American Sign Language Recognition Using Random Forest Classifier

Sign language recognition plays an important role in enabling communication between the deaf community and the rest of society. Although deep learning methods are dominant in this area, they are normally quite computationally expensive and require a large amount of data, making them unsuitable for lightweight applications. Here, we propose an efficient and interpretable approach based on the Random Forest classifier for sign language recognition system. Using the ASL Alphabet dataset which consist of American sign language, the system processes images through a robust feature extraction pipeline followed by Random Forest classification. The model achieved an impressive accuracy of 99%, showing its effectiveness in hand gesture recognition. This research demonstrates Random Forest's ability to obtain high performance at low computational cost, making it appropriate for real-time applications. The proposed system shows promise for incorporation into assistive technologies and can fill the communication gap for the hearing-impaired community.