KLASIFIKASI CITRA MAKANAN MENGGUNAKAN ARSITEKTUR VGG-16 UNTUK IDENTIFIKASI JENIS MAKANAN SEBAGAI DASAR INFORMASI KALORI

Muhammad Raditya Putra, . (2025) KLASIFIKASI CITRA MAKANAN MENGGUNAKAN ARSITEKTUR VGG-16 UNTUK IDENTIFIKASI JENIS MAKANAN SEBAGAI DASAR INFORMASI KALORI. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (633kB)
[img] Text
AWAL.pdf
Download (2MB)
[img] Text
BAB 1.pdf
Restricted to Repository UPNVJ Only
Download (2MB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (7MB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (4MB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (10MB)
[img] Text
BAB 5.pdf
Download (604kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (1MB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (104kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (6MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (12MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (809kB)

Abstract

The issue of managing dietary calorie intake has become increasingly important in efforts to prevent obesity and non-communicable diseases of modern society. Many individuals face challenges in monitoring their eating patterns manually due to limited time and access to information. This study aims to develop an image classification model architecture using a Convolutional Neural Network (CNN) with the VGG-16 architecture, capable of identifying types of food and providing calorie information through a mobile app implementation. The model is implemented in an Android-based mobile application. Image data were collected by scraping 1,600 food images representing 16 categories of Indonesian dishes from the Bing search engine. The data processed through augmentation, normalization, and resizing to 224×224 pixels. The model was trained using VGG-16 architecture and converted into TFLite format to ensure optimal performance on mobile devices. The best-performing model achieved a testing accuracy of 90%, with a precision of 90.75%, recall of 90%, and an F1-score of 90% and was evaluated through black-box testing with an average response time of five seconds per classification. This study shows that AI-based technology can be effectively implemented in mobile applications to help the public in monitoring their calorie intake with more practical, efficient, and accurate.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 2110511004] [Pembimbing 1: Supriyanto] [Pembimbing 2: Kharisma Wiati Gusti] [Penguji 1: Indra Permana Solihin] [Penguji 2: Muhammad Adrezo]
Uncontrolled Keywords: Image Classification, VGG-16, CNN, Food Calories, Mobile Application.
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: MUHAMMAD RADITYA PUTRA
Date Deposited: 06 Aug 2025 06:33
Last Modified: 06 Aug 2025 06:33
URI: http://repository.upnvj.ac.id/id/eprint/37492

Actions (login required)

View Item View Item