Objective: We investigate whether accounting for epistemic uncertainty can improve the reliability of automated defect detection in medical device manufacturing. Methods: We consider a machine learnin...
arXiv:2608. 07770v1 Announce Type: new Abstract: Automated anomaly detection methods often report strong performance on curated academic benchmarks, but their behavior under real-world industrial conditions is less clear.
arXiv:2610.41199v1 Announce Type: new Abstract: Cameras and vision sensors are widely used for product and process inspection in manufacturing environments. Traditionally, this process required thous...
arXiv:2606. 01023v1 Announce Type: cross Abstract: Visual inspection remains the dominant quality-control practice in woven and tufted carpet production, yet it is slow, subjective, and inconsistent at the line speeds and widths of modern looms.
The paper introduces ISP-AD, the largest publicly available industrial anomaly detection dataset, featuring both synthetic and real defects from a factory floor. It focuses on challenging, small, weakly contrasted surface defects within highly variable structured patterns, addressing the bias of existing datasets toward ideal imaging conditions. Experiments demonstrate that even a small amount of weakly labeled real defects improves model generalization and that synthetic defects can serve as a useful cold‑start baseline for scalable training.
arXiv:2604. 26633v2 Announce Type: replace-cross Abstract: Industrial surface defect inspection suffers from a fundamental data bottleneck: defects are rare, annotations require expert knowledge, and collecting balanced training sets is slow and costly.
arXiv:2608. 13937v1 Announce Type: cross Abstract: Smart manufacturing processes are often installed with a large number of sensors, imaging devices and computers, which not only enable instant communication across various modules of a production system but also aid in intelligent manufacturing management.
SafeRestore introduces a framework for certifying when an industrial image restoration should be automatically returned to a detector or require human review. It ranks five restoration candidates using action‑specific fitted scores, selects a threshold gate on tuning data, and evaluates the gate on a separate certification sample with two one‑sided exact binomial bounds—one for evidence‑loss incidents and one for excess‑activation incidents. In a retrospective study of 4,591 Carinthia‑S images, the protocol demonstrates auditable risk‑coverage behavior, with varying pass rates across different policies and morphologies.
arXiv:2605.20682v3 Announce Type: replace Abstract: Small defects in unfamiliar product categories can be difficult to distinguish from benign appearance variations in a global view. Additional reaso...
The paper introduces a region‑aware dual‑model inspection framework that uses instance segmentation for seat‑region defects and image‑level classification for shaft‑region anomalies, followed by a deterministic decision fusion layer that applies industrial SOPs to produce a final component‑level decision. In experiments on 380 automotive fuel injector needles, the fusion layer maintained 100% recall of non‑conforming parts while reducing the false‑rejection rate from 57.6% to 10.9%, an 81.1% drop in false positives. The study shows that formalizing acceptance criteria can translate sensitive visual detections into practical, traceable decisions for precision component inspection.
arXiv:2609.13914v1 Announce Type: new Abstract: Machine-learning models are commonly developed under an assumption that training and test data are sufficiently complete, balanced, labelled, and drawn...
Smart manufacturing processes are often installed with a large number of sensors, imaging devices and computers, which not only enable instant communication across various modules of a production syst...