Deep Learning Application in Detecting Glass Defects with Color Space Conversion and Adaptive Histogram Equalization
Bibliographic record
Abstract
Manually detecting defects on the surfaces of glass products is a slow and time-consuming process in the quality control process, so computer-aided systems, including image processing and machine learning techniques are used to overcome this problem. In this study, scratch and bubble defects of the jar, photographed in the studio with a white matte background and a -60° peak angle, are investigated with the Yolo-V3 deep learning technique. Obtained performance is 94.65% for the raw data. Color space conversion (CSC) techniques, HSV and CIE-Lab Luv, are applied to the resulting images. V channels select for preprocessing. While the HSV method decreases the performance, an increase has been observed in the CIE-Lab Luv method. With the CIE-Lab Luv method, to which is applied the adaptive histogram equalization, the maximum recall, precision, and F1-score reach above 97%. Also, Yolo-V3 compared with the Faster R-CNN, it is observed that Yolo-V3 gave better results in all analyzes, and the highest overall accuracy is achieved in both methods when adaptive histogram equalization is applied to CIE-Lab Luv.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".