Wavelet-based approach for writer identification in music score

Writer identification is a vibrant research field, though a lot of work has been done on writer identification on normal text, writer identification in music score sheet has not been addressed in that large scale. Here we propose a method to identify writers of music score sheets using Daubchies wavelet features along with SVM classifier. We have evaluated our proposed approach in a sub-set of CVC-MUSCIMA dataset. From the experiment on 140 score sheet images from 7 writers we obtained encouraging results.

[1]  Alicia Fornés,et al.  The ICDAR 2011 Music Scores Competition: Staff Removal and Writer Identification , 2011, 2011 International Conference on Document Analysis and Recognition.

[2]  Fumitaka Kimura,et al.  Handwritten Musical Document Retrieval Using Music-Score Spotting , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[3]  Alicia Fornés,et al.  Writer Identification in Old Handwritten Music Scores , 2008, 2008 The Eighth IAPR International Workshop on Document Analysis Systems.

[4]  Ilvio Bruder,et al.  Integrating knowledge components for writer identification in a digital archive of historical music scores , 2004, JCDL.

[5]  Alicia Fornés,et al.  On the Use of Textural Features for Writer Identification in Old Handwritten Music Scores , 2009, 2009 10th International Conference on Document Analysis and Recognition.

[6]  Alicia Fornés,et al.  A combination of features for symbol-independent writer identification in old music scores , 2010, International Journal on Document Analysis and Recognition (IJDAR).

[7]  Ernest Valveny,et al.  A bag of notes approach to writer identification in old handwritten musical scores , 2010, DAS '10.

[8]  Roland Göcke.  Building a system for writer identification on handwritten music scores , 2003 .

[9]  Nailja Luth,et al.  Automatic identification of music notations , 2002, Second International Conference on Web Delivering of Music, 2002. WEDELMUSIC 2002. Proceedings..

[10]  Somaya Al-Máadeed,et al.  Writer identification using edge-based directional probability distribution features for arabic words , 2008, 2008 IEEE/ACS International Conference on Computer Systems and Applications.

[11]  Ingrid Daubechies,et al.  The wavelet transform, time-frequency localization and signal analysis , 1990, IEEE Trans. Inf. Theory.

[12]  Somaya Al-Máadeed,et al.  Writer identification of Arabic handwriting documents using grapheme features , 2008, 2008 IEEE/ACS International Conference on Computer Systems and Applications.

[13]  Horst Bunke,et al.  A Set of Novel Features for Writer Identification , 2003, AVBPA.

[14]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.