Abstract
Automatic music score detection plays important role in the optical music recognition (OMR). In a visual image, the characteristic of the music scores is frequently degraded by illumination, distortion and other background elements. In this paper, to reduce the influences to OMR caused by those degradations especially the interference of Chinese character, an unsupervised feature learning detection method is proposed for improving the correctness of music score detection. Firstly, a detection framework was constructed. Then sub-image block features were extracted by simple unsupervised feature learning (UFL) method based on K-means and classified by SVM. Finally, music score detection processing was completed by connecting component searching algorithm based on the sub-image block label. Taking Chinese text as the main interferences, the detection rate was compared between UFL method and texture feature method based on 2D Gabor filter in the same framework. The experiment results show that unsupervised feature learning method gets less error detection rate than Gabor texture feature method with limited training set.
Similar content being viewed by others
References
Rebelo A, Fujinaga I, Paszkiewicz F et al (2012) Optical music recognition: state-of-the-art and openissues[J]. Int J Multimed Inf Retr 1(3):173–190. doi:10.1007/s13735-012-0004-6
Szwoch M (2005) A robust detector for distorted music staves[C]. In: Computer analysis of images and patterns. Springer, Berlin, pp 701–708
Rebelo A, Capela A, da Costa JFP et al (2007) A shortest path approach for staff line detection[C]. In: The third international conference on automated production of cross media content for multi-channel distribution 2007 (AXMEDIS’07). IEEE, pp 79–85
Cardoso JS, Capela A, Rebelo A et al (2009) Staff detection with stable paths. IEEE Trans Pattern Anal Mach Intell 31(6):1134–1139. doi:10.1109/TPAMI.2009.34
Dalitz C, Droettboom M, Pranzas B et al (2008) A comparative study of staff removal algorithms[J]. IEEE Trans Pattern Anal Mach Intell 30(5):753–766. doi:10.1109/TPAMI.2007.70749
Dutta A, Pal U, Fornes A et al (2010) An efficient staff removal approach from printed musical documents[C]. In: 20th international conference on pattern recognition (ICPR), 2010. IEEE, pp 1965–1968
Burgoyne JA, Pugin L, Eustace G et al (2007) A comparative survey of image binarization algorithms for optical recognition on degraded musical sources[C]. In; International society for music information retrieval conference (ISMIR), pp 509–512
Pinto T, Rebelo A, Giraldi G et al (2011) Music score binarization based on domain knowledge[M]. In: Pattern recognition and image analysis. Springer, Berlin, pp 700–708
Rebelo A, Cardoso JS (2013) Staff line detection and removal in the grayscale domain[C]. In: The 12th international conference on document analysis and recognition (ICDAR), pp 57–61
Timofe R, Gool LV (2013) Automatic stave discovery for musical facsimiles[C]. ACCV2012 4:510–523
Sun JD, Ma YY (2010) Summary of texture feature research[J]. Appl Comput Syst. 19(6):245–250
Zhang XZ (1992) Chinese character recognition technology [M]. Tsinghua university press, Beijing
Sharma A, Imoto S, Miyano S et al (2012) Null space based feature selection method for gene expression data[J]. Int J Mach Learn Cybernet 3(4):269–276
Subrahmanya N, Shin YC (2013) A variational Bayesian framework for group feature selection[J]. Int J Mach Learn Cybernet 4(6):609–619
Xie ZX, Xu Y (2014) Sparse group LASSO based uncertain feature selection[J]. Int J Mach Learn Cybernet 5(2):201–210
Coates A (2012) Demystifying unsupervised feature learning[D]. Stanford University, Stanford
Netzer Y, Wang T, Coates A et al (2011) Reading digits in natural images with unsupervised feature learning[C]. In: NIPS workshop on deep learning and unsupervised feature learning 2011
Ranzato MA, Huang FJ, Boureau YL et al (2007) Unsupervised learning of invariant feature hierarchies with applications to object recognition[C]. IEEE Conf Comput Vis Pattern Recogn 2007:1–8
Kavukcuoglu K, Sermanet P, Boureau YL et al (2010) Learning convolutional feature hierarchies for visual recognition[C]. In: Advances in neural information processing systems, pp 1090–1098
Saxe A, Koh PW, Chen Z et al (2011) On random weights and unsupervised feature learning[C]. In: Twenty-eighth international conference on machine learning, pp 1–9
Coates A, Lee H, Ng AY (2011) An analysis of single-layer networks in unsupervised feature learning [J]. JMLR W&CP. 15:215–223
Yeung D, Wang XZ (2002) Improving performance of similarity-based clustering by feature weight learning[J]. IEEE Trans Pattern Anal Mach Intell 24(4):556–561
Wang XZ, Wang YD, Wang LJ (2004) Improving fuzzy c-means clustering based on feature-weight learning[J]. Pattern Recogn Lett 25(10):1123–1132
Sarma TH, Viswanath P, Reddy BE (2013) A hybrid approach to speed-up the K-means clustering method [J]. Int J Mach Learn Cybernet 4(2):107–117
Jan W, Riedmiller M (2012) Unsupervised learning of local features for music classification[C].In: 13th international society for music information retrieval conference (ISMIR2012), pp 139–144
Musa AB (2013) Comparative study on classification performance between support vector machine and logistic regression[J]. Int J Mach Learn Cybernet 4(1):13–24
Zhang LF, Zhang LP, Tao DC et al (2012) On combining multiple features for hyperspectral remote sensing image classification[J]. IEEE Trans Geosci Remote Sens 50(3):879–893
Manjunath BS, Ma WY (1996) Texture features for browsing and retrieval of image data[J]. IEEE Trans Pattern Anal Mach Intell. 18(8):837–842
Qin LL, Li B (2006) Chinese and foreign music appreciation. Zhejiang University Press, Hangzhou
Zhu JX (2006) Music appreciation. Henan University Press, Kaifeng
Coates A, Carpenter B, Case C et al (2011) Text detection and character recognition in scene images with unsupervised feature learning[C]. In: IEEE 2011 international conference on document analysis and recognition (ICDAR), pp 440–445
Keerthi SS, Shevade SK, Bhattacharyya C et al (2001) Improvements to Platt’s SMO algorithm for SVM classifier design [J]. Neural Comput 13(3):637–649
Acknowledgments
This work is supported by the National Natural Science Foundation of China (No. 61375075) and Natural Science Foundation of Hebei Province (No. F2011201106, No. F2012201020).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Fang, Y., Gui-fa, T. Visual music score detection with unsupervised feature learning method based on K-means. Int. J. Mach. Learn. & Cyber. 6, 277–287 (2015). https://doi.org/10.1007/s13042-014-0260-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-014-0260-2