Arabic Sign Language Sentences for Real-Time YOLOv8 Detection

A dataset of images annotated for YOLOv8, designed for real-time detection of Arabic Sign Language (ArSL) sentences and words. The dataset's size, creator, and creation date are not specified in the provided information.

Use Cases

• Train a YOLOv8 model to detect and classify individual Arabic Sign Language words from image frames.
• Develop a real-time sentence-level Arabic Sign Language translator using object detection on video streams.
• Benchmark the performance of YOLOv8 against other architectures for sign language recognition tasks.

Strengths

• Annotated specifically for the YOLOv8 object detection framework, ensuring compatibility.
• Focuses on real-time application, suggesting optimization for speed and latency.

Limitations

• The total number of images, annotations, and vocabulary size are unknown.
• Potential for geographic or dialect bias within Arabic Sign Language is unspecified.
• Label quality, annotation consistency, and class balance are not documented.

Provenance

Source

Kaggle

Collection Method

Presumably images collected and annotated for computer vision training, but the specific gathering process is unknown.

Geography

Likely focused on regions using Arabic Sign Language, but specific coverage is unknown.