Intelligent detection of fastener defects and mixed assortments

Abstract

This paper investigates the use of artificial intelligence (AI) image detection and discrimination technology to address issues related to mixed assortments and defects encountered in the fastener manufacturing and packaging processes. The defect detection system primarily utilizes the YOLOv4-tiny model with parameter setting and data augmentation techniques. The mixed assortments detection system is constructed using U-Net-Light and Siamese network. The research results demonstrate that the developed systems can indeed replace or assist on-site personnel in conducting efficient and accurate inspections and screenings.

Keywords

• Artificial intelligence
• Fastener
• Defect
• Mixed assortments
• Detection