Pleora Technologies and perClass have announced a technology partnership that simplifies the deployment of machine learning hyperspectral imaging for inspection applications. Pleora will be demonstrating its new AI Gateway and hyperspectral imaging plug-in developed with perClass at SPIE Photonics West (Pleora booth #4263, perClass booth #5248) and ATX West (Pleora booth #4255 with Saber1).
Where traditional cameras capture images in broad red, green, and blue wavelengths to match human vision, hyperspectral imaging provides narrower wavelengths to include ultraviolet or near infrared information for each pixel on an inspected object. With the ability to capture the entire electromagnetic spectrum, hyperspectral imaging is being increasingly adopted across multiple industries to analyze, detect, and classify materials.
Food inspection, for example, is adopting hyperspectral imaging to detect foreign materials and ensure products meet quality standards while reducing costly visual inspection. In the pharmaceutical market, hyperspectral imaging can detect subtle changes in the composition of active ingredients in visually identical pills to screen out-of-specification products.
"Hyperspectral imaging provides deeper insight across a widening range of markets, but end-users and integrators consistently struggle with deployment," said Jonathan Hou, Chief Technology Officer, Pleora. "By including powerful automatic machine learning capabilities from perClass as a plug-in solution in our AI Gateway, Pleora is delivering the vision industry's most straightforward solution to train and deploy AI algorithms leveraging hyperspectral imaging for inspection applications."
"Working with Pleora, we're helping break down deployment barriers for spectral imaging," said Dr. Pavel Paclik, Founder and Managing Director, perClass BV. "Combining perClass interpretation software and runtime technology with Pleora's unique approach to AI deployment, it's easier for users and integrators to utilize hyperspectral imaging across a wider range of industrial applications including pharmaceuticals, food production, recycling, and manufacturing."
With the Pleora AI Gateway and perClass AI plug-in, end-users and integrators can deploy machine learning hyperspectral capabilities without any additional programming knowledge. Images and data are uploaded to perClass Mira(r) "no code" training software on a host PC, which automatically generates AI models that are deployed on the Pleora AI Gateway in a production environment.
Pleora's AI Gateway works seamlessly with any standards-compliant hyperspectral sensor, meaning end-users can avoid vendor lock-in while maintaining processes and analysis software. Many software processing solutions require custom workarounds to support hyperspectral through GigE Vision because they can't interpret multiband information. In comparison, the AI Gateway bridges the gap between applications and existing machine vision software by automatically handling image acquisition from the hyperspectral imaging source and sending out the processed data over GigE Vision to inspection and analysis platforms.
Pleora's AI Gateway provides additional plug-in AI skills for classification, sorting, and detecting, with the processing flexibility of an NVIDIA GPU to train and deploy open source or custom algorithms developed in popular frameworks like TensorFlow and OpenCV. Lead customers are now evaluating the AI Gateway in inspection applications to help reduce costly inspection errors, false-positives, and secondary screenings.
