Learning to See Where and What: Training a Net to Make Saccades and Recognize Handwritten Characters
Abstract
to integrated segmentation and This paper describes an approach recognition of hand-printed characters. The approach, called Saccade, integrates ballistic and corrective saccades (eye movements) with character recognition. A single backpropagation net is trained to make a classification decision on a character centered in its input window, as well as to estimate the distance of the current and next character from the center of the input window. The net learns to accurately estimate these distances regardless of variations in character width, spacing between characters, writing style and other factors. During testing, the system uses the net~xtracted classification and distance information, along with a set of jumping rules, to jump from character to character.
Cite
Text
Martin et al. "Learning to See Where and What: Training a Net to Make Saccades and Recognize Handwritten Characters." Neural Information Processing Systems, 1992.Markdown
[Martin et al. "Learning to See Where and What: Training a Net to Make Saccades and Recognize Handwritten Characters." Neural Information Processing Systems, 1992.](https://mlanthology.org/neurips/1992/martin1992neurips-learning/)BibTeX
@inproceedings{martin1992neurips-learning,
title = {{Learning to See Where and What: Training a Net to Make Saccades and Recognize Handwritten Characters}},
author = {Martin, Gale and Rashid, Mosfeq and Chapman, David and Pittman, James A.},
booktitle = {Neural Information Processing Systems},
year = {1992},
pages = {441-447},
url = {https://mlanthology.org/neurips/1992/martin1992neurips-learning/}
}