loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Maximilian Bundscherer ; Thomas Schmitt and Tobias Bocklet

Affiliation: Department of Computer Science, Technische Hochschule Nürnberg Georg Simon Ohm, Nuremberg, Germany

Keyword(s): Machine Learning, Quality Control, Industrial Manufacturing, Glass Bottle Prints.

Abstract: In industrial manufacturing of glass bottles, quality control of bottle prints is necessary as numerous factors can negatively affect the printing process. Even minor defects in the bottle prints must be detected despite reflections in the glass or manufacturing-related deviations. In cooperation with our medium-sized industrial partner, two ML-based approaches for quality control of these bottle prints were developed and evaluated, which can also be used in this challenging scenario. Our first approach utilized different filters to supress reflections (e.g. Sobel or Canny) and image quality metrics for image comparison (e.g. MSE or SSIM) as features for different supervised classification models (e.g. SVM or k-Neighbors), which resulted in an accuracy of 84%. The images were aligned based on the ORB algorithm, which allowed us to estimate the rotations of the prints, which may serve as an indicator for anomalies in the manufacturing process. In our second approach, we fine-tuned dif ferent pre-trained CNN models (e.g. ResNet or VGG) for binary classification, which resulted in an accuracy of 87%. Utilizing Grad-Cam on our fine-tuned ResNet-34, we were able to localize and visualize frequently defective bottle print regions. This method allowed us to provide insights that could be used to optimize the actual manufacturing process. This paper also describes our general approach and the challenges we encountered in practice with data collection during ongoing production, unsupervised preselection, and labeling. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.142.136.210

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Bundscherer, M.; Schmitt, T. and Bocklet, T. (2024). Machine Learning in Industrial Quality Control of Glass Bottle Prints. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-679-8; ISSN 2184-4321, SciTePress, pages 264-271. DOI: 10.5220/0012302600003660

@conference{visapp24,
author={Maximilian Bundscherer. and Thomas Schmitt. and Tobias Bocklet.},
title={Machine Learning in Industrial Quality Control of Glass Bottle Prints},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2024},
pages={264-271},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012302600003660},
isbn={978-989-758-679-8},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Machine Learning in Industrial Quality Control of Glass Bottle Prints
SN - 978-989-758-679-8
IS - 2184-4321
AU - Bundscherer, M.
AU - Schmitt, T.
AU - Bocklet, T.
PY - 2024
SP - 264
EP - 271
DO - 10.5220/0012302600003660
PB - SciTePress