Pengenalan Citra Makanan Tradisional Indonesia Menggunakan Deep Learning

Syarmadayu, Diaz Batara (2022) Pengenalan Citra Makanan Tradisional Indonesia Menggunakan Deep Learning. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

[img] Text
07211740000017-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 April 2024.

Download (9MB) | Request a copy

Abstract

Makanan sebagai salah satu kebutuhan pokok manusia kian berkembang dalam ragam pada tiap - tiap daerah dan negara di dunia. Makanan dari daerah - daerah tersebut memiliki keunikan masing - masing yang dapat ditentukan dari rasa, visual, maupun bahan. Indonesia dengan banyaknya daerah yang dimiliki tiap - tiap daerahnya memiliki makanan khas atau tradisional masing - masing, yang tidak semua orang mengetahui secara betul nama dan asal dari tiap makanan yang tersedia. Terdapat sebuah solusi terdapat hal ini yaitu dengan bantuan komputer melalui pengenalan citra. Pengenalan citra merupakan cabang studi dari pengolahan citra pada visi komputer dan deep learning yang tujuannya agar sebuah komputer dapat mengenali citra, dalam hal ini makanan, layaknya dari sudut pandang manusia. Pada penelitian ini dilakukan pengujian metode pengenalan citra yang diimplementasikan menggunakan Convolutional Neural Network yang mendapatkan hasil akurasi terbaik sebesar 55% untuk mengklasifikasi citra makanan tradisional dari 34 provinsi Indonesia. ===================================================================================================== Food as one of the basic human needs has been growing in terms of variety across the world, in each country and its respective regions. Food from such regions has its own uniqueness that differs each from others which can be determined from taste, visuals, and ingredients. Indonesia with its many regions, each has its own many unique or commonly known as traditional food, which not even every citizen present recognizes the exact name and from each of the available foods. A solution is present to help people recognizes foods they have never encountered, namely with the help of computers through image recognition. Image recognition is a branch of study from image processing in computer vision and deep learning which goal is to simulate how a computer can recognize images in the same way humans perceive and recognize things, in this case, food. In this book, the study of image recognition method is implemented using Convolutional Neural Network to classify traditional food datasets from 34 provinces of Indonesia which the model successfully achieve a 55% correct prediction accuracy.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Pengenalan, Convolutional Neural Network, Makanan, Recognition, Food
Subjects: Q Science > Q Science (General) > Q325.5 Machine learning.
Q Science > QA Mathematics > QA76.6 Computer programming.
R Medicine > R Medicine (General) > R858 Deep Learning
T Technology > T Technology (General) > T57.5 Data Processing
Divisions: Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Computer Engineering > 90243-(S1) Undergraduate Thesis
Depositing User: Diaz Batara Syarmadayu
Date Deposited: 20 Feb 2022 04:50
Last Modified: 20 Feb 2022 04:50
URI: https://repository.its.ac.id/id/eprint/94657

Actions (login required)

View Item View Item