Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Context and Hierarchy in a Probabilistic Image Model
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Hi-index | 0.10 |
The paper provides lower bounds on the number of all possible images that appear meaningful to a human observer as well as the number of all possible images that appear pair-wise distinct to a human observer. These numbers suggest that it is impractical to construct training or testing sets of images that are dense in the set of all images unless the class of images is restricted.