Fast Image Gradients Using Binary Feature Convolutions

Pierre-Luc St-Charles, Guillaume-Alexandre Bilodeau, Robert Bergevin; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2016, pp. 1-9

Abstract


The recent increase in popularity of binary feature descriptors has opened the door to new lightweight computer vision applications. Most research efforts thus far have been dedicated to the introduction of new large-scale binary features, which are primarily used for keypoint description and matching. In this paper, we show that the side products of small-scale binary feature computations can efficiently filter images and estimate image gradients. The improved efficiency of low-level operations can be especially useful in time-constrained applications. Through our experiments, we show that efficient binary feature convolutions can be used to mimic various image processing operations, and even outperform Sobel gradient estimation in the edge detection problem, both in terms of speed and F-Measure.

Related Material


[pdf]
[bibtex]
@InProceedings{St-Charles_2016_CVPR_Workshops,
author = {St-Charles, Pierre-Luc and Bilodeau, Guillaume-Alexandre and Bergevin, Robert},
title = {Fast Image Gradients Using Binary Feature Convolutions},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2016}
}