摘要
缺陷检测是纺织布生产中的重要环节。针对人工验布存在速度慢、漏检率高等问题,文中提出了一种基于数字图像处理技术的纺织布表面缺陷检测。对于采集到的织物图像,先对图像进行预处理,消除噪声干扰,随后采用Ostu法对织物缺陷区域图像进行分割,然后提取缺陷图像的矩形度、圆形度、长宽比、离心率以及Hu不变矩等特征,并将特征矩阵输入BP神经网络进行训练和检测,最终自动返回检测的缺陷类型。实验结果表明,文中所提算法能有效检测织物缺陷,具有检测精度高和检测时间短的特点。
Defect detection is an important process in textile fabric production.A surface defect detection method for textile fabrics based on digital image processing technology is proposed to address the issues of slow speed and high miss rate in manual fabric inspection.For the collected fabric images,the image is preprocessed to eliminate noise interference,and then the Ostu method is used to segment the fabric defect area image.Then,the rectangular degree,circularity,aspect ratio,eccentricity,and Hu invariant moments of the defect image are extracted,and the feature matrix is input into the BP neural network for training and detection,automatically returning to the detected defect type.The experiment results show that the algorithm proposed in this paper can detect fabric defects with high detection accuracy and short detection time.
作者
王敏
许永琪
吴佳
许卓汶
曹冉
WANG Min;XU Yong-qi;WU Jia;XU Zhuo-wen;CAO Ran(School of Electronics and Information Engineering,Nanjing University of Information Science and Technology,Nanjing 210044,China;Electronics and Information Engineering College,Anhui Jianzhu University,Hefei 230601,China;Suzhou Minjie Robot Technology Co.,Ltd.,Suzhou 215159,Jiangsu Province,China)
出处
《信息技术》
2025年第12期1-5,共5页
Information Technology
基金
国家自然科学基金资助项目(41775165,41775039)
安徽省高校杰出青年科研项目(2023AH020022)
南京信息工程大学人才启动经费资助项目(2021r034)。
关键词
织物缺陷检测
图像采集
图像处理
BP算法
fabric defect detection
image acquisition
image processing
BP algorithm
