Enhancing ASL Recognition with GCNs and Successive Residual Connections
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909290455891968 |
|---|---|
| author | Sarkar, Ushnish Chakraborti, Archisman Samanta, Tapas Pal, Sarbajit Das, Amitabha |
| author_facet | Sarkar, Ushnish Chakraborti, Archisman Samanta, Tapas Pal, Sarbajit Das, Amitabha |
| contents | 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%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_09567 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing ASL Recognition with GCNs and Successive Residual Connections Sarkar, Ushnish Chakraborti, Archisman Samanta, Tapas Pal, Sarbajit Das, Amitabha Computer Vision and Pattern Recognition 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%. |
| title | Enhancing ASL Recognition with GCNs and Successive Residual Connections |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.09567 |