KLASIFIKASI GAMBAR ANIME VULGAR MENGGUNAKAN METODE CONVOLUTION NEURAL NETWORK

DARMAWAN, MUHAMMAD REDHO and Fachrurrozi, Muhammad and Rachmatullah, Muhammad Naufal (2025) KLASIFIKASI GAMBAR ANIME VULGAR MENGGUNAKAN METODE CONVOLUTION NEURAL NETWORK. Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_55201_09021282025043_Cover.jpg]
Preview
Image
RAMA_55201_09021282025043_Cover.jpg - Cover Image
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Preview
[thumbnail of RAMA_55201_09021282025043.pdf] Text
RAMA_55201_09021282025043.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (3MB) | Request a copy
[thumbnail of RAMA_55201_09021282025043_TURNITIN.pdf] Text
RAMA_55201_09021282025043_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (3MB) | Request a copy
[thumbnail of RAMA_55201_09021282025043_0222058001_0001129204_01_front_ref.pdf] Text
RAMA_55201_09021282025043_0222058001_0001129204_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (1MB)
[thumbnail of RAMA_55201_09021282025043_0222058001_0001129204_02.pdf] Text
RAMA_55201_09021282025043_0222058001_0001129204_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (409kB) | Request a copy
[thumbnail of RAMA_55201_09021282025043_0222058001_0001129204_03.pdf] Text
RAMA_55201_09021282025043_0222058001_0001129204_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (201kB) | Request a copy
[thumbnail of RAMA_55201_09021282025043_0222058001_0001129204_04.pdf] Text
RAMA_55201_09021282025043_0222058001_0001129204_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (406kB) | Request a copy
[thumbnail of RAMA_55201_09021282025043_0222058001_0001129204_05.pdf] Text
RAMA_55201_09021282025043_0222058001_0001129204_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[thumbnail of RAMA_55201_09021282025043_0222058001_0001129204_06.pdf] Text
RAMA_55201_09021282025043_0222058001_0001129204_06.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (33kB) | Request a copy
[thumbnail of RAMA_55201_09021282025043_0222058001_0001129204_07_ref.pdf] Text
RAMA_55201_09021282025043_0222058001_0001129204_07_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (76kB) | Request a copy

Abstract

Anime is very popular and highly demanded by many circles ranged from children to adults. However, not all anime is appropriate for all ages. There are some anime that contains vulgar content which can be unintentionally exposed to children. This research aims to create a classifier that can seperate anime content that contains vulgarity using the convolution neural network method. The architecture of convolution neural network method that is used as the model in this research is an EfficientNet architecture using anime pictures dataset which contains 2869 safe images and 2734 vulgar images. This research is done by creating models using variations of batch size, epoch, and learning rate which has been previously established and evaluate them using confusion matrix and accuracy, precision, recall, and F1-score metrics. The results from this research shows the model is able to classify vulgar anime images with the highest accuracy being 96,79%. This research shows that convolution neural network method can be used to classify vulgar content although there are some room for improvement especially in collecting dataset with more defined criteria.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Klasifikasi gambar, anime, konten vulgar, convolution neural network, EfficientNet, akurasi
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: Muhammad Redho Darmawan
Date Deposited: 07 Sep 2025 08:13
Last Modified: 07 Sep 2025 08:13
URI: http://repository.unsri.ac.id/id/eprint/183622

Actions (login required)

View Item View Item