PERBANDINGAN ARSITEKTUR VISUAL GEOMETRY GROUP 16 (VGG 16) DAN VISUAL GEOMETRY GROUP 19 (VGG 19) DALAM MODEL KLASIFIKASI CITRA RIMPANG

Felicia Febriana, . (2023) PERBANDINGAN ARSITEKTUR VISUAL GEOMETRY GROUP 16 (VGG 16) DAN VISUAL GEOMETRY GROUP 19 (VGG 19) DALAM MODEL KLASIFIKASI CITRA RIMPANG. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (81kB)
[img] Text
AWAL.pdf
Download (608kB)
[img] Text
BAB 1.pdf
Download (86kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (377kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (133kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (588kB)
[img] Text
BAB 5.pdf
Download (71kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (76kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (79kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (48kB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (1MB)

Abstract

The rhizomes in Indonesia are diverse and difficult to distinguish. This study aims to compare the VGG16 and VGG19 models in classifying rhizome plant images. Two groups of datasets were used in this study, namely the intact rhizome dataset to show differences in shape, and the sliced rhizome dataset to show differences in color. Each dataset group consists of 100 data divided into five classes: ginger, lesser galangal, turmeric, galangal, and temulawak. Thus, a total of 200 data were used in this study. The datasets then underwent preprocessing, including cropping, resizing, and augmentation. The data were divided into three parts: training data, validation data, and test data, with an 80:10:10 ratio. Two models were built for each dataset group, namely VGG16 and VGG19, and their best accuracy performances were compared. The results showed that VGG19 achieved the highest accuracy of 90% in the intact rhizome dataset group. Moreover, VGG19 outperformed VGG16 overall in both dataset groups

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 1910511023] [Pembimbing: Jayanta] [Penguji 1: Nur Hafifah Matondang] [Penguji 2: Ria Astriratma]
Uncontrolled Keywords: classification, rhizome, VGG16, VGG19
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: Felicia Febriana
Date Deposited: 09 Aug 2023 05:18
Last Modified: 09 Aug 2023 05:18
URI: http://repository.upnvj.ac.id/id/eprint/25967

Actions (login required)

View Item View Item