Name
Abstract | ||
|---|---|---|
Non-local means (NLM) is a popular denoising scheme. Conceptually simple, the algorithm is computationally intensive for large images. We propose to speed up NLM by using random sampling. Our algorithm picks, uniformly at random, a small number of columns of the weight matrix, and uses these "representatives" to compute an approximate result. It also incorporates an extra column-normalization of the sampled columns, a form of symmetrization that often boosts the denoising performance on real images. Using statistical large deviation theory, we analyze the proposed algorithm and provide guarantees on its performance. We show that the probability of having a large approximation error decays exponentially as the image size increases. Thus, for large images, the random estimates generated by the algorithm are tightly concentrated around their limit values, even if the sampling ratio is small. Numerical results confirm our theoretical analysis: the proposed algorithm reduces the run time of NLM, and thanks to the symmetrization step, actually provides some improvement in peak signal-to-noise ratios. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/ICASSP.2013.6637922 | 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) |
Keywords | Field | DocType |
Non-local means, random sampling, Sinkhorn-Knopp balancing scheme, image denoising | Mathematical optimization,Pattern recognition,Computer science,Non-local means,Symmetrization,Filter (signal processing),Artificial intelligence,Large deviations theory,Sampling (statistics),Real image,Image resolution,Approximation error | Conference |
ISSN | Citations | PageRank |
1520-6149 | 1 | 0.35 |
References | Authors | |
18 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Stanley H. Chan | 1 | 403 | 30.95 |
| Todd Zickler | 2 | 1555 | 71.72 |
| Yue M. Lu | 3 | 677 | 60.17 |