Abstract

Optical music symbol recognition deals with the conversion of scanned musical symbols into digital readable form. Though existing techniques have achieved considerable result for printed musical symbols, for handwritten musical symbol, there is a lot of room for research as it comes with several challenges such as degradation, skew, and non-uniformity of symbols. In this paper, we have presented discrete wavelet transform and radon transform to extract directional multi-resolution features from the input musical symbols. Further, k-NN classifier is used to classify the music symbols and achieved an encouraging accuracy of classification as 95.04% with ten-fold cross-validation.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.