A Public Ground-Truth Dataset for Handwritten Circuit Diagram Images
This provides a public dataset for researchers in electrical engineering and computer vision, but it is incremental as it focuses on data creation rather than novel methods.
The authors tackled the lack of public training data for digitizing handwritten circuit diagrams by creating a dataset of 1,152 images with 48,563 annotations, and they reported a baseline performance using Faster RCNN.
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.