PENGEMBANGAN GAME DOODLE DENGAN PENILAIAN GAMBAR OTOMATIS MENGGUNAKAN MODEL CNN

ADIMAS, MUHAMMAD AMIR and Anggina, Primanita (2025) PENGEMBANGAN GAME DOODLE DENGAN PENILAIAN GAMBAR OTOMATIS MENGGUNAKAN MODEL CNN. Undergraduate thesis, Sriwijaya University.

Preview	Image RAMA_55201_09021282126065_cover.jpg - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (363kB) | Preview
	Text RAMA_55201_09021282126065.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021282126065_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_55201_09021282126065_0206088901_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_55201_09021282126065_0206088901_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (356kB) | Request a copy
	Text RAMA_55201_09021282126065_0206088901_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (105kB) | Request a copy
	Text RAMA_55201_09021282126065_0206088901_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (477kB) | Request a copy
	Text RAMA_55201_09021282126065_0206088901_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021282126065_0206088901_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (9kB) | Request a copy
	Text RAMA_55201_09021282126065_0206088901_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (78kB) | Request a copy
	Text RAMA_55201_09021282126065_0206088901_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (193kB) | Request a copy

Abstract

In the era of artificial intelligence (AI) development, the integration of machine learning technology in games continues to advance. This study aims to develop a Convolutional Neural Network (CNN) model that functions as an automatic evaluation agent for doodle images in a drawing game. The CNN model is trained using the Google Quick Draw dataset to recognize images created by players. Evaluation results show that the developed CNN model with 331 labels achieves an accuracy of 0.83. Additionally, other evaluation metrics indicate precision between 0.6 to 0.96, recall between 0.51 and 0.98, and an F1-score between 0.56 and 0.96. The model's average prediction time is recorded at 0.002836 seconds, allowing for instant evaluation. The developed CNN model effectively provides feedback to players as long as the input images do not differ significantly from the shapes in the dataset.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	CNN, AI, Doodle, Google Quick Draw
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Adimas Muhammad Amir
Date Deposited:	20 May 2025 03:32
Last Modified:	20 May 2025 03:32
URI:	http://repository.unsri.ac.id/id/eprint/173350

Actions (login required)

View Item