A Public Ground-Truth Dataset for Handwritten Circuit Diagram Images

TL;DR

This paper introduces a comprehensive public dataset of 1152 handwritten electrical circuit images with detailed annotations, facilitating research in digitizing line drawings in electrical engineering.

Contribution

It provides a new, publicly available dataset with diverse handwritten circuit images and annotations, along with baseline detection performance for the community.

Findings

Dataset includes 48,563 annotations across 1152 images.

Baseline Faster RCNN achieves initial object detection results.

Diverse conditions and materials enhance dataset robustness.

Abstract

The development of digitization methods for line drawings (especially in the area of electrical engineering) relies on the availability of publicly available training and evaluation data. This paper presents such an image set along with annotations. The dataset consists of 1152 images of 144 circuits by 12 drafters and 48 563 annotations. Each of these images depicts an electrical circuit diagram, taken by consumer grade cameras under varying lighting conditions and perspectives. A variety of different pencil types and surface materials has been used. For each image, all individual electrical components are annotated with bounding boxes and one out of 45 class labels. In order to simplify a graph extraction process, different helper symbols like junction points and crossovers are introduced, while texts are annotated as well. The geometric and taxonomic problems arising from this task as well as the classes themselves and statistics of their appearances are stated. The performance of a standard Faster RCNN on the dataset is provided as an object detection baseline.