Development of a written music recognition system using Java and open source technologies
Identifieur interne :
000384 ( PascalFrancis/Corpus );
précédent :
000383;
suivant :
000385
Development of a written music recognition system using Java and open source technologies
Auteurs : Gernot Loibner ;
Andreas Schwarzl ;
Matthias Kovac ;
Dietmar Paulus ;
Wolfgang PolzleitnerSource :
-
Proceedings of SPIE, the International Society for Optical Engineering [ 0277-786X ] ; 2005.
RBID : Pascal:06-0297695
Descripteurs français
- Pascal (Inist)
- Robotique,
Système ouvert,
Langage JAVA,
Logiciel libre,
Développement logiciel,
Texte,
Utilisation information,
Reconnaissance forme,
Reconnaissance caractère,
Reconnaissance optique caractère,
Génie logiciel,
Vision ordinateur,
Traitement image,
Musique,
Système temporisé,
Détection adaptative,
Détection seuil,
Méthode adaptative,
..
English descriptors
- KwdEn :
- Adaptive detection,
Adaptive method,
Character recognition,
Computer vision,
Image processing,
Information use,
JAVA language,
Music,
Open source software,
Open systems,
Optical character recognition,
Pattern recognition,
Robotics,
Software development,
Software engineering,
Text,
Threshold detection,
Timed system.
Abstract
We report on the development of a software system to recognize and interpret printed music. The overall goal is to scan printed music sheets, analyze and recognize the notes, timing, and written text, and derive the all necessary information to use the computers MIDI sound system to play the music. This function is primarily useful for musicians who want to digitize printed music for editing purposes. There exist a number of commercial systems that offer such a functionality. However, on testing these systems, we were astonished on how weak they behave in their pattern recognition parts. Although we submitted very clear and rather flawless scanning input, none of these systems was able to e.g. recognize all notes, staff lines, and systems. They all require a high degree of interaction, post-processing, and editing to get a decent digital version of the hard copy material. In this paper we focus on the pattern recognition area. In a first approach we tested more or less standard methods of adaptive thresholding, blob detection, line detection, and comer detection to find the notes, staff lines, and candidate objects subject to OCR. Many of the objects on this type of material can be learned in a training phase. None of the commercial systems we saw offers the option to train special characters or unusual signatures. A second goal in this project is to use a modern software engineering platform. We were interested in how well Java and open source technologies are suitable for pattern recognition and machine vision. The scanning of music served as a case-study.
Notice en format standard (ISO 2709)
Pour connaître la documentation sur le format Inist Standard.
pA |
A01 | 01 | 1 | | @0 0277-786X |
---|
A05 | | | | @2 6006 |
---|
A08 | 01 | 1 | ENG | @1 Development of a written music recognition system using Java and open source technologies |
---|
A09 | 01 | 1 | ENG | @1 Intelligent robots and computer vision XXIII : algorithms, techniques, and active vision : 23-25 October, 2005,Boston, Massachusetts, USA |
---|
A11 | 01 | 1 | | @1 LOIBNER (Gernot) |
---|
A11 | 02 | 1 | | @1 SCHWARZL (Andreas) |
---|
A11 | 03 | 1 | | @1 KOVAC (Matthias) |
---|
A11 | 04 | 1 | | @1 PAULUS (Dietmar) |
---|
A11 | 05 | 1 | | @1 POLZLEITNER (Wolfgang) |
---|
A12 | 01 | 1 | | @1 CASASENT (David Paul) @9 ed. |
---|
A12 | 02 | 1 | | @1 HALL (Ernest L.) @9 ed. |
---|
A14 | 01 | | | @1 Kaindorf College of Computer Information Systems @3 AUT @Z 1 aut. @Z 2 aut. @Z 3 aut. @Z 4 aut. |
---|
A14 | 02 | | | @1 Sensotech GmbH @3 AUT @Z 5 aut. |
---|
