Search technique for pattern recognition using relative distances
Identifieur interne : 000A48 ( PascalFrancis/Corpus ); précédent : 000A47; suivant : 000A49Search technique for pattern recognition using relative distances
Auteurs : T. E. PortegysSource :
- IEEE Transactions on Pattern Analysis and Machine Intelligence [ 0162-8828 ] ; 1995.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
A technique for creating and searching a tree of patterns using relative distances is presented. The search is conducted to find patterns which are nearest neighbors of a given test pattern. The structure of the tree is such that the search time is proportional to the distance between the test pattern and its nearest neighbor, which suggests the anomalous possibility that a larger tree, which can be expected on average to contain closer neighbors, can be searched faster than a smaller tree. The technique has been used to recognize OCR digit samples derived from NIST data at an accuracy rate of 97% using a tree of 7,000 patterns.
Notice en format standard (ISO 2709)
Pour connaître la documentation sur le format Inist Standard.
pA |
|
---|
Format Inist (serveur)
NO : | PASCAL 95-0527484 EI |
---|---|
ET : | Search technique for pattern recognition using relative distances |
AU : | PORTEGYS (T. E.) |
AF : | AT&T Bell Lab/Naperville IL/Etats-Unis (1 aut.) |
DT : | Publication en série; Niveau analytique |
SO : | IEEE Transactions on Pattern Analysis and Machine Intelligence; ISSN 0162-8828; Coden ITPIDJ; Etats-Unis; Da. 1995; Vol. 17; No. 9; Pp. 910-914; Bibl. 12 Refs. |
LA : | Anglais |
EA : | A technique for creating and searching a tree of patterns using relative distances is presented. The search is conducted to find patterns which are nearest neighbors of a given test pattern. The structure of the tree is such that the search time is proportional to the distance between the test pattern and its nearest neighbor, which suggests the anomalous possibility that a larger tree, which can be expected on average to contain closer neighbors, can be searched faster than a smaller tree. The technique has been used to recognize OCR digit samples derived from NIST data at an accuracy rate of 97% using a tree of 7,000 patterns. |
CC : | 001D02C; 001D02A; 001D02B07B; 001A02I01 |
FD : | Application; Reconnaissance optique caractère; Algorithme; Fonction récursive; Structure donnée; Calcul; Reconnaissance forme; Théorie |
ED : | Nearest neighbor; Distance metric; NIST digit samples; Pattern insertion; Pattern searching; Application; Optical character recognition; Algorithms; Recursive functions; Data structures; Calculations; Pattern recognition; Theory |
GD : | Anwendung |
SD : | Aplicación |
LO : | INIST-222 T |
ID : | 95-0527484 |
Links to Exploration step
Pascal:95-0527484Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Search technique for pattern recognition using relative distances</title>
<author><name sortKey="Portegys, T E" sort="Portegys, T E" uniqKey="Portegys T" first="T. E." last="Portegys">T. E. Portegys</name>
<affiliation><inist:fA14 i1="01"><s1>AT&T Bell Lab</s1>
<s2>Naperville IL</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">95-0527484</idno>
<date when="1995">1995</date>
<idno type="stanalyst">PASCAL 95-0527484 EI</idno>
<idno type="RBID">Pascal:95-0527484</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000A48</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Search technique for pattern recognition using relative distances</title>
<author><name sortKey="Portegys, T E" sort="Portegys, T E" uniqKey="Portegys T" first="T. E." last="Portegys">T. E. Portegys</name>
