possible are complex algorithms that can make sense of structured or unstructured data.
Cameras by themselves are dumb. They are only useful in capturing what happens in front of them. What makes machine vision possible are complex algorithms that can make sense of structured or unstructured data. Often considered under the umbrella term of vision technology, these algorithms make use of technologies like machine learning and deep learning to identify what is captured in the footage.

Deep learning-based image analysis

The industry is now turning more to deep learning technology to solve manufacturing inspections that are too complicated, time-consuming, and costly to program using traditional (rules-based) machine vision, according to Shweta Kabadi, Senior Director and Business Unit Manager of Vision SW and Accessories at Cognex.  Deep learning technology uses neural networks that mimic human intelligence to distinguish anomalies, parts, and characters while tolerating natural variations in complex patterns. 

“Deep learning complements rules-based approaches, and it reduces the need for deep vision domain expertise to construct an effective inspection,” Kabadi continued. “For particularly complex industrial vision applications, deep learning offers an advantage over traditional (rules-based) vision approaches, which struggle to appreciate variability and deviation between very visually similar parts.”

Deep learning-based software optimized for factory automation can solve vision applications that are too difficult to program with rules-based algorithms, handle confusing backgrounds and poor image quality, maintain applications and re-train on the factory floor, adapt to new examples without re-programming core algorithms, and be used by non-vision experts.

Liquid lens technology

Liquid lens autofocus technology enables image-based barcode readers to automatically adapt to changes in working distances for greater depth-of-field range. Liquid lenses use electrical charges to change the shape of the interface between oil and water.

“This bends the light and brings the image, or barcode, into focus quickly. Unlike traditional zoom lenses, liquid lenses do not have any moving parts that can wear out or fail,” Kabadi pointed out. “This simplifies installation, setup, and maintenance by eliminating the need to open the reader and manually touch the lens. Relative to other autofocus mechanisms, liquid lenses have extremely fast response times and good optical quality. It is ideal for applications with reading distances that change from part to part or during a part changeover.” 

High Dynamic Range (HDR) technology

Dynamic range is a term used to describe the difference between the brightest part of a scene and the darkest part of a scene at a given moment in time – essentially the amount of contrast within a single image. In many imaging applications, it becomes difficult to discern the dark and bright areas due to the lack of dynamic range within the camera.  

“HDR technology creates a more uniformed image in a single acquisition allowing greater depth-of-field, faster line speeds, and improved the handling of multi-point assembly verification and improved the handling of codes that are difficult to read,” Kabadi said.
Subscribe to Newsletter
Stay updated with the latest trends and technologies in physical security

Share to: