Searching High-Dimensional Neighbours: CPU-Based Tailored Data-Structures Versus GPU-Based Brute-Force Method

Many image processing algorithms rely on nearest neighbor (NN) or on the k nearest neighbor (kNN) search problem. Several methods have been proposed to reduce the computation time, for instance using space partitionning. However, these methods are very slow in high dimensional space. In this paper, we propose a fast implementation of the brute-force algorithm using GPU (Graphics Processing Units) programming. We show that our implementation is up to 150 times faster than the classical approaches on synthetic data, and up to 75 times faster on real image processing algorithms (finding similar patches in images and texture synthesis).

[1]  Thomas Wiegand,et al.  SIFT Implementation and Optimization for General-Purpose GPU , 2007 .

[2]  R. M. Díaz,et al.  On first-passage problems for asymmetric one-dimensional diffusions , 2007 .

[3]  Zhe Wang,et al.  Multi-Probe LSH: Efficient Indexing for High-Dimensional Similarity Search , 2007, VLDB.

[4]  Piotr Indyk,et al.  Approximate nearest neighbors: towards removing the curse of dimensionality , 1998, STOC '98.

[5]  Alexandr Andoni,et al.  Near-Optimal Hashing Algorithms for Approximate Nearest Neighbor in High Dimensions , 2006, 2006 47th Annual IEEE Symposium on Foundations of Computer Science (FOCS'06).

[6]  Piotr Indyk,et al.  Similarity Search in High Dimensions via Hashing , 1999, VLDB.

[7]  Sunil Arya,et al.  ANN: library for approximate nearest neighbor searching , 1998 .

[8]  Peter N. Yianilos,et al.  Data structures and algorithms for nearest neighbor search in general metric spaces , 1993, SODA '93.

[9]  Michel Barlaud,et al.  Image restoration using a kNN-variant of the mean-shift , 2008, 2008 15th IEEE International Conference on Image Processing.

[10]  Nicole Immorlica,et al.  Locality-sensitive hashing scheme based on p-stable distributions , 2004, SCG '04.

[11]  Hans-Jörg Schek,et al.  A Quantitative Analysis and Performance Study for Similarity-Search Methods in High-Dimensional Spaces , 1998, VLDB.

[12]  Shree K. Nayar,et al.  What Is a Good Nearest Neighbors Algorithm for Finding Similar Patches in Images? , 2008, ECCV.

[13]  Michel Barlaud,et al.  Image retrieval via Kullback-Leibler divergence of patches of multiscale coefficients in the KNN framework , 2008, 2008 International Workshop on Content-Based Multimedia Indexing.

[14]  Michel Barlaud,et al.  A nonparametric minimum entropy image deblurring algorithm , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[15]  Francisca Quintana,et al.  Accelerating Space Variant Gaussian Filtering on Graphics Processing Unit , 2007, EUROCAST.

[16]  Michel Barlaud,et al.  High-dimensional statistical distance for region-of-interest tracking: Application to combining a soft geometric constraint with radiometry , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Sunil Arya,et al.  An optimal algorithm for approximate nearest neighbor searching fixed dimensions , 1998, JACM.

[18]  Sung Yong Shin,et al.  On pixel-based texture synthesis by non-parametric sampling , 2006, Comput. Graph..