The DOI matches its Crossref record, with a small difference in title or year.
Multiresolution neural networks for omnifont character recognition
Abstract
A multiresolution optical character recognition (OCR) using neural networks is proposed for omnifont character recognition. It is motivated by the human reading process in which a low resolution is used to effectively process the majority of clean and unambiguous text, while a more complicated recognition scheme is invoked only when a high resolution is needed. Compared with the method that utilizes single resolution, the multiresolution system not only speeds up recognition by up to 20 times, but also improves accuracy of isolated character recognition from 99.8% to 99.9%. The multiresolution approach captures the essence of better reading, and provides the building blocks for the next-generation OCR systems.>
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Several recent works have shown that the same is true for handwriting recognition [38]: optimizing a word-level criterion is preferable to solely training a recognizer on presegmented characters because the recognizer can learn not only to recognize individual characters, but also to reject missegmented characters, thereby minimizing the overall word error.”
From Gradient-based learning applied to document recognition (1998) · cites this paper as [38]
In the citing paper
“Early experiments in zip code recognition [91], and more recent experiments in online handwriting recognition [38] have demonstrated the idea of globally trained SDNN/HMM hybrids.”
From Gradient-based learning applied to document recognition (1998) · cites this paper as [38]
In the citing paper
“Similar ideas have been applied to handwriting recognition (see [38] for a review).”
From Gradient-based learning applied to document recognition (1998) · cites this paper as [38]
Citations
Cites
No references could be resolved yet.
Research works printed but not linked: 19
- 10.1109/IJCNN.1991.155265 · DOI
- 10.1016/0031-3203(93)90099-I · DOI
- 10.1145/162754.168698 · DOI
- 10.1016/0893-6080(89)90023-3 · DOI
- 10.1109/IJCNN.1989.118426 · DOI
- 10.1109/TPAMI.1987.4767901 · DOI
- 10.1109/ICPR.1990.118211 · DOI
- 10.1016/0893-6080(90)90044-L · DOI
- 10.1109/72.317727 · DOI
- minsky, 1988, Perceptrons An Introduction to Computational Geometry
- 10.1162/neco.1992.4.6.888 · DOI · Paper page
- 10.1109/72.97912 · DOI
- 10.1016/0031-3203(81)90083-2 · DOI
- 10.1117/12.50345 · DOI
- meng, 1990, Text without typing, MacWorld, 177
- 10.1109/5.156474 · DOI
- 10.1109/40.124378 · DOI
- 10.1109/ICPR.1990.119325 · DOI
- diehl, 1991, Tame the paper tiger, Byte, 220
Cited by
Sorted by citations
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Object Recognition with Gradient-Based Learning
LeCun, Y., Haffner, P., Bottou, L., & Bengio, Y. (1999) · Lecture Notes in Computer Science · doi:10.1007/3-540-46805-6_19 · Cited by 947
Liu, R., Meng, G., Yang, B., Sun, C., & Chen, X. (2017) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2016.2645238 · Cited by 345
Metadata
- Authors
- Wang, J., & Jean, J.
- Affiliations
- Wright State University (US)
- ORCID
- Wang, J.
- Venue
- IEEE International Conference on Neural Networks
- Publisher
- IEEE
- Published
- 2002-12-30
- Pages
- 1588-1593
- ISSN
- 1098-7576 (ISSN-L)
- OpenAlex
- W2140005396
- Cited by
- 11
- References
- 0
- Citations by year
- 2026: 1 · 2023: 1 · 2016: 1
- FWCI
- 0.62
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Neural Networks/IEEE ... International Conference on Neural Networks (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Handwritten Text Recognition Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Vehicle License Plate Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- isolated character recognition, artificial neural networks
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
