基于迁移学习和改进ResNet50网络的织物疵点检测算法  

Fabric defect detection algorithm based on migration learning and improved ResNet50 network

作　　者：罗维平 徐洋 陈永恒 周博 马双宝 吴雨川 LUO Weiping;XU Yang;CHEN Yongheng;ZHOU Bo;MA Shuangbao;WU Yuchuan(School of Mechanical Engineering and Automation,Wuhan Textile University,Wuhan,Hubei 430200,China;Hubei Provincial Key Laboratory of Digital Textile Equipment,Wuhan,Hubei 430200,China)

机构地区：[1]武汉纺织大学机械工程与自动化学院,湖北武汉430200 [2]湖北省数字化纺织装备重点实验室,湖北武汉430200

出　　处：《毛纺科技》2021年第2期71-78,共8页Wool Textile Journal

基　　金：国家自然科学基金项目(61271008);湖北省数字化纺织装备重点实验室公开项目(DTL2019020)。

摘　　要：针对目前工业现场织物疵点检测准确率低、速度慢和疵点识别种类少的问题,提出一种改进ResNet50网络的织物疵点检测算法。首先对数据集进行预处理,对数据样本切割增强生成模型训练集,包括无疵点和8类常见疵点类别;然后改进ResNet50网络结构,提取在大型数据集ImageNet上预训练好的权重参数迁移学习;最后反复调整超参数训练得到的疵点检测识别模型。通过多组对比实验结果表明,改进模型对正常织物和8类常见疵点识别准确率达到96.32%,比标准模型精度提升4.2%,速度提升1倍。在不同织物疵点数据集中测试,综合性能最好,泛化能力强,鲁棒性好,可以满足工业生产现场织物疵点检测需求。Aiming at the problems of low accuracy,slow speed and low defect identification of industrial site fabric defect detection,a improved fabric defect detection algorithm based on ResNet50 network is proposed.Firstly,the data set was preprocessed,and the model training set was enhanced by cutting the data samples,including the fault-free and 8 common defect categories.Then,the structure of Resnet50 network was improved to extract the weight parameters pre-trained on the large data set ImageNet for transfer learning.Finally,the defect detection and recognition model obtained by hyper parameter training was adjusted repeatedly.The results of several groups of comparative experiments show that the recognition accuracy of the improved model for normal fabric and 8 common defects reaches 96.32%,which is 4.2%higher than that of the standard model,and the speed is doubled.The test in different fabric defect data sets has the best comprehensive performance,strong generalization ability and good robustness,which can meet the requirements of fabric defect detection in industrial production sites.

关 键 词：疵点检测 迁移学习 特征提取 ResNet50 预训练模型 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TS106[自动化与计算机技术—控制科学与工程]