In-Sight 2800 is programmed using the EasyBuilder interface within the In-Sight Vision Suite. With its point-and-click training, EasyBuilder is ideal for setting up jobs, from simple to complex. The intuitive process guides developers step-by-step through setup — from image capture to the final result and beyond — allowing both new and experienced users to configure vision applications.
In-Sight 2800 is also embedded with a full suite of traditional and deep learning-based vision tools that solve a variety of error-proofing applications. The extensive library accommodates all skill levels by providing access to industry-proven, rule-based algorithms, such as Measure Distance, Pixel Count, Count Patterns and Math and Logic Tools, as well as innovative, easy-to-use ViDi EL tools.
Using a pre-trained set of deep learning-based algorithms, ViDi EL tools solve complex applications, like advanced segmentation and classification, in minutes. Training is simple, requiring as few as 5 to 10 images per class and delivering fast, reliable results in real-time – no programming or deep learning expertise needed.
ViDi EL Classify
The ViDi EL Classify tool uses deep learning to automatically identify and sort objects into classes based on multiple defect types or user-defined features. Within the same class of objects, this advanced classifier is capable of discerning visually similar, but different objects. From as simple as OK/NG all the way to classifying parts with variation, ViDi EL Classify can be used to detect errors for a wide range of products.