OMR of early plainchant manuscripts in square notation: A two-stage system

Carolina Ramirez, Jun Ohya

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    2 Citations (Scopus)

    Abstract

    While Optical Music Recognition (OMR) of modern printed and handwritten documents is considered a solved problem, with many commercial systems available today, the OMR of ancient musical manuscripts still remains an open problem. In this paper we present a system for the OMR of degraded western plainchant manuscripts in square notation from the XIV to XVI centuries. The system has two main blocks, the first one deals with symbol extraction and recognition, while the second one acts as an error detection stage for the first block outputs. For symbol extraction we use widely known image-processing techniques, such as Sobel filtering and Hough Transform, and SVM for classification. The error detection stage is implemented with a hidden Markov model (HMM), which takes advantage of a priori knowledge for this specific kind of music.

    Original languageEnglish
    Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
    Volume7874
    DOIs
    Publication statusPublished - 2011
    EventDocument Recognition and Retrieval XVIII - San Francisco, CA
    Duration: 2011 Jan 262011 Jan 27

    Other

    OtherDocument Recognition and Retrieval XVIII
    CitySan Francisco, CA
    Period11/1/2611/1/27

    Fingerprint

    music
    Error detection
    Music
    Notation
    coding
    Hough transforms
    Error Detection
    Hidden Markov models
    Image processing
    Hough Transform
    Markov Model
    image processing
    Image Processing
    Open Problems
    Filtering
    output
    Output

    Keywords

    • binarization
    • Degraded document analysis
    • handwritten music scores
    • HMM
    • OCR
    • OMR
    • SVM

    ASJC Scopus subject areas

    • Applied Mathematics
    • Computer Science Applications
    • Electrical and Electronic Engineering
    • Electronic, Optical and Magnetic Materials
    • Condensed Matter Physics

    Cite this

    Ramirez, C., & Ohya, J. (2011). OMR of early plainchant manuscripts in square notation: A two-stage system. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 7874). [787417] https://doi.org/10.1117/12.876771

    OMR of early plainchant manuscripts in square notation : A two-stage system. / Ramirez, Carolina; Ohya, Jun.

    Proceedings of SPIE - The International Society for Optical Engineering. Vol. 7874 2011. 787417.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Ramirez, C & Ohya, J 2011, OMR of early plainchant manuscripts in square notation: A two-stage system. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 7874, 787417, Document Recognition and Retrieval XVIII, San Francisco, CA, 11/1/26. https://doi.org/10.1117/12.876771
    Ramirez C, Ohya J. OMR of early plainchant manuscripts in square notation: A two-stage system. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 7874. 2011. 787417 https://doi.org/10.1117/12.876771
    Ramirez, Carolina ; Ohya, Jun. / OMR of early plainchant manuscripts in square notation : A two-stage system. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 7874 2011.
    @inproceedings{c476b40727fc4e1286d96cbfd2a00a82,
    title = "OMR of early plainchant manuscripts in square notation: A two-stage system",
    abstract = "While Optical Music Recognition (OMR) of modern printed and handwritten documents is considered a solved problem, with many commercial systems available today, the OMR of ancient musical manuscripts still remains an open problem. In this paper we present a system for the OMR of degraded western plainchant manuscripts in square notation from the XIV to XVI centuries. The system has two main blocks, the first one deals with symbol extraction and recognition, while the second one acts as an error detection stage for the first block outputs. For symbol extraction we use widely known image-processing techniques, such as Sobel filtering and Hough Transform, and SVM for classification. The error detection stage is implemented with a hidden Markov model (HMM), which takes advantage of a priori knowledge for this specific kind of music.",
    keywords = "binarization, Degraded document analysis, handwritten music scores, HMM, OCR, OMR, SVM",
    author = "Carolina Ramirez and Jun Ohya",
    year = "2011",
    doi = "10.1117/12.876771",
    language = "English",
    isbn = "9780819484116",
    volume = "7874",
    booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

    }

    TY - GEN

    T1 - OMR of early plainchant manuscripts in square notation

    T2 - A two-stage system

    AU - Ramirez, Carolina

    AU - Ohya, Jun

    PY - 2011

    Y1 - 2011

    N2 - While Optical Music Recognition (OMR) of modern printed and handwritten documents is considered a solved problem, with many commercial systems available today, the OMR of ancient musical manuscripts still remains an open problem. In this paper we present a system for the OMR of degraded western plainchant manuscripts in square notation from the XIV to XVI centuries. The system has two main blocks, the first one deals with symbol extraction and recognition, while the second one acts as an error detection stage for the first block outputs. For symbol extraction we use widely known image-processing techniques, such as Sobel filtering and Hough Transform, and SVM for classification. The error detection stage is implemented with a hidden Markov model (HMM), which takes advantage of a priori knowledge for this specific kind of music.

    AB - While Optical Music Recognition (OMR) of modern printed and handwritten documents is considered a solved problem, with many commercial systems available today, the OMR of ancient musical manuscripts still remains an open problem. In this paper we present a system for the OMR of degraded western plainchant manuscripts in square notation from the XIV to XVI centuries. The system has two main blocks, the first one deals with symbol extraction and recognition, while the second one acts as an error detection stage for the first block outputs. For symbol extraction we use widely known image-processing techniques, such as Sobel filtering and Hough Transform, and SVM for classification. The error detection stage is implemented with a hidden Markov model (HMM), which takes advantage of a priori knowledge for this specific kind of music.

    KW - binarization

    KW - Degraded document analysis

    KW - handwritten music scores

    KW - HMM

    KW - OCR

    KW - OMR

    KW - SVM

    UR - http://www.scopus.com/inward/record.url?scp=79955738238&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=79955738238&partnerID=8YFLogxK

    U2 - 10.1117/12.876771

    DO - 10.1117/12.876771

    M3 - Conference contribution

    AN - SCOPUS:79955738238

    SN - 9780819484116

    VL - 7874

    BT - Proceedings of SPIE - The International Society for Optical Engineering

    ER -