What question did this study set out to answer?

This work aims to integrate classical computer vision techniques with quality engineering metrics for automated inspection.

August 13, 2026Open Access

Classical Computer Vision for Automated Quality Inspection: A Reproducible Study Integrating SPC and Process Capability

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial evaluates automated visual inspection effectiveness in quality control, suggesting improvements in defect detection.

This work aims to integrate classical computer vision techniques with quality engineering metrics for automated inspection.
Evaluated a classical computer-vision workflow using OpenCV for inspection and dimensional measurement on 240 images.
Applied statistical process control (SPC) and process capability analysis to assess inspection reliability and accuracy.
Conducted a threshold sensitivity analysis to optimize performance metrics.
The system achieved 88.33% accuracy, 100.00% precision, and 81.58% defect recall at a frozen threshold of 95.
Reduced false accept rate from 18.42% to 4.61% by adjusting the threshold to 150, without false rejects.
Vision-based dimensional measurement showed a bias of +0.006 mm, with MAE of 0.095 mm and RMSE of 0.184 mm.

Romulo Giancarlo Colorado Balboa (2026) studied this question.

View Full Paper

Ask AI

Bookmark

August 13, 2026Open Access

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial evaluates automated visual inspection effectiveness in quality control, suggesting improvements in defect detection.

This work aims to integrate classical computer vision techniques with quality engineering metrics for automated inspection.
Evaluated a classical computer-vision workflow using OpenCV for inspection and dimensional measurement on 240 images.
Applied statistical process control (SPC) and process capability analysis to assess inspection reliability and accuracy.
Conducted a threshold sensitivity analysis to optimize performance metrics.
The system achieved 88.33% accuracy, 100.00% precision, and 81.58% defect recall at a frozen threshold of 95.
Reduced false accept rate from 18.42% to 4.61% by adjusting the threshold to 150, without false rejects.
Vision-based dimensional measurement showed a bias of +0.006 mm, with MAE of 0.095 mm and RMSE of 0.184 mm.

Romulo Giancarlo Colorado Balboa (2026) studied this question.

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark