Knowledge-Guided Machine Learning for Automated Recognition of Irregular Patterns in Industrial Image Analysis
Keywords:
knowledge-guided learning; irregular pattern recognition; industrial image analysis; uncertainty calibration; anomaly detection; visual inspectionAbstract
Industrial image analysis increasingly depends on learned visual representations, yet irregular patterns such as fine scratches, porphyrin-like inclusions, weld discontinuities, textile faults, surface porosity, and deformation marks remain difficult to recognize reliably because their appearance is sparse, geometry is variable, contrast is weak, and nuisance factors often mimic defect evidence. Purely data-driven detectors can achieve strong fit to observed production conditions while failing when illumination, material batch, camera calibration, or process settings shift. This article develops a knowledge-guided machine learning framework for automated recognition of irregular industrial patterns. The central contribution is a constraint-coupled representation-and-decision architecture that separates pattern-bearing evidence from benign texture and sensor variation, injects process and imaging knowledge through differentiable consistency terms, scores irregularity against learned regular-pattern prototypes, and calibrates uncertainty before automated accept, review, or reject decisions. The formulation integrates convolutional representation learning, weak supervision, prior-consistency penalties, Mahalanobis-style irregularity scoring, ensemble-based uncertainty estimation, and cost-sensitive decision thresholds. The article analyzes why knowledge constraints can improve sample efficiency and shift robustness, how prior misspecification can induce systematic false negatives, and which failure modes require explicit review policies rather than additional model capacity. The resulting manuscript provides a technically grounded design logic for industrial vision systems that must recognize rare and ambiguous irregularities while maintaining auditable decision behavior. The framework is intended to support reliable inspection design, not to replace domain-specific validation.
References
1. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. In F. Pereira, C. J. C. Burges, L. Bottou, & K. Q. Weinberger (Eds.), Advances in neural information processing systems (Vol. 25, pp. 1097–1105). Curran Associates.
2. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444.
3. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 770–778). IEEE.
4. Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. In C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, & R. Garnett (Eds.), Advances in neural information processing systems (Vol. 28, pp. 91–99). Curran Associates.
5. Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. In N. Navab, J. Hornegger, W. M. Wells, & A. F. Frangi (Eds.), Medical image computing and computer-assisted intervention – MICCAI 2015 (pp. 234–241). Springer.
6. Liu, F. T., Ting, K. M., & Zhou, Z. H. (2008). Isolation forest. In Proceedings of the 8th IEEE International Conference on Data Mining (pp. 413–422). IEEE.
7. Schölkopf, B., Williamson, R. C., Smola, A. J., Shawe-Taylor, J., & Platt, J. C. (2000). Support vector method for novelty detection. In S. A. Solla, T. K. Leen, & K.-R. Müller (Eds.), Advances in neural information processing systems (Vol. 12, pp. 582–588). MIT Press.
8. Bergmann, P., Fauser, M., Sattlegger, D., & Steger, C. (2019). MVTec AD: A comprehensive real-world dataset for unsupervised anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 9592–9600). IEEE.
9. Ruff, L., Kauffmann, J. R., Vandermeulen, R. A., Montavon, G., Samek, W., Kloft, M., Dietterich, T. G., & Müller, K. R. (2021). A unifying review of deep and shallow anomaly detection. Proceedings of the IEEE, 109(5), 756–795.
10. Pang, G., Shen, C., Cao, L., & van den Hengel, A. (2021). Deep learning for anomaly detection: A review. ACM Computing Surveys, 54(2), Article 38.
11. von Rueden, L., Mayer, S., Beckh, K., Georgiev, B., Giesselbach, S., Heese, R., Kirsch, B., Pfrommer, J., Pick, A., Ramamurthy, R., Walczak, M., Machicao, J., Bauckhage, C., & Schuecker, J. (2023). Informed machine learning – A taxonomy and survey of integrating prior knowledge into learning systems. IEEE Transactions on Knowledge and Data Engineering, 35(1), 614–633.
12. Karniadakis, G. E., Kevrekidis, I. G., Lu, L., Perdikaris, P., Wang, S., & Yang, L. (2021). Physics-informed machine learning. Nature Reviews Physics, 3(6), 422–440.
13. Willard, J., Jia, X., Xu, S., Steinbach, M., & Kumar, V. (2022). Integrating scientific knowledge with machine learning for engineering and environmental systems. ACM Computing Surveys, 55(4), Article 82.
14. Gal, Y., & Ghahramani, Z. (2016). Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In Proceedings of the 33rd International Conference on Machine Learning (pp. 1050–1059). PMLR.
15. Lakshminarayanan, B., Pritzel, A., & Blundell, C. (2017). Simple and scalable predictive uncertainty estimation using deep ensembles. In I. Guyon, U. von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, & R. Garnett (Eds.), Advances in neural information processing systems (Vol. 30, pp. 6402–6413). Curran Associates.
16. Zhou, Z. H. (2018). A brief introduction to weakly supervised learning. National Science Review, 5(1), 44–53.
17. Luo, D., Gattas, J. M., & Tan, P. S. S. (2020, July). Real-time defect recognition and optimized decision making for structural timber jointing. In The International Conference on Computational Design and Robotic Fabrication (pp. 36-45). Singapore: Springer Singapore.
18. Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-CAM: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision (pp. 618–626). IEEE.
19. Kendall, A., & Gal, Y. (2017). What uncertainties do we need in Bayesian deep learning for computer vision? In I. Guyon, U. von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, & R. Garnett (Eds.), Advances in neural information processing systems (Vol. 30, pp. 5574–5584). Curran Associates.
20. Weimer, D., Scholz-Reiter, B., & Shpitalni, M. (2016). Design of deep convolutional neural network architectures for automated feature extraction in industrial inspection. CIRP Annals, 65(1), 417–420.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Computational Intelligence Systems

This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.