KLASIFIKASI CITRA KUE TRADISIONAL MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK (CNN)

PUTRA, INDRA JULIANSYAH and Rini, Dian Palupi and Rizqie, M. Qurhanul (2025) KLASIFIKASI CITRA KUE TRADISIONAL MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK (CNN). Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_55201_09021182126016_cover.jpg]
Preview
Image
RAMA_55201_09021182126016_cover.jpg - Cover Image
Available under License Creative Commons Public Domain Dedication.

Download (89kB) | Preview
[thumbnail of RAMA_55201_09021182126016.pdf] Text
RAMA_55201_09021182126016.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (4MB) | Request a copy
[thumbnail of RAMA_55201_09021182126016_TURNITIN.pdf] Text
RAMA_55201_09021182126016_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (6MB) | Request a copy
[thumbnail of RAMA_55201_09021182126016_0023027804_0203128701_01_front_ref.pdf] Text
RAMA_55201_09021182126016_0023027804_0203128701_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (689kB)
[thumbnail of RAMA_55201_09021182126016_0023027804_0203128701_02.pdf] Text
RAMA_55201_09021182126016_0023027804_0203128701_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (831kB) | Request a copy
[thumbnail of RAMA_55201_09021182126016_0023027804_0203128701_03.pdf] Text
RAMA_55201_09021182126016_0023027804_0203128701_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (417kB) | Request a copy
[thumbnail of RAMA_55201_09021182126016_0023027804_0203128701_04.pdf] Text
RAMA_55201_09021182126016_0023027804_0203128701_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (871kB) | Request a copy
[thumbnail of RAMA_55201_09021182126016_0023027804_0203128701_05.pdf] Text
RAMA_55201_09021182126016_0023027804_0203128701_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (358kB) | Request a copy
[thumbnail of RAMA_55201_09021182126016_0023027804_0203128701_06.pdf] Text
RAMA_55201_09021182126016_0023027804_0203128701_06.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (9kB) | Request a copy
[thumbnail of RAMA_55201_09021182126016_0023027804_0203128701_07_ref.pdf] Text
RAMA_55201_09021182126016_0023027804_0203128701_07_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (89kB) | Request a copy
[thumbnail of RAMA_55201_09021182126016_0023027804_0203128701_08_lamp.pdf] Text
RAMA_55201_09021182126016_0023027804_0203128701_08_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (3kB) | Request a copy

Abstract

Traditional cake image classification aims to recognize various types of cakes based on visual features, thereby assisting in the effort to introduce traditional cakes. Indonesian traditional cakes hold significant cultural value that must be preserved while also presenting substantial potential in supporting tourism through culinary tourism. This study develops a classification model based on Convolutional Neural Networks (CNN) to identify eight types of Indonesian traditional cakes namely Dadar Gulung, Kastengel, Klepon, Lapis, Lumpur, Risoles, Serabi, and Putri Salju. The dataset was sourced from Kaggle and further enriched by utilizing the Google Custom Search API. The research stages included image preprocessing such as cropping and resizing, splitting the dataset into training (70%), validation (15%), and testing (15%) sets, and augmenting the data to increase variability. The model was trained using two CNN architectures, Xception and VGG-19, with 24 fine-tuning scenarios involving various combinations of batch size, learning rate, and layer settings. The results showed that Xception outperformed VGG-19 in all metrics. Xception achieved the best performance with a configuration of unfreezing layers, a learning rate of 0,0001, and a batch size of 64, resulting in an accuracy of 97,38%, precision of 97,4%, recall of 97,38%, and F1-score of 97,38%. Meanwhile, VGG- 19 achieved its best performance with unfrozen layers, a learning rate of 0.00001, and a batch size of 32, yielding 96.46% accuracy, 96.48% precision, 96.46% recall, and 96.44% F1-score.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Kue tradisional Indonesia, Convolutional Neural Network, Xception, VGG-19, Klasifikasi Citra
Subjects: Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions: 09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User: Indra Juliansyah Putra
Date Deposited: 24 Mar 2025 04:12
Last Modified: 24 Mar 2025 04:12
URI: http://repository.unsri.ac.id/id/eprint/169996

Actions (login required)

View Item View Item