Klasifikasi Kualitas Biji Kopi Arabika Menggunakan Algoritma Faster Region Convolutional Neural Network (Faster R-Cnn) dan Convolutional Neural Network (Cnn)

Pratama, Gede Ardi (2024) Klasifikasi Kualitas Biji Kopi Arabika Menggunakan Algoritma Faster Region Convolutional Neural Network (Faster R-Cnn) dan Convolutional Neural Network (Cnn). Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 20081010018.-cover.pdf Download (1MB)
	Text (Bab 1) 20081010018.-bab1.pdf Download (32kB)
	Text (Bab 2) 20081010018.-bab2.pdf Restricted to Repository staff only until 12 July 2026. Download (485kB)
	Text (Bab 3) 20081010018.-bab3.pdf Restricted to Repository staff only until 12 July 2026. Download (290kB)
	Text (Bab 4) 20081010018.-bab4.pdf Restricted to Repository staff only until 12 July 2026. Download (822kB)
	Text (Bab 5) 20081010018.-bab5.pdf Download (13kB)
	Text (Daftar Pustaka) 20081010018.-daftarpustaka.pdf Download (153kB)

Abstract

Coffee is a plantation product widely cultivated in various countries, including Indonesia. The journey of coffee from harvest to the cup is quite lengthy, involving several stages such as harvesting and grinding the coffee beans into powder ready for brewing. One of the processes in coffee production is coffee grading, which determines the quality of the coffee beans before they reach the market or our cups. Since the grading is done bean by bean, it can be very time-consuming if done manually. Therefore, this study introduces the methods of Faster R-CNN and CNN VGG-16 for classifying the quality of coffee beans. The two algorithms differ in their processes; Faster R-CNN uses a Region Proposal Network (RPN), whereas CNN with the VGG-16 architecture does not use an RPN. The Faster R-CNN algorithm achieved the best accuracy results with a training data split of 60%, validation data of 20%, and test data of 20%, attaining an accuracy weight of 93%. The VGG-16 algorithm obtained a lower accuracy result of 86%.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Puspaningrum, Eva Yulia	NIDN0005078908	evapuspaningrum.if@upnjatim.ac.id
Thesis advisor	Maulana, Hendra	NIDN1423128301	hendra.maulana.if@upnjatim.ac.id

Subjects:

Q Science > Q Science (General)
T Technology > T Technology (General) > T385 Computer Graphics

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Gede Ardi Pratama

Date Deposited:

12 Jul 2024 09:34

Last Modified:

12 Jul 2024 09:34

URI:

https://repository.upnjatim.ac.id/id/eprint/25929