Vial and Ampoule Body Inspection
Detect defects in transparent and reflective vials
Cracks on the bottom or edges of glass vials and ampoules and other defects such as scratches, bubbles, black spots, and inclusions can cause contamination of the contents or a breach of sterility. Vial and ampoule inspection must identify these defects before they reach customers to protect patient safety. Pharmaceutical glass can also exhibit minor defects, such as scratches, that do not affect function and can safely be shipped.
Given the transparent nature of the borosilicate glass used in vials and ampoules, it can be difficult to discern between defective and tolerable defects with standard machine vision, both because of transparency and reflections, and because rule-based vial defect detection cannot be programmed to handle all possible unpredictable defects.
Cognex Deep Learning is designed to solve these types of complex inspections since it is able to distinguish between true defects and acceptable cosmetic anomalies. The defect detection tool trains on a wide selection of glass vials, at different angles, to learn the full variation of normal parts, including the acceptable level of cosmetic defects. Then, as it scans through the vials it analyzes and flags any that are outside the acceptable range, while minimizing false positives caused by cosmetic defects.
In addition to powerful deep learning toolsets, Cognex Deep Learning supports High Dynamic Range Plus (HDR+) technology. HDR+ is a patent-pending, advanced image formation technology by Cognex. It overcomes the bright, changing reflections from glass to create a more uniform image, revealing hidden defects and improving inspections. HDR+ differs from standard HDR as it can be done with a single acquisition at high-speed on moving parts, whereas standard HDR would need to be stationary and capture multiple images to obtain the same results.