Enhancing ASL Recognition with GCNs and Successive Residual Connections
This work addresses ASL recognition for improved human-computer interaction, representing a strong specific gain in this domain.
This paper tackled the problem of American Sign Language (ASL) recognition by integrating Graph Convolutional Networks (GCNs) with successive residual connections, achieving a validation accuracy of 99.14%.
This study presents a novel approach for enhancing American Sign Language (ASL) recognition using Graph Convolutional Networks (GCNs) integrated with successive residual connections. The method leverages the MediaPipe framework to extract key landmarks from each hand gesture, which are then used to construct graph representations. A robust preprocessing pipeline, including translational and scale normalization techniques, ensures consistency across the dataset. The constructed graphs are fed into a GCN-based neural architecture with residual connections to improve network stability. The architecture achieves state-of-the-art results, demonstrating superior generalization capabilities with a validation accuracy of 99.14%.