A Novel Scratch Detection and Measurement Method for Automotive Stamping Parts

作者：Changying Liu, Bo-Wen An, Yuguang Hou, Hao Wang, Yang Liu · 发表于：IEEE Transactions on Instrumentation and Measurement · 年份：2022 · DOI：10.1109/tim.2022.3193970 · 被引用次数：7 · 研究领域：Industrial Vision Systems and Defect Detection、Optical measurement and interference techniques、Image and Object Detection Techniques

In this paper, 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 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 with other methods. The results prove the practicality and effectiveness of the method.