A18 | 01 | 1 | | @1 Society of photo-optical instrumentation engineers @3 USA @9 org-cong. |
---|
A20 | | | | @2 60060W.1-60060W.12 |
---|
A21 | | | | @1 2005 |
---|
A23 | 01 | | | @0 ENG |
---|
A26 | 01 | | | @0 0-8194-6030-3 |
---|
A43 | 01 | | | @1 INIST @2 21760 @5 354000153475790310 |
---|
A44 | | | | @0 0000 @1 © 2006 INIST-CNRS. All rights reserved. |
---|
A45 | | | | @0 9 ref. |
---|
A47 | 01 | 1 | | @0 06-0297695 |
---|
A60 | | | | @1 P @2 C |
---|
A61 | | | | @0 A |
---|
A64 | 01 | 1 | | @0 Proceedings of SPIE, the International Society for Optical Engineering |
---|
A66 | 01 | | | @0 USA |
---|
C01 | 01 | | ENG | @0 We report on the development of a software system to recognize and interpret printed music. The overall goal is to scan printed music sheets, analyze and recognize the notes, timing, and written text, and derive the all necessary information to use the computers MIDI sound system to play the music. This function is primarily useful for musicians who want to digitize printed music for editing purposes. There exist a number of commercial systems that offer such a functionality. However, on testing these systems, we were astonished on how weak they behave in their pattern recognition parts. Although we submitted very clear and rather flawless scanning input, none of these systems was able to e.g. recognize all notes, staff lines, and systems. They all require a high degree of interaction, post-processing, and editing to get a decent digital version of the hard copy material. In this paper we focus on the pattern recognition area. In a first approach we tested more or less standard methods of adaptive thresholding, blob detection, line detection, and comer detection to find the notes, staff lines, and candidate objects subject to OCR. Many of the objects on this type of material can be learned in a training phase. None of the commercial systems we saw offers the option to train special characters or unusual signatures. A second goal in this project is to use a modern software engineering platform. We were interested in how well Java and open source technologies are suitable for pattern recognition and machine vision. The scanning of music served as a case-study. |
---|
C02 | 01 | X | | @0 001D02C03 |
---|
C03 | 01 | X | FRE | @0 Robotique @5 01 |
---|
C03 | 01 | X | ENG | @0 Robotics @5 01 |
---|
C03 | 01 | X | SPA | @0 Robótica @5 01 |
---|
C03 | 02 | X | FRE | @0 Système ouvert @5 06 |
---|
C03 | 02 | X | ENG | @0 Open systems @5 06 |
---|
C03 | 02 | X | SPA | @0 Sistema abierto @5 06 |
---|
C03 | 03 | X | FRE | @0 Langage JAVA @5 07 |
---|
C03 | 03 | X | ENG | @0 JAVA language @5 07 |
---|
C03 | 03 | X | SPA | @0 Lenguaje JAVA @5 07 |
---|
C03 | 04 | X | FRE | @0 Logiciel libre @5 08 |
---|
C03 | 04 | X | ENG | @0 Open source software @5 08 |
---|
C03 | 04 | X | SPA | @0 Software libre @5 08 |
---|
C03 | 05 | X | FRE | @0 Développement logiciel @5 09 |
---|
C03 | 05 | X | ENG | @0 Software development @5 09 |
---|
C03 | 05 | X | SPA | @0 Desarrollo logicial @5 09 |
---|
C03 | 06 | X | FRE | @0 Texte @5 10 |
---|
C03 | 06 | X | ENG | @0 Text @5 10 |
---|
C03 | 06 | X | SPA | @0 Texto @5 10 |
---|
C03 | 07 | X | FRE | @0 Utilisation information @5 11 |
---|
C03 | 07 | X | ENG | @0 Information use @5 11 |
---|
C03 | 07 | X | SPA | @0 Uso información @5 11 |
---|
C03 | 08 | X | FRE | @0 Reconnaissance forme @5 12 |
---|
C03 | 08 | X | ENG | @0 Pattern recognition @5 12 |
---|
C03 | 08 | X | SPA | @0 Reconocimiento patrón @5 12 |
---|
C03 | 09 | X | FRE | @0 Reconnaissance caractère @5 13 |
---|
C03 | 09 | X | ENG | @0 Character recognition @5 13 |
---|
C03 | 09 | X | SPA | @0 Reconocimiento carácter @5 13 |
---|
C03 | 10 | X | FRE | @0 Reconnaissance optique caractère @5 14 |
---|
C03 | 10 | X | ENG | @0 Optical character recognition @5 14 |
---|
