A Multiscale Approach for Recognizing Complex Annotations in Engineering Documents

Abstract

A novel method for character recognition targeted at complex annotations found in engineering documents is presented. A feasibility study is described in which characters extracted from engineering drawings were recognized without error from a class of 36 distinct alphanumeric patterns by a neural network classifier trained with multiscale representations. An incremental strategy is presented for resolution which relies upon the continuity between hierarchical levels of a novel multiscale decomposition. The authors observed a 16-fold reduction in the amount of information needed to represent each character for recognition. These results suggest high reliability at a reduced cost of representation.

Cite

Text

Laine et al. "A Multiscale Approach for Recognizing Complex Annotations in Engineering Documents." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991. doi:10.1109/CVPR.1991.139812

Markdown

[Laine et al. "A Multiscale Approach for Recognizing Complex Annotations in Engineering Documents." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991.](https://mlanthology.org/cvpr/1991/laine1991cvpr-multiscale/) doi:10.1109/CVPR.1991.139812

BibTeX

@inproceedings{laine1991cvpr-multiscale,
  title     = {{A Multiscale Approach for Recognizing Complex Annotations in Engineering Documents}},
  author    = {Laine, Andrew and Ball, William E. and Kumar, Arun},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1991},
  pages     = {749-750},
  doi       = {10.1109/CVPR.1991.139812},
  url       = {https://mlanthology.org/cvpr/1991/laine1991cvpr-multiscale/}
}