Instance Segmentation Based Graph Extraction for Handwritten Circuit Diagram Images

Johannes Bayer, Amit Roy, Andreas Dengel

2023

Abstract

Handwritten circuit diagrams from educational scenarios or historic sources usually exist on analogue media. For deriving their functional principles or flaws automatically, they need to be digitized, extracting their electrical graph. Recently, the base technologies for automated pipelines facilitating this process shifted from computer vision to machine learning. This paper describes an approach for extracting both the electrical components (including their terminals and describing texts) as well their interconnections (including junctions and wire hops) by the means of instance segmentation and keypoint extraction. Consequently, the resulting graph extraction process consists of a simple two-step process of model inference and trivial geometric keypoint matching. The dataset itself, its preparation, model training and post-processing are described and publicly available.

Download


Paper Citation


in Harvard Style

Bayer J., Roy A. and Dengel A. (2023). Instance Segmentation Based Graph Extraction for Handwritten Circuit Diagram Images. In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-626-2, pages 926-931. DOI: 10.5220/0011752600003411


in Bibtex Style

@conference{icpram23,
author={Johannes Bayer and Amit Roy and Andreas Dengel},
title={Instance Segmentation Based Graph Extraction for Handwritten Circuit Diagram Images},
booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2023},
pages={926-931},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011752600003411},
isbn={978-989-758-626-2},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Instance Segmentation Based Graph Extraction for Handwritten Circuit Diagram Images
SN - 978-989-758-626-2
AU - Bayer J.
AU - Roy A.
AU - Dengel A.
PY - 2023
SP - 926
EP - 931
DO - 10.5220/0011752600003411