Contour Extraction and Size Estimation of Garment Images Based on Edge Detection and Morphological Analysis
Bibliographic record
Abstract
With the rapid development of the apparel e-commerce and intelligent manufacturing sectors, the efficient processing of garment images has become a key demand for the digital and intelligent transformation of the industry.Among these, the contour extraction and size estimation of garment images directly impact virtual try-on effects, clothing customization accuracy, and the level of production automation.However, in practical applications, garment images are often disturbed by complex backgrounds, diverse textures, and lighting variations, which require higher processing accuracy.Current research in contour extraction and size estimation of garment images shows significant shortcomings: traditional Canny edge detection operators often face edge fragmentation or excessive false edges when processing complex textures or images with uneven lighting; conventional morphological methods are sensitive to noise, making it difficult to precisely extract edges under noisy conditions; existing size estimation methods mainly rely on single contour features, leading to larger errors when garment shapes deform, thus failing to meet the high-precision demands.In response to these issues, this paper presents a novel approach for contour extraction and size estimation of garment images, combining edge detection and morphological analysis.The main contributions are: proposing an improved Canny operator-based edge detection method with enhanced morphological analysis, integrating the strengths of both methods to achieve more accurate and complete contour extraction of garment images; establishing a mapping relationship between the extracted contours and actual sizes, forming a reliable size estimation strategy.The innovation of this study lies in the targeted improvements of the Canny operator and morphological methods, enhancing edge detection performance under complex textures, uneven lighting, and noisy environments; the integration of these two improved methods ensures complementary advantages and improves the robustness of contour extraction; constructing a size estimation strategy based on multi-feature mapping effectively reduces errors caused by garment shape deformations, providing more precise technical support for the garment industry.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".