OCR in a hierarchical feature space
Identifieur interne : 001E22 ( Main/Exploration ); précédent : 001E21; suivant : 001E23OCR in a hierarchical feature space
Auteurs : J. Park [États-Unis] ; Venugopal Govindaraju [États-Unis] ; S. N. SrihariSource :
- IEEE Transactions on Pattern Analysis and Machine Intelligence [ 0162-8828 ] ; 2000.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
This paper describes a character recognition methodology (henceforth referred to as Hierarchical OCR) that achieves high speed and accuracy by using a multiresolution and hierarchical feature space. Features at different resolutions, from coarse to fine-grained, are implemented by means of a recursive classification scheme. Typically, recognizers have to balance the use of features at many resolutions (which yields a high accuracy), with the burden on computational resources in terms of storage space and processing time. We present in this paper, a method that adaptively determines the degree of resolution necessary in order to classify an input pattern. This leads to optimal use of computational resources. The Hierarchical OCR dynamically adapts to factors such as the quality of the input pattern, its intrinsic similarities and differences from patterns of other classes it is being compared against, and the processing time available. Furthermore, the finer resolution is accorded to only certain zones' of the input pattern which are deemed important given the classes that are being discriminated. Experimental results support the methodology presented. When tested on standard NIST data sets, the Hierarchical OCR proves to be 300 times faster than a traditional K-nearest-neighbor classification method, and 10 times faster than a neural network method. The comparison uses the same feature set for all methods. Recognition rate of about 96 percent is achieved by the Hierarchical OCR. This is at par with the other two traditional methods.
Affiliations:
- États-Unis
- État de New York
- Buffalo (New York)
- Université d'État de New York, Université d'État de New York à Buffalo
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000775
- to stream PascalFrancis, to step Curation: 000019
- to stream PascalFrancis, to step Checkpoint: 000716
- to stream Main, to step Merge: 001F28
- to stream Main, to step Curation: 001E22
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">OCR in a hierarchical feature space</title>
<author><name sortKey="Park, J" sort="Park, J" uniqKey="Park J" first="J." last="Park">J. Park</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>State Univ of New York at Buffalo</s1>
<s2>Amherst NY</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<wicri:noRegion>State Univ of New York at Buffalo</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Govindaraju, V" sort="Govindaraju, V" uniqKey="Govindaraju V" first="V." last="Govindaraju">Venugopal Govindaraju</name>
<affiliation><country>États-Unis</country>
<placeName><settlement type="city">Buffalo (New York)</settlement>
<region type="state">État de New York</region>
</placeName>
<orgName type="university" n="3">Université d'État de New York à Buffalo</orgName>
<orgName type="institution">Université d'État de New York</orgName>
</affiliation>
</author>
<author><name sortKey="Srihari, S N" sort="Srihari, S N" uniqKey="Srihari S" first="S. N." last="Srihari">S. N. Srihari</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">00-0310307</idno>
<date when="2000">2000</date>
<idno type="stanalyst">PASCAL 00-0310307 EI</idno>
<idno type="RBID">Pascal:00-0310307</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000775</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000019</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000716</idno>
<idno type="wicri:doubleKey">0162-8828:2000:Park J:ocr:in:a</idno>
<idno type="wicri:Area/Main/Merge">001F28</idno>
<idno type="wicri:Area/Main/Curation">001E22</idno>
<idno type="wicri:Area/Main/Exploration">001E22</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">OCR in a hierarchical feature space</title>
<author><name sortKey="Park, J" sort="Park, J" uniqKey="Park J" first="J." last="Park">J. Park</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>State Univ of New York at Buffalo</s1>
<s2>Amherst NY</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<wicri:noRegion>State Univ of New York at Buffalo</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Govindaraju, V" sort="Govindaraju, V" uniqKey="Govindaraju V" first="V." last="Govindaraju">Venugopal Govindaraju</name>
<affiliation><country>États-Unis</country>
<placeName><settlement type="city">Buffalo (New York)</settlement>
<region type="state">État de New York</region>
</placeName>
<orgName type="university" n="3">Université d'État de New York à Buffalo</orgName>
<orgName type="institution">Université d'État de New York</orgName>
</affiliation>
</author>
<author><name sortKey="Srihari, S N" sort="Srihari, S N" uniqKey="Srihari S" first="S. N." last="Srihari">S. N. Srihari</name>
</author>
</analytic>
<series><title level="j" type="main">IEEE Transactions on Pattern Analysis and Machine Intelligence</title>
<title level="j" type="abbreviated">IEEE Trans Pattern Anal Mach Intell</title>
<idno type="ISSN">0162-8828</idno>
<imprint><date when="2000">2000</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">IEEE Transactions on Pattern Analysis and Machine Intelligence</title>
<title level="j" type="abbreviated">IEEE Trans Pattern Anal Mach Intell</title>
<idno type="ISSN">0162-8828</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Data structures</term>
<term>Hierarchical optical character recognition</term>
<term>Image analysis</term>
<term>Optical character recognition</term>
<term>Theory</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Théorie</term>
<term>Analyse image</term>
<term>Structure donnée</term>
<term>Reconnaissance optique caractère</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">This paper describes a character recognition methodology (henceforth referred to as Hierarchical OCR) that achieves high speed and accuracy by using a multiresolution and hierarchical feature space. Features at different resolutions, from coarse to fine-grained, are implemented by means of a recursive classification scheme. Typically, recognizers have to balance the use of features at many resolutions (which yields a high accuracy), with the burden on computational resources in terms of storage space and processing time. We present in this paper, a method that adaptively determines the degree of resolution necessary in order to classify an input pattern. This leads to optimal use of computational resources. The Hierarchical OCR dynamically adapts to factors such as the quality of the input pattern, its intrinsic similarities and differences from patterns of other classes it is being compared against, and the processing time available. Furthermore, the finer resolution is accorded to only certain zones' of the input pattern which are deemed important given the classes that are being discriminated. Experimental results support the methodology presented. When tested on standard NIST data sets, the Hierarchical OCR proves to be 300 times faster than a traditional K-nearest-neighbor classification method, and 10 times faster than a neural network method. The comparison uses the same feature set for all methods. Recognition rate of about 96 percent is achieved by the Hierarchical OCR. This is at par with the other two traditional methods.</div>
</front>
</TEI>
<affiliations><list><country><li>États-Unis</li>
</country>
<region><li>État de New York</li>
</region>
<settlement><li>Buffalo (New York)</li>
</settlement>
<orgName><li>Université d'État de New York</li>
<li>Université d'État de New York à Buffalo</li>
</orgName>
</list>
<tree><noCountry><name sortKey="Srihari, S N" sort="Srihari, S N" uniqKey="Srihari S" first="S. N." last="Srihari">S. N. Srihari</name>
</noCountry>
<country name="États-Unis"><noRegion><name sortKey="Park, J" sort="Park, J" uniqKey="Park J" first="J." last="Park">J. Park</name>
</noRegion>
<name sortKey="Govindaraju, V" sort="Govindaraju, V" uniqKey="Govindaraju V" first="V." last="Govindaraju">Venugopal Govindaraju</name>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001E22 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001E22 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= Main |étape= Exploration |type= RBID |clé= Pascal:00-0310307 |texte= OCR in a hierarchical feature space }}
This area was generated with Dilib version V0.6.32. |