YOLOv11-LLR: An Enhanced Framework for Steel Surface Defect Detection in Industrial Settings

Steel surface defects in manufacturing are typically tiny, low-contrast, and boundary-ambiguous, especially under complex textures (e.g., rolling marks, crazing), poor illumination, and high noise. These characteristics cause frequent missed detections and localization errors, particularly for defec...

Descrición completa

Detalles Bibliográficos

Principais autores:	Jin Li, Yingjian Yang, Runhua Geng, Yaohui Chang, Yuan Jiang, Kaiwen Wu, Jinhuan Lu
Formato:	Artigo
Idioma:	Inglês
Publicado:	MDPI AG 2026-05-01
Series:	Applied Sciences
Assuntos:	YOLOv11 defect detection Deformable Large Kernel Attention (DLKA) Lightweight Group Attention (LWGA) Re-parameterized Convolution (RepConv)
Acceso en liña:	https://www.mdpi.com/2076-3417/16/10/4609
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!