摘要
为了控制产品质量,保障织物的美观和舒适性,针对织物表面的缺陷,课题组提出了一种基于L0梯度最小化和K-Means聚类的缺陷检测方法。主要分为2个步骤:首先,使用L0梯度最小化将缺陷图像进行平滑,去除背景纹理的影响,保留图像较大的边缘;然后,使用K-Means聚类对平滑后的图像进行聚类,从而分割出缺陷区域。将该检测方法用于纺织厂收集的缺陷图像上进行验证,实验结果表明该方法能准确地检测出织物表面缺陷。该项研究提高了检测效率,满足织物生产的要求。
In order to control the product quality and ensure the aesthetic and comfort of the fabric,a defect detection method based on L0 gradient minimization and K-Means clustering was proposed for the defects on the fabric surface.It is mainly divided into two steps,the L0 gradient minimization was used to smooth the defective image and remove the influence of the background texture firstly,and the larger edges of the image were retained.Then the K-Means clustering was used to cluster the smoothed image to segment the defect area.Finally,the proposed method was applied to verify the defect images collected by textile factory.The experimental results show that the method can accurately detect the defects on fabric surface,which improves the detection efficiency and meet the requirements of fabric production.
作者
刘纪
张团善
李秀昊
LIU Ji;ZHANG Tuanshan;LI Xiuhao(School of Mechanical and Electrical Engineering,Xi’an Polytechnic University,Xi'an 710048,China;Guangzhou Institute of Advanced Technology,Chinese Academy of Sciences,Guangzhou 511458,China)
出处
《轻工机械》
CAS
2021年第1期67-71,共5页
Light Industry Machinery
基金
国家自然科学基金青年项目(61701384)。