ML Anthology

Hexagonal Wavelet Representations for Recognizing Complex Annotations

Andrew F. Laine, Sergio Schuler
CVPR 1994 pp. 740-745
doi:10.1109/CVPR.1994.323890 /cvpr/1994/laine1994cvpr-hexagonal/

Abstract

This paper describes a method of pattern recognition targeted for recognizing complex annotations found in paper documents. Our investigation is motivated by the high reliability required for accomplishing autonomous interpretation of maps and engineering drawings. Our approach includes a strategy based on multiscale representations obtained by hexagonal wavelet analysis. A feasibility study is described in which more than 10,000 patterns were recognized with an error rate of 2.06% by a neural network trained using multiscale representations from a class of 52 distinct patterns. We observed a 21-fold reduction in the amount of information needed to represent each pattern for recognition. These results suggest that high reliability is possible at a reduced cost of representation.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

CVPR Semantic Scholar

Cite

Text

Laine and Schuler. "Hexagonal Wavelet Representations for Recognizing Complex Annotations." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1994. doi:10.1109/CVPR.1994.323890

Markdown

[Laine and Schuler. "Hexagonal Wavelet Representations for Recognizing Complex Annotations." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1994.](https://mlanthology.org/cvpr/1994/laine1994cvpr-hexagonal/) doi:10.1109/CVPR.1994.323890

BibTeX

@inproceedings{laine1994cvpr-hexagonal,
  title     = {{Hexagonal Wavelet Representations for Recognizing Complex Annotations}},
  author    = {Laine, Andrew F. and Schuler, Sergio},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1994},
  pages     = {740-745},
  doi       = {10.1109/CVPR.1994.323890},
  url       = {https://mlanthology.org/cvpr/1994/laine1994cvpr-hexagonal/}
}