Convolutional Networks for Voting-based Anomaly Classification in Metal Surface Inspection

6 p.

Saved in:

Bibliographic Details
Main Authors:	Natarajan, Vidhya, Hung, Tzu-Yi, Vaikundam, Sriram, Chia, Liang-Tien
Other Authors:	School of Computer Science and Engineering
Format:	Conference or Workshop Item
Language:	English
Published:	2017
Subjects:	Anomaly classification Convolutional neural network
Online Access:	https://hdl.handle.net/10356/83012 http://hdl.handle.net/10220/42367
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University
Language:	English

id	sg-ntu-dr.10356-83012
record_format	dspace
spelling	sg-ntu-dr.10356-830122020-03-07T11:48:45Z Convolutional Networks for Voting-based Anomaly Classification in Metal Surface Inspection Natarajan, Vidhya Hung, Tzu-Yi Vaikundam, Sriram Chia, Liang-Tien School of Computer Science and Engineering 2017 IEEE International Conference on Industrial Technology (ICIT) Rolls-Royce@NTU Corporate Lab Anomaly classification Convolutional neural network 6 p. Automated Visual Inspection (AVI) systems for metal surface inspection is increasingly used in industries to aid human visual inspectors for classification of possible anomalies. For classification, the challenge lies in having a small and specific dataset that may easily result in over-fitting. As a solution, we propose to use deep Convolutional Neural Networks (ConvNets) learnt from the large ImageNet dataset [9] for image representations via transfer learning. Since a small dataset cannot be used to fine-tune a ConvNet due to overfitting, we also propose a Majority Voting Mechanism (MVM), which fuses the features extracted from the last three layers of ConvNets using Support Vector Machine (SVM) classifiers. This classification framework is effective where no prior knowledge of the best performing ConvNet layers is needed. This also allows flexibility in the choice of ConvNet used for feature extraction. The proposed method not only outperforms state-of-the-art traditional hand-crafted features in terms of classification but also obtains good results compared to other deep ConvNet features extracted from a pre-selected best layer on several anomaly and texture datasets. NRF (Natl Research Foundation, S’pore) Accepted Version 2017-05-11T03:43:31Z 2019-12-06T15:10:12Z 2017-05-11T03:43:31Z 2019-12-06T15:10:12Z 2017-03-01 2017 Conference Paper Natarajan, V., Hung, T.-Y., Vaikundam, S., & Chia, L.-T. (2017). Convolutional Networks for Voting-based Anomaly Classification in Metal Surface Inspection. 2017 IEEE International Conference on Industrial Technology (ICIT), 986-991. https://hdl.handle.net/10356/83012 http://hdl.handle.net/10220/42367 10.1109/ICIT.2017.7915495 199824 en © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: [https://doi.org/10.1109/ICIT.2017.7915495]. application/pdf
institution	Nanyang Technological University
building	NTU Library
country	Singapore
collection	DR-NTU
language	English
topic	Anomaly classification Convolutional neural network
spellingShingle	Anomaly classification Convolutional neural network Natarajan, Vidhya Hung, Tzu-Yi Vaikundam, Sriram Chia, Liang-Tien Convolutional Networks for Voting-based Anomaly Classification in Metal Surface Inspection
description	6 p.
author2	School of Computer Science and Engineering
author_facet	School of Computer Science and Engineering Natarajan, Vidhya Hung, Tzu-Yi Vaikundam, Sriram Chia, Liang-Tien
format	Conference or Workshop Item
author	Natarajan, Vidhya Hung, Tzu-Yi Vaikundam, Sriram Chia, Liang-Tien
author_sort	Natarajan, Vidhya
title	Convolutional Networks for Voting-based Anomaly Classification in Metal Surface Inspection
title_short	Convolutional Networks for Voting-based Anomaly Classification in Metal Surface Inspection
title_full	Convolutional Networks for Voting-based Anomaly Classification in Metal Surface Inspection
title_fullStr	Convolutional Networks for Voting-based Anomaly Classification in Metal Surface Inspection
title_full_unstemmed	Convolutional Networks for Voting-based Anomaly Classification in Metal Surface Inspection
title_sort	convolutional networks for voting-based anomaly classification in metal surface inspection
publishDate	2017
url	https://hdl.handle.net/10356/83012 http://hdl.handle.net/10220/42367
_version_	1681039410785681408

Convolutional Networks for Voting-based Anomaly Classification in Metal Surface Inspection

Similar Items