Catching and analyzing defects in real-time helps manufacturers improve production efficiency and achieve higher yields by catching problems when they are the easiest and most cost-effective to fix.
Prusight application is trained on a dataset of specific objects (e.g., images of defects) and then it classifies each of these objects into different sets of categories as modeled on your shop floor. The application is trained to recognize a specific instance of an object. For instance, when it determines two components in an image it can mark one as a circuit board and the other as a microcontroller.
The application encompasses deep learning techniques that learn from images of good and bad parts, reducing the time needed to specify defects and respond to changing requirements.