THE COMPARISON OF EFFICIENTNETB0, RESNET50, AND INCEPTIONV3 ARCHITECTURES FOR SIGN LANGUAGE RECOGNITION

ANGELO, CHRISTOPHER MARCO (2025) THE COMPARISON OF EFFICIENTNETB0, RESNET50, AND INCEPTIONV3 ARCHITECTURES FOR SIGN LANGUAGE RECOGNITION. S1 thesis, Universitas Mercu Buana Jakarta.

[img]
Preview
Text (HAL COVER)
01 COVERS.pdf

Download (602kB) | Preview
[img] Text (BAB I)
02 CHAPTER 1.pdf
Restricted to Registered users only

Download (91kB)
[img] Text (BAB II)
03 CHAPTER 2.pdf
Restricted to Registered users only

Download (141kB)
[img] Text (BAB III)
04 CHAPTER 3.pdf
Restricted to Registered users only

Download (329kB)
[img] Text (BAB IV)
05 CHAPTER 4.pdf
Restricted to Registered users only

Download (74kB)
[img] Text (BAB V)
06 CHAPTER 5.pdf
Restricted to Registered users only

Download (82kB)
[img] Text (DAFTAR PUSTAKA)
07 REFERENCES.pdf
Restricted to Registered users only

Download (168kB)
[img] Text (LAMPIRAN)
08 ATTACHMENT.pdf
Restricted to Registered users only

Download (955kB)

Abstract

This study explores the application of Convolutional Neural Networks (CNN) in recognizing sign language through image processing techniques, with a specific focus on the EfficientNet architecture. Sign language is a vital mode of communication for the hearing impaired, yet it remains underutilized due to limited understanding and a lack of tools for translation. The research aims to develop an image recognition model that accurately interprets sign language gestures by leveraging CNNs, particularly the EfficientNet model, known for its computational efficiency and high performance. EfficientNet's scalable architecture enhances the model's ability to process images of hand signs, learning to identify and translate them into text with improved accuracy and reduced computational requirements. Experimental results demonstrate that EfficientNet outperforms traditional CNN architectures in distinguishing between a variety of sign language gestures, making this approach highly promising for real-time applications. This study contributes to the field of assistive technologies by potentially bridging communication barriers for the hearing impaired through an efficient and robust solution. Keywords: Sign Language, Image Processing, CNN, EfficientNet.

Item Type: Thesis (S1)
Call Number CD: FIK/INFO. 25 164
NIM/NIDN Creators: 41521010106
Uncontrolled Keywords: Sign Language, Image Processing, CNN, EfficientNet.
Subjects: 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika
000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 006 Special Computer Methods/Metode Komputer Tertentu > 006.3 Artificial Intelligence/Kecerdasan Buatan > 006.32 Neural Nets (Neural Network)/Jaringan Saraf Buatan
000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 006 Special Computer Methods/Metode Komputer Tertentu > 006.4 Computer Pattern Recognition/Pola Pengenalan Komputer > 006.42 Barcoding/Barcode > 006.424 Optical Character Recognition (OCR)/OCR
400 Language/Bahasa > 410 Linguistics/Linguistik > 419 Sign Language/Bahasa Isyarat
Divisions: Fakultas Ilmu Komputer > Informatika
Depositing User: khalimah
Date Deposited: 26 Aug 2025 08:08
Last Modified: 26 Aug 2025 08:08
URI: http://repository.mercubuana.ac.id/id/eprint/97112

Actions (login required)

View Item View Item