C03 | 10 | X | SPA | @0 Reconocimento óptico de caracteres @5 14 |
---|
C03 | 11 | X | FRE | @0 Génie logiciel @5 15 |
---|
C03 | 11 | X | ENG | @0 Software engineering @5 15 |
---|
C03 | 11 | X | SPA | @0 Ingeniería informática @5 15 |
---|
C03 | 12 | X | FRE | @0 Vision ordinateur @5 16 |
---|
C03 | 12 | X | ENG | @0 Computer vision @5 16 |
---|
C03 | 12 | X | SPA | @0 Visión ordenador @5 16 |
---|
C03 | 13 | X | FRE | @0 Traitement image @5 17 |
---|
C03 | 13 | X | ENG | @0 Image processing @5 17 |
---|
C03 | 13 | X | SPA | @0 Procesamiento imagen @5 17 |
---|
C03 | 14 | X | FRE | @0 Musique @5 18 |
---|
C03 | 14 | X | ENG | @0 Music @5 18 |
---|
C03 | 14 | X | SPA | @0 Música @5 18 |
---|
C03 | 15 | X | FRE | @0 Système temporisé @5 19 |
---|
C03 | 15 | X | ENG | @0 Timed system @5 19 |
---|
C03 | 15 | X | SPA | @0 Sistema temporizado @5 19 |
---|
C03 | 16 | X | FRE | @0 Détection adaptative @5 20 |
---|
C03 | 16 | X | ENG | @0 Adaptive detection @5 20 |
---|
C03 | 16 | X | SPA | @0 Detección adaptativa @5 20 |
---|
C03 | 17 | X | FRE | @0 Détection seuil @5 21 |
---|
C03 | 17 | X | ENG | @0 Threshold detection @5 21 |
---|
C03 | 17 | X | SPA | @0 Detección umbral @5 21 |
---|
C03 | 18 | X | FRE | @0 Méthode adaptative @5 23 |
---|
C03 | 18 | X | ENG | @0 Adaptive method @5 23 |
---|
C03 | 18 | X | SPA | @0 Método adaptativo @5 23 |
---|
C03 | 19 | X | FRE | @0 . @4 INC @5 82 |
---|
N21 | | | | @1 191 |
---|
N44 | 01 | | | @1 OTO |
---|
N82 | | | | @1 OTO |
---|
|
pR |
A30 | 01 | 1 | ENG | @1 Intellignet robots and computer vision. Conference @2 23 @3 Boston MA USA @4 2005 |
---|
|
Format Inist (serveur)
NO : | PASCAL 06-0297695 INIST |
ET : | Development of a written music recognition system using Java and open source technologies |
AU : | LOIBNER (Gernot); SCHWARZL (Andreas); KOVAC (Matthias); PAULUS (Dietmar); POLZLEITNER (Wolfgang); CASASENT (David Paul); HALL (Ernest L.) |
AF : | Kaindorf College of Computer Information Systems/Autriche (1 aut., 2 aut., 3 aut., 4 aut.); Sensotech GmbH/Autriche (5 aut.) |
DT : | Publication en série; Congrès; Niveau analytique |
SO : | Proceedings of SPIE, the International Society for Optical Engineering; ISSN 0277-786X; Etats-Unis; Da. 2005; Vol. 6006; 60060W.1-60060W.12; Bibl. 9 ref. |
LA : | Anglais |
EA : | We report on the development of a software system to recognize and interpret printed music. The overall goal is to scan printed music sheets, analyze and recognize the notes, timing, and written text, and derive the all necessary information to use the computers MIDI sound system to play the music. This function is primarily useful for musicians who want to digitize printed music for editing purposes. There exist a number of commercial systems that offer such a functionality. However, on testing these systems, we were astonished on how weak they behave in their pattern recognition parts. Although we submitted very clear and rather flawless scanning input, none of these systems was able to e.g. recognize all notes, staff lines, and systems. They all require a high degree of interaction, post-processing, and editing to get a decent digital version of the hard copy material. In this paper we focus on the pattern recognition area. In a first approach we tested more or less standard methods of adaptive thresholding, blob detection, line detection, and comer detection to find the notes, staff lines, and candidate objects subject to OCR. Many of the objects on this type of material can be learned in a training phase. None of the commercial systems we saw offers the option to train special characters or unusual signatures. A second goal in this project is to use a modern software engineering platform. We were interested in how well Java and open source technologies are suitable for pattern recognition and machine vision. The scanning of music served as a case-study. |
