Presentation | 2012-02-09 Informative Patches Sampling for Image Classification by Utilizing Bottom-up and Top-down Information Shuang BAI, Tetsuya MATSUMOTO, Yoshinori TAKEUCHI, Hiroaki KUDO, Noboru OHNISHI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In image classification based on bag of visual words framework, image patches used for creating image representations affect the classification performance significantly. However, currently, image patches are sampled mainly based on processing low-level image information or just extracted regularly or randomly. These methods are not effective. In this report, we propose to explore both bottom-up information through processing low-level image information and top-down information through utilizing the statistical properties of training image grids to extract image patches. In the proposed work, an input image is divided into regular grids, each of which is evaluated based on its bottom-up information and/or top-down information. Subsequently, a saliency value is assigned to every grid based on the evaluation results, so that a saliency map can be created for the input image. Finally, the sampling of image patches is performed on the basis of the obtained saliency map. Furthermore, we propose a method to fuse the two kinds of information. The proposed methods are evaluated on both object categories and scene categories. Experiment results demonstrate their effectiveness. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Image classification / Patch sampling / Bottom up / Top down |
Paper # | PRMU2011-200,SP2011-115 |
Date of Issue |
Conference Information | |
Committee | SP |
---|---|
Conference Date | 2012/2/2(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Speech (SP) |
---|---|
Language | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Informative Patches Sampling for Image Classification by Utilizing Bottom-up and Top-down Information |
Sub Title (in English) | |
Keyword(1) | Image classification |
Keyword(2) | Patch sampling |
Keyword(3) | Bottom up |
Keyword(4) | Top down |
1st Author's Name | Shuang BAI |
1st Author's Affiliation | Graduate School of Information Science, Nagoya University() |
2nd Author's Name | Tetsuya MATSUMOTO |
2nd Author's Affiliation | Graduate School of Information Science, Nagoya University |
3rd Author's Name | Yoshinori TAKEUCHI |
3rd Author's Affiliation | Graduate School of Information Science, Nagoya University |
4th Author's Name | Hiroaki KUDO |
4th Author's Affiliation | Graduate School of Information Science, Nagoya University |
5th Author's Name | Noboru OHNISHI |
5th Author's Affiliation | Graduate School of Information Science, Nagoya University |
Date | 2012-02-09 |
Paper # | PRMU2011-200,SP2011-115 |
Volume (vol) | vol.111 |
Number (no) | 431 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |