Visual music score detection with unsupervised feature learning method based on K-means

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.

[1]  Liangpei Zhang,et al.  On Combining Multiple Features for Hyperspectral Remote Sensing Image Classification , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[2]  B. Eswara Reddy,et al.  A hybrid approach to speed-up the k-means clustering method , 2012, International Journal of Machine Learning and Cybernetics.

[3]  Marc'Aurelio Ranzato,et al.  Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  S. Sathiya Keerthi,et al.  Improvements to Platt's SMO Algorithm for SVM Classifier Design , 2001, Neural Computation.

[5]  Ichiro Fujinaga,et al.  A Comparative Study of Staff Removal Algorithms , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Sun Jun.  Summary of Texture Feature Research , 2010 .

[7]  E. Carrapatoso,et al.  A Shortest Path Approach for Staff Line Detection , 2007, Third International Conference on Automated Production of Cross Media Content for Multi-Channel Distribution (AXMEDIS'07).

[8]  Satoru Miyano,et al.  Null space based feature selection method for gene expression data , 2012, Int. J. Mach. Learn. Cybern..

[9]  Jaime S. Cardoso,et al.  Staff Line Detection and Removal in the Grayscale Domain , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[10]  V. Rodriguez,et al.  From Narrative Contracts to Electronic Licenses: A Guided Translation Process for the Case of Audiovisual Content Management , 2007, Third International Conference on Automated Production of Cross Media Content for Multi-Channel Distribution (AXMEDIS'07).

[11]  Andrew Y. Ng,et al.  Text Detection and Character Recognition in Scene Images with Unsupervised Feature Learning , 2011, 2011 International Conference on Document Analysis and Recognition.

[12]  Umapada Pal,et al.  An Efficient Staff Removal Approach from Printed Musical Documents , 2010, 2010 20th International Conference on Pattern Recognition.

[13]  B. S. Manjunath,et al.  Texture Features for Browsing and Retrieval of Image Data , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Carlos Guedes,et al.  Optical music recognition: state-of-the-art and open issues , 2012, International Journal of Multimedia Information Retrieval.

[15]  Y-Lan Boureau,et al.  Learning Convolutional Feature Hierarchies for Visual Recognition , 2010, NIPS.

[16]  Carlos Guedes,et al.  Staff Detection with Stable Paths , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  D. S. Yeung,et al.  Improving Performance of Similarity-Based Clustering by Feature Weight Learning , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Andrew Y. Ng,et al.  Reading Digits in Natural Images with Unsupervised Feature Learning , 2011 .

[19]  Yung C. Shin,et al.  A variational Bayesian framework for group feature selection , 2013, Int. J. Mach. Learn. Cybern..

[20]  Abdallah Bashir Musa.  Comparative study on classification performance between support vector machine and logistic regression , 2012, International Journal of Machine Learning and Cybernetics.

[21]  Zhenghao Chen,et al.  On Random Weights and Unsupervised Feature Learning , 2011, ICML.

[22]  Yadong Wang,et al.  Improving fuzzy c-means clustering based on feature-weight learning , 2004, Pattern Recognit. Lett..

[23]  Ichiro Fujinaga,et al.  A Comparative Survey of Image Binarisation Algorithms for Optical Recognition on Degraded Musical Sources , 2007, ISMIR.

[24]  Honglak Lee,et al.  An Analysis of Single-Layer Networks in Unsupervised Feature Learning , 2011, AISTATS.

[25]  Luc Van Gool,et al.  Automatic Stave Discovery for Musical Facsimiles , 2012, ACCV.

[26]  Gilson A. Giraldi,et al.  Music Score Binarization Based on Domain Knowledge , 2011, IbPRIA.

[27]  Mariusz Szwoch,et al.  A Robust Detector for Distorted Music Staves , 2005, CAIP.

[28]  Yong Xu,et al.  Sparse group LASSO based uncertain feature selection , 2014, Int. J. Mach. Learn. Cybern..

[29]  Martin A. Riedmiller,et al.  Unsupervised Learning of Local Features for Music Classification , 2012, ISMIR.