CC : | 001D02C03 |
FD : | Robotique; Système ouvert; Langage JAVA; Logiciel libre; Développement logiciel; Texte; Utilisation information; Reconnaissance forme; Reconnaissance caractère; Reconnaissance optique caractère; Génie logiciel; Vision ordinateur; Traitement image; Musique; Système temporisé; Détection adaptative; Détection seuil; Méthode adaptative; . |
ED : | Robotics; Open systems; JAVA language; Open source software; Software development; Text; Information use; Pattern recognition; Character recognition; Optical character recognition; Software engineering; Computer vision; Image processing; Music; Timed system; Adaptive detection; Threshold detection; Adaptive method |
SD : | Robótica; Sistema abierto; Lenguaje JAVA; Software libre; Desarrollo logicial; Texto; Uso información; Reconocimiento patrón; Reconocimiento carácter; Reconocimento óptico de caracteres; Ingeniería informática; Visión ordenador; Procesamiento imagen; Música; Sistema temporizado; Detección adaptativa; Detección umbral; Método adaptativo |
LO : | INIST-21760.354000153475790310 |
ID : | 06-0297695 |
Links to Exploration step
Pascal:06-0297695
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Development of a written music recognition system using Java and open source technologies</title>
<author><name sortKey="Loibner, Gernot" sort="Loibner, Gernot" uniqKey="Loibner G" first="Gernot" last="Loibner">Gernot Loibner</name>
<affiliation><inist:fA14 i1="01"><s1>Kaindorf College of Computer Information Systems</s1>
<s3>AUT</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Schwarzl, Andreas" sort="Schwarzl, Andreas" uniqKey="Schwarzl A" first="Andreas" last="Schwarzl">Andreas Schwarzl</name>
<affiliation><inist:fA14 i1="01"><s1>Kaindorf College of Computer Information Systems</s1>
<s3>AUT</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Kovac, Matthias" sort="Kovac, Matthias" uniqKey="Kovac M" first="Matthias" last="Kovac">Matthias Kovac</name>
<affiliation><inist:fA14 i1="01"><s1>Kaindorf College of Computer Information Systems</s1>
<s3>AUT</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Paulus, Dietmar" sort="Paulus, Dietmar" uniqKey="Paulus D" first="Dietmar" last="Paulus">Dietmar Paulus</name>
<affiliation><inist:fA14 i1="01"><s1>Kaindorf College of Computer Information Systems</s1>
<s3>AUT</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Polzleitner, Wolfgang" sort="Polzleitner, Wolfgang" uniqKey="Polzleitner W" first="Wolfgang" last="Polzleitner">Wolfgang Polzleitner</name>
<affiliation><inist:fA14 i1="02"><s1>Sensotech GmbH</s1>
<s3>AUT</s3>
<sZ>5 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">06-0297695</idno>
<date when="2005">2005</date>
<idno type="stanalyst">PASCAL 06-0297695 INIST</idno>
<idno type="RBID">Pascal:06-0297695</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000384</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Development of a written music recognition system using Java and open source technologies</title>
<author><name sortKey="Loibner, Gernot" sort="Loibner, Gernot" uniqKey="Loibner G" first="Gernot" last="Loibner">Gernot Loibner</name>
<affiliation><inist:fA14 i1="01"><s1>Kaindorf College of Computer Information Systems</s1>
<s3>AUT</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Schwarzl, Andreas" sort="Schwarzl, Andreas" uniqKey="Schwarzl A" first="Andreas" last="Schwarzl">Andreas Schwarzl</name>
<affiliation><inist:fA14 i1="01"><s1>Kaindorf College of Computer Information Systems</s1>
<s3>AUT</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Kovac, Matthias" sort="Kovac, Matthias" uniqKey="Kovac M" first="Matthias" last="Kovac">Matthias Kovac</name>
<affiliation><inist:fA14 i1="01"><s1>Kaindorf College of Computer Information Systems</s1>
