Phase Fourier Reconstruction for Anomaly Detection on Metal Surface Using Salient Irregularity
Date of Issue2017
23rd International Conference on Multimedia Modeling (MMM 2017)
School of Computer Science and Engineering
Rolls-Royce@NTU Corporate Lab
Rolls-Royce@NTU Corporate Laboratory
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.
© 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].