Image of DETEKSI SISTEM ISYARAT BAHASA INDONESIA (SIBI) MENGGUNAKAN ARSITEKTUR CONVOLUTIONAL NEURAL NETWORK (CNN) DENGAN METODE RESNET-50 SECARA REAL-TIME

Skripsi

DETEKSI SISTEM ISYARAT BAHASA INDONESIA (SIBI) MENGGUNAKAN ARSITEKTUR CONVOLUTIONAL NEURAL NETWORK (CNN) DENGAN METODE RESNET-50 SECARA REAL-TIME

Penilaian

0,0

dari 5
Penilaian anda saat ini :  

Communication is essential in life but poses a significant barrier between the hearing-impaired community and the general public due to a lack of understanding of Sign Language. This research aims to develop a real-time detection system for the Indonesian Sign Language System (SIBI) to bridge this communication gap. The method employed is a Deep Learning architecture using a Convolutional Neural Network (CNN) with transfer learning from a ResNet-50 model pre-trained on the ImageNet dataset. The SIBI dataset used consists of 5,280 images covering 24 letters (A-Y). The data was split into training (70%), validation (15%), and test (15%) sets. Model training involved fine-tuning, data augmentation, and class weighting application. The best model M2 achieved an accuracy of 97.47%, precision of 97.72%, recall of 97.47%, and an F1-Score of 97.60% on the test data. The real-time system implementation using a webcam successfully detected and classified the 24 SIBI letters with an average accuracy of 99.5% and sufficient speed. The results prove that the ResNet-50 architecture is highly effective and accurate for real-time SIBI sign language detection, holding great potential to be developed into an inclusive communication aid.

Availability
Inventory Code Barcode Call Number Location Status
2507006247T185598T1855982025Central Library (Reference)Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1855982025
Publisher
Indralaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya.,
Collation
xiv, 93 hlm.; ilus.; tab.; 29 cm.
Language
Indonesia
ISBN/ISSN
-
Classification
419.07
Content Type
Text
Media Type
unmediated
Carrier Type
other (computer)
Edition
-
Subject(s)
Bahasa Isyarat
Prodi Sistem Komputer
Specific Detail Info
-
Statement of Responsibility
Other version/related
File Attachment
Comments
You must be logged in to post a comment