Faster RCNN模型在坯布疵点检测中的应用
|
摘要
探讨Faster RCNN模型在坯布疵点检测中的应用效果。在原始Faster RCNN的基础上,采用提取特征效果更好的深度残差网络,先使用残差网络进行坯布图像特征提取,再通过区域生成网络及Fast RCNN检测网络对坯布的疵点目标进行分类与检测。试验对比了Faster RCNN分别与VGG16、ResNet101结合时的检测结果,并讨论了不同参数对结果的影响。试验结果表明:该方法可以有效解决坯布疵点检测问题,检测准确率能够达到99.6%。认为:基于Faster RCNN目标检测与ResNet101卷积神经网络相结合的方法能够满足坯布生产过程中对于表面疵点进行准确检测的需求。
The application effect of Faster RCNN mold used in gray fabric defect detection was discussed.Based on original Faster RCNN,deep residual network with better feature extraction effect was adopted.Residual network was firstly used for the feature extraction of grey fabric.Then,network was generated by district and Fast RCNN detection network was used for the classification and detection of targeted defects in gray fabrics.The detection effect was compared when Faster RCNN was combined with VGG16 and ResNet101respectively.The influence of different parameters on the results were discussed.The test results showed that the method could efficiently solve the defect detection problem of gray fabrics.The detection accuracy could be reached 99.6%.It is considered that the method by combining Faster RCNN target detection and ResNet 101 convolution neural network can meet the requirement of gray fabric production process on surface defect detection.
The application effect of Faster RCNN mold used in gray fabric defect detection was discussed.Based on original Faster RCNN,deep residual network with better feature extraction effect was adopted.Residual network was firstly used for the feature extraction of grey fabric.Then,network was generated by district and Fast RCNN detection network was used for the classification and detection of targeted defects in gray fabrics.The detection effect was compared when Faster RCNN was combined with VGG16 and ResNet101respectively.The influence of different parameters on the results were discussed.The test results showed that the method could efficiently solve the defect detection problem of gray fabrics.The detection accuracy could be reached 99.6%.It is considered that the method by combining Faster RCNN target detection and ResNet 101 convolution neural network can meet the requirement of gray fabric production process on surface defect detection.
引文
[1]陈俊杰,谢春萍.自动验布系统[J].纺织科技进展,2004(5):56-57.
[2]杨曼.基于改进迭代匹配滤波的织物疵点检测[J].西安工程大学学报,2017,31(3):383-389.
[3] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenet Classification with Deep Convolutional Neural Networks[C]∥Advances in Neural Information Processing Systems,2012:1097-1105.
[4] DENG J,DONG W,SOCHER R,et al.Imagenet:A Large-scale Hierarchical Image Database[C]∥Computer Vision and Pattern Recognition,2009:248-255.
[5] SZEGEDY C,LIU W,JIA Y,et al.Going Deeper with Convolutions[C]∥Computer Vision and Pattern Recognition,2015.
[6] SIMONYAN K,ZISSERMAN A.Very Deep Convolutional Networks for Large-Scale Image Recognition[J].Computer Science,2014.
[7]HE K,ZHANG X,REN S,et al.Deep Residual Learning for Image Recognition[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016,770-778.
[8] HE K,ZHANG X,REN S,et al.Identity Mappings in Deep Residual Networks[C]∥European Conference on Computer Vision.Springer,Cham,2016:630-645.
[9] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2014:580-587.
[10]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards Real-time Object Detection with Region Proposal Networks[C]∥Advances in Neural Information Processing Systems,2015:91-99.
[11]UIJLINGS J R R,SANDE K E A V D,GEVERS T,et al.Selective Search for Object Recognition[J].International Journal of Computer Vision,2013,104(2):154-171.
[12]LONG J,SHELHAMER E,DARRELL T.Fully Convolutional Networks for Semantic Segmentation[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2015:3431-3440.
[13]ELZENSZWALB P F,GIRSHICK R B,MCALLESTER D,et al.Object Detection with Discriminatively Trained Part-based Models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(9):1627-1645.
[2]杨曼.基于改进迭代匹配滤波的织物疵点检测[J].西安工程大学学报,2017,31(3):383-389.
[3] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenet Classification with Deep Convolutional Neural Networks[C]∥Advances in Neural Information Processing Systems,2012:1097-1105.
[4] DENG J,DONG W,SOCHER R,et al.Imagenet:A Large-scale Hierarchical Image Database[C]∥Computer Vision and Pattern Recognition,2009:248-255.
[5] SZEGEDY C,LIU W,JIA Y,et al.Going Deeper with Convolutions[C]∥Computer Vision and Pattern Recognition,2015.
[6] SIMONYAN K,ZISSERMAN A.Very Deep Convolutional Networks for Large-Scale Image Recognition[J].Computer Science,2014.
[7]HE K,ZHANG X,REN S,et al.Deep Residual Learning for Image Recognition[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016,770-778.
[8] HE K,ZHANG X,REN S,et al.Identity Mappings in Deep Residual Networks[C]∥European Conference on Computer Vision.Springer,Cham,2016:630-645.
[9] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2014:580-587.
[10]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards Real-time Object Detection with Region Proposal Networks[C]∥Advances in Neural Information Processing Systems,2015:91-99.
[11]UIJLINGS J R R,SANDE K E A V D,GEVERS T,et al.Selective Search for Object Recognition[J].International Journal of Computer Vision,2013,104(2):154-171.
[12]LONG J,SHELHAMER E,DARRELL T.Fully Convolutional Networks for Semantic Segmentation[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2015:3431-3440.
[13]ELZENSZWALB P F,GIRSHICK R B,MCALLESTER D,et al.Object Detection with Discriminatively Trained Part-based Models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(9):1627-1645.