Case Study: Visual Defect Detection on a Production Line
Design a factory-line visual inspection system — one-class anomaly detection when almost no defects are labelled, per-SKU edge inference under a hard cycle-time budget, and an escape-cost-vs-scrap-cost decision policy
Model interview answer for industrial visual inspection (electronics, automotive, pharma manufacturing lines, Landing-AI-class vendors): why this is the block's detection-not-generation and edge case, argued against every other case study in the series. The approach ladder from impossible supervised detection to one-class anomaly detection trained on normal parts only — reconstruction-based methods (AnoGAN, f-AnoGAN, grounded in this track's GAN vocabulary) versus pretrained-feature memory-bank methods (PaDiM, PatchCore) — and why memory-bank methods are the current pragmatic default on MVTec-AD-style benchmarks. Golden-sample capture, alignment and lighting normalization, synthetic defects for validation only (cross-referencing this track's synthetic-data-for-CV case), pixel-level anomaly maps pooled into an image-level score, and image-level AUROC plus pixel-level PRO/AUROC as the evaluation pair FID cannot replace. A decision-policy section mirroring the fraud-detection case's asymmetric-cost framing, but for escape cost versus scrap cost. A system design where inference happens on an edge box synchronised to a PLC reject signal, and a scalability deep-dive built entirely around this case's signature problem: one model (or memory bank) per SKU per line, a model-zoo registry, physical drift fixed by re-capturing golden samples, and onboarding a new SKU in hours with 50 images as the real scaling unit.
Practice questions (6)
-
View →
Setting the Reject Threshold from Escape Cost vs. Scrap Cost
Advanced · Free -
View →
Reconstruction-Based vs. Memory-Bank Anomaly Detection for a New SKU
Advanced · Free -
View →
Why Pixel-Level AUROC Alone Can Mislead
Advanced -
View →
Diagnosing a Rising False-Reject Rate: Drift or Real Defects?
Advanced -
View →
Designing the New-SKU Onboarding Pipeline
Advanced