A Computer Vision Engineering Management System for Automated Defect Detection in Electronic Components Manufacturing
Bibliographic record
Abstract
Traditional digital image processing techniques face problems such as complex feature extraction and weak robustness when dealing with surface defects of multiple categories of electronic components. Deep learning is widely used in industrial defect detection. However, the performance of electronic component defect detection at the pixel segmentation level needs to be improved. For pixel-level defect detection, this paper constructs a defect detection model (ECSDDNet) for electronic component surface defects in computer vision engineering management system. To improve the segmentation accuracy and detection effect, three stages of experiments are conducted to address mis-segmentation problems and the shortcomings of the Unet network structure. Firstly, a classification network that can perform weight transfer is used to replace the encoding structure in the Unet network. Secondly, a simplified version of the feature fusion is proposed and added to the skip connection of the Unet network. Finally, label smoothing is used to optimize the loss and improve the generalization of the network. After the optimization experiment, some noisy contours and small defect contours that are mis-segmented are removed. Experimental results show that ECSDDNet has good segmentation effects on electronic component surface defects and can meet the segmentation and detection needs of electronic component surface defects.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.010 | 0.004 |
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".