# hukenovs/hagrid

HAnd Gesture Recognition Image Dataset

Repository: https://github.com/hukenovs/hagrid
Canonical: https://ross.abutalabs.com/products/hagrid
Homepage: https://arxiv.org/abs/2206.08219
Language: Python
License Family: other
Topics: computer-vision, dataset, deep-learning, gesture-recognition, gestures-classification, image-classification, bounding-boxes, hands
Last push: 2025-02-27T13:24:21+00:00

## Health v2 (maintenance only)
Score: 36/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 8, release rhythm 35, longevity 100
- inputs: {"age_days": 1540, "days_push": 552, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1048, forks 149 (observed 2026-08-28T04:03:22.401380+00:00)

## What it is
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
- artifact type: dataset
- maturity: active
- function: computer-vision, machine-learning, image-processing
- domain: computer-vision, machine-learning, deep-learning
- platform: python, cross-platform
- tags: hand-gesture-recognition, image-dataset, bounding-boxes, gesture-classification, object-detection, video-conferencing

## Member repositories
- hukenovs/hagrid (main) score 36

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:22.401380+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:00:44.237149+00:00, confidence not recorded.
  - readme: https://github.com/hukenovs/hagrid (fetched 2026-08-28T04:03:22.401380+00:00, sha b4064f2574f8)
  - homepage: https://arxiv.org/abs/2206.08219 (fetched 2026-08-29T13:02:34.902387+00:00, sha f23fbdf7adbb)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T13:02:34.911650+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T13:02:34.915493+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T13:02:34.917478+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T13:02:34.913684+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.