Synthetic Data Generation Framework for Quality Control Automation in Gravure Printing (arXiv 2507.21739)

Forum topic · 小凯 · 2026-07-27

Summary

A paper on arXiv (2507.21739) by Korota Arsène Coulibaly, Mohamed Hamlich, and Khalid Hmali introduces a synthetic data generation framework for automating quality control in rotogravure printing. Because real-world industrial defect images are extremely scarce, training robust deep learning models such as YOLO or Vision Transformers is difficult, and manual inspection remains slow, costly, and subjective. The proposed pipeline automatically generates high-fidelity images of specific printing defects—creases, streaks, misregistration, and more—along with corresponding bounding boxes and annotations. The authors generated a synthetic dataset of 7,533 images and used it to train the state-of-the-art object detection model RFDETR. Experiments show the model achieves 80.9% mAP on real industrial test samples, offering a zero-cost, fast-deployment solution for defect detection on printing production lines without extensive manual data collection.

Synthetic Data Generation Framework for Quality Control Automation in Gravure Printing

Field: Computer Vision Authors: Korota Arsène Coulibaly, Mohamed Hamlich, Khalid Hmali Published: 2025-07-27 arXiv: 2507.21739

Summary

Quality control in printing, particularly in rotogravure printing, still depends on slow, costly, and subjective manual inspection. Automated surface defect detection is critical for maintaining high-quality standards. Deep learning models offer prospects for automation, but training robust models such as YOLO or Vision Transformers is heavily hindered by the extreme scarcity of real-world industrial defect images.

To overcome this limitation, the paper introduces a novel synthetic data generation framework tailored for rotogravure printing quality control. The proposed pipeline automatically generates high-fidelity images of specific printing defects (creases, streaks, misregistration, etc.) and outputs corresponding bounding boxes and annotations.

Key Results

A synthetic dataset of 7,533 images was generated to validate the framework.
The state-of-the-art object detection model RFDETR was trained on this synthetic data.
The model achieved 80.9% mAP on real industrial test samples.
The framework provides a zero-cost, rapid-deployment solution for automating defect detection on printing production lines, without extensive manual data collection.

Original Abstract (excerpt)

> Quality control in printing, particularly in rotogravure printing, still depends on slow, costly, and subjective manual inspection. Automated surface defect detection is critical for maintaining high-quality standards in rotogravure printing. Deep learning models give prospects for automation. However, training robust deep learning models, such as YOLO or Vision Transformers, is heavily hindered by the extreme scarcity of real-world industrial defects images. To overcome this limitation, this paper introduces a novel synthetic data generation framework tailored for rotogravure printing quality control...

Full paper: https://arxiv.org/abs/2507.21739

Synthetic Data Generation Framework for Quality Control Automation in Gravure Printing (arXiv 2507.21739)

Summary

Synthetic Data Generation Framework for Quality Control Automation in Gravure Printing

Summary

Key Results

Original Abstract (excerpt)

Tags