Research Article

View Coverage and Evidence Gating for Vision-Based Robotic Quality Inspection

Authors

Victoria Nozick * Departmant of Operations and Information Management Group, Aston Business School, Aston University, B4 7ET Birmingham, United Kingdom.
Fatemeh Rasoulpour Department of Computer Engineering, Institute of Higher Education, RVF6+JJ9 Tenekabon, Iran.
Milos Milovancevic Department of Mechanical Engineering, University of Nis, Serbia.

https://doi.org/10.48314/ceti.v3i3.91

Downloads

Abstract

Robotic quality inspection must translate observations of individual surfaces into a justified disposition of a physical item. An image without a visible defect does not establish that the item is defect free, particularly when different views expose different surfaces. This study develops an evidence-gated inspection architecture that binds image scores to item identity, acquisition epoch, required view coverage, model and calibration versions, evidence age, and independent execution permits. The architecture is evaluated through an object-disjoint public-data experiment, an executable supervisory replay, and a separate numerical geometry fixture. KolektorSDD contains 399 images from 50 defective items, including 52 images with visible defects. Fixed logistic-regression and extremely randomized-tree baselines achieved pooled held-out image AUROCs of 0.968 and 0.960, respectively. Nevertheless, a first-view binary policy released 44 of the 50 defective items with either model. Aggregating all available views reduced these escapes to six and fourteen; adding a fixed abstention interval and an eight-view release requirement reduced them to one and zero, while holding five and fourteen items. Nine adverse evidence or permit conditions prevented release in all 450 constructed fault traces. A 100,000-sample, explicitly assumed pose-error fixture agreed with the linearized covariance to within 0.87% relative Frobenius error. These results establish an auditable connection between perception evidence and supervisory disposition. They do not establish normal-item specificity, production throughput, physical robot performance, or safety compliance. The supplied code, split manifests, per-image predictions, decision traces, and equation sources support independent reproduction.

Keywords

Robotic inspection Industrial vision Multi-view evidence Selective decision Item traceability Pose uncertainty.

References (30)

[1] Szeliski, R. (2011). Computer vision: Algorithms and applications (Vol. 1). Springer, London. http://mesh.brown.edu/engn1610/szeliski/03-imageprocessing.pdf

[2] Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press. https://aikosh.indiaai.gov.in/static/deep+learning+ian+goodfellow.pdf

[3] Tabernik, D., Šela, S., Skvarč, J., & Skočaj, D. (2020). Segmentation-based deep-learning approach for surface-defect detection. Journal of Intelligent Manufacturing, 31(3), 759–776. https://doi.org/10.1007/s10845-019-01476-x

[4] Visual Cognitive Systems Laboratory. (2019). Kolektor surface-defect dataset (KolektorSDD). https://www.indatlas.com/datasets/kolektor-surface-defect-dataset-kolektorsdd/

[5] Bergmann, P., Fauser, M., Sattlegger, D., & Steger, C. (2019). MVTec ad: A comprehensive real-world dataset for unsupervised anomaly detection. 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR) (pp. 9584–9592). IEEE. https://doi.org/10.1109/CVPR.2019.00982

[6] Roth, K., Pemula, L., Zepeda, J., Schölkopf, B., Brox, T., & Gehler, P. (2022). Towards total recall in industrial anomaly detection. 2022 IEEE/CVF conference on computer vision and pattern recognition (CVPR) (pp. 14298–14308). IEEE. https://doi.org/10.1109/CVPR52688.2022.01392

[7] Batzner, K., Heckler, L., & König, R. (2024). EfficientAD: Accurate visual anomaly detection at millisecond-level latencies. 2024 IEEE/CVF winter conference on applications of computer vision (WACV) (pp. 127–137). IEEE. https://doi.org/10.1109/WACV57701.2024.00020

[8] Zou, Y., Jeong, J., Pemula, L., Zhang, D., & Dabeer, O. (2022). SPot-the-difference self-supervised pre-training for anomaly detection and segmentation. Computer vision - ECCV 2022 (pp. 392–408). Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-20056-4_23

[9] Wang, C., Zhu, W., Gao, B. B., Gan, Z., Zhang, J., Gu, Z., ..., & Ma, L. (2024). Real-iad: A real-world multi-view dataset for benchmarking versatile industrial anomaly detection. 2024 IEEE/CVF conference on computer vision and pattern recognition (CVPR) (pp. 22883-22892). IEEE. https://doi.org/10.1109/CVPR52733.2024.02159

[10] Zhu, W., Wang, L., Zhou, Z., Wang, C., Pan, Y., Zhang, R. (2025). Real-iad 3D: A real-world 2D/pseudo-3D/3D dataset for industrial anomaly detection. 2025 IEEE/CVF conference on computer vision and pattern recognition (CVPR) (pp. 15214–15223). IEEE. https://doi.org/10.1109/CVPR52734.2025.01417