<s3>AUT</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Paulus, Dietmar" sort="Paulus, Dietmar" uniqKey="Paulus D" first="Dietmar" last="Paulus">Dietmar Paulus</name>
<affiliation><inist:fA14 i1="01"><s1>Kaindorf College of Computer Information Systems</s1>
<s3>AUT</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Polzleitner, Wolfgang" sort="Polzleitner, Wolfgang" uniqKey="Polzleitner W" first="Wolfgang" last="Polzleitner">Wolfgang Polzleitner</name>
<affiliation><inist:fA14 i1="02"><s1>Sensotech GmbH</s1>
<s3>AUT</s3>
<sZ>5 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Proceedings of SPIE, the International Society for Optical Engineering</title>
<idno type="ISSN">0277-786X</idno>
<imprint><date when="2005">2005</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">Proceedings of SPIE, the International Society for Optical Engineering</title>
<idno type="ISSN">0277-786X</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Adaptive detection</term>
<term>Adaptive method</term>
<term>Character recognition</term>
<term>Computer vision</term>
<term>Image processing</term>
<term>Information use</term>
<term>JAVA language</term>
<term>Music</term>
<term>Open source software</term>
<term>Open systems</term>
<term>Optical character recognition</term>
<term>Pattern recognition</term>
<term>Robotics</term>
<term>Software development</term>
<term>Software engineering</term>
<term>Text</term>
<term>Threshold detection</term>
<term>Timed system</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Robotique</term>
<term>Système ouvert</term>
<term>Langage JAVA</term>
<term>Logiciel libre</term>
<term>Développement logiciel</term>
<term>Texte</term>
<term>Utilisation information</term>
<term>Reconnaissance forme</term>
<term>Reconnaissance caractère</term>
<term>Reconnaissance optique caractère</term>
<term>Génie logiciel</term>
<term>Vision ordinateur</term>
<term>Traitement image</term>
<term>Musique</term>
<term>Système temporisé</term>
<term>Détection adaptative</term>
<term>Détection seuil</term>
<term>Méthode adaptative</term>
<term>.</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">We report on the development of a software system to recognize and interpret printed music. The overall goal is to scan printed music sheets, analyze and recognize the notes, timing, and written text, and derive the all necessary information to use the computers MIDI sound system to play the music. This function is primarily useful for musicians who want to digitize printed music for editing purposes. There exist a number of commercial systems that offer such a functionality. However, on testing these systems, we were astonished on how weak they behave in their pattern recognition parts. Although we submitted very clear and rather flawless scanning input, none of these systems was able to e.g. recognize all notes, staff lines, and systems. They all require a high degree of interaction, post-processing, and editing to get a decent digital version of the hard copy material. In this paper we focus on the pattern recognition area. In a first approach we tested more or less standard methods of adaptive thresholding, blob detection, line detection, and comer detection to find the notes, staff lines, and candidate objects subject to OCR. Many of the objects on this type of material can be learned in a training phase. None of the commercial systems we saw offers the option to train special characters or unusual signatures. A second goal in this project is to use a modern software engineering platform. We were interested in how well Java and open source technologies are suitable for pattern recognition and machine vision. The scanning of music served as a case-study.</div>
</front>
</TEI>
<inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>0277-786X</s0>
</fA01>
<fA05><s2>6006</s2>
