Superpixel-based Anomaly Detection for Irregular Textures with a Focus on Pixel-level Accuracy

Rafiei, M.; Breckon, T. P.; Iosifidis, A.

Abstract

Recent anomaly detection methods achieve high performance on commonly used image and pixel-level metrics. However, due to the imbalance in the number of normal and abnormal pixels commonly encountered in anomaly detection problems, commonly adopted pixel-level performance metrics cannot effectively evaluate model performance. This paper proposes a novel approach for anomaly detection within the irregular texture domain, focusing on pixel-level accuracy metrics suitable for such imbalanced problems. The proposed Superpixel-based Coupled-hypersphere-based Feature Adaptation (Sp-CFA) method leverages the intermediate adaptive representation of superpixels to enable superior pixel-level anomaly detection performance. We demonstrate superior performance over the irregular texture classes within the MVTec AD benchmark dataset, KSDD2 dataset, and an X-ray dataset of manufactured fibrous products.

Citation

Rafiei, M., Breckon, T. P., & Iosifidis, A. (2024, June). Superpixel-based Anomaly Detection for Irregular Textures with a Focus on Pixel-level Accuracy. Presented at 2024 International Joint Conference on Neural Networks (IJCNN), Yokohama, Japan

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2024 International Joint Conference on Neural Networks (IJCNN)
• Start Date: Jun 30, 2024
• End Date: Jul 5, 2024
• Acceptance Date: Mar 17, 2024
• Online Publication Date: Sep 9, 2024
• Publication Date: Sep 9, 2024
• Deposit Date: Mar 25, 2024
• Publicly Available Date: Sep 9, 2024
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Series ISSN: 2161-4393
• Book Title: Proceedings of the 2024 International Joint Conference on Neural Networks (IJCNN)
• ISBN: 9798350359329
• DOI: https://doi.org/10.1109/IJCNN60899.2024.10651419
• Keywords: anomay detection, texture analysis, superpixels
• Public URL: https://durham-repository.worktribe.com/output/2346917