Cognex presents the In-Sight D900 embedded vision system that features the company’s ViDi deep learning software inside an industrial-grade smart camera.
The self-contained system is designed to solve a broad range of complex in-line inspection applications including optical character recognition (OCR), assembly verification, and defect detection. The solution is designed for automating complex inspection applications across a range of industries including automotive, consumer electronics, consumer products, packaging, food and beverage, medical devices and logistics.
“Sophisticated manufacturers are increasingly turning to deep learning vision to solve inspections that are too complicated, time-consuming, or costly to program using human or rule-based machine vision – explains Joerg Kuechen, senior vice president of vision products at Cognex -. By embedding our ViDi deep learning software on In-Sight, customers can solve even the most complex visual inspections quickly, easily, and more cost-effectively”.
In-Sight ViDi Check reliably detects complex features and objects within a field of view and verifies that parts and kits are assembled correctly based on their location and attributes. Manufacturers can train the In-Sight ViDi Check tool to handle wide ranges of part-to-part variation in order to locate and confirm whether components are present and in the correct location. The tool also recognizes multiple types of components within varying layouts and configurations.
Companies can then take advantage of deep learning tools moving from image collection to deployment in a matter of weeks using the D900, with most seeing a return on investment within 3-6 months. Combining the self-learning ability of a human inspector with the robustness and consistency of a vision system, the In-Sight D900 expands the limits of what can be inspected in factory automation.
The system, which can be setup using a small number of image samples, leverages Cognex’s familiar and easy-to-use spreadsheet platform and does not require a PC or deep learning expertise to deploy.