Pleora Technologies unveils "no code" machine learning platform
The new embedded AI Gateway from Pleora Technologies is designed to simplify the deployment of advanced machine learning capabilities and improve the reliability and lower the cost of visual quality inspection.
The AI Gateway offers plug-in machine learning skills for classification, sorting, and defect detection, and the ability to train and deploy open source and custom algorithms, without additional programming knowledge. Images and data are uploaded to “no code” training software through a simple Web-based interface on a host PC. This generates a neural network that is deployed on the Pleora AI Gateway.
An operating system built on Pleora’s eBUS SDK provides a user-friendly network to upload custom skills developed in Python. The AI Gateway then automatically handles visual acquisition from the camera source and sending processed data via GigE Vision interface. The AI Gateway’s operating system supports development in TensorFlow and OpenCV. Hardware acceleration is provided by a built-in NVIDIA GPU.
The gateway supports GigE Vision, USB3 Vision, Camera Link, and MIPI cameras from any manufacturer, which allows designers to retain existing infrastructure while adding AI skills to their processes. The camera feed is received by the gateway, which automatically performs the deployed plug-in or custom AI skill, and transmits the pre-processed data over a real-time GigE Vision connection to the existing inspection application.
The AI Gateway is easily upgraded for applications requiring more powerful AI image processing. Multiple gateways can be networked to enable distributed image processing to leverage the multicast capabilities of GigE Vision.
Pleora Technologies will demonstrate the AI Gateway at SPIE Photonics West 2020 from Feb. 4-6, at Booth 4263. The AI Gateway will also be shown at the ATX West Conference 2020 from Feb. 11-13 at Booth 4255. To book a demo, visit the AI Gateway page on the Pleora Technologies website.
Share your vision-related news by contacting Dennis Scimeca, Associate Editor, Vision Systems Design
SUBSCRIBE TO OUR NEWSLETTERS