hukenovs/hagrid resource

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1048 stars · 149 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

HaGRID is a large-scale hand gesture recognition image dataset containing over one million FullHD RGB images across 33 gesture classes plus a no_gesture class, with bounding box annotations. It supports training models for gesture classification and hand detection tasks, with pretrained models and a dynamic gesture recognition algorithm also available.

Use cases

• train a hand gesture classifier on a large labeled image dataset
• build gesture detection models for video conferencing apps
• pretrain a hand detection model with bounding box annotations
• recognize dynamic gestures like swipes from static gesture data
• build touchless smart home control using hand gestures
• train gesture recognition for automotive in-cabin systems

When to choose

• you need a large, diverse dataset of hand gestures with bounding boxes
• you are building gesture-based human-computer interaction systems
• you need varied lighting conditions and subject distances in training data
• you want pretrained gesture or hand detection models as a starting point

When to avoid

• you need real-time gesture recognition without training your own model and the companion repos don't fit
• you need fine-grained finger tracking or 3D hand pose rather than gesture classes
• you need a permissively licensed dataset and cannot work with the unspecified license terms
• your application requires small or non-FullHD images only

Facets

dataset · maturity active

computer-vision machine-learning image-processing computer-vision machine-learning deep-learning python cross-platform hand-gesture-recognition image-dataset bounding-boxes gesture-classification object-detection video-conferencing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="hukenovs/hagrid")