K-nearest neighbor search: Fast GPU-based implementations and application to high-dimensional feature matching
Ecole Polytechnique, Laboratoire d’informatique LIX, 91128 Palaiseau Cedex, France
17th IEEE International Conference on Image Processing (ICIP), 2010
@conference{garcia2010k,
title={K-nearest neighbor search: Fast GPU-based implementations and application to high-dimensional feature matching},
author={Garcia, V. and Debreuve, E. and Nielsen, F. and Barlaud, M.},
booktitle={Image Processing (ICIP), 2010 17th IEEE International Conference on},
pages={3757–3760},
issn={1522-4880},
organization={IEEE}
}
The k-nearest neighbor (kNN) search problem is widely used in domains and applications such as classification, statistics, and biology. In this paper, we propose two fast GPU-based implementations of the brute-force kNN search algorithm using the CUDA and CUBLAS APIs. We show that our CUDA and CUBLAS implementations are up to, respectively, 64X and 189X faster on synthetic data than the highly optimized ANN C++ library, and up to, respectively, 25X and 62X faster on high-dimensional SIFT matching.
May 5, 2011 by hgpu