</fA05>
<fA08 i1="01" i2="1" l="ENG"><s1>Development of a written music recognition system using Java and open source technologies</s1>
</fA08>
<fA09 i1="01" i2="1" l="ENG"><s1>Intelligent robots and computer vision XXIII : algorithms, techniques, and active vision : 23-25 October, 2005,Boston, Massachusetts, USA</s1>
</fA09>
<fA11 i1="01" i2="1"><s1>LOIBNER (Gernot)</s1>
</fA11>
<fA11 i1="02" i2="1"><s1>SCHWARZL (Andreas)</s1>
</fA11>
<fA11 i1="03" i2="1"><s1>KOVAC (Matthias)</s1>
</fA11>
<fA11 i1="04" i2="1"><s1>PAULUS (Dietmar)</s1>
</fA11>
<fA11 i1="05" i2="1"><s1>POLZLEITNER (Wolfgang)</s1>
</fA11>
<fA12 i1="01" i2="1"><s1>CASASENT (David Paul)</s1>
<s9>ed.</s9>
</fA12>
<fA12 i1="02" i2="1"><s1>HALL (Ernest L.)</s1>
<s9>ed.</s9>
</fA12>
<fA14 i1="01"><s1>Kaindorf College of Computer Information Systems</s1>
<s3>AUT</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</fA14>
<fA14 i1="02"><s1>Sensotech GmbH</s1>
<s3>AUT</s3>
<sZ>5 aut.</sZ>
</fA14>
<fA18 i1="01" i2="1"><s1>Society of photo-optical instrumentation engineers</s1>
<s3>USA</s3>
<s9>org-cong.</s9>
</fA18>
<fA20><s2>60060W.1-60060W.12</s2>
</fA20>
<fA21><s1>2005</s1>
</fA21>
<fA23 i1="01"><s0>ENG</s0>
</fA23>
<fA26 i1="01"><s0>0-8194-6030-3</s0>
</fA26>
<fA43 i1="01"><s1>INIST</s1>
<s2>21760</s2>
<s5>354000153475790310</s5>
</fA43>
<fA44><s0>0000</s0>
<s1>© 2006 INIST-CNRS. All rights reserved.</s1>
</fA44>
<fA45><s0>9 ref.</s0>
</fA45>
<fA47 i1="01" i2="1"><s0>06-0297695</s0>
</fA47>
<fA60><s1>P</s1>
<s2>C</s2>
</fA60>
<fA64 i1="01" i2="1"><s0>Proceedings of SPIE, the International Society for Optical Engineering</s0>
</fA64>
<fA66 i1="01"><s0>USA</s0>
</fA66>
<fC01 i1="01" l="ENG"><s0>We report on the development of a software system to recognize and interpret printed music. The overall goal is to scan printed music sheets, analyze and recognize the notes, timing, and written text, and derive the all necessary information to use the computers MIDI sound system to play the music. This function is primarily useful for musicians who want to digitize printed music for editing purposes. There exist a number of commercial systems that offer such a functionality. However, on testing these systems, we were astonished on how weak they behave in their pattern recognition parts. Although we submitted very clear and rather flawless scanning input, none of these systems was able to e.g. recognize all notes, staff lines, and systems. They all require a high degree of interaction, post-processing, and editing to get a decent digital version of the hard copy material. In this paper we focus on the pattern recognition area. In a first approach we tested more or less standard methods of adaptive thresholding, blob detection, line detection, and comer detection to find the notes, staff lines, and candidate objects subject to OCR. Many of the objects on this type of material can be learned in a training phase. None of the commercial systems we saw offers the option to train special characters or unusual signatures. A second goal in this project is to use a modern software engineering platform. We were interested in how well Java and open source technologies are suitable for pattern recognition and machine vision. The scanning of music served as a case-study.</s0>
</fC01>
<fC02 i1="01" i2="X"><s0>001D02C03</s0>
</fC02>
<fC03 i1="01" i2="X" l="FRE"><s0>Robotique</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="X" l="ENG"><s0>Robotics</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="X" l="SPA"><s0>Robótica</s0>
<s5>01</s5>
</fC03>
<fC03 i1="02" i2="X" l="FRE"><s0>Système ouvert</s0>
<s5>06</s5>
</fC03>
<fC03 i1="02" i2="X" l="ENG"><s0>Open systems</s0>
<s5>06</s5>
</fC03>
<fC03 i1="02" i2="X" l="SPA"><s0>Sistema abierto</s0>
<s5>06</s5>
</fC03>
<fC03 i1="03" i2="X" l="FRE"><s0>Langage JAVA</s0>
