Neural network-based systems for handprint OCR applications.
Identifieur interne : 002187 ( Main/Merge ); précédent : 002186; suivant : 002188Neural network-based systems for handprint OCR applications.
Auteurs : M D Ganis [États-Unis] ; C L Wilson ; J L BlueSource :
- IEEE transactions on image processing : a publication of the IEEE Signal Processing Society [ 1057-7149 ] ; 1998.
Abstract
Over the last five years or so, neural network (NN)-based approaches have been steadily gaining performance and popularity for a wide range of optical character recognition (OCR) problems, from isolated digit recognition to handprint recognition. We present an NN classification scheme based on an enhanced multilayer perceptron (MLP) and describe an end-to-end system for form-based handprint OCR applications designed by the National Institute of Standards and Technology (NIST) Visual Image Processing Group. The enhancements to the MLP are based on (i) neuron activations functions that reduce the occurrences of singular Jacobians; (ii) successive regularization to constrain the volume of the weight space; and (iii) Boltzmann pruning to constrain the dimension of the weight space. Performance characterization studies of NN systems evaluated at the first OCR systems conference and the NIST form-based handprint recognition system are also summarized.
DOI: 10.1109/83.704304
PubMed: 18276327
Links toward previous steps (curation, corpus...)
- to stream PubMed, to step Corpus: 000053
- to stream PubMed, to step Curation: 000053
- to stream PubMed, to step Checkpoint: 000053
- to stream Ncbi, to step Merge: 000047
- to stream Ncbi, to step Curation: 000047
- to stream Ncbi, to step Checkpoint: 000047
Links to Exploration step
pubmed:18276327Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Neural network-based systems for handprint OCR applications.</title><author><name sortKey="Ganis, M D" sort="Ganis, M D" uniqKey="Ganis M" first="M D" last="Ganis">M D Ganis</name><affiliation wicri:level="2"><nlm:affiliation>Nat. Inst. of Stand. and Technol., Gaithersburg, MD 20899, USA. mgarris@nist.gov</nlm:affiliation><country xml:lang="fr">États-Unis</country><wicri:regionArea>Nat. Inst. of Stand. and Technol., Gaithersburg, MD 20899</wicri:regionArea><placeName><region type="state">Maryland</region></placeName></affiliation></author><author><name sortKey="Wilson, C L" sort="Wilson, C L" uniqKey="Wilson C" first="C L" last="Wilson">C L Wilson</name></author><author><name sortKey="Blue, J L" sort="Blue, J L" uniqKey="Blue J" first="J L" last="Blue">J L Blue</name></author></titleStmt><publicationStmt><idno type="wicri:source">PubMed</idno><date when="1998">1998</date><idno type="doi">10.1109/83.704304</idno><idno type="RBID">pubmed:18276327</idno><idno type="pmid">18276327</idno><idno type="wicri:Area/PubMed/Corpus">000053</idno><idno type="wicri:Area/PubMed/Curation">000053</idno><idno type="wicri:Area/PubMed/Checkpoint">000053</idno><idno type="wicri:Area/Ncbi/Merge">000047</idno><idno type="wicri:Area/Ncbi/Curation">000047</idno><idno type="wicri:Area/Ncbi/Checkpoint">000047</idno><idno type="wicri:doubleKey">1057-7149:1998:Ganis M:neural:network:based</idno><idno type="wicri:Area/Main/Merge">002187</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Neural network-based systems for handprint OCR applications.</title><author><name sortKey="Ganis, M D" sort="Ganis, M D" uniqKey="Ganis M" first="M D" last="Ganis">M D Ganis</name><affiliation wicri:level="2"><nlm:affiliation>Nat. Inst. of Stand. and Technol., Gaithersburg, MD 20899, USA. mgarris@nist.gov</nlm:affiliation><country xml:lang="fr">États-Unis</country><wicri:regionArea>Nat. Inst. of Stand. and Technol., Gaithersburg, MD 20899</wicri:regionArea><placeName><region type="state">Maryland</region></placeName></affiliation></author><author><name sortKey="Wilson, C L" sort="Wilson, C L" uniqKey="Wilson C" first="C L" last="Wilson">C L Wilson</name></author><author><name sortKey="Blue, J L" sort="Blue, J L" uniqKey="Blue J" first="J L" last="Blue">J L Blue</name></author></analytic><series><title level="j">IEEE transactions on image processing : a publication of the IEEE Signal Processing Society</title><idno type="ISSN">1057-7149</idno><imprint><date when="1998" type="published">1998</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Over the last five years or so, neural network (NN)-based approaches have been steadily gaining performance and popularity for a wide range of optical character recognition (OCR) problems, from isolated digit recognition to handprint recognition. We present an NN classification scheme based on an enhanced multilayer perceptron (MLP) and describe an end-to-end system for form-based handprint OCR applications designed by the National Institute of Standards and Technology (NIST) Visual Image Processing Group. The enhancements to the MLP are based on (i) neuron activations functions that reduce the occurrences of singular Jacobians; (ii) successive regularization to constrain the volume of the weight space; and (iii) Boltzmann pruning to constrain the dimension of the weight space. Performance characterization studies of NN systems evaluated at the first OCR systems conference and the NIST form-based handprint recognition system are also summarized.</div></front></TEI></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 002187 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 002187 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= Main
|étape= Merge
|type= RBID
|clé= pubmed:18276327
|texte= Neural network-based systems for handprint OCR applications.
}}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Merge/RBID.i -Sk "pubmed:18276327" \
| HfdSelect -Kh $EXPLOR_AREA/Data/Main/Merge/biblio.hfd \
| NlmPubMed2Wicri -a OcrV1
| This area was generated with Dilib version V0.6.32. |  |