Open AccessQuantisation‐free binary feature aggregation for fast image representation
Author(s) -
Lee S.,
Yang H.S.
Publication year - 2017
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
ISSN - 1350-911X
DOI - 10.1049/el.2017.2501
Subject(s) - representation (politics) , binary number , feature (linguistics) , histogram , image (mathematics) , binary image , pattern recognition (psychology) , artificial intelligence , computer science , feature detection (computer vision) , local binary patterns , image processing , algorithm , mathematics , computer vision , arithmetic , linguistics , philosophy , politics , political science , law
A method for aggregating binary features to represent an image in a single vector is proposed. Binary features are decomposed into several sub‐features to permit the individual aggregation of each sub‐feature into a histogram. The method is completely quantisation‐free, enabling exceptionally fast image representation. Experimental results demonstrate that the method is a competitive alternative for image representation when runtime efficiency is crucial.