基于深度学习的织物缺陷在线检测算法
|
摘要
织物缺陷在线检测是纺织行业面临的重大难题,针对当前织物缺陷检测中存在的误检率高、漏检率高、实时性不强等问题,提出了一种基于深度学习的织物缺陷在线检测算法。首先基于GoogLeNet网络架构,并参考其他分类模型的经典算法,搭建出适用于实际生产环境的织物缺陷分类模型;其次利用质检人员标注的不同种类织物图片组建织物缺陷数据库,并用该数据库对织物缺陷分类模型进行训练;最后对高清相机在织物验布机上采集的图片进行分割,并将分割后的小图以批量的方式传入训练好的分类模型,实现对每张小图的分类,以此来检测缺陷并确定其位置。对该模型在织物缺陷数据库上进行了验证。实验结果表明:织物缺陷分类模型平均每张小图的测试时间为0.37 ms,平均测试时间比GoogLeNet减少了67%,比ResNet-50减少了93%;同时模型在测试集上的正确率达到99.99%。说明其准确率与实时性均满足实际工业需求。
On-line detection of fabric defects is a major problem faced by textile industry. Aiming at the problems such as high false positive rate, high false negative rate and low real-time in the existing detection of fabric defects, an on-line detection algorithm for fabric defects based on deep learning was proposed. Firstly, based on GoogLeNet network architecture, and referring to classical algorithm of other classification models, a fabric defect classification model suitable for actual production environment was constructed. Secondly, a fabric defect database was set up by using different kinds of fabric pictures marked by quality inspectors, and the database was used to train the fabric defect classification model. Finally, the images collected by high-definition camera on fabric inspection machine were segmented, and the segmented small images were sent to the trained classification model in batches to realize the classification of each small image. Thereby the defects were detected and their positions were determined. The model was validated on a fabric defect database. The experimental results show that the average test time of each small picture is 0.37 ms by this proposed model, which is 67% lower than that by GoogLeNet, 93% lower than that by ResNet-50, and the accuracy of the proposed model is 99.99% on test set, which shows that its accuracy and real-time performance meet actual industrial demands.
On-line detection of fabric defects is a major problem faced by textile industry. Aiming at the problems such as high false positive rate, high false negative rate and low real-time in the existing detection of fabric defects, an on-line detection algorithm for fabric defects based on deep learning was proposed. Firstly, based on GoogLeNet network architecture, and referring to classical algorithm of other classification models, a fabric defect classification model suitable for actual production environment was constructed. Secondly, a fabric defect database was set up by using different kinds of fabric pictures marked by quality inspectors, and the database was used to train the fabric defect classification model. Finally, the images collected by high-definition camera on fabric inspection machine were segmented, and the segmented small images were sent to the trained classification model in batches to realize the classification of each small image. Thereby the defects were detected and their positions were determined. The model was validated on a fabric defect database. The experimental results show that the average test time of each small picture is 0.37 ms by this proposed model, which is 67% lower than that by GoogLeNet, 93% lower than that by ResNet-50, and the accuracy of the proposed model is 99.99% on test set, which shows that its accuracy and real-time performance meet actual industrial demands.
引文
[1] HARALICK R M,SHANGMUGAN K,DINSTEIN I.Textural features for image classification[J].IEEE Transactions on Systems,Man,and Cybernetics,1973,3(6):610-621.
[2] NGAN H Y T,PANG G K H,YUNG S P,et al.Wavelet based methods on patterned fabric defect detection[J].Pattern Recognition,2005,38(4):559-576.
[3] 张杨,蒋高明,姚君洲,等.基于MRF层次模型的贾失经编针织物图像分割技术[J].纺织学报,2012,33(12):102-106.(ZHANG Y,JIANG G M,YAO J Z,et al.Segmentation of jacquard warp-knitted fabric image based on hierarchical Markov random field model[J].Journal of Textile Research,2013,33(12):102-106.)
[4] SZEGEDY C,IOFFE S,VANHOUCKE V,et al.Inception-v4,Inception-ResNet and the impact of residual connections on learning [EB/OL] (2016- 08- 23) [2018- 10- 15].https://arxiv.org/pdf/1602.07261.pdf.
[5] LIU W,ANGUELOV D,ERHAN D,et al.SSD:single shot multibox detector [EB/OL].[2018- 10- 15] https://arxiv.org/pdf/1512.02325.pdf.
[6] CHEN L C,PAPANDREOU G,KOKKINOS I,et al.DeepLab:semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected CRFs[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,40(4):834-848.
[7] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet classification with deep convolutional neural networks[C]// Proceedings of the 9th International Conference on Neural Information Processing Systems.Berlin:Springer,2012:1097-1105.
[8] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition [EB/OL].(2015- 04- 10) [2018- 10- 15].https://arxiv.org/abs/1409.1556.
