Document Type

Conference Paper

Publication Date

2022

Publication Title

CEUR Workshop Proceedings- SDU 2022 Proceedings of the Workshop on Scientific Document Understanding

Volume

3164

Pages

1-6

Conference Name

SDU 2022: The AAAI-22 Workshop on Scientific Document Understanding, 1 March 2022, Virtual

Abstract

Image segmentation is the core computer vision problem for identifying objects within a scene. Segmentation is a challenging task because the prediction for each pixel label requires contextual information. Most recent research deals with the segmentation of natural images rather than drawings. However, there is very little research on sketched image segmentation. In this study, we introduce heuristic (point-shooting) and deep learning-based methods (U-Net, HR-Net, MedT, DETR) to segment technical drawings in US patent documents. Our proposed methods on the US Patent dataset achieved over 90% accuracy where transformer performs well with 97% segmentation accuracy, which is promising and computationally efficient. Our source codes and datasets are available at https://github.com/GoFigure-LANL/figure-segmentation.

Comments

© 2022 Copyright for this paper by its authors.

Use permitted under a Creative Commons License Attribution 4.0 International (CC BY 4.0) License.

Conference landing page available at: http://ceur-ws.org/Vol-3164/

Original Publication Citation

Hoque, M. R. U., Wei, X., Choudhury, M. H., Ajayi, K., Gryder, M., Wu, J., & Oyen, D. (2022). CEUR Workshop Proceedings- SDU 2022 Proceedings of the Workshop on Scientific Document Understanding, 3164 (1-6). http://ceur-ws.org/Vol-3164/paper28.pdf

ORCID

0000-0003-4055-2582 (Hoque), 0000-0002-9318-8844 (Choudhury), 0000-0002-5124-0739 (Ajayi), 0000-0003-0173-4463 (Wu)

Share

COinS