Cosmetic Defect Inspection
Detect unpredictable defects on challenging surfaces
One of the biggest challenges when dealing with surface defects on consumer packaged goods is that they are dynamic, often caused by the forming process. Typical defects like hits, scratches, or stains may be indiscernable on a part’s textured surface during early production. These defects only become visible under specific lighting conditions later in the production process. While the cost of late detection can be painfully high, so can false rejects be. Normal variations and certain cosmetic anomalies that do not affect a product’s performance need to be tolerated by the inspection system. Traditional rules-based vision algorithms often struggle to appreciate these nuances.
Cognex ViDi deep learning-based image analysis software detects defects on rough and strongly-textured metal surfaces as reliably as human inspectors, but with the speed of a computerized system. The ViDi Red-Analyze tool catches defects on coarse material with standard illumination, even when image quality is poor, by forming a reliable model of the part’s shape and texture based on training images. From here, ViDi identifies deviations in the surface texture as anomalies and classifies them as hits or scratches.