<![CDATA[Sistem Bahasa Isyarat Indonesia (SIBI) is a visual communication medium used by individuals with hearing impairments; however, public awareness and understanding of sign language remain limited, creating significant communication barriers in daily life. This study aims to develop a SIBI alphabet recognition system based on deep learning by utilizing a Convolutional Neural Network (CNN) approach supported by computer vision using MediaPipe. The research stages include hand image acquisition, preprocessing through normalization and augmentation, and model training using a CNN architecture. The dataset is divided into 80% for training, 10% for validation, and 10% for testing to evaluate the model’s generalization performance. Experimental results show that the model achieves a training accuracy of 99.72% and a validation accuracy of 96%, indicating highly effective performance in real-time SIBI gesture classification. Therefore, this study contributes to the development of assistive technologies that facilitate inclusive communication for individuals with hearing impairments in Indonesia.]]>
Copyrights © 2026
