| Datum
|
2021/05/19 10:30 – 2021/05/19 11:30
|
| Ort
|
https://teams.microsoft.com/l/team/19%3aede66f482bd94928b260e22292b8d41d%40thread.tacv2/conversations?groupId=a0cbe15d-dc9a-4162-8796-3417d585dcae&tenantId=4f5eec75-46fd-43f8-8d24-62bebd9771e5
|
| Vortragende(r)
|
Dominik Fuchß
|
| Forschungsgruppe
|
MCSE
|
| Titel
|
Arrow R-CNN for handwritten diagram recognition
|
| Autoren
|
Bernhard Schäfer, Margret Keuper, Heiner Stuckenschmidt
|
| PDF
|
https://link.springer.com/content/pdf/10.1007/s10032-020-00361-1.pdf
|
| URL
|
https://doi.org/10.1007/s10032-020-00361-1
|
| BibTeX
|
https://sdqweb.ipd.kit.edu/wiki-intern/BibTeX-Eintrag/Sch%C3%A4fer21
|
| Abstract
|
We address the problem of offline handwritten diagram recognition. Recently, it has been shown that diagram symbols can be directly recognized with deep learning object detectors. However, object detectors are not able to recognize the diagram structure.We propose Arrow R-CNN, the first deep learning system for joint symbol and structure recognition in handwritten diagrams. Arrow R-CNN extends the Faster R-CNN object detector with an arrow head and tail keypoint predictor and a diagram-aware postprocessing method. We propose a network architecture and data augmentation methods targeted at small diagram datasets. Our diagram-aware postprocessing method addresses the insufficiencies of standard Faster R-CNN postprocessing. It reconstructs a diagram from a set of symbol detections and arrow keypoints. Arrow R-CNN improves state-of-the-art substantially: on a scanned flowchart dataset, we increase the rate of recognized diagrams from 37.7 to 78.6%.
|
