自动化与信息工程2026，Vol.47Issue(4)：55-62,8.DOI:10.12475/aie.20260408
改进SAM的皮革缺陷分割与自适应裁切方法
An Improved SAM for Leather Defect Segmentation and Adaptive Cropping
郭瑞桁 1郭瑞洲 1刘夏丽2
作者信息
- 1. 广东瑞洲科技有限公司,广东佛山 528200
- 2. 广东工业大学,广东 广州 510006
- 折叠
摘要
Abstract
To address the issues of leather surface defect localization and CAD path deviations caused by flexible cutting piece deformation,we propose an improved SAM-based method for leather defect segmentation and adaptive cropping.This method constructs Leather-SAM based on the SAM-Med2D ViT-B image encoder and a channel-spatial dual-branch adapter,and combines ORB feature matching,global affine transformation matrix,and multi-beam cutting safety control to build a defect recognition and cutting optimization algorithm based on Leather-SAM.Experimental results show that the method achieves IoU,Dice,and contour Fl scores of 54.58％,65.22％,and 88.08％,respectively,with an inference speed of 12.2 f/s,providing a reproducible technical pipeline for intelligent leather layout and cutting.关键词
皮革缺陷/SAM-Med2D/二值分割/仿射校正/自适应裁切Key words
leather defect/SAM-Med2D/binary segmentation/affine correction/adaptive cropping分类
信息技术与安全科学引用本文复制引用
郭瑞桁,郭瑞洲,刘夏丽..改进SAM的皮革缺陷分割与自适应裁切方法[J].自动化与信息工程,2026,47(4):55-62,8.
