Fast real-time recognition and quality inspection of printed characters via point-correlation
Identifieur interne :
000690 ( PascalFrancis/Corpus );
précédent :
000689;
suivant :
000691
Fast real-time recognition and quality inspection of printed characters via point-correlation
Auteurs : H. Penz ;
I. Bajla ;
A. Vrabl ;
W. Krattenthaler ;
K. MayerSource :
-
SPIE proceedings series [ 1017-2653 ] ; 2001.
RBID : Pascal:02-0062190
Descripteurs français
English descriptors
Abstract
Some technical applications need a fast and reliable OCR (optical character recognition) for critical circumstances like low resolution and poor contrast. A concrete example is the real-time quality inspection system of Austrian banknotes. One requirement to the system is that it has to read two serial numbers on each banknote and to check if they are identical. To solve the problem we have developed a novel method based on an idea similar to pattern matching. However, instead of comparing entire images we use reduced sets of pixels, one for each different numeral (character). The detection (point correlation) is performed by matching these pixel sets with the corresponding pixels in the image being analyzed. We present an algorithm based on two cost functions that computes in a reasonable time the reduced pixel (point) sets from a given set of image templates. The efficiency of our OCR has been increased considerably by introducing an appropriate set of image preprocessing operations. These are tailored especially to images with low resolution and poor contrast, but they are simple enough to allow a fast real-time implementation. They can be seen as a normalization step that improves the image properties which are essential for pattern matching.
Notice en format standard (ISO 2709)
Pour connaître la documentation sur le format Inist Standard.
| pA |
| A01 | 01 | 1 | | @0 1017-2653 |
|---|
| A05 | | | | @2 4303 |
|---|
| A08 | 01 | 1 | ENG | @1 Fast real-time recognition and quality inspection of printed characters via point-correlation |
|---|
| A09 | 01 | 1 | ENG | @1 Real-time imaging V : San Jose CA, 24-25 January 2001 |
|---|
| A11 | 01 | 1 | | @1 PENZ (H.) |
|---|
| A11 | 02 | 1 | | @1 BAJLA (I.) |
|---|
| A11 | 03 | 1 | | @1 VRABL (A.) |
|---|
| A11 | 04 | 1 | | @1 KRATTENTHALER (W.) |
|---|
| A11 | 05 | 1 | | @1 MAYER (K.) |
|---|
| A12 | 01 | 1 | | @1 KEHTARNAVAZ (Nasser) @9 ed. |
|---|
| A14 | 01 | | | @1 Austrian Research Centers Seibersdorf @2 2444 Seibersdorf @3 AUT @Z 1 aut. @Z 2 aut. @Z 3 aut. @Z 4 aut. @Z 5 aut. |
|---|
| A18 | 01 | 1 | | @1 International Society for Optical Engineering @2 Bellingham WA @3 USA @9 patr. |
|---|
| A20 | | | | @1 127-137 |
|---|
| A21 | | | | @1 2001 |
|---|
| A23 | 01 | | | @0 ENG |
|---|
| A26 | 01 | | | @0 0-8194-3981-9 |
|---|
| A43 | 01 | | | @1 INIST @2 21760 @5 354000097026230150 |
|---|
| A44 | | | | @0 0000 @1 © 2002 INIST-CNRS. All rights reserved. |
|---|
| A45 | | | | @0 4 ref. |
|---|
| A47 | 01 | 1 | | @0 02-0062190 |
|---|
| A60 | | | | @1 P @2 C |
|---|
| A61 | | | | @0 A |
|---|
| A64 | 01 | 1 | | @0 SPIE proceedings series |
|---|
| A66 | 01 | | | @0 USA |
|---|
