How to Train and Deploy Edge Learning
Training edge learning is similar to training a new employee on the line.
What the user of edge learning needs to know is not how vision systems or artificial intelligence (AI) works, but what problem they need to solve. If it is straightforward, for instance classifying acceptable and unacceptable parts as OK/NG, the user needs to know which parts are acceptable and which are not. This can include knowledge not readily apparent, derived from testing down the line, that reveals defects hard for a human to detect. Edge learning is particularly effective at determining which variations in the part are significant, and which variations are purely cosmetic and do not affect functionality.
Edge learning is not limited to binary classification but can classify into any number of categories. If parts need to be sorted into three or four different categories, depending on components or configurations, that can be deployed just as easily. Edge learning is also capable of directing attention to multiple regions of interest (ROI) in the image. And, of course, both multiple ROIs and multiple categories can be handled together, as in the classification example here (link to page with frozen food tray example).
Watch a step-by-step tutorial on how to train and deploy edge learning tools below.