Camera-based Music Score Recognition Using Inverse Filter
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The influence of acquisition environment on music score images captured by a camera has not yet been seriously examined. All existing Optical Music Recognition (OMR) systems attempt to recognize music score images captured by a scanner under idealconditions. Therefore, when such systems process images under the influence of distortion, different viewpoints or suboptimal illumination effects, the performance, in terms of recognition accuracy and processing time, is unacceptable for deployment in practice. In this paper, a novel, lightweight but effective approach for dealing with the issues caused by camera based music scores is proposed. Based on the staff line information, musical rules, run length code, and projection, all regions of interest are determined. Templates created from inverse filter are then used to recognize the music symbols. Therefore, all fragmentation and deformation problems, as well as missed recognition, can be overcome using the developed method. The system was evaluated on a dataset consisting of real images captured by a smartphone. The achieved recognition rate and processing time were relatively competitive with state of the art works. In addition, the system was designed to be lightweight compared with the other approaches, which mostly adopted machine learning algorithms, to allow further deployment on portable devices with limited computing resources.
Abstract
The influence of acquisition environment on music score images captured by a camera has not yet been seriously examined. All existing Optical Music Recognition (OMR) systems attempt to recognize music score images captured by a scanner under idealconditions. Therefore, when such systems process images under the influence of distortion, different viewpoints or suboptimal illumination effects, the performance, in terms of recognition accuracy and processing time, is unacceptable for deployment in practice. In this paper, a novel, lightweight but effective approach for dealing with the issues caused by camera based music scores is proposed. Based on the staff line information, musical rules, run length code, and projection, all regions of interest are determined. Templates created from inverse filter are then used to recognize the music symbols. Therefore, all fragmentation and deformation problems, as well as missed recognition, can be overcome using the developed method. The system was evaluated on a dataset consisting of real images captured by a smartphone. The achieved recognition rate and processing time were relatively competitive with state of the art works. In addition, the system was designed to be lightweight compared with the other approaches, which mostly adopted machine learning algorithms, to allow further deployment on portable devices with limited computing resources.
참고문헌 (17)
- Rebelo, "Optical recognition of music symbol: A comparative study", Int. J. Doc. Anal Recognit, pp.19~31 (2010)
- P. Bellini, "Opticalmusic recognition: architecture andalgorithmas", Interactive multimedia music technologies, pp.8~110 (2008)
- G. Choudhury, "Optical music recognition system within a large scale digitization project", In Proceedings of the International Society for Music information retrieval (2000)
- M. Droettboom, "Optical music interpretation", LAPR, pp.378~386 (2002)
- H. Miyao, "Note symbol extraction for printed piano scores using neural networks", In IEICE Trans Inform Syst (1996)
- L. Pugin, "Optical music recognition of early typographic prints using Hidden Markov models", Proceedings of the International Society for Music, pp.53~56 (2006)
- L. Pugin, "MAP adaptation to improveopticalmusic recognition of early music documents using Hidden Markov models", In Proceedings of the 8th International Society for Music, pp.513~516 (2007)
- I. Fujinaga, "Visual perception of music notation: online and offline recognition", pp.1~39 (2004), Idea Group Inc.
- W. Homenda, "Automatic knowledge acquitiwion;' recognizing music notation with methods of centroids and classifications trees", In Proceedings of the International joint conference on neural networks, pp.3382~3388 (2006)
- J. TardonL, "Optical music recognition for scores written in white mensural notation", In EURASIP (2009)
- Musichand: a handwritten music recognition system, "G. Taubman", ~ (2005)
- K. T. Reed, "Automatic computer recognition of printed music", In ICPR, 3, pp.803~807 (1996)
- P. Bellini, "Optical music sheet segmentation", In Proceedings of the first international conference on web delivering of music, pp.183~190 (2001)
- S. Sheridan, "Defacing music score for improved recognition", Proceedings of the Second Australian undergraduate students' computing conference, pp.1~7 (2004)
- Vo Quang Nhat, "Adaptive line fitting for staff detection in handwritten music score images", ICUIMC 2014 (2014)
- Nawapon Luangnapa, "Optical Music Recognition on Andrioid Platform", pp.106~115 (2012), Springer Berlin Heidelberg
- Thanavhai Soontornwutikul, "Optical Music Recognition on Windows Phone 7", In The 9th International Conference on Computing and Information Technology(IC2IT2013) (2013)