| C01 | 01 | | ENG | @0 Some technical applications need a fast and reliable OCR (optical character recognition) for critical circumstances like low resolution and poor contrast. A concrete example is the real-time quality inspection system of Austrian banknotes. One requirement to the system is that it has to read two serial numbers on each banknote and to check if they are identical. To solve the problem we have developed a novel method based on an idea similar to pattern matching. However, instead of comparing entire images we use reduced sets of pixels, one for each different numeral (character). The detection (point correlation) is performed by matching these pixel sets with the corresponding pixels in the image being analyzed. We present an algorithm based on two cost functions that computes in a reasonable time the reduced pixel (point) sets from a given set of image templates. The efficiency of our OCR has been increased considerably by introducing an appropriate set of image preprocessing operations. These are tailored especially to images with low resolution and poor contrast, but they are simple enough to allow a fast real-time implementation. They can be seen as a normalization step that improves the image properties which are essential for pattern matching. |
|---|
| C02 | 01 | X | | @0 001D04A05C |
|---|
| C03 | 01 | X | FRE | @0 Traitement image @5 01 |
|---|
| C03 | 01 | X | ENG | @0 Image processing @5 01 |
|---|
| C03 | 01 | X | SPA | @0 Procesamiento imagen @5 01 |
|---|
| C03 | 02 | X | FRE | @0 Traitement temps réel @5 02 |
|---|
| C03 | 02 | X | ENG | @0 Real time processing @5 02 |
|---|
| C03 | 02 | X | SPA | @0 Tratamiento tiempo real @5 02 |
|---|
| C03 | 03 | X | FRE | @0 Caractère imprimé @5 03 |
|---|
| C03 | 03 | X | ENG | @0 Printed character @5 03 |
|---|
| C03 | 03 | X | SPA | @0 Carácter impreso @5 03 |
|---|
| C03 | 04 | X | FRE | @0 Reconnaissance caractère @5 04 |
|---|
| C03 | 04 | X | ENG | @0 Character recognition @5 04 |
|---|
| C03 | 04 | X | SPA | @0 Reconocimiento carácter @5 04 |
|---|
| C03 | 05 | X | FRE | @0 Inspection @5 05 |
|---|
| C03 | 05 | X | ENG | @0 Inspection @5 05 |
|---|
| C03 | 05 | X | SPA | @0 Inspección @5 05 |
|---|
| C03 | 06 | X | FRE | @0 Qualité image @5 06 |
|---|
| C03 | 06 | X | ENG | @0 Image quality @5 06 |
|---|
| C03 | 06 | X | SPA | @0 Calidad imagen @5 06 |
|---|
| C03 | 07 | X | FRE | @0 Concordance forme @5 07 |
|---|
| C03 | 07 | X | ENG | @0 Pattern matching @5 07 |
|---|
| C03 | 08 | X | FRE | @0 Corrélation @5 08 |
|---|
| C03 | 08 | X | ENG | @0 Correlation @5 08 |
|---|
| C03 | 08 | X | SPA | @0 Correlación @5 08 |
|---|
| C03 | 09 | X | FRE | @0 Algorithme @5 09 |
|---|
| C03 | 09 | X | ENG | @0 Algorithm @5 09 |
|---|
| C03 | 09 | X | SPA | @0 Algoritmo @5 09 |
|---|
| N21 | | | | @1 028 |
|---|
|
|---|
| pR |
| A30 | 01 | 1 | ENG | @1 Real-time imaging. Conference @2 5 @3 San Jose CA USA @4 2001-01-24 |
|---|
|
|---|
Format Inist (serveur)
| NO : | PASCAL 02-0062190 INIST |
|---|
| ET : | Fast real-time recognition and quality inspection of printed characters via point-correlation |
|---|
| AU : | PENZ (H.); BAJLA (I.); VRABL (A.); KRATTENTHALER (W.); MAYER (K.); KEHTARNAVAZ (Nasser) |
|---|
| AF : | Austrian Research Centers Seibersdorf/2444 Seibersdorf/Autriche (1 aut., 2 aut., 3 aut., 4 aut., 5 aut.) |
|---|
| DT : | Publication en série; Congrès; Niveau analytique |
|---|
| SO : | SPIE proceedings series; ISSN 1017-2653; Etats-Unis; Da. 2001; Vol. 4303; Pp. 127-137; Bibl. 4 ref. |
|---|
| LA : | Anglais |
|---|
| EA : | Some technical applications need a fast and reliable OCR (optical character recognition) for critical circumstances like low resolution and poor contrast. A concrete example is the real-time quality inspection system of Austrian banknotes. One requirement to the system is that it has to read two serial numbers on each banknote and to check if they are identical. To solve the problem we have developed a novel method based on an idea similar to pattern matching. However, instead of comparing entire images we use reduced sets of pixels, one for each different numeral (character). The detection (point