Penerapan Arsitektur CNN-EfficientNetB2 Dengan Transfer Learning Pada Klasifikasi Gambar Tokoh Wayang Kulit

Maulana, Hafizh Kennandya (2025) Penerapan Arsitektur CNN-EfficientNetB2 Dengan Transfer Learning Pada Klasifikasi Gambar Tokoh Wayang Kulit. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) COVER REVISI.pdf Download (615kB)
	Text (Bab 1) BAB 1.pdf Download (104kB)
	Text (Bab 2) BAB 2.pdf Restricted to Repository staff only until 17 June 2027. Download (620kB)
	Text (Bab 3) BAB 3.pdf Restricted to Repository staff only until 17 June 2027. Download (370kB)
	Text (Bab 4) BAB 4.pdf Restricted to Repository staff only until 17 June 2027. Download (2MB)
	Text (Bab 5) BAB 5.pdf Download (8kB)
	Text (Daftar Pustaka) DAFTAR PUSTAKA.pdf Download (57kB)

Abstract

Wayang kulit is a traditional Indonesian performing art with high cultural and moral values. However, recognizing its characters remains a challenge, especially for the younger generation, due to the visual similarities between them. This study aims to classify wayang kulit character images using the EfficientNetB2 architecture with Transfer Learning techniques. The model was tested on a dataset consisting of 22 wayang characters and compared with ResNet50. Experimental results show that the scenario with a 70:30 data ratio, 64 epochs, and a batch size of 128 provides the most stable performance for EfficientNetB2, achieving a test accuracy of 96.78% and a loss of 0.10. Some classes demonstrated high precision and recall, though a few still experienced misclassification. Meanwhile, ResNet50 achieved its best performance with an 80:20 ratio, 64 epochs, and a batch size of 128, reaching a test accuracy of 95.92% and a loss of 0.13. Based on these results, EfficientNetB2 outperforms ResNet50 in classifying wayang kulit characters, particularly in maintaining a balance between precision and recall across most classes.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Wahanani, Henni Endah	NIDN0022097811	henniendah@upnjatim.ac.id
Thesis advisor	Al Haromainy, Muhammad Muharrom	NIDN0701069503	muhammad.muharrom.if@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Hafizh Kennandya Maulana

Date Deposited:

18 Jun 2025 01:58

Last Modified:

18 Jun 2025 02:52

URI:

https://repository.upnjatim.ac.id/id/eprint/37991