Handprinted Digit Recognition Using Spatiotemporal Connectionist Models
Abstract
A connectionist model for recognizing unconstrained handprinted digits is described. Instead of treating the input as a static signal, the image is canned over time and converted into a time-varying signal. The temporalized image is processed by a spatiotemporal connectionist network. The resulting system offers shift-invariance along the temporalized axis, a reduction in the number of free parameters, and the ability to process images of arbitrary length. For a set of real-world ZIP code digit images, the system achieved a 99.1% recognition rate on the training set and a 96.0% recognition rate on the test with no rejections. A 99.0% recognition rate on the test set was achieved when 14.6% of the images were rejected.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
Cite
Text
Fontaine and Shastri. "Handprinted Digit Recognition Using Spatiotemporal Connectionist Models." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1992. doi:10.1109/CVPR.1992.223277Markdown
[Fontaine and Shastri. "Handprinted Digit Recognition Using Spatiotemporal Connectionist Models." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1992.](https://mlanthology.org/cvpr/1992/fontaine1992cvpr-handprinted/) doi:10.1109/CVPR.1992.223277BibTeX
@inproceedings{fontaine1992cvpr-handprinted,
title = {{Handprinted Digit Recognition Using Spatiotemporal Connectionist Models}},
author = {Fontaine, Thomas and Shastri, Lokendra},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {1992},
pages = {169-175},
doi = {10.1109/CVPR.1992.223277},
url = {https://mlanthology.org/cvpr/1992/fontaine1992cvpr-handprinted/}
}