AUTOMATED RECOGNITION SYSTEM FOR MUSICAL SCORE - THE VISION SYSTEM OF WABOT-2.

Toshiaki Matsushima, Tadanori Harada, Itaru Sonomoto, Katsuhiro Kanamori, Akio Uesugi, Yuji Nimura, Shuji Hashimoto, Sadamu Ohteru

    Research output: Contribution to journalArticle

    8 Citations (Scopus)

    Abstract

    This paper reports on WABOT-2 vision system, which can recognize not only commercially available printed musical scores but also instant lettering scores in real time, using an extraction algorithm based on the musical score structure with special hardware and knowledge-base music comprehension software. Several automated recognition systems for printed music have been reported. However, none of these systems are suitable for use as vision for music playing robots, where real time recognition is required under an extremely poor data environment where a video camera is placed in the robot's head and music sheets are often curved or otherwise deformed on the music stand. In order to directly convey the vision system output to the robot hands, contradictions and inharmonic codes in the pattern discrimination results are checked, using knowledge-base music notation. The resulting music robot vision performance is able to recognize, one sheet of commercially available printed of nursery song music for an electric piano, having up to three parts in 15 seconds, with approximately 100% accuracy.

    Original languageEnglish
    Pages (from-to)25-52
    Number of pages28
    JournalWaseda Daigaku Rikogaku Kenkyusho Hokoku/Bulletin of Science and Engineering Research Laboratory, Waseda University
    Issue number112
    Publication statusPublished - 1985

    Fingerprint

    Robots
    Video cameras
    End effectors
    Computer vision
    Hardware

    ASJC Scopus subject areas

    • Engineering(all)

    Cite this

    AUTOMATED RECOGNITION SYSTEM FOR MUSICAL SCORE - THE VISION SYSTEM OF WABOT-2. / Matsushima, Toshiaki; Harada, Tadanori; Sonomoto, Itaru; Kanamori, Katsuhiro; Uesugi, Akio; Nimura, Yuji; Hashimoto, Shuji; Ohteru, Sadamu.

    In: Waseda Daigaku Rikogaku Kenkyusho Hokoku/Bulletin of Science and Engineering Research Laboratory, Waseda University, No. 112, 1985, p. 25-52.

    Research output: Contribution to journalArticle

    Matsushima, T, Harada, T, Sonomoto, I, Kanamori, K, Uesugi, A, Nimura, Y, Hashimoto, S & Ohteru, S 1985, 'AUTOMATED RECOGNITION SYSTEM FOR MUSICAL SCORE - THE VISION SYSTEM OF WABOT-2.', Waseda Daigaku Rikogaku Kenkyusho Hokoku/Bulletin of Science and Engineering Research Laboratory, Waseda University, no. 112, pp. 25-52.
    Matsushima, Toshiaki ; Harada, Tadanori ; Sonomoto, Itaru ; Kanamori, Katsuhiro ; Uesugi, Akio ; Nimura, Yuji ; Hashimoto, Shuji ; Ohteru, Sadamu. / AUTOMATED RECOGNITION SYSTEM FOR MUSICAL SCORE - THE VISION SYSTEM OF WABOT-2. In: Waseda Daigaku Rikogaku Kenkyusho Hokoku/Bulletin of Science and Engineering Research Laboratory, Waseda University. 1985 ; No. 112. pp. 25-52.
    @article{9b4e2e7ba7384e97af3bce7e66c96f4b,
    title = "AUTOMATED RECOGNITION SYSTEM FOR MUSICAL SCORE - THE VISION SYSTEM OF WABOT-2.",
    abstract = "This paper reports on WABOT-2 vision system, which can recognize not only commercially available printed musical scores but also instant lettering scores in real time, using an extraction algorithm based on the musical score structure with special hardware and knowledge-base music comprehension software. Several automated recognition systems for printed music have been reported. However, none of these systems are suitable for use as vision for music playing robots, where real time recognition is required under an extremely poor data environment where a video camera is placed in the robot's head and music sheets are often curved or otherwise deformed on the music stand. In order to directly convey the vision system output to the robot hands, contradictions and inharmonic codes in the pattern discrimination results are checked, using knowledge-base music notation. The resulting music robot vision performance is able to recognize, one sheet of commercially available printed of nursery song music for an electric piano, having up to three parts in 15 seconds, with approximately 100{\%} accuracy.",
    author = "Toshiaki Matsushima and Tadanori Harada and Itaru Sonomoto and Katsuhiro Kanamori and Akio Uesugi and Yuji Nimura and Shuji Hashimoto and Sadamu Ohteru",
    year = "1985",
    language = "English",
    pages = "25--52",
    journal = "Waseda Daigaku Rikogaku Kenkyusho Hokoku/Bulletin of Science and Engineering Research Laboratory, Waseda University",
    issn = "0372-7181",
    number = "112",

    }

    TY - JOUR

    T1 - AUTOMATED RECOGNITION SYSTEM FOR MUSICAL SCORE - THE VISION SYSTEM OF WABOT-2.

    AU - Matsushima, Toshiaki

    AU - Harada, Tadanori

    AU - Sonomoto, Itaru

    AU - Kanamori, Katsuhiro

    AU - Uesugi, Akio

    AU - Nimura, Yuji

    AU - Hashimoto, Shuji

    AU - Ohteru, Sadamu

    PY - 1985

    Y1 - 1985

    N2 - This paper reports on WABOT-2 vision system, which can recognize not only commercially available printed musical scores but also instant lettering scores in real time, using an extraction algorithm based on the musical score structure with special hardware and knowledge-base music comprehension software. Several automated recognition systems for printed music have been reported. However, none of these systems are suitable for use as vision for music playing robots, where real time recognition is required under an extremely poor data environment where a video camera is placed in the robot's head and music sheets are often curved or otherwise deformed on the music stand. In order to directly convey the vision system output to the robot hands, contradictions and inharmonic codes in the pattern discrimination results are checked, using knowledge-base music notation. The resulting music robot vision performance is able to recognize, one sheet of commercially available printed of nursery song music for an electric piano, having up to three parts in 15 seconds, with approximately 100% accuracy.

    AB - This paper reports on WABOT-2 vision system, which can recognize not only commercially available printed musical scores but also instant lettering scores in real time, using an extraction algorithm based on the musical score structure with special hardware and knowledge-base music comprehension software. Several automated recognition systems for printed music have been reported. However, none of these systems are suitable for use as vision for music playing robots, where real time recognition is required under an extremely poor data environment where a video camera is placed in the robot's head and music sheets are often curved or otherwise deformed on the music stand. In order to directly convey the vision system output to the robot hands, contradictions and inharmonic codes in the pattern discrimination results are checked, using knowledge-base music notation. The resulting music robot vision performance is able to recognize, one sheet of commercially available printed of nursery song music for an electric piano, having up to three parts in 15 seconds, with approximately 100% accuracy.

    UR - http://www.scopus.com/inward/record.url?scp=0022229415&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0022229415&partnerID=8YFLogxK

    M3 - Article

    SP - 25

    EP - 52

    JO - Waseda Daigaku Rikogaku Kenkyusho Hokoku/Bulletin of Science and Engineering Research Laboratory, Waseda University

    JF - Waseda Daigaku Rikogaku Kenkyusho Hokoku/Bulletin of Science and Engineering Research Laboratory, Waseda University

    SN - 0372-7181

    IS - 112

    ER -