correlation) is performed by matching these pixel sets with the corresponding pixels in the image being analyzed. We present an algorithm based on two cost functions that computes in a reasonable time the reduced pixel (point) sets from a given set of image templates. The efficiency of our OCR has been increased considerably by introducing an appropriate set of image preprocessing operations. These are tailored especially to images with low resolution and poor contrast, but they are simple enough to allow a fast real-time implementation. They can be seen as a normalization step that improves the image properties which are essential for pattern matching. |
|---|
| CC : | 001D04A05C |
|---|
| FD : | Traitement image; Traitement temps réel; Caractère imprimé; Reconnaissance caractère; Inspection; Qualité image; Concordance forme; Corrélation; Algorithme |
|---|
| ED : | Image processing; Real time processing; Printed character; Character recognition; Inspection; Image quality; Pattern matching; Correlation; Algorithm |
|---|
| SD : | Procesamiento imagen; Tratamiento tiempo real; Carácter impreso; Reconocimiento carácter; Inspección; Calidad imagen; Correlación; Algoritmo |
|---|
| LO : | INIST-21760.354000097026230150 |
|---|
| ID : | 02-0062190 |
|---|
Links to Exploration step
Pascal:02-0062190
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Fast real-time recognition and quality inspection of printed characters via point-correlation</title>
<author><name sortKey="Penz, H" sort="Penz, H" uniqKey="Penz H" first="H." last="Penz">H. Penz</name>
<affiliation><inist:fA14 i1="01"><s1>Austrian Research Centers Seibersdorf</s1>
<s2>2444 Seibersdorf</s2>
<s3>AUT</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14><author><name sortKey="Bajla, I" sort="Bajla, I" uniqKey="Bajla I" first="I." last="Bajla">I. Bajla</name>
<affiliation><inist:fA14 i1="01"><s1>Austrian Research Centers Seibersdorf</s1>
<s2>2444 Seibersdorf</s2>
<s3>AUT</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14><author><name sortKey="Vrabl, A" sort="Vrabl, A" uniqKey="Vrabl A" first="A." last="Vrabl">A. Vrabl</name>
<affiliation><inist:fA14 i1="01"><s1>Austrian Research Centers Seibersdorf</s1>
<s2>2444 Seibersdorf</s2>
<s3>AUT</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14><author><name sortKey="Krattenthaler, W" sort="Krattenthaler, W" uniqKey="Krattenthaler W" first="W." last="Krattenthaler">W. Krattenthaler</name>
<affiliation><inist:fA14 i1="01"><s1>Austrian Research Centers Seibersdorf</s1>
<s2>2444 Seibersdorf</s2>
<s3>AUT</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14><author><name sortKey="Mayer, K" sort="Mayer, K" uniqKey="Mayer K" first="K." last="Mayer">K. Mayer</name>
<affiliation><inist:fA14 i1="01"><s1>Austrian Research Centers Seibersdorf</s1>
<s2>2444 Seibersdorf</s2>
<s3>AUT</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14><publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">02-0062190</idno>
<date when="2001">2001</date>
<idno type="stanalyst">PASCAL 02-0062190 INIST</idno>
<idno type="RBID">Pascal:02-0062190</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000690</idno>
</publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Fast real-time recognition and quality inspection of printed characters via point-correlation</title>
<author><name sortKey="Penz, H" sort="Penz, H" uniqKey="Penz H" first="H." last="Penz">H. Penz</name>
<affiliation><inist:fA14 i1="01"><s1>Austrian Research Centers Seibersdorf</s1>
<s2>2444 Seibersdorf</s2>
<s3>AUT</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14><author><name sortKey="Bajla, I" sort="Bajla, I" uniqKey="Bajla I" first="I." last="Bajla">I. Bajla</name>
