IMPLEMENTASI DEEP LEARNING UNTUK DETEKSI REAL-TIME BAHASA ISYARAT SIBI MENGGUNAKAN BASIS ARSITEKTUR MOBILENETV2 BERBASIS ANDROID

MUZAKKI, AHMAD NAUFAL and Arsalan, Osvari (2024) IMPLEMENTASI DEEP LEARNING UNTUK DETEKSI REAL-TIME BAHASA ISYARAT SIBI MENGGUNAKAN BASIS ARSITEKTUR MOBILENETV2 BERBASIS ANDROID. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021282126117.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_55201_09021282126117_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (24MB) | Request a copy
	Text RAMA_55201_09021282126117_0028068806_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_55201_09021282126117_0028068806_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_55201_09021282126117_0028068806_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (272kB) | Request a copy
	Text RAMA_55201_09021282126117_0028068806_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_55201_09021282126117_0028068806_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (660kB) | Request a copy
	Text RAMA_55201_09021282126117_0028068806_06.pdf - Updated Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (159kB) | Request a copy
	Text RAMA_55201_09021282126117_0028068806_07_ref.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (130kB) | Request a copy
	Text RAMA_55201_09021282126117_0028068806_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (217kB) | Request a copy

Abstract

This research focuses on implementing a deep learning model for real-time recognition of SIBI (Sistem Isyarat Bahasa Indonesia) sign language using MobileNetV2 architecture on the Android platform. The increasing need for communication tools to assist the deaf community motivates the development of a mobile application that translates SIBI hand gestures into readable information. MobileNetV2, optimized with transfer learning and TensorFlow Lite, ensures both computational efficiency and high accuracy for mobile devices. The resulting application detects and classifies the 26 alphabetic SIBI hand gestures in real-time, achieving outstanding performance with over 99% accuracy during testing. This research contributes to assistive technology development, offering a practical and accessible communication tool for the deaf community while advancing deep learning applications in mobile environments.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	SIBI, MobileNetV2, Deep Learning, Bahasa Isyarat, Pengenalan Real-time, TensorFlow Lite.
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Ahmad Naufal Muzakki
Date Deposited:	14 Jan 2025 01:28
Last Modified:	14 Jan 2025 01:28
URI:	http://repository.unsri.ac.id/id/eprint/163860

Actions (login required)

View Item