<affiliation><inist:fA14 i1="01"><s1>AT&T Bell Lab</s1>
<s2>Naperville IL</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
</affiliation>
</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="1995">1995</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>Algorithms</term>
<term>Application</term>
<term>Calculations</term>
<term>Data structures</term>
<term>Distance metric</term>
<term>NIST digit samples</term>
<term>Nearest neighbor</term>
<term>Optical character recognition</term>
<term>Pattern insertion</term>
<term>Pattern recognition</term>
<term>Pattern searching</term>
<term>Recursive functions</term>
<term>Theory</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Application</term>
<term>Reconnaissance optique caractère</term>
<term>Algorithme</term>
<term>Fonction récursive</term>
<term>Structure donnée</term>
<term>Calcul</term>
<term>Reconnaissance forme</term>
<term>Théorie</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">A technique for creating and searching a tree of patterns using relative distances is presented. The search is conducted to find patterns which are nearest neighbors of a given test pattern. The structure of the tree is such that the search time is proportional to the distance between the test pattern and its nearest neighbor, which suggests the anomalous possibility that a larger tree, which can be expected on average to contain closer neighbors, can be searched faster than a smaller tree. The technique has been used to recognize OCR digit samples derived from NIST data at an accuracy rate of 97% using a tree of 7,000 patterns.</div>
</front>
</TEI>
<inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>0162-8828</s0>
</fA01>
<fA02 i1="01"><s0>ITPIDJ</s0>
</fA02>
<fA03 i2="1"><s0>IEEE Trans Pattern Anal Mach Intell</s0>
</fA03>
<fA05><s2>17</s2>
</fA05>
<fA06><s2>9</s2>
</fA06>
<fA08 i1="01" i2="1" l="ENG"><s1>Search technique for pattern recognition using relative distances</s1>
</fA08>
<fA11 i1="01" i2="1"><s1>PORTEGYS (T. E.)</s1>
</fA11>
<fA14 i1="01"><s1>AT&T Bell Lab</s1>
<s2>Naperville IL</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
</fA14>
<fA20><s1>910-914</s1>
</fA20>
<fA21><s1>1995</s1>
</fA21>
<fA23 i1="01"><s0>ENG</s0>
</fA23>
<fA43 i1="01"><s1>INIST</s1>
<s2>222 T</s2>
</fA43>
<fA44><s0>A100</s0>
</fA44>
<fA45><s0>12 Refs.</s0>
</fA45>
<fA47 i1="01" i2="1"><s0>95-0527484</s0>
</fA47>
<fA60><s1>P</s1>
</fA60>
<fA61><s0>A</s0>
</fA61>
<fA64 i1="01" i2="1"><s0>IEEE Transactions on Pattern Analysis and Machine Intelligence</s0>
</fA64>
<fA66 i1="01"><s0>USA</s0>
</fA66>
<fC01 i1="01" l="ENG"><s0>A technique for creating and searching a tree of patterns using relative distances is presented. The search is conducted to find patterns which are nearest neighbors of a given test pattern. The structure of the tree is such that the search time is proportional to the distance between the test pattern and its nearest neighbor, which suggests the anomalous possibility that a larger tree, which can be expected on average to contain closer neighbors, can be searched faster than a smaller tree. The technique has been used to recognize OCR digit samples derived from NIST data at an accuracy rate of 97% using a tree of 7,000 patterns.</s0>
</fC01>
<fC02 i1="01" i2="1"><s0>001D02C</s0>
</fC02>
<fC02 i1="02" i2="1"><s0>001D02A</s0>
</fC02>
<fC02 i1="03" i2="1"><s0>001D02B07B</s0>
</fC02>
<fC02 i1="04" i2="1"><s0>001A02I01</s0>
</fC02>
<fC03 i1="01" i2="1" l="ENG"><s0>Nearest neighbor</s0>
