Development of the Histogram of Oriented Gradients Method for Feature Extraction in Welding Defect Detection
Bibliographic record
Abstract
Welding defect detection is a critical component of quality inspection systems in the manufacturing industry.This study proposes the Trigonometry and Adaptive Histogram of Oriented Gradients (TAHOG) method as an extension of the conventional Histogram of Oriented Gradients (HOG), incorporating logarithmic and adaptive exponential functions in the gradient angle decomposition process to enhance feature extraction sensitivity in Xray welding images.The methodology involves preprocessing, weld region segmentation, and feature extraction using both HOG and TAHOG on a dataset of 500 X-ray images, divided into training and testing sets.Comparatively, TAHOG demonstrates superior performance in detecting defect quantity, orientation, and defect area.The HOG method yields an average defect ratio of 7.58%, lower than 11.85% obtained using TAHOG, and tends to generate fragmented defect mappings, leading to less representative damage characterization.In contrast, TAHOG maintains higher sensitivity to variations in defect structure and orientation.Experimental results indicate that TAHOG achieves 99.77% accuracy, 100% precision, 99.54% recall, 99.77% F1-score, and 100% specificity, reflecting an optimal balance between defect detection capability and avoidance of misclassification in non-defective regions.Therefore, TAHOG effectively addresses the limitations of HOG in detecting low-intensity defects and contributes significantly to improving the accuracy and reliability of automated welding inspection systems in industrial environments.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".