A Review of the Applications of Machine Vision in Industrial Surface Defect Detection
Bibliographic record
Abstract
Surface defects of industrial products directly affect product quality, operational safety, and market competitiveness. Traditional manual inspection methods suffer from low efficiency, strong subjectivity, and high missed detection rates, which can hardly meet the high-precision and high-speed inspection requirements of modern industrial production. With the advantages of non-contact measurement, high automation, and stable detection results, machine vision technology has gradually become a core technical means in the field of industrial surface defect detection. This paper focuses on the surface defect detection scenarios of typical industrial materials such as metals, plastics, and glass, systematically sorting out the application logic and applicable scenarios of three core machine vision technologies: object detection, semantic segmentation, and image classification. It details the characteristics and application scopes of mainstream public datasets such as NEU-DET and MTM-Surface-Defect, and deeply analyzes the influence mechanisms of key factors such as illumination changes and material reflection on detection accuracy. Finally, centering on the real-time inspection needs of production lines, it looks forward to future development directions such as lightweight model deployment and multimodal data fusion. This paper aims to provide a comprehensive technical reference for researchers and engineers in the field of industrial surface defect detection, and promote the large-scale application and optimization upgrading of machine vision technology in industrial production.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.006 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".