ML Anthology

Fast Recognition of Noisy Digits

Jeffrey N. Kidder, Daniel Seligson
NeCo 1993 pp. 885-892
doi:10.1162/NECO.1993.5.6.885 /neco/1993/kidder1993neco-fast/

Abstract

We describe a hardware solution to a high-speed optical character recognition (OCR) problem. Noisy 15 × 10 binary images of machine written digits were processed and applied as input to Intel's Electrically Trainable Analog Neural Network (ETANN). In software simulation, we trained an 80 × 54 × 10 feedforward network using a modified version of backprop. We then downloaded the synaptic weights of the trained network to ETANN and tweaked them to account for differences between the simulation and the chip itself. The best recognition error rate was 0.9% in hardware with a 3.7% rejection rate on a 1000-character test set.

NeCo Semantic Scholar

Cite

Text

Kidder and Seligson. "Fast Recognition of Noisy Digits." Neural Computation, 1993. doi:10.1162/NECO.1993.5.6.885

Markdown

[Kidder and Seligson. "Fast Recognition of Noisy Digits." Neural Computation, 1993.](https://mlanthology.org/neco/1993/kidder1993neco-fast/) doi:10.1162/NECO.1993.5.6.885

BibTeX

@article{kidder1993neco-fast,
  title     = {{Fast Recognition of Noisy Digits}},
  author    = {Kidder, Jeffrey N. and Seligson, Daniel},
  journal   = {Neural Computation},
  year      = {1993},
  pages     = {885-892},
  doi       = {10.1162/NECO.1993.5.6.885},
  volume    = {5},
  url       = {https://mlanthology.org/neco/1993/kidder1993neco-fast/}
}