T-SignSys: An Efficient CNN-Based Turkish Sign Language Recognition System

Sign language (SL) is a communication tool playing a crucial role in facilitating the daily life of deaf or hearing-impaired people. Large varieties in the existing SLs and lack of interpretation knowledge in the general public lead to a communication barrier between the deaf and hearing communities. This issue has been addressed by automated sign language recognition (SLR) systems, mostly proposed for American Sign Language (ASL) with limited number of research studies on the other SLs. Consequently, this paper focuses on static Turkish Sign Language (TSL) recognition for its alphabets and digits by proposing an efficient novel Convolutional Neural Network (CNN) model. Our proposed CNN model comprises 9 layers, of which 6 layers are employed for feature extraction, and the remaining 3 layers are adopted for classification. The model is prevented from overfitting while dealing with small-scale datasets by benefiting from two regularization techniques: 1) ignoring a specified portion of neurons during training by applying a dropout layer, and 2) applying penalties during loss function optimization by employing L₂ kernel regularizer in the convolution layers. The arrangement of the layers, learning rate, optimization technique, model hyper-parameters, and dropout layers are carefully adjusted so that the proposed CNN model can recognize both TSL alphabets and digits fast and accurately. The feasibility of our proposed T-SignSys is investigated through a comprehensive ablation study. Our model is evaluated on two datasets of TSL alphabets and digits with an accuracy of 97.85% and 99.52%, respectively, demonstrating its competitive performance despite straightforward implementation.