<affiliation><inist:fA14 i1="01"><s1>Austrian Research Centers Seibersdorf</s1>
<s2>2444 Seibersdorf</s2>
<s3>AUT</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14><author><name sortKey="Vrabl, A" sort="Vrabl, A" uniqKey="Vrabl A" first="A." last="Vrabl">A. Vrabl</name>
<affiliation><inist:fA14 i1="01"><s1>Austrian Research Centers Seibersdorf</s1>
<s2>2444 Seibersdorf</s2>
<s3>AUT</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14><author><name sortKey="Krattenthaler, W" sort="Krattenthaler, W" uniqKey="Krattenthaler W" first="W." last="Krattenthaler">W. Krattenthaler</name>
<affiliation><inist:fA14 i1="01"><s1>Austrian Research Centers Seibersdorf</s1>
<s2>2444 Seibersdorf</s2>
<s3>AUT</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14><author><name sortKey="Mayer, K" sort="Mayer, K" uniqKey="Mayer K" first="K." last="Mayer">K. Mayer</name>
<affiliation><inist:fA14 i1="01"><s1>Austrian Research Centers Seibersdorf</s1>
<s2>2444 Seibersdorf</s2>
<s3>AUT</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14><series><title level="j" type="main">SPIE proceedings series</title>
<idno type="ISSN">1017-2653</idno>
<imprint><date when="2001">2001</date>
</imprint><seriesStmt><title level="j" type="main">SPIE proceedings series</title>
<idno type="ISSN">1017-2653</idno>
</seriesStmt><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithm</term>
<term>Character recognition</term>
<term>Correlation</term>
<term>Image processing</term>
<term>Image quality</term>
<term>Inspection</term>
<term>Pattern matching</term>
<term>Printed character</term>
<term>Real time processing</term>
</keywords><keywords scheme="Pascal" xml:lang="fr"><term>Traitement image</term>
<term>Traitement temps réel</term>
<term>Caractère imprimé</term>
<term>Reconnaissance caractère</term>
<term>Inspection</term>
<term>Qualité image</term>
<term>Concordance forme</term>
<term>Corrélation</term>
<term>Algorithme</term>
</keywords><front><div type="abstract" xml:lang="en">Some technical applications need a fast and reliable OCR (optical character recognition) for critical circumstances like low resolution and poor contrast. A concrete example is the real-time quality inspection system of Austrian banknotes. One requirement to the system is that it has to read two serial numbers on each banknote and to check if they are identical. To solve the problem we have developed a novel method based on an idea similar to pattern matching. However, instead of comparing entire images we use reduced sets of pixels, one for each different numeral (character). The detection (point correlation) is performed by matching these pixel sets with the corresponding pixels in the image being analyzed. We present an algorithm based on two cost functions that computes in a reasonable time the reduced pixel (point) sets from a given set of image templates. The efficiency of our OCR has been increased considerably by introducing an appropriate set of image preprocessing operations. These are tailored especially to images with low resolution and poor contrast, but they are simple enough to allow a fast real-time implementation. They can be seen as a normalization step that improves the image properties which are essential for pattern matching.</div>
</front><inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>1017-2653</s0>
</fA01><fA05><s2>4303</s2>
</fA05><fA08 i1="01" i2="1" l="ENG"><s1>Fast real-time recognition and quality inspection of printed characters via point-correlation</s1>
</fA08><fA09 i1="01" i2="1" l="ENG"><s1>Real-time imaging V : San Jose CA, 24-25 January 2001</s1>
</fA09><fA11 i1="01" i2="1"><s1>PENZ (H.)</s1>
