Summary
A paper by Korota Arsene Coulibaly, Mohamed Hamlich, and Khalid Hmali (arXiv:2507.19313) introduces a synthetic data generation framework for automated quality control in rotogravure printing. Manual inspection remains slow, costly, and subjective, while deep learning models like YOLO and Vision Transformers are hindered by the extreme scarcity of real industrial defect images. The proposed pipeline automatically generates high-fidelity images of specific printing defects—creases, streaks, misregistration, and more—complete with bounding box annotations. The authors built a 7,533-image synthetic dataset and trained the state-of-the-art RFDETR object detection model on it. The model achieved 80.9% mean average precision (mAP) on real industrial test samples. This zero-cost, rapid-deployment approach eliminates the need for extensive manual data collection and offers a practical path to automating defect detection in printing lines.
Overview
Field: Computer Vision
Authors: Korota Arsene Coulibaly, Mohamed Hamlich, Khalid Hmali
Published: 2026-07-24
arXiv: 2507.19313
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 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 defect images.
To overcome this limitation, this 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 using the proposed pipeline.
- The state-of-the-art object detection model RFDETR was trained on this synthetic dataset.
- The model achieved 80.9% mAP (mean average precision) on real industrial test samples.
The framework provides a zero-cost, rapid-deployment solution for automated defect detection in printing lines, without requiring extensive manual data collection.
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/178447087