• DocumentCode
    2524857
  • Title

    Automatic selection of the region of interest in ancient scores

  • Author

    Barbancho, Isabel ; Segura, Cristian ; Tardón, Lorenzo J. ; Barbancho, Ana M.

  • Author_Institution
    Dept. de Ing. de Comun., Univ. de Malaga, Málaga, Spain
  • fYear
    2010
  • fDate
    26-28 April 2010
  • Firstpage
    326
  • Lastpage
    331
  • Abstract
    In this paper, an automatic system for the extraction of the region of interest in ancient scores is presented. The system is able to separate the image into two pages, when needed, then, using images that contain one page of score, the method performs a correction of the rotation before estimating the region of interest. For the estimation of the region of interest, three different methods have been developed: eroded edges method, wavelet method and eroded image and edge method. The three methods obtain quite good performance, being the wavelet based method the one that achieves best performance regarding execution time and accuracy in the process of selection of the region of interest.
  • Keywords
    feature extraction; history; image recognition; music; wavelet transforms; OMR; ancient scores; automatic system; eroded edges method; eroded image method; feature extraction; image separation; optical music recognition; region of interest; rotation correction; wavelet method; Books; Color; Data mining; Degradation; Digital images; Fungi; Ink; Lighting; Optical computing; Ordinary magnetoresistance;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    MELECON 2010 - 2010 15th IEEE Mediterranean Electrotechnical Conference
  • Conference_Location
    Valletta
  • Print_ISBN
    978-1-4244-5793-9
  • Type

    conf

  • DOI
    10.1109/MELCON.2010.5476269
  • Filename
    5476269