Information Theoretic Rotationwise Robust Binary Descriptor Learning

Youssef El Rhabi 1 Loic Simon 1 Luc Brun 1 Josep Llados 2 Felipe Lumbreras 2
1 Equipe Image - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
Abstract : In this paper, we propose a new data-driven approach for binary descriptor selection. In order to draw a clear analysis of common designs, we present a general information-theoretic selection paradigm. It encompasses several standard binary descriptor construction schemes, including a recent state-of-the-art one named BOLD. We pursue the same endeavor to increase the stability of the produced descriptors with respect to rotations. To achieve this goal, we have designed a novel of-fline selection criterion which is better adapted to the online matching procedure. The effectiveness of our approach is demonstrated on two standard datasets, where our descriptor is compared to BOLD and to several classical descriptors. In particular, it emerges that our approach can reproduce equivalent if not better performance as BOLD while relying on twice shorter descriptors. Such an improvement can be influential for real-time applications.
Document type :
Conference papers
Liste complète des métadonnées
Contributor : Luc Brun <>
Submitted on : Saturday, December 17, 2016 - 8:01:33 PM
Last modification on : Thursday, February 7, 2019 - 5:45:21 PM
Document(s) archivé(s) le : Tuesday, March 21, 2017 - 12:50:45 AM


Files produced by the author(s)


  • HAL Id : hal-01418934, version 1


Youssef El Rhabi, Loic Simon, Luc Brun, Josep Llados, Felipe Lumbreras. Information Theoretic Rotationwise Robust Binary Descriptor Learning. Structural, Syntactic, and Statistical Pattern Recognition , Nov 2016, Mérida, Mexico. pp.368--378. ⟨hal-01418934⟩



Record views


Files downloads