<s4>INC</s4>
</fC03>
<fC03 i1="02" i2="1" l="ENG"><s0>Distance metric</s0>
<s4>INC</s4>
</fC03>
<fC03 i1="03" i2="1" l="ENG"><s0>NIST digit samples</s0>
<s4>INC</s4>
</fC03>
<fC03 i1="04" i2="1" l="ENG"><s0>Pattern insertion</s0>
<s4>INC</s4>
</fC03>
<fC03 i1="05" i2="1" l="ENG"><s0>Pattern searching</s0>
<s4>INC</s4>
</fC03>
<fC03 i1="06" i2="X" l="FRE"><s0>Application</s0>
</fC03>
<fC03 i1="06" i2="X" l="ENG"><s0>Application</s0>
</fC03>
<fC03 i1="06" i2="X" l="GER"><s0>Anwendung</s0>
</fC03>
<fC03 i1="06" i2="X" l="SPA"><s0>Aplicación</s0>
</fC03>
<fC03 i1="07" i2="1" l="FRE"><s0>Reconnaissance optique caractère</s0>
</fC03>
<fC03 i1="07" i2="1" l="ENG"><s0>Optical character recognition</s0>
</fC03>
<fC03 i1="08" i2="1" l="FRE"><s0>Algorithme</s0>
</fC03>
<fC03 i1="08" i2="1" l="ENG"><s0>Algorithms</s0>
</fC03>
<fC03 i1="09" i2="1" l="FRE"><s0>Fonction récursive</s0>
</fC03>
<fC03 i1="09" i2="1" l="ENG"><s0>Recursive functions</s0>
</fC03>
<fC03 i1="10" i2="1" l="FRE"><s0>Structure donnée</s0>
</fC03>
<fC03 i1="10" i2="1" l="ENG"><s0>Data structures</s0>
</fC03>
<fC03 i1="11" i2="1" l="FRE"><s0>Calcul</s0>
</fC03>
<fC03 i1="11" i2="1" l="ENG"><s0>Calculations</s0>
</fC03>
<fC03 i1="12" i2="1" l="FRE"><s0>Reconnaissance forme</s0>
<s3>P</s3>
</fC03>
<fC03 i1="12" i2="1" l="ENG"><s0>Pattern recognition</s0>
<s3>P</s3>
</fC03>
<fC03 i1="13" i2="1" l="FRE"><s0>Théorie</s0>
</fC03>
<fC03 i1="13" i2="1" l="ENG"><s0>Theory</s0>
</fC03>
<fN21><s1>302</s1>
</fN21>
</pA>
</standard>
<server><NO>PASCAL 95-0527484 EI</NO>
<ET>Search technique for pattern recognition using relative distances</ET>
<AU>PORTEGYS (T. E.)</AU>
<AF>AT&T Bell Lab/Naperville IL/Etats-Unis (1 aut.)</AF>
<DT>Publication en série; Niveau analytique</DT>
<SO>IEEE Transactions on Pattern Analysis and Machine Intelligence; ISSN 0162-8828; Coden ITPIDJ; Etats-Unis; Da. 1995; Vol. 17; No. 9; Pp. 910-914; Bibl. 12 Refs.</SO>
<LA>Anglais</LA>
<EA>A technique for creating and searching a tree of patterns using relative distances is presented. The search is conducted to find patterns which are nearest neighbors of a given test pattern. The structure of the tree is such that the search time is proportional to the distance between the test pattern and its nearest neighbor, which suggests the anomalous possibility that a larger tree, which can be expected on average to contain closer neighbors, can be searched faster than a smaller tree. The technique has been used to recognize OCR digit samples derived from NIST data at an accuracy rate of 97% using a tree of 7,000 patterns.</EA>
<CC>001D02C; 001D02A; 001D02B07B; 001A02I01</CC>
<FD>Application; Reconnaissance optique caractère; Algorithme; Fonction récursive; Structure donnée; Calcul; Reconnaissance forme; Théorie</FD>
<ED>Nearest neighbor; Distance metric; NIST digit samples; Pattern insertion; Pattern searching; Application; Optical character recognition; Algorithms; Recursive functions; Data structures; Calculations; Pattern recognition; Theory</ED>
<GD>Anwendung</GD>
<SD>Aplicación</SD>
<LO>INIST-222 T</LO>
<ID>95-0527484</ID>
</server>
</inist>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/PascalFrancis/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000A48 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Corpus/biblio.hfd -nk 000A48 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= PascalFrancis |étape= Corpus |type= RBID |clé= Pascal:95-0527484 |texte= Search technique for pattern recognition using relative distances }}
![]() | This area was generated with Dilib version V0.6.32. | ![]() |