High-Performance Fine Defect Detection in Artificial Leather Using Dual Feature Pool Object Detection

Abstract

In this study, the structural problems of the YOLOv5 model were analyzed emphatically. Based on the characteristics of fine defects in artificial leather, four innovative structures, namely DFP, IFF, AMP, and EOS, were designed. These advancements led to the proposal of a high-performance artificial leather fine defect detection model named YOLOD. YOLOD demonstrated outstanding performance on the artificial leather defect dataset, achieving an impressive increase of 11.7% - 13.5% in AP50 compared to YOLOv5, along with a significant reduction of 5.2% - 7.2% in Average Error Detection (AE). Furthermore, YOLOD demonstrated outstanding performance on the comprehensive MS-COCO dataset, showcasing an improvement ranging from 0.4% to 2.6% in AP when compared to YOLOv5. Notably, it achieved a significant boost of 2.5% and 4.1% in APS compared to YOLOX-L and YOLOv4-CSP, respectively. These results demonstrate the superiority of YOLOD in both artificial leather defect detection and general object detection tasks, making it a highly efficient and effective model for real-world applications.

Keywords: Object detection, defect detection, Artificial leather, Fine defect