Context-aware features and robust image representations

Published: 01 Jan 2014, Last Modified: 08 Apr 2025J. Vis. Commun. Image Represent. 2014EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•No a priori assumption is made on the type of structure to be extracted.•Suitable for robust image representation.•Different instances of the method can be created.•In some cases, context-aware features can be complemented with strictly local features without inducing redundancy.•Repeatability scores are comparable to state-of-the-art methods.
Loading