Machine-learning based Hybrid Method for Surface Defect Detection and Categorization in PU Foam

Foam making is an important industry, their main applications being foam mattresses. Hence, their production in the industries is subject to very strict safety checks to ensure their quality. There are many types of defects that can arise during their manufacturing process, like holes, cuts, a misconfiguration in the material and many more. These defects are reviewed manually which leads to an inadequate accuracy and many defects are not detected. This paper proposes a novel approach that identifies defects in the foam material and on the surface using a hybrid method. Both supervised and unsupervised approaches are used to categorize materials based on normal or defective, including the type of defect. Then the reliable model is chosen according to the precision rates of both the models.

[1]  Ihab F. Ilyas,et al.  Data Cleaning: Overview and Emerging Challenges , 2016, SIGMOD Conference.

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

[3]  Raman Arora,et al.  Understanding Deep Neural Networks with Rectified Linear Units , 2016, Electron. Colloquium Comput. Complex..

[4]  I. Santos,et al.  Machine-learning-based surface defect detection and categorisation in high-precision foundry , 2012, 2012 7th IEEE Conference on Industrial Electronics and Applications (ICIEA).

[5]  Sebastian Nowozin,et al.  Structured Learning and Prediction in Computer Vision , 2011, Found. Trends Comput. Graph. Vis..

[6]  Luis Perez,et al.  The Effectiveness of Data Augmentation in Image Classification using Deep Learning , 2017, ArXiv.

[7]  Éric Gaussier,et al.  A Probabilistic Interpretation of Precision, Recall and F-Score, with Implication for Evaluation , 2005, ECIR.

[8]  Keiron O'Shea,et al.  An Introduction to Convolutional Neural Networks , 2015, ArXiv.

[9]  Gareth Halfacree,et al.  Raspberry Pi User Guide , 2012 .

[10]  A. R. Yuvaraj,et al.  Polyurethane types, synthesis and applications – a review , 2016 .

[11]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[12]  R. Sathya,et al.  Comparison of Supervised and Unsupervised Learning Algorithms for Pattern Classification , 2013 .

[13]  Wilhelm Burger,et al.  Digital Image Processing - An Algorithmic Introduction using Java , 2008, Texts in Computer Science.

[14]  M. Tănăsescu,et al.  Our Experience in Chronic Wounds Care with Polyurethane Foam , 2018 .