Handwritten digit recognition: applications of neural network chips and automatic learning
Abstract
Two novel methods for achieving handwritten digit recognition are described. The first method is based on a neural network chip that performs line thinning and feature extraction using local template matching. The second method is implemented on a digital signal processor and makes extensive use of constrained automatic learning. Experimental results obtained using isolated handwritten digits taken from postal zip codes, a rather difficult data set, are reported and discussed.>
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The citation lists haven’t been fetched yet
References 14 · Cited by 480
- Authors
- Le Cun, Y., Jackel, L. D., Boser, B., Denker, J. S., Graf, H. P., Guyon, I., Henderson, D., Howard, R. E., & Hubbard, W.
- Affiliations
- AT&T (United States) (US)
- Venue
- IEEE Communications Magazine
- Published
- 1989-11
- Volume
- 27
- Issue
- 11
- Pages
- 41-46
- ISSN
- 0163-6804 (ISSN-L)
- OpenAlex
- W2141504882
- Cited by
- 480
- References
- 14
- Citations by year
- 2026: 7 · 2025: 17 · 2024: 27 · 2023: 48 · 2022: 56 · 2021: 58 · 2020: 50 · 2019: 53 · 2018: 24 · 2017: 15 · 2016: 14 · 2015: 5 · 2014: 6 · 2013: 3 · 2012: 8
- FWCI
- 7.05
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Communications Magazine (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Handwritten Text Recognition Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Engineering › Media Technology › Vehicle License Plate Recognition
- Keywords
- handwritten digit recognition, neural network chip, line thinning, feature extraction, template matching, digital signal processor
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
