基于光电自动验布机视觉系统的织物疵点检测
2020-07-07 10:41:18   来源：   评论：0 点击：

 
摘要：为了提升织造织物质量、提高验布效率，介绍FS220型光电自动验布机的工作原理，以及特征明显织物疵点和特征不明显织物疵点的检测流程，对其采用的傅里叶变换与高斯滤波相结合的疵点检测算法和Sobel算子与Laplace算子相结合的疵点检测算法进行分析；对比分析纺织厂使用FS220型光电自动验布机与人工验布的结果。指出：采用多算法混合检测的FS220型光电自动验布机验布速度快、疵点的正检率高，可有效替代人工验布、节约人工成本，提高织物质量和企业经济效益，可促进织物疵点检测的数字化、智能化发展。
关键词：光电自动验布机；视觉；织物；疵点；检测；傅里叶变换；高斯滤波；Sobel；Laplace；算子；正检率；误判率
中图分类号：TS105.5⁺1    文献标志码：B    文章编号：1001-9634(2020)01-0057-04
 
收稿日期：2019-09-20
作者简介：董康乐(1987—)，男，陕西商洛人，硕士研究生，主要从事纺织类机器视觉、图像处理、模式识别方面的研究。
   
Abstract:In order to improve the fabric quality and efficiency of cloth inspection,the working principle of photoelectric automatic cloth inspection machine FS220 and the detection process of fabric defects with obvious features and non-obvious features are introduced.The defect detection algorithm based on Fourier transform and Gauss filter and the defect detection algorithm based on Sobel operator and Laplace operator are analyzed.The results of photoelectric automatic cloth inspection machine FS220 and manual cloth inspection in textile mills are compared and analyzed.It is pointed out that the photoelectric automatic cloth inspection machine FS220 with multi-algorithm hybrid detection has the advantages of fast speed of cloth inspection and high positive rate of defects.It can effectively replace manual cloth inspection,save labor costs,improve fabric quality and economic benefits of enterprises,and promote the development of digitalization and intellectualization of fabric defect detection.
Key Words:photoelectric automatic cloth inspection machine;vision;fabric;defect; detection;Fourier transform;Gauss filtering;Sobel;Laplace;operator;correction rate;misjudgment rate
 
参考文献：
［1］ Srinivasan K，Dastoor P H，Radhakrishnaiah P，et al.FDAS:A Knowledge-based Frame Detection Work for Analysis of Defects in Woven Textile Structures［J］.Journal of the Textile Institute，1992，83(3)：431-447.
［2］ Schiktanz K.Automatic Fault Detection Possibilities on Nonwoven Fabrics［J］.Melliand Textilberichte,1993,74：294-295.
［3］ Kim S C,Kang T J.Automated Defect Detection System Using Wavelet Packet Frame and Gaussian Mixture Model［J］.J OPT SOC AM A,2006,23(11)：2690-2701.
［4］ EVS Corporation.IQ-TEX Introduction［N］.Texas Digital Newspaper，2009-02-19（1）.
［5］ 李立轻.基于计算机视觉的织物疵点自动检测系统研究［D］.上海：东华大学，2003.
［6］ 夏良正.数字图像处理［M］.南京：东南大学出版社，1999.