Defect Segmentation in Surfaces using Deep Learning

Surface inspection is one of the most challenging tasks in the manufacturing industry. Defect classification and segmentation are the two main tasks associated with surface inspection. The major challenge lies in the collection of the dataset as it is a very costly procedure and the occurrences of defected samples are very less as compared to non defective samples. Therefore, it becomes important to devise a method that can leverage the limited data available and can also handle the class imbalance between the defected and non defected samples. In this paper, a deep learning approach is proposed that uses pertained networks to perform defect segmentation on industrial surfaces. The deep learning approach consists of an encoder and decoder architecture where on the encoder side, VGG is used with pertained imagenet weights for faster training of the model and on the decoder side, the UNet decoder model is used. The evaluation of the approach shows that the proposed method can be used for surface inspection in various industrial applications.

[1]  M. Mirmehdi,et al.  TEXEMS: Texture Exemplars for Defect Detection on Random Textured Surfaces , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Kay Chen Tan,et al.  A Generic Deep-Learning-Based Approach for Automated Surface Inspection , 2018, IEEE Transactions on Cybernetics.

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

[4]  Bernd Scholz-Reiter,et al.  Learning Defect Classifiers for Textured Surfaces Using Neural Networks and Statistical Feature Representations , 2013 .

[5]  Xinggang Wang,et al.  Automated defect inspection of LED chip using deep convolutional neural network , 2019, J. Intell. Manuf..

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

[7]  Xiang Zhang,et al.  OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks , 2013, ICLR.

[8]  Dorit Merhof,et al.  Blind weave detection for woven fabrics , 2014, Pattern Analysis and Applications.

[9]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[10]  Hong Zhang,et al.  Smooth Nonnegative Matrix Factorization for Defect Detection Using Microwave Nondestructive Testing and Evaluation , 2014, IEEE Transactions on Instrumentation and Measurement.

[11]  Yuxi Wang,et al.  Fast Surface Defect Detection Using Improved Gabor Filters , 2018, 2018 25th IEEE International Conference on Image Processing (ICIP).

[12]  Dejan Tomazevic,et al.  A Compact Convolutional Neural Network for Textured Surface Anomaly Detection , 2018, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[13]  Michael Lütjen,et al.  Anomaly detection with convolutional neural networks for industrial surface inspection , 2019, Procedia CIRP.

[14]  Hua Yang,et al.  An Unsupervised-Learning-Based Approach for Automated Defect Inspection on Textured Surfaces , 2018, IEEE Transactions on Instrumentation and Measurement.

[15]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[17]  Yundong Li,et al.  Deformable Patterned Fabric Defect Detection With Fisher Criterion-Based Deep Learning , 2017, IEEE Transactions on Automation Science and Engineering.

[18]  Z. Hocenski,et al.  Improved Canny Edge Detector in Ceramic Tiles Defect Detection , 2006, IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics.

[19]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[20]  Shen-Shyang Ho,et al.  Is overfeat useful for image-based surface defect classification tasks? , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[21]  Changick Kim,et al.  Total variation flow-based multiscale framework for unsupervised surface defect segmentation , 2012 .