Summary of Advanced Arabic Alphabet Sign Language Recognition Using Transfer Learning and Transformer Models, by Mazen Balat et al.
Advanced Arabic Alphabet Sign Language Recognition Using Transfer Learning and Transformer Models
by Mazen Balat, Rewaa Awaad, Hend Adel, Ahmed B. Zaky, Salah A. Aly
First submitted to arxiv on: 1 Oct 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel approach to recognizing Arabic Alphabet Sign Language (ArSL) is proposed, combining deep learning methods with transfer learning and transformer-based models. The study evaluates the performance of various variants on two publicly available datasets: ArSL2018 and AASL. Pre-trained CNN architectures like ResNet50, MobileNetV2, and EfficientNetB7, as well as transformer models such as Google ViT and Microsoft Swin Transformer, are fine-tuned on these datasets to capture unique features of Arabic sign language motions. The methodology achieves high recognition accuracy, up to 99.6% on ArSL2018 and 99.43% on AASL, surpassing previous state-of-the-art approaches. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Arabic-speaking deaf and hard-of-hearing people can now communicate more easily thanks to a new method for recognizing Arabic Alphabet Sign Language (ArSL). This approach uses deep learning and special models to recognize the signs. The researchers tested different versions of this method on two big datasets: ArSL2018 and AASL. They even used powerful computer models like ResNet50, MobileNetV2, and EfficientNetB7 to help with recognition. The results show that their method is really accurate, with a success rate of 99.6% or more. This breakthrough can make communication more inclusive for Arabic-speaking deaf and hard-of-hearing people. |
Keywords
» Artificial intelligence » Cnn » Deep learning » Transfer learning » Transformer » Vit
