Industrial Image Grouping Through Pre-Trained CNN Encoder-Based Feature Extraction and Sub-Clustering

Selvine Mathias, Saara Asif, Muhammad Uzair Akmal, Simon Knollmeyer, Leonid Koval, Daniel Grossmann

2025

Abstract

A common challenge faced by many industries today is the classification of unlabeled image data from production processes into meaningful groups or patterns for better documentation and analysis. This paper presents a sequential approach for leveraging industrial image data to identify patterns in products or processes for plant floor operators. The dataset used is sourced from steel production, and the model architecture integrates feature reduction through convolutional neural networks (CNNs) like VGG, EfficientNet, and ResNet, followed by clustering algorithms to assign appropriate labels to the observed data. The model’s selection criteria combine clustering metrics, including entropy minimization and silhouette score maximization. Once primary clusters are identified, sub-clustering is performed using near-labels, which are pre-assigned to images with initial distinctions. A novel metric, C-Score, is introduced to assess cluster convergence and grouping accuracy. Experimental results demonstrate that this method can address challenges in detecting variations across images, improving pattern recognition and classification.

Paper Citation

in Harvard Style

Mathias S., Asif S., Akmal M., Knollmeyer S., Koval L. and Grossmann D. (2025). Industrial Image Grouping Through Pre-Trained CNN Encoder-Based Feature Extraction and Sub-Clustering. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 496-506. DOI: 10.5220/0013189000003890

in Bibtex Style

@conference{icaart25,
author={Selvine Mathias and Saara Asif and Muhammad Uzair Akmal and Simon Knollmeyer and Leonid Koval and Daniel Grossmann},
title={Industrial Image Grouping Through Pre-Trained CNN Encoder-Based Feature Extraction and Sub-Clustering},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2025},
pages={496-506},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013189000003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - Industrial Image Grouping Through Pre-Trained CNN Encoder-Based Feature Extraction and Sub-Clustering
SN - 978-989-758-737-5
AU - Mathias S.
AU - Asif S.
AU - Akmal M.
AU - Knollmeyer S.
AU - Koval L.
AU - Grossmann D.
PY - 2025
SP - 496
EP - 506
DO - 10.5220/0013189000003890
PB - SciTePress