Automatic Recognition of Square Notation Symbols in Western Plainchant Manuscripts

Carolina Ramirez, Jun Ohya

    Research output: Contribution to journalArticle

    11 Citations (Scopus)

    Abstract

    Abstract: While the Optical Music Recognition (OMR) of printed and handwritten music scores in modern standard notation has been broadly studied, this is not the case for early music manuscripts. This is mainly due to the high variability in the sources introduced by their severe physical degradation, the lack of notation standards and, in the case of the scanned versions, by non-homogenous image-acquisition protocols. The volume of early musical manuscripts available is considerable, and therefore we believe that computational methods can be extremely useful in helping to preserve, share and analyse this information. This paper presents an approach to recognizing handwritten square musical notation in degraded western plainchant manuscripts from the XIVth to XVIth centuries. We propose the use of image processing techniques that behave robustly under high data variability and which do not require strong hypotheses regarding the condition of the sources. The main differences from traditional OMR approaches are our avoidance of the staff line removal stage and the use of grey-level images to perform primitive segmentation and feature extraction. We used 136 images from the Digital Scriptorium repository (DS, 2007), from which we were able to extract over 90% of the staves and over 88% of all symbols present. For symbol classification, we used gradient-based features and SVM classifiers, obtaining over 90% precision and recall over eight basic symbol classes.

    Original languageEnglish
    Pages (from-to)390-399
    Number of pages10
    JournalJournal of New Music Research
    Volume43
    Issue number4
    DOIs
    Publication statusPublished - 2014 Oct 1

    Fingerprint

    Symbol
    Music
    Manuscripts
    Notation
    Plainchant
    Optical
    Physical
    Avoidance
    Computational
    Musical Notation
    Repository
    Staff
    Scriptorium
    Feature Extraction
    Music Manuscripts
    Stave
    Classifier
    Segmentation
    Degradation
    Image Processing

    Keywords

    • musical manuscript analysis
    • OMR (Optical Music Recognition)
    • plainchant
    • SVM

    ASJC Scopus subject areas

    • Visual Arts and Performing Arts
    • Music

    Cite this

    Automatic Recognition of Square Notation Symbols in Western Plainchant Manuscripts. / Ramirez, Carolina; Ohya, Jun.

    In: Journal of New Music Research, Vol. 43, No. 4, 01.10.2014, p. 390-399.

    Research output: Contribution to journalArticle

    @article{1ce7514e9c88481abf304043edf1b967,
    title = "Automatic Recognition of Square Notation Symbols in Western Plainchant Manuscripts",
    abstract = "Abstract: While the Optical Music Recognition (OMR) of printed and handwritten music scores in modern standard notation has been broadly studied, this is not the case for early music manuscripts. This is mainly due to the high variability in the sources introduced by their severe physical degradation, the lack of notation standards and, in the case of the scanned versions, by non-homogenous image-acquisition protocols. The volume of early musical manuscripts available is considerable, and therefore we believe that computational methods can be extremely useful in helping to preserve, share and analyse this information. This paper presents an approach to recognizing handwritten square musical notation in degraded western plainchant manuscripts from the XIVth to XVIth centuries. We propose the use of image processing techniques that behave robustly under high data variability and which do not require strong hypotheses regarding the condition of the sources. The main differences from traditional OMR approaches are our avoidance of the staff line removal stage and the use of grey-level images to perform primitive segmentation and feature extraction. We used 136 images from the Digital Scriptorium repository (DS, 2007), from which we were able to extract over 90{\%} of the staves and over 88{\%} of all symbols present. For symbol classification, we used gradient-based features and SVM classifiers, obtaining over 90{\%} precision and recall over eight basic symbol classes.",
    keywords = "musical manuscript analysis, OMR (Optical Music Recognition), plainchant, SVM",
    author = "Carolina Ramirez and Jun Ohya",
    year = "2014",
    month = "10",
    day = "1",
    doi = "10.1080/09298215.2014.931438",
    language = "English",
    volume = "43",
    pages = "390--399",
    journal = "Journal of New Music Research",
    issn = "0929-8215",
    publisher = "Taylor and Francis Ltd.",
    number = "4",

    }

    TY - JOUR

    T1 - Automatic Recognition of Square Notation Symbols in Western Plainchant Manuscripts

    AU - Ramirez, Carolina

    AU - Ohya, Jun

    PY - 2014/10/1

    Y1 - 2014/10/1

    N2 - Abstract: While the Optical Music Recognition (OMR) of printed and handwritten music scores in modern standard notation has been broadly studied, this is not the case for early music manuscripts. This is mainly due to the high variability in the sources introduced by their severe physical degradation, the lack of notation standards and, in the case of the scanned versions, by non-homogenous image-acquisition protocols. The volume of early musical manuscripts available is considerable, and therefore we believe that computational methods can be extremely useful in helping to preserve, share and analyse this information. This paper presents an approach to recognizing handwritten square musical notation in degraded western plainchant manuscripts from the XIVth to XVIth centuries. We propose the use of image processing techniques that behave robustly under high data variability and which do not require strong hypotheses regarding the condition of the sources. The main differences from traditional OMR approaches are our avoidance of the staff line removal stage and the use of grey-level images to perform primitive segmentation and feature extraction. We used 136 images from the Digital Scriptorium repository (DS, 2007), from which we were able to extract over 90% of the staves and over 88% of all symbols present. For symbol classification, we used gradient-based features and SVM classifiers, obtaining over 90% precision and recall over eight basic symbol classes.

    AB - Abstract: While the Optical Music Recognition (OMR) of printed and handwritten music scores in modern standard notation has been broadly studied, this is not the case for early music manuscripts. This is mainly due to the high variability in the sources introduced by their severe physical degradation, the lack of notation standards and, in the case of the scanned versions, by non-homogenous image-acquisition protocols. The volume of early musical manuscripts available is considerable, and therefore we believe that computational methods can be extremely useful in helping to preserve, share and analyse this information. This paper presents an approach to recognizing handwritten square musical notation in degraded western plainchant manuscripts from the XIVth to XVIth centuries. We propose the use of image processing techniques that behave robustly under high data variability and which do not require strong hypotheses regarding the condition of the sources. The main differences from traditional OMR approaches are our avoidance of the staff line removal stage and the use of grey-level images to perform primitive segmentation and feature extraction. We used 136 images from the Digital Scriptorium repository (DS, 2007), from which we were able to extract over 90% of the staves and over 88% of all symbols present. For symbol classification, we used gradient-based features and SVM classifiers, obtaining over 90% precision and recall over eight basic symbol classes.

    KW - musical manuscript analysis

    KW - OMR (Optical Music Recognition)

    KW - plainchant

    KW - SVM

    UR - http://www.scopus.com/inward/record.url?scp=84907590575&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84907590575&partnerID=8YFLogxK

    U2 - 10.1080/09298215.2014.931438

    DO - 10.1080/09298215.2014.931438

    M3 - Article

    VL - 43

    SP - 390

    EP - 399

    JO - Journal of New Music Research

    JF - Journal of New Music Research

    SN - 0929-8215

    IS - 4

    ER -