</fA11><fA11 i1="02" i2="1"><s1>BAJLA (I.)</s1>
</fA11><fA11 i1="03" i2="1"><s1>VRABL (A.)</s1>
</fA11><fA11 i1="04" i2="1"><s1>KRATTENTHALER (W.)</s1>
</fA11><fA11 i1="05" i2="1"><s1>MAYER (K.)</s1>
</fA11><fA12 i1="01" i2="1"><s1>KEHTARNAVAZ (Nasser)</s1>
<s9>ed.</s9>
</fA12><fA14 i1="01"><s1>Austrian Research Centers Seibersdorf</s1>
<s2>2444 Seibersdorf</s2>
<s3>AUT</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</fA14><fA18 i1="01" i2="1"><s1>International Society for Optical Engineering</s1>
<s2>Bellingham WA</s2>
<s3>USA</s3>
<s9>patr.</s9>
</fA18><fA20><s1>127-137</s1>
</fA20><fA21><s1>2001</s1>
</fA21><fA23 i1="01"><s0>ENG</s0>
</fA23><fA26 i1="01"><s0>0-8194-3981-9</s0>
</fA26><fA43 i1="01"><s1>INIST</s1>
<s2>21760</s2>
<s5>354000097026230150</s5>
</fA43><fA44><s0>0000</s0>
<s1>© 2002 INIST-CNRS. All rights reserved.</s1>
</fA44><fA45><s0>4 ref.</s0>
</fA45><fA47 i1="01" i2="1"><s0>02-0062190</s0>
</fA47><fA60><s1>P</s1>
<s2>C</s2>
</fA60><fA64 i1="01" i2="1"><s0>SPIE proceedings series</s0>
</fA64><fA66 i1="01"><s0>USA</s0>
</fA66><fC01 i1="01" l="ENG"><s0>Some technical applications need a fast and reliable OCR (optical character recognition) for critical circumstances like low resolution and poor contrast. A concrete example is the real-time quality inspection system of Austrian banknotes. One requirement to the system is that it has to read two serial numbers on each banknote and to check if they are identical. To solve the problem we have developed a novel method based on an idea similar to pattern matching. However, instead of comparing entire images we use reduced sets of pixels, one for each different numeral (character). The detection (point correlation) is performed by matching these pixel sets with the corresponding pixels in the image being analyzed. We present an algorithm based on two cost functions that computes in a reasonable time the reduced pixel (point) sets from a given set of image templates. The efficiency of our OCR has been increased considerably by introducing an appropriate set of image preprocessing operations. These are tailored especially to images with low resolution and poor contrast, but they are simple enough to allow a fast real-time implementation. They can be seen as a normalization step that improves the image properties which are essential for pattern matching.</s0>
</fC01><fC02 i1="01" i2="X"><s0>001D04A05C</s0>
</fC02><fC03 i1="01" i2="X" l="FRE"><s0>Traitement image</s0>
<s5>01</s5>
</fC03><fC03 i1="01" i2="X" l="ENG"><s0>Image processing</s0>
<s5>01</s5>
</fC03><fC03 i1="01" i2="X" l="SPA"><s0>Procesamiento imagen</s0>
<s5>01</s5>
</fC03><fC03 i1="02" i2="X" l="FRE"><s0>Traitement temps réel</s0>
<s5>02</s5>
</fC03><fC03 i1="02" i2="X" l="ENG"><s0>Real time processing</s0>
<s5>02</s5>
</fC03><fC03 i1="02" i2="X" l="SPA"><s0>Tratamiento tiempo real</s0>
<s5>02</s5>
</fC03><fC03 i1="03" i2="X" l="FRE"><s0>Caractère imprimé</s0>
<s5>03</s5>
</fC03><fC03 i1="03" i2="X" l="ENG"><s0>Printed character</s0>
<s5>03</s5>
</fC03><fC03 i1="03" i2="X" l="SPA"><s0>Carácter impreso</s0>
<s5>03</s5>
</fC03><fC03 i1="04" i2="X" l="FRE"><s0>Reconnaissance caractère</s0>
<s5>04</s5>
</fC03><fC03 i1="04" i2="X" l="ENG"><s0>Character recognition</s0>
<s5>04</s5>
</fC03><fC03 i1="04" i2="X" l="SPA"><s0>Reconocimiento carácter</s0>
<s5>04</s5>
</fC03><fC03 i1="05" i2="X" l="FRE"><s0>Inspection</s0>
<s5>05</s5>
</fC03><fC03 i1="05" i2="X" l="ENG"><s0>Inspection</s0>
<s5>05</s5>
</fC03><fC03 i1="05" i2="X" l="SPA"><s0>Inspección</s0>
<s5>05</s5>
</fC03><fC03 i1="06" i2="X" l="FRE"><s0>Qualité image</s0>
<s5>06</s5>
</fC03><fC03 i1="06" i2="X" l="ENG"><s0>Image quality</s0>
