Handwritten Numeral Recognition Based on Hierarchically Self-Organizing Learning Networks with Spatio-Temporal Pattern Representation

Lee, Sukhan; Pan, Jack C.

doi:10.1109/CVPR.1992.223276

Handwritten Numeral Recognition Based on Hierarchically Self-Organizing Learning Networks with Spatio-Temporal Pattern Representation

Sukhan Lee, Jack C. Pan

CVPR 1992 pp. 176-182

doi:10.1109/CVPR.1992.223276 /cvpr/1992/lee1992cvpr-handwritten/

Abstract

An approach for tracing, representation, and recognition of a handwritten numeral in an offline environment is presented. A 2D spatial representation of a numeral is first transformed into a 3D spatiotemporal representation by identifying the tracing sequence based on a set of heuristic rules acting as transformation operators. Given the dynamic information of the tracing sequence, a multiresolution critical-point segmentation method is proposed to extract local feature points, at varying degrees of scale and coarseness. A neural network architecture, the hierarchically self-organizing learning (HSOL) network (S. Lee, J.C. Pan, 1989), especially for handwritten numeral recognition, is presented. Experimental results based on a bidirectional HSOL network indicated that the method is robust in terms of variations, deformations, and corruption, achieving about 99% recognition rate for the test patterns.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>

CVPR Semantic Scholar

Cite

Text

Lee and Pan. "Handwritten Numeral Recognition Based on Hierarchically Self-Organizing Learning Networks with Spatio-Temporal Pattern Representation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1992. doi:10.1109/CVPR.1992.223276

Markdown

[Lee and Pan. "Handwritten Numeral Recognition Based on Hierarchically Self-Organizing Learning Networks with Spatio-Temporal Pattern Representation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1992.](https://mlanthology.org/cvpr/1992/lee1992cvpr-handwritten/) doi:10.1109/CVPR.1992.223276

BibTeX

@inproceedings{lee1992cvpr-handwritten,
  title     = {{Handwritten Numeral Recognition Based on Hierarchically Self-Organizing Learning Networks with Spatio-Temporal Pattern Representation}},
  author    = {Lee, Sukhan and Pan, Jack C.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1992},
  pages     = {176-182},
  doi       = {10.1109/CVPR.1992.223276},
  url       = {https://mlanthology.org/cvpr/1992/lee1992cvpr-handwritten/}
}