A Novel Scratch Detection and Measurement Method for Automotive Stamping Parts

In this article, a novel scratch detection and measurement method for automotive stamping parts is proposed to detect and measure scratches. This method uses the geometric characteristics of the point cloud for the detection and measurement of scratches and does not require registration with a standard point cloud model. In this method, a scratch localization algorithm called bilateral weight integration is proposed. Then a scratch complement algorithm called NRPCA-RG is proposed to ensure that the complete scratch is obtained. Finally, we propose an improved principal component analysis (PCA)-based scratch size measurement method called P-NRPCA to measure the length, width, and depth of scratches. We conducted an experimental study on two stamping parts with scratches and compared them with other methods. The results prove the practicality and effectiveness of the method.