Constructing Binary Descriptors with a Stochastic Hill Climbing Search
Computer Vision and Pattern Recognition
2016-08-07 v2
Abstract
Binary descriptors of image patches provide processing speed advantages and require less storage than methods that encode the patch appearance with a vector of real numbers. We provide evidence that, despite its simplicity, a stochastic hill climbing bit selection procedure for descriptor construction defeats recently proposed alternatives on a standard discriminative power benchmark. The method is easy to implement and understand, has no free parameters that need fine tuning, and runs fast.
Keywords
Cite
@article{arxiv.1501.04782,
title = {Constructing Binary Descriptors with a Stochastic Hill Climbing Search},
author = {Nenad Markuš and Igor S. Pandžić and Jörgen Ahlberg},
journal= {arXiv preprint arXiv:1501.04782},
year = {2016}
}