Chewing gum inspection
Detect cosmetic defects among large numbers of small, curved items
Graphical programming environment for deep learning-based industrial image analysis
Chewing gum, nicotine gum, and other small, smooth, curved items can have a variety of cosmetic defects such as dents or scratches on their surface, as well as other anomalies that are considered acceptable.
Minor damage to such small smooth-surfaced items is common and frequently missed among the large number that need to be inspected.
The subtlety and variability of the possible defects along with the variation in acceptable appearance makes it impossible to program conventional machine vision to detect all defects while passing acceptable items.
Cognex AI-powered solutions reliably inspect these types of products to avoid defective items reaching customers. It trains on a small set of images of undamaged items and another of items with various types of cosmetic damage. The classification tool then rapidly sorts the gum or other item into acceptable and unacceptable categories. This enables a level of quality not achievable through other types of visual inspection.
Customers receive blemish-free chewing or nicotine gum.