Yarn-dyed fabric defect classification based on convolutional neural network

Abstract. Considering that manual inspection of the yarn-dyed fabric can be time consuming and inefficient, we propose a yarn-dyed fabric defect classification method by using a convolutional neural network (CNN) based on a modified AlexNet. CNN shows powerful ability in performing feature extraction and fusion by simulating the learning mechanism of human brain. The local response normalization layers in AlexNet are replaced by the batch normalization layers, which can enhance both the computational efficiency and classification accuracy. In the training process of the network, the characteristics of the defect are extracted step by step and the essential features of the image can be obtained from the fusion of the edge details with several convolution operations. Then the max-pooling layers, the dropout layers, and the fully connected layers are employed in the classification model to reduce the computation cost and extract more precise features of the defective fabric. Finally, the results of the defect classification are predicted by the softmax function. The experimental results show promising performance with an acceptable average classification rate and strong robustness on yarn-dyed fabric defect classification.

[1]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[2]  Wing-Keung Wong,et al.  An intelligent model for detecting and classifying color-textured fabric defects using genetic algorithms and the Elman neural network , 2011 .

[3]  Fan Wang,et al.  Automatic detection of microcalcifications using mathematical morphology and a support vector machine. , 2014, Bio-medical materials and engineering.

[4]  Jia Deng,et al.  A large-scale hierarchical image database , 2009, CVPR 2009.

[5]  Tae Jin Kang,et al.  Texture classification and segmentation using wavelet packet frame and Gaussian mixture model , 2007, Pattern Recognit..

[6]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[7]  Lapo Governi,et al.  Machine vision tool for real-time detection of defects on textile raw fabrics , 2008 .

[8]  Eric R. Burke,et al.  Segmenting delaminations in carbon fiber reinforced polymer composite CT using convolutional neural networks , 2016 .

[9]  Jingjing Liu,et al.  Classification of Fabric Defect Based on PSO-BP Neural Network , 2008, 2008 Second International Conference on Genetic and Evolutionary Computing.

[10]  Wai Keung Wong,et al.  Stitching defect detection and classification using wavelet transform and BP neural network , 2009, Expert Syst. Appl..

[11]  Longdi Cheng,et al.  Yarn-dyed woven defect characterization and classification using combined features and support vector machine , 2014 .

[12]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[13]  G. Campbell,et al.  FLAW DETECTION IN WOVEN TEXTILES BY NEURALNETWORKJonathan , 1997 .

[14]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[15]  Zhigang Fan,et al.  Automated Inspection of Textile Fabrics Using Textural Models , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Md. Tarek Habib,et al.  Fabric defect classification with geometric features using Bayesian classifier , 2015, 2015 International Conference on Advances in Electrical Engineering (ICAEE).

[17]  Anindya Ghosh,et al.  Pattern classification of fabric defects using support vector machines , 2011 .

[18]  Tarek Habib,et al.  A Preprocessed Counterpropagation Neural Network Classifier for Automated Textile Defect Classification , 2016 .

[19]  Jürgen Schmidhuber,et al.  Steel defect classification with Max-Pooling Convolutional Neural Networks , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[20]  Bart De Schutter,et al.  Deep convolutional neural networks for detection of rail surface defects , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[21]  Wang Ke,et al.  Banknote Image Defect Recognition Method Based on Convolution Neural Network , 2016 .

[22]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[23]  Ajay Kumar,et al.  Neural network based detection of local textile defects , 2003, Pattern Recognit..

[24]  Pierre Alliez,et al.  Convolutional Neural Networks for Large-Scale Remote-Sensing Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[25]  Geoffrey E. Hinton,et al.  On the importance of initialization and momentum in deep learning , 2013, ICML.