[9] SZEGEDY C,LIU W,JIA Y,et al.Going deeper with convolutions [EB/OL].(2014- 07- 17) [2016- 12- 10].https://arxiv.org/abs/1409.4842.
[10] HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[EB/OL].(2015- 12- 10) [2018- 10- 15].https://arxiv.org/abs/1512.03- 385.
[11] LeCUN Y,BOTTOU I,BENGIO Y,et al.Gradient-based learning applied do document recognition [J].Proceedings of the IEEE,1998,86(11):2278-2324.
[12] JARRETT K,KAVUKCUOGLU K,RANZATO M,et al.What is the best multi-stage architecture for object recognition?[EB/OL] [2018- 10- 15].http://yann.lecun.com/exdb/publis/orig/jarrett-iccv- 09.pdf.
[13] LIN M,CHEN Q,YAN S.Network in network[EB/OL].(2014- 03- 04) [2018- 10- 15].https://arxiv.org/abs/1312.4400.
[14] HE K,ZHANG X,REN S,et al.Identity mappings in deep residual networks [EB/OL].(2016- 07- 25) [2018- 10- 15].http://arxiv.org/obs/1603.05027.
[15] IOFFE S,SZEGEDY C.Batch normalization:accelerating deep network training by reducing internal covariate shift [EB/OL].[2018- 10- 15].http//arxiv.org/pdf/1502.03167.pdf.
[16] BOTTOU L.Large-scale machine learning with stochastic gradient descent [C]// Proceedings of the 19th International Conference on Computational Statistics.Berlin:Springer,2010:177-186.
[17] RUDER S.An overview of gradient descent optimization algorithms [EB/OL].(2017- 06- 15) [2018- 10- 15].https://arxiv.org/abs/1609.04747.
[2] NGAN H Y T,PANG G K H,YUNG S P,et al.Wavelet based methods on patterned fabric defect detection[J].Pattern Recognition,2005,38(4):559-576.
[3] 张杨,蒋高明,姚君洲,等.基于MRF层次模型的贾失经编针织物图像分割技术[J].纺织学报,2012,33(12):102-106.(ZHANG Y,JIANG G M,YAO J Z,et al.Segmentation of jacquard warp-knitted fabric image based on hierarchical Markov random field model[J].Journal of Textile Research,2013,33(12):102-106.)
[4] SZEGEDY C,IOFFE S,VANHOUCKE V,et al.Inception-v4,Inception-ResNet and the impact of residual connections on learning [EB/OL] (2016- 08- 23) [2018- 10- 15].https://arxiv.org/pdf/1602.07261.pdf.
[5] LIU W,ANGUELOV D,ERHAN D,et al.SSD:single shot multibox detector [EB/OL].[2018- 10- 15] https://arxiv.org/pdf/1512.02325.pdf.
[6] CHEN L C,PAPANDREOU G,KOKKINOS I,et al.DeepLab:semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected CRFs[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,40(4):834-848.
[7] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet classification with deep convolutional neural networks[C]// Proceedings of the 9th International Conference on Neural Information Processing Systems.Berlin:Springer,2012:1097-1105.
[8] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition [EB/OL].(2015- 04- 10) [2018- 10- 15].https://arxiv.org/abs/1409.1556.
[9] SZEGEDY C,LIU W,JIA Y,et al.Going deeper with convolutions [EB/OL].(2014- 07- 17) [2016- 12- 10].https://arxiv.org/abs/1409.4842.
[10] HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[EB/OL].(2015- 12- 10) [2018- 10- 15].https://arxiv.org/abs/1512.03- 385.
[11] LeCUN Y,BOTTOU I,BENGIO Y,et al.Gradient-based learning applied do document recognition [J].Proceedings of the IEEE,1998,86(11):2278-2324.
[12] JARRETT K,KAVUKCUOGLU K,RANZATO M,et al.What is the best multi-stage architecture for object recognition?[EB/OL] [2018- 10- 15].http://yann.lecun.com/exdb/publis/orig/jarrett-iccv- 09.pdf.
[13] LIN M,CHEN Q,YAN S.Network in network[EB/OL].(2014- 03- 04) [2018- 10- 15].https://arxiv.org/abs/1312.4400.
[14] HE K,ZHANG X,REN S,et al.Identity mappings in deep residual networks [EB/OL].(2016- 07- 25) [2018- 10- 15].http://arxiv.org/obs/1603.05027.
[15] IOFFE S,SZEGEDY C.Batch normalization:accelerating deep network training by reducing internal covariate shift [EB/OL].[2018- 10- 15].http//arxiv.org/pdf/1502.03167.pdf.
[16] BOTTOU L.Large-scale machine learning with stochastic gradient descent [C]// Proceedings of the 19th International Conference on Computational Statistics.Berlin:Springer,2010:177-186.
[17] RUDER S.An overview of gradient descent optimization algorithms [EB/OL].(2017- 06- 15) [2018- 10- 15].https://arxiv.org/abs/1609.04747.