BISINDO (Bahasa Isyarat Indonesia) Sign Language Recognition Using Deep Learning

Abstract

Sign language recognition plays a crucial role in facilitating communication for individuals with hearing impairments. This paper presents a deep learning-based approach for recognizing Bahasa Isyarat Indonesia (BISINDO), the sign language used in Indonesia. The proposed system employs convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to automatically extract features from sign language gestures and classify them into corresponding linguistic units. The dataset used for training and evaluation consists of annotated BISINDO sign language videos. Preprocessing techniques such as normalization and augmentation are applied to enhance the robustness of the model. Experimental results demonstrate the effectiveness of the proposed approach in accurately recognizing BISINDO sign language gestures, achieving state-of-the-art performance compared to existing methods. The developed system shows promising potential for real-world applications in enhancing communication accessibility for the hearing-impaired community in Indonesia.