Shypd.aiThe largest open index of AI toolshagrid is an open-source image dataset for hand gesture recognition. It provides a large collection of FullHD RGB images for training and testing HGR systems, supporting both image classification and detection tasks.
Trending
About
HaGRID (HAnd Gesture Recognition Image Dataset) is a comprehensive, open-source dataset designed for developing and evaluating hand gesture recognition (HGR) systems. The latest version, HaGRIDv2, boasts over 1 million FullHD RGB images across 33 gesture classes, plus a 'no_gesture' class for natural hand postures. It supports both image classification and detection tasks, making it suitable for applications in video conferencing, home automation, and automotive sectors. The dataset includes diverse lighting conditions, subject distances, and a robust train/validation/test split by user ID. Additionally, HaGRID provides pre-trained models for gesture and hand detection (YOLOv10x, YOLOv10n, SSDLiteMobileNetV3Large) and full-frame classification (MobileNetV3, VitB16, ResNet, ConvNeXt), along with tools for converting annotations to YOLO and COCO formats. It also features a novel algorithm for dynamic gesture recognition trained exclusively on static gestures.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
