Version 1
: Received: 23 August 2024 / Approved: 26 August 2024 / Online: 26 August 2024 (07:09:12 CEST)
How to cite:
Rolf, J.; Gerhard, D.; Kosic, P. Clustering Visual Similar Objects for Enhanced Synthetic Image Data for Object Detection. Preprints2024, 2024081793. https://doi.org/10.20944/preprints202408.1793.v1
Rolf, J.; Gerhard, D.; Kosic, P. Clustering Visual Similar Objects for Enhanced Synthetic Image Data for Object Detection. Preprints 2024, 2024081793. https://doi.org/10.20944/preprints202408.1793.v1
Rolf, J.; Gerhard, D.; Kosic, P. Clustering Visual Similar Objects for Enhanced Synthetic Image Data for Object Detection. Preprints2024, 2024081793. https://doi.org/10.20944/preprints202408.1793.v1
APA Style
Rolf, J., Gerhard, D., & Kosic, P. (2024). Clustering Visual Similar Objects for Enhanced Synthetic Image Data for Object Detection. Preprints. https://doi.org/10.20944/preprints202408.1793.v1
Chicago/Turabian Style
Rolf, J., Detlef Gerhard and Pero Kosic. 2024 "Clustering Visual Similar Objects for Enhanced Synthetic Image Data for Object Detection" Preprints. https://doi.org/10.20944/preprints202408.1793.v1
Abstract
Object detection often struggles with accurately identifying visually similar parts, a challenge commonly faced in industrial applications. To address this issue, we propose a clustering methodology based on the visual similarity of 3D object models. This approach is particularly effective when integrated with synthetic image generation, as both processes rely on 3D models. In a case study, we observed a 22 % increase in classification performance on a validation dataset when training an object detector on visually similar groups rather than on all classes, suggesting the potential of our method as a baseline for a multi-stage classification scheme.
Keywords
similarity analysis; object detection; deep embedded clustering
Subject
Engineering, Industrial and Manufacturing Engineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.