<s5>07</s5>
</fC03>
<fC03 i1="03" i2="X" l="ENG"><s0>JAVA language</s0>
<s5>07</s5>
</fC03>
<fC03 i1="03" i2="X" l="SPA"><s0>Lenguaje JAVA</s0>
<s5>07</s5>
</fC03>
<fC03 i1="04" i2="X" l="FRE"><s0>Logiciel libre</s0>
<s5>08</s5>
</fC03>
<fC03 i1="04" i2="X" l="ENG"><s0>Open source software</s0>
<s5>08</s5>
</fC03>
<fC03 i1="04" i2="X" l="SPA"><s0>Software libre</s0>
<s5>08</s5>
</fC03>
<fC03 i1="05" i2="X" l="FRE"><s0>Développement logiciel</s0>
<s5>09</s5>
</fC03>
<fC03 i1="05" i2="X" l="ENG"><s0>Software development</s0>
<s5>09</s5>
</fC03>
<fC03 i1="05" i2="X" l="SPA"><s0>Desarrollo logicial</s0>
<s5>09</s5>
</fC03>
<fC03 i1="06" i2="X" l="FRE"><s0>Texte</s0>
<s5>10</s5>
</fC03>
<fC03 i1="06" i2="X" l="ENG"><s0>Text</s0>
<s5>10</s5>
</fC03>
<fC03 i1="06" i2="X" l="SPA"><s0>Texto</s0>
<s5>10</s5>
</fC03>
<fC03 i1="07" i2="X" l="FRE"><s0>Utilisation information</s0>
<s5>11</s5>
</fC03>
<fC03 i1="07" i2="X" l="ENG"><s0>Information use</s0>
<s5>11</s5>
</fC03>
<fC03 i1="07" i2="X" l="SPA"><s0>Uso información</s0>
<s5>11</s5>
</fC03>
<fC03 i1="08" i2="X" l="FRE"><s0>Reconnaissance forme</s0>
<s5>12</s5>
</fC03>
<fC03 i1="08" i2="X" l="ENG"><s0>Pattern recognition</s0>
<s5>12</s5>
</fC03>
<fC03 i1="08" i2="X" l="SPA"><s0>Reconocimiento patrón</s0>
<s5>12</s5>
</fC03>
<fC03 i1="09" i2="X" l="FRE"><s0>Reconnaissance caractère</s0>
<s5>13</s5>
</fC03>
<fC03 i1="09" i2="X" l="ENG"><s0>Character recognition</s0>
<s5>13</s5>
</fC03>
<fC03 i1="09" i2="X" l="SPA"><s0>Reconocimiento carácter</s0>
<s5>13</s5>
</fC03>
<fC03 i1="10" i2="X" l="FRE"><s0>Reconnaissance optique caractère</s0>
<s5>14</s5>
</fC03>
<fC03 i1="10" i2="X" l="ENG"><s0>Optical character recognition</s0>
<s5>14</s5>
</fC03>
<fC03 i1="10" i2="X" l="SPA"><s0>Reconocimento óptico de caracteres</s0>
<s5>14</s5>
</fC03>
<fC03 i1="11" i2="X" l="FRE"><s0>Génie logiciel</s0>
<s5>15</s5>
</fC03>
<fC03 i1="11" i2="X" l="ENG"><s0>Software engineering</s0>
<s5>15</s5>
</fC03>
<fC03 i1="11" i2="X" l="SPA"><s0>Ingeniería informática</s0>
<s5>15</s5>
</fC03>
<fC03 i1="12" i2="X" l="FRE"><s0>Vision ordinateur</s0>
<s5>16</s5>
</fC03>
<fC03 i1="12" i2="X" l="ENG"><s0>Computer vision</s0>
<s5>16</s5>
</fC03>
<fC03 i1="12" i2="X" l="SPA"><s0>Visión ordenador</s0>
<s5>16</s5>
</fC03>
<fC03 i1="13" i2="X" l="FRE"><s0>Traitement image</s0>
<s5>17</s5>
</fC03>
<fC03 i1="13" i2="X" l="ENG"><s0>Image processing</s0>
<s5>17</s5>
</fC03>
<fC03 i1="13" i2="X" l="SPA"><s0>Procesamiento imagen</s0>
<s5>17</s5>
</fC03>
<fC03 i1="14" i2="X" l="FRE"><s0>Musique</s0>
<s5>18</s5>
</fC03>
<fC03 i1="14" i2="X" l="ENG"><s0>Music</s0>
<s5>18</s5>
</fC03>
<fC03 i1="14" i2="X" l="SPA"><s0>Música</s0>
<s5>18</s5>
</fC03>
<fC03 i1="15" i2="X" l="FRE"><s0>Système temporisé</s0>
<s5>19</s5>
</fC03>
<fC03 i1="15" i2="X" l="ENG"><s0>Timed system</s0>
<s5>19</s5>
</fC03>
<fC03 i1="15" i2="X" l="SPA"><s0>Sistema temporizado</s0>
<s5>19</s5>
</fC03>
<fC03 i1="16" i2="X" l="FRE"><s0>Détection adaptative</s0>
<s5>20</s5>
</fC03>
<fC03 i1="16" i2="X" l="ENG"><s0>Adaptive detection</s0>
<s5>20</s5>
</fC03>
<fC03 i1="16" i2="X" l="SPA"><s0>Detección adaptativa</s0>
<s5>20</s5>
</fC03>
<fC03 i1="17" i2="X" l="FRE"><s0>Détection seuil</s0>
<s5>21</s5>
</fC03>
<fC03 i1="17" i2="X" l="ENG"><s0>Threshold detection</s0>
<s5>21</s5>
</fC03>
<fC03 i1="17" i2="X" l="SPA"><s0>Detección umbral</s0>
<s5>21</s5>
</fC03>
<fC03 i1="18" i2="X" l="FRE"><s0>Méthode adaptative</s0>
<s5>23</s5>
</fC03>
<fC03 i1="18" i2="X" l="ENG"><s0>Adaptive method</s0>
<s5>23</s5>
</fC03>
<fC03 i1="18" i2="X" l="SPA"><s0>Método adaptativo</s0>
<s5>23</s5>
</fC03>
<fC03 i1="19" i2="X" l="FRE"><s0>.</s0>
<s4>INC</s4>
<s5>82</s5>
</fC03>
<fN21><s1>191</s1>
</fN21>
<fN44 i1="01"><s1>OTO</s1>
</fN44>
<fN82><s1>OTO</s1>
</fN82>
</pA>
<pR><fA30 i1="01" i2="1" l="ENG"><s1>Intellignet robots and computer vision. Conference</s1>
