A High-Efficiency Fully Convolutional Networks for Pixel-Wise Surface Defect Detection

In this paper, we propose a highly efficient deep learning-based method for pixel-wise surface defect segmentation algorithm in machine vision. Our method is composed of a segmentation stage (stage 1), a detection stage (stage 2), and a matting stage (stage 3). In the segmentation stage, a lightweight fully convolutional network (FCN) is employed to make a pixel-wise prediction of the defect areas. Those predicted defect areas act as the initialization of stage 2, guiding the process of detection to correct the improper segmentation. In the matting stage, a guided filter is utilized to refine the contour of the defect area to reflect the real abnormal region. Besides that, aiming to achieve the tradeoff between efficiency and accuracy, and simultaneously we use depthwise&pointwise convolution layer, strided depthwise convolution layer, and upsample depthwise convolution layer to replace the standard convolution layer, pooling layer, and deconvolution layer, respectively. We validate our findings by analyzing the performance obtained on the dataset of DAGM 2007.

[1]  Jian Sun,et al.  Guided Image Filtering , 2010, ECCV.

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

[3]  Michael S. Lew,et al.  Deep learning for visual understanding: A review , 2016, Neurocomputing.

[4]  Paul W. Fieguth,et al.  A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure , 2015, Adv. Eng. Informatics.

[5]  Tony Lindeberg,et al.  A computational theory of visual receptive fields , 2013, Biological Cybernetics.

[6]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[7]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[8]  Sergio Guadarrama,et al.  The Devil is in the Decoder , 2017, BMVC.

[9]  Graham W. Taylor,et al.  Deconvolutional networks , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  Zhenjie Hou,et al.  Fabric defect inspection based on lattice segmentation and Gabor filtering , 2017, Neurocomputing.

[11]  Luc Van Gool,et al.  The Pascal Visual Object Classes Challenge: A Retrospective , 2014, International Journal of Computer Vision.

[12]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[13]  Jian Gao,et al.  Automatic surface defect detection for mobile phone screen glass based on machine vision , 2017, Appl. Soft Comput..

[14]  Ning Zhou,et al.  Multiscale fully convolutional network with application to industrial inspection , 2016, 2016 IEEE Winter Conference on Applications of Computer Vision (WACV).

[15]  Yi Li,et al.  Instance-Sensitive Fully Convolutional Networks , 2016, ECCV.