Abstract
Surface defects have a significant effect on the mechanical properties of aluminium strips. However, the current defect identification algorithm needs to be further improved to meet the quality inspection requirements for aluminium products. The scheme of non-subsampled shearlet transform and the kernel locality preserving projection (NSST-KLPP) are applied to identify surface defects of aluminium strips. The defect images collected from a cold rolling line of aluminium strips were tested, including five true defect types of point imprints, scratches, dents, roll marks and wrinkles, and three pseudo defect types of lighting variation, water marks and oil stains. The test results show that a 97.71% recognition rate is achieved, which is higher than those obtained from the commonly used methods published in literature. The NSST-KLPP provides a new scheme for the identification of surface defects of aluminium strips.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call