<s5>06</s5>
</fC03><fC03 i1="06" i2="X" l="SPA"><s0>Calidad imagen</s0>
<s5>06</s5>
</fC03><fC03 i1="07" i2="X" l="FRE"><s0>Concordance forme</s0>
<s5>07</s5>
</fC03><fC03 i1="07" i2="X" l="ENG"><s0>Pattern matching</s0>
<s5>07</s5>
</fC03><fC03 i1="08" i2="X" l="FRE"><s0>Corrélation</s0>
<s5>08</s5>
</fC03><fC03 i1="08" i2="X" l="ENG"><s0>Correlation</s0>
<s5>08</s5>
</fC03><fC03 i1="08" i2="X" l="SPA"><s0>Correlación</s0>
<s5>08</s5>
</fC03><fC03 i1="09" i2="X" l="FRE"><s0>Algorithme</s0>
<s5>09</s5>
</fC03><fC03 i1="09" i2="X" l="ENG"><s0>Algorithm</s0>
<s5>09</s5>
</fC03><fC03 i1="09" i2="X" l="SPA"><s0>Algoritmo</s0>
<s5>09</s5>
</fC03><fN21><s1>028</s1>
</fN21><pR><fA30 i1="01" i2="1" l="ENG"><s1>Real-time imaging. Conference</s1>
<s2>5</s2>
<s3>San Jose CA USA</s3>
<s4>2001-01-24</s4>
</fA30><server><NO>PASCAL 02-0062190 INIST</NO>
<ET>Fast real-time recognition and quality inspection of printed characters via point-correlation</ET>
<AU>PENZ (H.); BAJLA (I.); VRABL (A.); KRATTENTHALER (W.); MAYER (K.); KEHTARNAVAZ (Nasser)</AU>
<AF>Austrian Research Centers Seibersdorf/2444 Seibersdorf/Autriche (1 aut., 2 aut., 3 aut., 4 aut., 5 aut.)</AF>
<DT>Publication en série; Congrès; Niveau analytique</DT>
<SO>SPIE proceedings series; ISSN 1017-2653; Etats-Unis; Da. 2001; Vol. 4303; Pp. 127-137; Bibl. 4 ref.</SO>
<LA>Anglais</LA>
<EA>Some technical applications need a fast and reliable OCR (optical character recognition) for critical circumstances like low resolution and poor contrast. A concrete example is the real-time quality inspection system of Austrian banknotes. One requirement to the system is that it has to read two serial numbers on each banknote and to check if they are identical. To solve the problem we have developed a novel method based on an idea similar to pattern matching. However, instead of comparing entire images we use reduced sets of pixels, one for each different numeral (character). The detection (point correlation) is performed by matching these pixel sets with the corresponding pixels in the image being analyzed. We present an algorithm based on two cost functions that computes in a reasonable time the reduced pixel (point) sets from a given set of image templates. The efficiency of our OCR has been increased considerably by introducing an appropriate set of image preprocessing operations. These are tailored especially to images with low resolution and poor contrast, but they are simple enough to allow a fast real-time implementation. They can be seen as a normalization step that improves the image properties which are essential for pattern matching.</EA>
<CC>001D04A05C</CC>
<FD>Traitement image; Traitement temps réel; Caractère imprimé; Reconnaissance caractère; Inspection; Qualité image; Concordance forme; Corrélation; Algorithme</FD>
<ED>Image processing; Real time processing; Printed character; Character recognition; Inspection; Image quality; Pattern matching; Correlation; Algorithm</ED>
<SD>Procesamiento imagen; Tratamiento tiempo real; Carácter impreso; Reconocimiento carácter; Inspección; Calidad imagen; Correlación; Algoritmo</SD>
<LO>INIST-21760.354000097026230150</LO>
<ID>02-0062190</ID>
</server>
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 000690 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Corpus/biblio.hfd -nk 000690 | 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:02-0062190
|texte= Fast real-time recognition and quality inspection of printed characters via point-correlation
}}
| This area was generated with Dilib version V0.6.32.
Data generation: Sat Nov 11 16:53:45 2017. Site generation: Mon Mar 11 23:15:16 2024 |  |
