Machine Learning based Hybrid Method for Surface Defect Detection and Categorization in PU Foam
Shailendra Singh Kathait, Sakshi Mathur
Foam making is an important industry with foam mattress being one of the main end products. To ensure quality production, their manufacturing is subject to very strict safety checks. There are many types of defects that can arise during their manufacturing process such as holes, cuts, mis-configuration in the material etc. Manual defect detection leads to inaccuracy and increases the chances of defects going unnoticed. This further reduces the process efficiency and creates adverse affect on overall production.
To counter this situation, this research paper proposes a hybrid approach that identifies defects present in and on the surface of PU (Polyurethane) foam material. Both supervised and unsupervised approaches are used to classify the PU foam into two categories: normal and defective, considering the type of defect. Then the reliable model is selected according to the precision rate of both the models.