基于Closed-Form抠图算法的线缆绝缘边缘检测  

Cable Insulation Edge Detection Based on Closed-Form Matting Algorithm

作　　者：张吉福 李日新 ZHANG Jifu;LI Rixin(Jiangxi General Institute of Testing and Certification Institute of Inspection and Testing for Industrial Products,Nanchang 330000,China)

机构地区：[1]江西省检验检测认证总院工业产品检验检测院,南昌330000

出　　处：《电线电缆》2025年第3期74-79,共6页Wire & Cable

摘　　要：针对当前自动化设备存在的因线缆绝缘边缘检测精度不足导致厚度测量不精确的问题,提出一种基于Closed-Form抠图算法的绝缘边缘检测方法。将成像中的绝缘部分视为前景像素,垫片部分视为背景像素,对成像施加一定的约束条件,通过Closed-Form抠图算法估算未知像素的不透明度,实现绝缘像素精确提取,最终测量出线缆的绝缘厚度。仿真与试验结果表明,文中所提方法能够有效提取线缆绝缘边缘,提升绝缘厚度的测量精度。Aiming at the problem of inaccurate thickness measurement caused by insufficient detection accuracy of cable insulation edge in current automated equipment,a insulation edge detection method based on Closed-Form matting algorithm was proposed.Regarding insulating part in imaging as foreground pixels and gasket part as background pixels,imposing certain constraints on imaging,opacity of unknown pixels through Closed-Form matting algorithm was estimated,accurate extraction of insulation pixels was achieved,finally insulation thickness of cables was measured.Simulation and experimental results showed that the proposed method could effectively extract cable insulation edges and improve measurement accuracy of insulation thickness.

关 键 词：Closed-Form 抠图 线缆绝缘 前景像素 背景像素 不透明度 

分 类 号：TM247[一般工业技术—材料科学与工程]