DocumentCode
1350334
Title
Building and Using a Database of One Trillion Natural-Image Patches
Author
Arietta, S.M. ; Lawrence, J.
Volume
31
Issue
1
fYear
2011
Firstpage
9
Lastpage
19
Abstract
Many example-based imageprocessing algorithms operate on image patches (texture synthesis, resolution enhancement, image denoising, and so on). However, inaccessibility to a large, varied collection of image patches has hindered widespread adoption of these methods. The authors describe the construction of a database of one trillion image patches and demonstrate its research utility.
Keywords
image denoising; image enhancement; image resolution; image texture; visual databases; database construction; example-based image processing algorithms; image denoising; natural-image patches; resolution enhancement; texture synthesis; Accuracy; Approximation algorithms; Approximation methods; Artificial neural networks; Databases; Image segmentation; Nearest neighbor searches; LSH; computer graphics; distributed processing; graphics and multimedia; image databases; image patches; image processing; image search; kd-trees; locality-sensitive hashing; natural images; nearest neighbor;
fLanguage
English
Journal_Title
Computer Graphics and Applications, IEEE
Publisher
ieee
ISSN
0272-1716
Type
jour
DOI
10.1109/MCG.2010.105
Filename
5601662
Link To Document