In-Sight 2800 Tutorial

#insight2800 #visionsystems #cognexmachinevision The In-Sight 2800 Vision System makes vision automation simple. This fully integrated system combines deep learning technology with rule-based vision tools to solve a wide range of inspection applications. From presence/absence detection to advanced categorization and sorting, In-Sight 2800 provides an easy to deploy solution for error-proofing tasks. For more information, visit: https://www.cognex.com/en/products/2d... -- ABOUT US: For over 40 years, Cognex has been making advanced machine vision easy, paving the way for manufacturing and distribution companies to get faster, smarter, and more efficient through automation. Innovative technology in our 2D and 3D vision systems and industrial barcode scanners solves critical manufacturing and distribution challenges, providing unparalleled performance for industries from automotive to logistics to packaged goods. Cognex makes these tools more capable and easier to deploy and thanks to a longstanding focus on AI, helping factories and warehouses improve quality and maximize efficiency without needing highly technical expertise. We are headquartered near Boston, USA, with locations in over 30 countries and more than 30,000 customers worldwide. CONTACT US: LinkedIn: / cognex-corporation Support: https://www.cognex.com/en/support?utm... Contact Cognex: https://www.cognex.com/en/contact-us?... Get a Product Demo: https://www.cognex.com/en/contact-us/... Cognex Machine Vision Systems: https://www.cognex.com/en/products/2d... -- SUMMARY: The video demonstrates configuring a smart camera for visual inspection using a new classification tool. The process involves connecting to the device, optimizing lighting and focus, and defining a region of interest. Users train the system by capturing images of acceptable parts, defective items, and empty fields. The software automatically assigns classes and calculates a model health metric. Once stability is reached, the application is deployed. Finally, a runtime display is created to show predicted classes and confidence scores, allowing users to monitor performance and integrate data with factory controllers. KEY TAKEAWAYS: -Connect to the smart camera and optimize lighting and focus instantly. -Define the region of interest to specify the inspection area. -Create default classes for acceptable, defective, and missing parts. -Capture images of each part type to train the classification model. -Monitor the model health metric to ensure stability before deployment. -Import pre-collected image folders to accelerate the training process. -Test the deployed application by rotating parts and varying positions. -Configure the runtime HMI to display confidence scores and predictions. -Integrate the system with PLCs or other factory floor devices. -Deploy the application once the model health exceeds 80% and stabilizes.