Frequency-dependent Image Reconstruction Error for Micro Defect Detection

Yuhei Nomura, Hirotaka Hachiya
Proceedings of the 15th Asian Conference on Machine Learning, PMLR 222:1007-1022, 2024.

Abstract

Micro defects, such as casting pores in industrial products, have been detected by human visual inspection using X-ray CT images and image processing tools. Automatic detection of micro defects is challenging for anomaly detection methods using image reconstruction errors and nearest neighbor distances because these metrics are dominated by low-frequency information and are insensitive to minor defects. Although recent methods achieve high anomaly detection performances, their detection abilities are insufficient for micro defects. To overcome these problems, we propose to extend a state-of-the-art anomaly detection method by introducing frequency-dependent losses to capture reconstruction errors appearing around micro defects and frequency-dependent data augmentation to improve the sensitivity against the errors. We demonstrate the effectiveness of the proposed method through experiments with MVTec AD dataset especially on the detection of micro defects.

Cite this Paper

BibTeX
@InProceedings{pmlr-v222-nomura24a, title = {Frequency-dependent Image Reconstruction Error for Micro Defect Detection}, author = {Nomura, Yuhei and Hachiya, Hirotaka}, booktitle = {Proceedings of the 15th Asian Conference on Machine Learning}, pages = {1007--1022}, year = {2024}, editor = {Yanıkoğlu, Berrin and Buntine, Wray}, volume = {222}, series = {Proceedings of Machine Learning Research}, month = {11--14 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v222/nomura24a/nomura24a.pdf}, url = {https://proceedings.mlr.press/v222/nomura24a.html}, abstract = {Micro defects, such as casting pores in industrial products, have been detected by human visual inspection using X-ray CT images and image processing tools. Automatic detection of micro defects is challenging for anomaly detection methods using image reconstruction errors and nearest neighbor distances because these metrics are dominated by low-frequency information and are insensitive to minor defects. Although recent methods achieve high anomaly detection performances, their detection abilities are insufficient for micro defects. To overcome these problems, we propose to extend a state-of-the-art anomaly detection method by introducing frequency-dependent losses to capture reconstruction errors appearing around micro defects and frequency-dependent data augmentation to improve the sensitivity against the errors. We demonstrate the effectiveness of the proposed method through experiments with MVTec AD dataset especially on the detection of micro defects.} }
Endnote
%0 Conference Paper %T Frequency-dependent Image Reconstruction Error for Micro Defect Detection %A Yuhei Nomura %A Hirotaka Hachiya %B Proceedings of the 15th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Berrin Yanıkoğlu %E Wray Buntine %F pmlr-v222-nomura24a %I PMLR %P 1007--1022 %U https://proceedings.mlr.press/v222/nomura24a.html %V 222 %X Micro defects, such as casting pores in industrial products, have been detected by human visual inspection using X-ray CT images and image processing tools. Automatic detection of micro defects is challenging for anomaly detection methods using image reconstruction errors and nearest neighbor distances because these metrics are dominated by low-frequency information and are insensitive to minor defects. Although recent methods achieve high anomaly detection performances, their detection abilities are insufficient for micro defects. To overcome these problems, we propose to extend a state-of-the-art anomaly detection method by introducing frequency-dependent losses to capture reconstruction errors appearing around micro defects and frequency-dependent data augmentation to improve the sensitivity against the errors. We demonstrate the effectiveness of the proposed method through experiments with MVTec AD dataset especially on the detection of micro defects.
APA
Nomura, Y. & Hachiya, H.. (2024). Frequency-dependent Image Reconstruction Error for Micro Defect Detection. Proceedings of the 15th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 222:1007-1022 Available from https://proceedings.mlr.press/v222/nomura24a.html.

Related Material