Implementasi ResNet Dan Faster R-CNN Untuk Transformasi Notasi Balok Ke Angka Nada Berbasis Web Flask

Nurilhaq, Muhammad Sabili (2024) Implementasi ResNet Dan Faster R-CNN Untuk Transformasi Notasi Balok Ke Angka Nada Berbasis Web Flask. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 20081010101.-cover.pdf Download (1MB)
	Text (BAB I) 20081010101.-bab1.pdf Download (1MB)
	Text (BAB II) 20081010101.-bab2.pdf Restricted to Repository staff only until 22 July 2026. Download (2MB)
	Text (BAB III) 20081010101.-bab3.pdf Restricted to Repository staff only until 22 July 2026. Download (3MB)
	Text (BAB IV) 20081010101.-bab4.pdf Restricted to Repository staff only until 22 July 2026. Download (7MB)
	Text (BAB V) 20081010101.-bab5.pdf Download (379kB)
	Text (Daftar Pustaka) 20081010101.-daftarpustaka.pdf Download (808kB)

Abstract

Standard notation is the standardized depiction of a song in written form. However, in the modern world of music processing, computer-based processing systems are often used. Thus, data representation in numeric form becomes important considering that computers can only process data in numeric form. Therefore, the development of technology in the field of machine learning to transform standard notation into numeric notation (pitch notation) is very important. The methods used to detect standard notation objects are Residual Network (ResNet) and Faster Region-Based Convolutional Neural Network (Faster R-CNN). ResNet serves as a layer that extracts image features from the music sheet. Meanwhile, Faster R-CNN functions as a layer for detecting standard notation objects and classifying them into 19 pitch notation classes. The Graphical User Interface (GUI) that connects the methods with the users is a website created using the Flask micro-framework. The mean average precision (mAP) value obtained from the combination of Faster R-CNN and ResNet using bounding-box scales of 4, 8, 16, and 32 is 78%. This result is achieved because the method has a weakness in detecting standard notation found in portrait-oriented images.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Mandyartha, Eka Prakarsa	NIDN0725058805	eka_prakarsa.fik@upnjatim.ac.id
Thesis advisor	Rizki, Agung Mustika	NIDN0025079302	agung.mustika.if@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Muhammad Sabili Nurilhaq

Date Deposited:

22 Jul 2024 07:16

Last Modified:

22 Jul 2024 07:16

URI:

https://repository.upnjatim.ac.id/id/eprint/26942