Instance Segmentation Based Graph Extraction for Handwritten Circuit Diagram Images

TL;DR

This paper presents a machine learning-based method for automatically extracting electrical graphs from handwritten circuit diagrams using instance segmentation and keypoint extraction, facilitating digital analysis of analog media.

Contribution

It introduces a novel approach combining instance segmentation and keypoint extraction for electrical graph extraction from handwritten diagrams, with publicly available dataset and training pipeline.

Findings

Effective extraction of electrical components and connections.

Simplified two-step graph extraction process.

Public dataset and model training resources provided.

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.