<![CDATA[Communication barriers between people with hearing impairments and the general public remain a significant challenge in everyday interactions. BISINDO is a widely used sign language in Indonesia’s deaf community; however, public understanding of sign language remains limited. This study aims to develop a hand image-based BISINDO alphabet classification system using a Convolutional Neural Network model and implement the trained model in an Android application. The public dataset used consists of 10,686 BISINDO alphabet letter images representing 26 classes from A to Z, obtained from Kaggle. All images were preprocessed, including resizing, normalization, and data augmentation to increase the diversity of the training data. The model was trained and evaluated using accuracy, precision, recall, and F1-score metrics. The evaluation results showed that the model achieved a validation accuracy of 94.21%, precision of 94.38%, recall of 94.20%, and F1-score of 94.21%. The trained model was then integrated into an Android application named IsyaratKu using the Flutter framework and the Dart programming language. The implementation results showed that the application successfully recognized the letters of the BISINDO alphabet through camera and gallery input and performed effectively on Android devices. These results indicate that the CNN can classify the 26 BISINDO alphabet classes with validation accuracy above 94% and can be deployed in an Android application for offline alphabet classification.]]>
Copyrights © 2026
