ML Anthology

Dimension Recognition and Geometry Reconstruction in Vectorization of Engineering Drawings

Feng Su, Jiqiang Song, Chiew-Lan Tai, Shijie Cai
CVPR 2001 pp. I:710-716
doi:10.1109/CVPR.2001.990545 /cvpr/2001/su2001cvpr-dimension/

Abstract

This paper presents a novel approach for recognizing and interpreting dimensions in engineering drawings. It starts by detecting potential dimension frames, each comprising only the line and text components of a dimension, then verifies them by detecting the dimension symbols. By removing the prerequisite of symbol recognition from detection of dimension sets, our method is capable of handling low quality drawings. We also propose a reconstruction algorithm for rebuilding the drawing entities based on the recognized dimension annotations. A coordinate grid structure is introduced to represent and analyze two-dimensional spatial constraints between entities; this simplifies and unifies the process of rectifying deviations of entity dimensions induced during scanning and vectorization.

CVPR Semantic Scholar

Cite

Text

Su et al. "Dimension Recognition and Geometry Reconstruction in Vectorization of Engineering Drawings." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001. doi:10.1109/CVPR.2001.990545

Markdown

[Su et al. "Dimension Recognition and Geometry Reconstruction in Vectorization of Engineering Drawings." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001.](https://mlanthology.org/cvpr/2001/su2001cvpr-dimension/) doi:10.1109/CVPR.2001.990545

BibTeX

@inproceedings{su2001cvpr-dimension,
  title     = {{Dimension Recognition and Geometry Reconstruction in Vectorization of Engineering Drawings}},
  author    = {Su, Feng and Song, Jiqiang and Tai, Chiew-Lan and Cai, Shijie},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2001},
  pages     = {I:710-716},
  doi       = {10.1109/CVPR.2001.990545},
  url       = {https://mlanthology.org/cvpr/2001/su2001cvpr-dimension/}
}