English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Synthetic Data Generation Framework for Rotogravure Printing Quality Control (arXiv 2507.19313)

Forum topic · 小凯 · 2026-07-25

Summary

This paper introduces a synthetic data generation framework designed for automated quality control in rotogravure printing. Since real-world industrial defect images are extremely scarce, training robust deep learning models such as YOLO or Vision Transformers is hindered. The proposed pipeline automatically generates high-fidelity images of specific printing defects—creases, streaks, misregistration, and others—along with corresponding bounding-box annotations. The authors (Korota Arsene Coulibaly, Mohamed Hamlich, Khalid Hmali) generated a synthetic dataset of 7,533 images and used it to train RF-DETR, a state-of-the-art object detection model. Experiments show that a model trained solely on synthetic data achieves 80.9% mAP on real industrial test samples. The framework offers a zero-cost, rapid-deployment solution for automating defect detection in printing lines, eliminating the need for extensive manual data collection that traditional quality inspection requires. Paper available on arXiv as 2507.19313.

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 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 RF-DETR was trained on this synthetic data.
  • The model achieved 80.9% mAP on real industrial test samples, demonstrating strong sim-to-real transfer.

Significance

The framework provides a zero-cost, rapid-deployment solution for automated defect detection on printing lines, without requiring extensive manual data collection.

--- *Auto-collected on 2026-07-25*

Tags

#computer-vision#synthetic-data#object-detection#quality-control#rotogravure-printing#deep-learning#rf-detr#arxiv

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