基于机器视觉的纺织品疵点检测系统  

The Fabric Defect Inspection System Based on Machine Visual Technology

作　　者：姜荣[1] 董军宇[1] 唐瑞春[1] 

机构地区：[1]中国海洋大学

出　　处：《楚雄师范学院学报》2005年第6期1-3,9,共4页Journal of Chuxiong Normal University

摘　　要：本文研究了一种基于机器视觉的纺织品疵点检测系统,它采用模块化硬件设计,图像处理软件满足实时检测的要求,可以有效检测出生产线上的疵点。并为该系统设计了一种基于规则表分类器、模糊算法及人工神经网络的组合式多级分类器,具有一定的学习能力,当待测材料或有关设备发生变化时,系统可根据疵点样本库对分类器进行训练,以适应生产线的相关变化。实验结果验证了该方法的有效性。The fabric defect inspection system based on machine visual technology was presentecl using modularized frame of hardware. The software of image processing can detect and classify defects across the entire fabric surface. The system develops an effective assembled classifier by several pattern recognition technologies including role - based table, fuzzy algorithm and neural network. The software has the ability of self- learning and can adapt to different equipments and materials by the training of classifier according to different sets of samples. The experimental results demonstrate the effectiveness of our approach.

关 键 词：机器视觉技术 织物疵点检测 分类器 神经网络 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]