[11] Heckler-Kram, L., Neudeck, J. H., Scheler, U., König, R., & Steger, C. (2026). The MVTec AD 2 dataset: Advanced scenarios for unsupervised anomaly detection. International Journal of Computer Vision, 134(4), 175. https://doi.org/10.1007/s11263-026-02743-0

[12] Silva, C. A. de S., & Paladini, E. P. (2025). Smart machine vision system to improve decision-making on the assembly line. Machines, 13(2), 98. https://doi.org/10.3390/machines13020098

[13] Puttero, S., Verna, E., Genta, G., & Galetto, M. (2026). Collaborative robots for quality control: An overview of recent studies and emerging trends. Journal of Intelligent Manufacturing, 37(4), 1345–1381. https://doi.org/10.1007/s10845-025-02600-w

[14] Chow, C. (1970). On optimum recognition error and reject tradeoff. IEEE Transactions on Information Theory, 16(1), 41–46. https://doi.org/10.1109/TIT.1970.1054406

[15] El-Yaniv, R. (2010). On the foundations of noise-free selective classification. Journal of Machine Learning Research, 11(5), 1605–1641. https://doi.org/10.5555/1756006.1859904

[16] Geifman, Y., & El-Yaniv, R. (2017). Selective classification for deep neural networks. Advances in neural information processing systems (Vol. 30, pp. 1–10). Curran Associates, Inc. https://proceedings.neurips.cc/paper_files/paper/2017/file/4a8423d5e91fda00bb7e46540e2b0cf1-Paper.pdf

[17] Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017). On calibration of modern neural networks. Proceedings of the 34th international conference on machine learning (pp. 1321–1330). PMLR. https://proceedings.mlr.press/v70/guo17a.html

[18] Saito, T., & Rehmsmeier, M. (2015). The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PloS One, 10(3), e0118432. https://doi.org/10.1371/journal.pone.0118432

[19] Zhang, Z. (2000). A flexible new technique for camera calibration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(11), 1330–1334. https://doi.org/10.1109/34.888718

[20] Tsai, R. Y., Lenz, R. K. (1989). A new technique for fully autonomous and efficient 3D robotics hand/eye calibration. IEEE Transactions on Robotics and Automation, 5(3), 345–358. https://doi.org/10.1109/70.34770

[21] Park, F. C., & Martin, B. J. (1994). Robot sensor calibration: Solving AX=XB on the Euclidean group. IEEE Transactions on Robotics and Automation, 10(5), 717–721. https://doi.org/10.1109/70.326576

[22] Chaumette, F., & Hutchinson, S. (2006). Visual servo control. I. Basic approaches. IEEE Robotics & Automation Magazine, 13(4), 82–90. https://doi.org/10.1109/MRA.2006.250573

[23] Macenski, S., Foote, T., Gerkey, B., Lalancette, C., & Woodall, W. (2022). Robot operating system 2: Design, architecture, and uses in the wild. Science Robotics, 7(66), eabm6074. https://doi.org/10.1126/scirobotics.abm6074

[24] Lamport, L. (2019). Time, clocks, and the ordering of events in a distributed system. Concurrency: The works of leslie lamport (pp. 179–196). New York, NY, USA: Association for Computing Machinery. https://doi.org/10.1145/3335772.3335934

[25] Sculley, D., Holt, G., Golovin, D., Davydov, E., Phillips, T., Ebner, D., …, & Dennison, D. (2015). Hidden technical debt in machine learning systems. Advances in neural information processing systems. Curran Associates, Inc. https://proceedings.neurips.cc/paper_files/paper/2015/file/86df7dcfd896fcaf2674f757a2463eba

[26] International Organization for Standardization. (2025). ISO 10218-1:2025: Robotics — safety requirements — Part 1: Industrial robots. ISO. https://www.iso.org/standard/73933.html

[27] International Organization for Standardization. (2025). ISO 10218-2:2025: Robotics — safety requirements — Part 2: Industrial robot applications and robot cells. https://www.iso.org/standard/73934.html

[28] Geurts, P., Ernst, D., & Wehenkel, L. (2006). Extremely randomized trees. Machine Learning, 63(1), 3–42. https://doi.org/10.1007/s10994-006-6226-1

[29] Fabian, P. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825. https://doi.org/10.5555/1953048.2078195

[30] Efron, B., & Tibshirani, R. J. (1994). An introduction to the bootstrap. Chapman and Hall/CRC. https://doi.org/10.1201/9780429246593

Article Metrics

Published 2026-07-30
Issue Vol. 3 No. 3 (2026): Computational Engineering and Technology Innovations
Section Articles
Document Type Research Article
Views 0
Downloads 0

