<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>The traditional music teaching method in the informationization era has been difficult to adapt to the needs of modern teaching and must be reformed in the direction of informationization. In this paper, based on the closure, inflection point and outer enclosing box features of the stroke line element, the recognition of handwritten notes is carried out from the three categories of straight line segments, folded line segments and quadratic curves. Meanwhile, for the binarized music score image, the multi-directional LBP features for spectral line detection are improved, and the computation method of multi-scale spectral line detection LBP features is established. The Manhattan distance is used to evaluate and select the features, which are inputted into XGBoost for classification and recognition training based on the statistical distribution characteristics of the features. Note recognition and spectral line recognition are applied to college music teaching, and the effectiveness of teaching is explored. In the rhythm-recognition path, the recognition teaching based on multi-scale and multi-directional LBP features led to an increase in students’ mastery of the musical score by 2.8 and in the phrasing and segmentation path by 3.5. Informational teaching led to a deepening of students’ mastery of the notes and musical scores.</p>
</abstract>

The traditional music teaching method in the informationization era has been difficult to adapt to the needs of modern teaching and must be reformed in the direction of informationization. In this paper, based on the closure, inflection point and outer enclosing box features of the stroke line element, the recognition of handwritten notes is carried out from the three categories of straight line segments, folded line segments and quadratic curves. Meanwhile, for the binarized music score image, the multi-directional LBP features for spectral line detection are improved, and the computation method of multi-scale spectral line detection LBP features is established. The Manhattan distance is used to evaluate and select the features, which are inputted into XGBoost for classification and recognition training based on the statistical distribution characteristics of the features. Note recognition and spectral line recognition are applied to college music teaching, and the effectiveness of teaching is explored. In the rhythm-recognition path, the recognition teaching based on multi-scale and multi-directional LBP features led to an increase in students’ mastery of the musical score by 2.8 and in the phrasing and segmentation path by 3.5. Informational teaching led to a deepening of students’ mastery of the notes and musical scores.

Construction of college music information teaching mode under the background of Internet

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

The traditional music teaching method in the informationization era has been difficult to adapt to the needs of modern teaching and must be reformed in the...

Construction of college music information teaching mode under the background of Internet

Pubblicato online: 02 dic 2023

Pagine: -

Ricevuto: 20 feb 2023

Accettato: 12 giu 2023

DOI: https://doi.org/10.2478/amns.2023.2.01330

Parole chiave
Stroke line element, Handwritten notes, LBP features, XGBoost algorithm, Music informatization

© 2023 Li Hai Yan, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Construction of college music information teaching mode under the background of Internet

Pubblicato online: 02 dic 2023

Pagine: -

Ricevuto: 20 feb 2023

Accettato: 12 giu 2023

DOI: https://doi.org/10.2478/amns.2023.2.01330

Parole chiaveStroke line element, Handwritten notes, LBP features, XGBoost algorithm, Music informatization

© 2023 Li Hai Yan, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Parole chiave
Stroke line element, Handwritten notes, LBP features, XGBoost algorithm, Music informatization