Efficient Discriminative Projections for Compact Binary Descriptors
Abstract
Binary descriptors of image patches are increasingly popular given that they require less storage and enable faster processing. This, however, comes at a price of lower recognition performances. To boost these performances, we project the image patches to a more discriminative subspace, and threshold their coordinates to build our binary descriptor. However, applying complex projections to the patches is slow, which negates some of the advantages of binary descriptors. Hence, our key idea is to learn the discriminative projections so that they can be decomposed into a small number of simple filters for which the responses can be computed fast. We show that with as few as 32 bits per descriptor we outperform the state-of-the-art binary descriptors in terms of both accuracy and efficiency.
Cite
Text
Trzcinski and Lepetit. "Efficient Discriminative Projections for Compact Binary Descriptors." European Conference on Computer Vision, 2012. doi:10.1007/978-3-642-33718-5_17Markdown
[Trzcinski and Lepetit. "Efficient Discriminative Projections for Compact Binary Descriptors." European Conference on Computer Vision, 2012.](https://mlanthology.org/eccv/2012/trzcinski2012eccv-efficient/) doi:10.1007/978-3-642-33718-5_17BibTeX
@inproceedings{trzcinski2012eccv-efficient,
title = {{Efficient Discriminative Projections for Compact Binary Descriptors}},
author = {Trzcinski, Tomasz and Lepetit, Vincent},
booktitle = {European Conference on Computer Vision},
year = {2012},
pages = {228-242},
doi = {10.1007/978-3-642-33718-5_17},
url = {https://mlanthology.org/eccv/2012/trzcinski2012eccv-efficient/}
}