<s2>23</s2>
<s3>Boston MA USA</s3>
<s4>2005</s4>
</fA30>
</pR>
</standard>
<server><NO>PASCAL 06-0297695 INIST</NO>
<ET>Development of a written music recognition system using Java and open source technologies</ET>
<AU>LOIBNER (Gernot); SCHWARZL (Andreas); KOVAC (Matthias); PAULUS (Dietmar); POLZLEITNER (Wolfgang); CASASENT (David Paul); HALL (Ernest L.)</AU>
<AF>Kaindorf College of Computer Information Systems/Autriche (1 aut., 2 aut., 3 aut., 4 aut.); Sensotech GmbH/Autriche (5 aut.)</AF>
<DT>Publication en série; Congrès; Niveau analytique</DT>
<SO>Proceedings of SPIE, the International Society for Optical Engineering; ISSN 0277-786X; Etats-Unis; Da. 2005; Vol. 6006; 60060W.1-60060W.12; Bibl. 9 ref.</SO>
<LA>Anglais</LA>
<EA>We report on the development of a software system to recognize and interpret printed music. The overall goal is to scan printed music sheets, analyze and recognize the notes, timing, and written text, and derive the all necessary information to use the computers MIDI sound system to play the music. This function is primarily useful for musicians who want to digitize printed music for editing purposes. There exist a number of commercial systems that offer such a functionality. However, on testing these systems, we were astonished on how weak they behave in their pattern recognition parts. Although we submitted very clear and rather flawless scanning input, none of these systems was able to e.g. recognize all notes, staff lines, and systems. They all require a high degree of interaction, post-processing, and editing to get a decent digital version of the hard copy material. In this paper we focus on the pattern recognition area. In a first approach we tested more or less standard methods of adaptive thresholding, blob detection, line detection, and comer detection to find the notes, staff lines, and candidate objects subject to OCR. Many of the objects on this type of material can be learned in a training phase. None of the commercial systems we saw offers the option to train special characters or unusual signatures. A second goal in this project is to use a modern software engineering platform. We were interested in how well Java and open source technologies are suitable for pattern recognition and machine vision. The scanning of music served as a case-study.</EA>
<CC>001D02C03</CC>
<FD>Robotique; Système ouvert; Langage JAVA; Logiciel libre; Développement logiciel; Texte; Utilisation information; Reconnaissance forme; Reconnaissance caractère; Reconnaissance optique caractère; Génie logiciel; Vision ordinateur; Traitement image; Musique; Système temporisé; Détection adaptative; Détection seuil; Méthode adaptative; .</FD>
<ED>Robotics; Open systems; JAVA language; Open source software; Software development; Text; Information use; Pattern recognition; Character recognition; Optical character recognition; Software engineering; Computer vision; Image processing; Music; Timed system; Adaptive detection; Threshold detection; Adaptive method</ED>
<SD>Robótica; Sistema abierto; Lenguaje JAVA; Software libre; Desarrollo logicial; Texto; Uso información; Reconocimiento patrón; Reconocimiento carácter; Reconocimento óptico de caracteres; Ingeniería informática; Visión ordenador; Procesamiento imagen; Música; Sistema temporizado; Detección adaptativa; Detección umbral; Método adaptativo</SD>
<LO>INIST-21760.354000153475790310</LO>
<ID>06-0297695</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 000384 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Corpus/biblio.hfd -nk 000384 | 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:06-0297695
|texte= Development of a written music recognition system using Java and open source technologies
}}
| 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 | |