A Dual-Branch Ensemble Learning Method for Industrial Anomaly Detection: Fusion and Optimization of Scattering and PCA Features
Open Access
- 5 February 2026
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 16 (3) , 1597
Abstract
Industrial visual anomaly detection remains challenging because practical inspection systems must achieve high detection accuracy while operating under highly imbalanced data, diverse defect patterns, limited computational resources, and increasing demands for interpretability. This work aims to develop a lightweight yet effective and explainable anomaly detection framework for industrial images in settings where a limited number of labeled anomalous samples are available. We propose a dual-branch feature-based supervised ensemble method that integrates complementary representations: a PCA branch to capture linear global structure and a scattering branch to model multi-scale textures. A heterogeneous pool of classical learners (SVM, RF, ET, XGBoost, and LightGBM) is trained on each feature branch, and stable probability outputs are obtained via stratified K-fold out-of-fold training, probability calibration, and a quantile-based threshold search. Decision-level fusion is then performed by stacking, where logistic regression, XGBoost, and LightGBM serve as meta-learners over the out-of-fold probabilities of the selected top-K base learners. Experiments on two public benchmarks (MVTec AD and BTAD) show that the proposed method substantially improves the best PCA-based single model, achieving relative F1_score gains of approximately 31% (MVTec AD) and 26% (BTAD), with maximum AUC values of about 0.91 and 0.96, respectively, under comparable inference complexity. Overall, the results demonstrate that combining high-quality handcrafted features with supervised ensemble fusion provides a practical and interpretable alternative/complement to heavier deep models for resource-constrained industrial anomaly detection, and future work will explore more category-adaptive decision strategies to further enhance robustness on challenging classes.Keywords
Funding Information
- National Natural Science Foundation of China (52576145)
- National Natural Science Foundation of China (52406162)
- Natural Science Foundation Project of Hubei Province (2025AFB913)
- Postdoctoral Fellowship Program of CPSF (GZC20241593)
- China Postdoctoral Science Foundation (2024M753029)
- Postdoctoral Project of Hubei Province (2024HBBHCXA090)
- “CUG Scholar” scientific Research Funds at China University of Geosciences (2023097)
- Fundamental Research Funds for the Central University, China University of Geosciences (162301242612)
This publication has 41 references indexed in Scilit:
- Enhancing ML-based anomaly detection in data management for security through integration of IoT, cloud, and edge computingExpert Systems with Applications, 2025
- A survey on RGB, 3D, and multimodal approaches for unsupervised industrial image anomaly detectionInformation Fusion, 2025
- A Comprehensive Survey of Anomaly Detection AlgorithmsAnnals of Data Science, 2021
- The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly DetectionInternational Journal of Computer Vision, 2021
- Improving security using SVM-based anomaly detection: issues and challengesSoft Computing, 2020
- Anomaly detection model based on data stream clusteringCluster Computing, 2017
- A survey of intrusion detection systems based on ensemble and hybrid classifiersComputers & Security, 2017
- Group Invariant ScatteringCommunications on Pure and Applied Mathematics, 2012
- Principal component analysisWIREs Computational Statistics, 2010
- Plastic card fraud detection using peer group analysisAdvances in Data Analysis and Classification, 2008