Egyptian Sign Language

Each video demonstrates a single ESL sign performed by a native signer under consistent lighting and background conditions. The goal of this dataset is to support the development and benchmarking of vision-based sign language recognition systems, especially those targeting Arabic-speaking communities. 📚 Key Features: 50+ distinct ESL classes, representing everyday words and phrases frequently used in Egyptian culture. 3~10 video samples per class, totaling 400+ labeled videos.

Filmed using a Logitech HD Webcam at 720p resolution and 30 FPS. The dataset includes natural signer variations (slight movement differences), supporting real-world model training.