I'm looking for the NTU-HD dataset (a hand gesture dataset; each gesture consists of a color image and the corresponding depth map).
The reference article is Robust hand gesture recognition based on finger-earth mover's distance with a commodity depth camera.
NTU = Nanyang Technical University, Singapore
From Hand Gesture Recognition at Nanyang Technical University, Singapore:
We have collected a 10-gesture hand gesture dataset with Kinect sensor which contains both color images and depth maps. Our dataset is collected under cluttered background, which includes 10 subjects × 10 gestures/subject × 10 cases/gesture = 1000 cases. Download here.
(Please cite the papers to use the dataset)
Hint Found by googling Robust hand gesture recognition based on finger-earth mover's distance with a commodity depth camera site:ntu.edu.sg