How to Cite

Nozick, V., Rasoulpour, F., & Milovancevic, M. (2026). View Coverage and Evidence Gating for Vision-Based Robotic Quality Inspection. Computational Engineering and Technology Innovations, 3(3), 176-192. https://doi.org/10.48314/ceti.v3i3.91

Download Citation

Similar Articles

Mahmoud Alimoradi, Setayesh Zahiri, Maryam Khani, RaDOD-Net: A Data-Contracted CNN–LSTM–Attention Architecture for Radar Enhancement and Airport Obstacle Detection , Computational Engineering and Technology Innovations: Vol. 3 No. 1 (2026): Computational Engineering and Technology Innovations
Maedeh Fasihi, Azadeh Shemshad, A Taxonomy and Evidence Framework for Hybrid Metaheuristics in Smart Manufacturing and Supply Chains , Computational Engineering and Technology Innovations: Vol. 3 No. 1 (2026): Computational Engineering and Technology Innovations
Renas Rajab Asaad, Viktor P. Sokolov, Adaptive Accuracy and Cost Control under Distribution Shift in Model Cascades , Computational Engineering and Technology Innovations: Vol. 3 No. 3 (2026): Computational Engineering and Technology Innovations
Sama Mirfallah, Arafa Abdelzaher Nasef, Heart Disease Classification Using Machine Learning by Modified Support Vector Machine and Improved Ensemble Extreme Gradient Boosting (XGBoost) , Computational Engineering and Technology Innovations: Vol. 3 No. 1 (2026): Computational Engineering and Technology Innovations
Khris Swain, Elif Ceviz, Maduabuchi Okafor, Rina V. Petrova, Hiroshi Tanabe, Nature-Inspired Optimization Across the Mine Value Chain: A Critical Review , Computational Engineering and Technology Innovations: Vol. 3 No. 2 (2026): Computational Engineering and Technology Innovations
Renas Rajab Asaad, Madasu Hanmandlu, Kharabela Swain, AISR: A Protocol-Closed Architecture for Interference-Aware Channel-Mask Control in Industrial LoRaWAN , Computational Engineering and Technology Innovations: Vol. 3 No. 2 (2026): Computational Engineering and Technology Innovations
Mahmoud Alimoradi, Eisa Abdolmaleki, Hashem Saberi Najafi, Hadi Faghihmaleki, Latency Aware Metaheuristics for Earthquake Early Warning Network Design , Computational Engineering and Technology Innovations: Vol. 3 No. 3 (2026): Computational Engineering and Technology Innovations
Habibeh Karimi, Khatereh Bagherzadeh Asl, Samira Torabi, A Geometry-Gated Coordination of Reconfigurable Intelligent Surfaces for Maritime Surveillance Communications , Computational Engineering and Technology Innovations: Vol. 3 No. 2 (2026): Computational Engineering and Technology Innovations
Omar Mar Cornelio, Mingyue Wang, Rania A. Mahmoud, Exact Predictive Ventilation Control with Causal Occupancy Forecasts and Concentration Guarantees , Computational Engineering and Technology Innovations: Vol. 3 No. 2 (2026): Computational Engineering and Technology Innovations
Seyyed Ahmad Edalatpanah, Markus Hess, Advancing Football Analytics: Predictive Modeling and Performance Analysis in the Bundesliga Using Machine Learning , Computational Engineering and Technology Innovations: Vol. 1 No. 4 (2024): Computational Engineering and Technology Innovations

1-10 of 55 Next

You may also start an advanced similarity search for this article.

Most read articles by the same author(s)

Fatemeh Rasoulpour *, Milos Milovancevic, Multi-Object Detection for Real-time Video Surveillance Systems , Computational Engineering and Technology Innovations: Vol. 1 No. 1 (2024): Computational Engineering and Technology Innovations
Mingyue Wang, Fatemeh Rasoulpour, IoT-Based Urban Mobility Solutions for Traffic Congestion , Computational Engineering and Technology Innovations: Vol. 2 No. 1 (2025): Computational Engineering and Technology Innovations
Ramin Safa, Nikola Petrovic, Victoria Nozick, Lorenzo Cevallos-Torres, Human Age Prediction Based on Facial Patterns Using CNN , Computational Engineering and Technology Innovations: Vol. 1 No. 2 (2024): Computational Engineering and Technology Innovations
Seyyed Ahmad Edalatpanah, Eisa Abdolmaleki, Victoria Nozick, Quantum Bat Algorithm Using Ensemble Bayesian Neural Networks for Cad-Based Lung Cancer Prediction , Computational Engineering and Technology Innovations: Vol. 2 No. 3 (2025): Computational Engineering and Technology Innovations