Saddle: Fast and repeatable features with good coverage.

Javier Aldana-Iuit Dmytro Mishkin Ondrej Chum Jiri Matas

Published in: Image Vis. Comput. (2020)

Keyphrases

low level
feature vectors
feature space
feature extraction
rich set
benchmark datasets
feature set
data mining
database systems
high dimensional
high level
prior knowledge
clustering algorithm
classification accuracy
information retrieval
key features
extracted features
databases