Camera-based Music Score Recognition Using Inverse Filter

다국어 초록 (Multilingual 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 ideal conditions. 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 (Reference)

1 I. Fujinaga, "Visual perception of music notation: online and offline recognition" Idea Group Inc. 1-39, 2004

2 P. Bellini, "Opticalmusic recognition: architecture andalgorithmas" 8-110, 2008

3 Rebelo, "Optical recognition of music symbol: A comparative study" 19-31, 2010

4 P. Bellini, "Optical music sheet segmentation" 183-190, 2001

5 G. Choudhury, "Optical music recognition system within a large scale digitization project" 2000

6 L. Pugin, "Optical music recognition of early typographic prints using Hidden Markov models" 53-56, 2006

7 J. TardonL, "Optical music recognition for scores written in white mensural notation" 2009

8 M. Droettboom, "Optical music interpretation" 378-386, 2002

9 Thanavhai Soontornwutikul, "Optical Music Recognition on Windows Phone 7" 2013

10 Nawapon Luangnapa, "Optical Music Recognition on Andrioid Platform" Springer Berlin Heidelberg 106-115, 2012

11 H. Miyao, "Note symbol extraction for printed piano scores using neural networks" 1996

12 G. Taubman, "Musichand: a handwritten music recognition system" 2005

13 L. Pugin, "MAP adaptation to improveopticalmusic recognition of early music documents using Hidden Markov models" 513-516, 2007

14 S. Sheridan, "Defacing music score for improved recognition" 1-7, 2004

15 W. Homenda, "Automatic knowledge acquitiwion;' recognizing music notation with methods of centroids and classifications trees" 3382-3388, 2006

16 K. T. Reed, "Automatic computer recognition of printed music" 3 : 803-807, 1996

17 Vo Quang Nhat, "Adaptive line fitting for staff detection in handwritten music score images" 2014