Phase Fourier Reconstruction for Anomaly Detection on Metal Surface Using Salient Irregularity

12 p.

Bibliographic Details
Main Authors: Hung, Tzu-Yi, Vaikundam, Sriram, Natarajan, Vidhya, Chia, Liang-Tien
Other Authors: School of Computer Science and Engineering
Format: Conference Paper
Language:English
Published: 2017
Subjects:
Online Access:https://hdl.handle.net/10356/83030
http://hdl.handle.net/10220/42366
_version_ 1824453701579833344
author Hung, Tzu-Yi
Vaikundam, Sriram
Natarajan, Vidhya
Chia, Liang-Tien
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Hung, Tzu-Yi
Vaikundam, Sriram
Natarajan, Vidhya
Chia, Liang-Tien
author_sort Hung, Tzu-Yi
collection NTU
description 12 p.
first_indexed 2025-02-19T03:10:36Z
format Conference Paper
id ntu-10356/83030
institution Nanyang Technological University
language English
last_indexed 2025-02-19T03:10:36Z
publishDate 2017
record_format dspace
spelling ntu-10356/830302020-03-07T11:48:45Z Phase Fourier Reconstruction for Anomaly Detection on Metal Surface Using Salient Irregularity Hung, Tzu-Yi Vaikundam, Sriram Natarajan, Vidhya Chia, Liang-Tien School of Computer Science and Engineering 23rd International Conference on Multimedia Modeling (MMM 2017) Rolls-Royce@NTU Corporate Lab Defect detection Anomaly detection 12 p. In this paper, we propose a Phase Fourier Reconstruction (PFR) approach for anomaly detection on metal surfaces using salient irregularities. To get salient irregularity with images captured from an automatic visual inspection (AVI) system using different lighting settings, we first trained a classifier for image selection as only dark images are utilized for anomaly detection. By doing so, surface details, part design, and boundaries between foreground/background become indistinct, but anomaly regions are highlighted because of diffuse reflection caused by rough surfaces. Then PFR is applied so that regular patterns and homogeneous regions are further de-emphasized, and simultaneously, anomaly areas are distinct and located. Different from existing phase-based methods which require substantial texture information, our PFR works on both textual and non-textual images. Unlike existing template matching methods which require prior knowledge of defect-free patterns, our PFR is an unsupervised approach which detects anomalies using a single image. Experimental results on anomaly detection clearly demonstrate the effectiveness of the proposed method which outperforms several well-designed methods with a running time of less than 0.01 seconds per image. NRF (Natl Research Foundation, S’pore) Accepted Version 2017-05-11T03:29:51Z 2019-12-06T15:10:32Z 2017-05-11T03:29:51Z 2019-12-06T15:10:32Z 2017-01-01 2017 Conference Paper Hung, T.-Y., Vaikundam, S., Natarajan, V., & Chia, L.-T. (2017). Phase Fourier Reconstruction for Anomaly Detection on Metal Surface Using Salient Irregularity. 23rd International Conference on Multimedia Modeling (MMM 2017), 290-302. https://hdl.handle.net/10356/83030 http://hdl.handle.net/10220/42366 10.1007/978-3-319-51811-4_24 199817 en © 2017 Springer International Publishing AG. This is the author created version of a work that has been peer reviewed and accepted for publication by 23rd International Conference on Multimedia Modeling (MMM 2017), Springer International Publishing AG. It incorporates referee’s comments but changes resulting from the publishing process, such as copyediting, structural formatting, may not be reflected in this document. The published version is available at: [http://dx.doi.org/10.1007/978-3-319-51811-4_24]. application/pdf
spellingShingle Defect detection
Anomaly detection
Hung, Tzu-Yi
Vaikundam, Sriram
Natarajan, Vidhya
Chia, Liang-Tien
Phase Fourier Reconstruction for Anomaly Detection on Metal Surface Using Salient Irregularity
title Phase Fourier Reconstruction for Anomaly Detection on Metal Surface Using Salient Irregularity
title_full Phase Fourier Reconstruction for Anomaly Detection on Metal Surface Using Salient Irregularity
title_fullStr Phase Fourier Reconstruction for Anomaly Detection on Metal Surface Using Salient Irregularity
title_full_unstemmed Phase Fourier Reconstruction for Anomaly Detection on Metal Surface Using Salient Irregularity
title_short Phase Fourier Reconstruction for Anomaly Detection on Metal Surface Using Salient Irregularity
title_sort phase fourier reconstruction for anomaly detection on metal surface using salient irregularity
topic Defect detection
Anomaly detection
url https://hdl.handle.net/10356/83030
http://hdl.handle.net/10220/42366
work_keys_str_mv AT hungtzuyi phasefourierreconstructionforanomalydetectiononmetalsurfaceusingsalientirregularity
AT vaikundamsriram phasefourierreconstructionforanomalydetectiononmetalsurfaceusingsalientirregularity
AT natarajanvidhya phasefourierreconstructionforanomalydetectiononmetalsurfaceusingsalientirregularity
AT chialiangtien phasefourierreconstructionforanomalydetectiononmetalsurfaceusingsalientirregularity