Assessing optical music recognition tools

被引:17
作者
Bellini, Pierfrancesco [1 ]
Bruno, Ivan [1 ]
Nesi, Paolo [1 ]
机构
[1] Univ Florence, Dept Syst & Informat, Distributed Syst & Internet Technol Lab, I-50139 Florence, Italy
关键词
PREDICTION;
D O I
10.1162/comj.2007.31.1.68
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Two models that respectively examine the recognition rates of more-or-less atomic symbols and composite symbols were applied to three optical music recognition (OMR) software packages: SmartScore, O3MR and SharpEye2. To validate the models, the opinions of human experts were sought in two phases. First, the experts were given a questionnaire in which they rated the importance of the different types of symbols. Following this, in a "blind" test, the experts judged the accuracy of the three OMR programs, by comparing the program's outputs when given identical inputs. Results confirm that the metrics can approximate the evaluations of human experts. Concerning the specific OMR systems tested, SharpEye2 had the best recognition of a large set of symbols, whereas O3MR had the most robust recognition of notes and rests.
引用
收藏
页码:68 / 93
页数:26
相关论文
共 39 条
[1]  
[Anonymous], 2000, IAPR WORKSHOP DOCUME
[2]  
[Anonymous], THESIS MCGILL U
[3]  
Bainbridge D., 1996, Australian Computer Science Communications, V18, P308
[4]   A music notation construction engine for optical music recognition [J].
Bainbridge, D ;
Bell, T .
SOFTWARE-PRACTICE & EXPERIENCE, 2003, 33 (02) :173-200
[5]   Optical music sheet segmentation [J].
Bellini, P ;
Bruno, I ;
Nesi, P .
FIRST INTERNATIONAL CONFERENCE ON WEB DELIVERING OF MUSIC, PROCEEDINGS, 2001, :183-190
[6]   WEDELMUSIC format: An XML music notation format for emerging applications [J].
Bellini, P ;
Nesi, P .
FIRST INTERNATIONAL CONFERENCE ON WEB DELIVERING OF MUSIC, PROCEEDINGS, 2001, :79-86
[7]  
BELLINI P, 2004, VISUAL PERCEPTION MU, P40
[8]  
Blostein Dorothea, 1992, STRUCTURED DOCUMENT, P573
[9]  
BRUNO I, 2004, IST20013370 IMUTUS
[10]  
BRUNO I, 2003, THESIS U FLORENCE