Small Defect Detection Using Convolutional Neural Network Features and Random Forests

We address the problem of identifying small abnormalities in an imaged region, important in applications such as industrial inspection. The goal is to label the pixels corresponding to a defect with a minimum of false positives. A common approach is to run a sliding-window classifier over the image. Recent Fully Convolutional Networks (FCNs), such as U-Net, can be trained to identify pixels corresponding to abnormalities given a suitable training set. However in many application domains it is hard to collect large numbers of defect examples (by their nature they are rare). Although U-Net can work in this scenario, we show that better results can be obtained by replacing the final softmax layer of the network with a Random Forest (RF) using features sampled from the earlier network layers. We also demonstrate that rather than just thresholding the resulting probability image to identify defects it is better to compute Maximally Stable Extremal Regions (MSERs). We apply the approach to the challenging problem of identifying defects in radiographs of aerospace welds.

[1]  Gang Wang,et al.  Automatic identification of different types of welding defects in radiographic images , 2002 .

[2]  Mohammad R. Jahanshahi,et al.  Video-based crack detection using deep learning and Nave Bayes data fusion , 2018, Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring.

[3]  Hamzah Arof,et al.  Discontinuities detection in welded joints based on inverse surface thresholding , 2011 .

[4]  Luca Maria Gambardella,et al.  Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images , 2012, NIPS.

[5]  Jiri Matas,et al.  Robust wide-baseline stereo from maximally stable extremal regions , 2004, Image Vis. Comput..

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

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

[8]  A. Kehoe,et al.  An intelligent knowledge based approach for the automated radiographic inspection of castings , 1992 .

[9]  Stefan Carlsson,et al.  CNN Features Off-the-Shelf: An Astounding Baseline for Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[10]  Walter J. Scheirer,et al.  Neuron Segmentation Using Deep Complete Bipartite Networks , 2017, MICCAI.

[11]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[12]  Xinghui Dong,et al.  Automatic Inspection of Aerospace Welds Using X-Ray Images , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[13]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Robinson Piramuthu,et al.  HD-CNN: Hierarchical Deep Convolutional Neural Networks for Large Scale Visual Recognition , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[15]  Lin Yang,et al.  Deep Adversarial Networks for Biomedical Image Segmentation Utilizing Unannotated Images , 2017, MICCAI.

[16]  Hao Wang,et al.  Detection of line weld defects based on multiple thresholds and support vector machine , 2008 .

[17]  Junyu Dong,et al.  Automatic Chinese Postal Address Block Location Using Proximity Descriptors and Cooperative Profit Random Forests , 2018, IEEE Transactions on Industrial Electronics.

[18]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[19]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[20]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[21]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[22]  Yueming Li,et al.  An automated radiographic NDT system for weld inspection: Part II—Flaw detection , 1998 .

[23]  Dina Q. Goldin,et al.  On Similarity Queries for Time-Series Data: Constraint Specification and Implementation , 1995, CP.

[24]  Jitendra Malik,et al.  Hypercolumns for object segmentation and fine-grained localization , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Zaixing He,et al.  Defect detection of castings in radiography images using a robust statistical feature. , 2014, Journal of the Optical Society of America. A, Optics, image science, and vision.

[26]  Claudia Lindner,et al.  Robust and Accurate Shape Model Matching Using Random Forest Regression-Voting. , 2015, IEEE transactions on pattern analysis and machine intelligence.

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

[28]  Geoff S. Nitschke,et al.  Improving Deep Learning with Generic Data Augmentation , 2018, 2018 IEEE Symposium Series on Computational Intelligence (SSCI).

[29]  Tania Mezzadri Centeno,et al.  Automated detection of welding defects in pipelines from radiographic images DWDI , 2017 .