Taking Computer Vision to the Next Level, with AI Behind It


Researchers have assembled a computer vision system that uses AI and optical measurement technology to detect, classify, and visualize product defects in real time.

One of the interesting aspects of real-time capabilities is computer vision – when linked to back-end intelligence, it can be used for a multitude of applications – from highway toll booths to shipping logistics. Now, new developments in this field may bring instantaneous analysis and action right at the point of contact.

Researchers at the Fraunhofer Institute report they have that assembled a computer vision system that employs artificial intelligence and optical measurement technology to detect, classify and visualize defects in real time, and report them to plant administrators. The demonstration project, under development for a year, detects surface defects, artifacts as well as texture changes, and that evaluates them with the support of AI.

See also: The Benefits of Analytics-Based Product Engineering

Sponsored: Mainframe Data Is Critical for Cloud Analytics Success—But Getting  to It Isn’t Easy [Read Now]

“This process can capture 3D-information of surfaces rapidly and in high resolution,” the Fraunhofer report indicates. “The measurement data is used to generate supplementary information in-line for ongoing production processes.”

The real-time photo analysis goes a step further, the researchers add. “The system does not just detect defects – it classifies them at the same time and immediately establishes a wider context. Our customers receive information about the type of defect, along with many other parameters like the defect’s density, geometric dimensions and frequency.”

AI enters the picture with the system being trained within ongoing production using a defect catalog. “As defects are reported, they are fed into a neural network, thereby refining the detection accuracy.”

The researchers say there are many applicable areas for the technology, and apply such as continuous fiber-composite manufacturing processes. “Currently, the Fraunhofer solution uses a maximum of four cameras, which will increase. .


About Joe McKendrick

Joe McKendrick is RTInsights Industry Editor. He is a regular contributor to Forbes on digital, cloud and Big Data topics. He served on the organizing committee for the recent IEEE International Conference on Edge Computing (full bio). Follow him on Twitter @joemckendrick.

Leave a Reply

Your email address will not be published. Required fields are marked *