| Presentation | 2012-03-30 ThumbPop : Visual Attention-Based Pseudo 3D Thumbnail Keisuke ARAI, Hiromasa Takei, Hayato YAMANA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We propose a pseudo 3D thumbnail generation method to improve the recognizability of visual attention objects by decomposing an original image into visual attention objects and a background. Thumbnails created by scaling, used as general, are not suitable for mobile devices equipped a small display, because attention objects become too small to recognize. Furthermore, previous visual attention-based thumbnail generation methods cannot preserve recognizability of visual attention objects by burying them in the background image. To solve these problems, we propose a pseudo 3D thumbnail generation method. The method starts with decomposing an input image into visual attention objects and a background, and then combines visual attention objects and affine transformed background. Our thumbnail is able to emphasize visual attention objects without burying them in the background. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Thumbnail / Small size displays / Pseudo 3D / Content-aware image retargeting / GrabCut |
| Paper # | PRMU2011-268,HIP2011-96 |
| Date of Issue |
| Conference Information | |
| Committee | HIP |
|---|---|
| Conference Date | 2012/3/22(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 | Human Information Processing (HIP) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | ThumbPop : Visual Attention-Based Pseudo 3D Thumbnail |
| Sub Title (in English) | |
| Keyword(1) | Thumbnail |
| Keyword(2) | Small size displays |
| Keyword(3) | Pseudo 3D |
| Keyword(4) | Content-aware image retargeting |
| Keyword(5) | GrabCut |
| 1st Author's Name | Keisuke ARAI |
| 1st Author's Affiliation | Graduate School of Fundamental Science and Engineering, Waseda University() |
| 2nd Author's Name | Hiromasa Takei |
| 2nd Author's Affiliation | Graduate School of Fundamental Science and Engineering, Waseda University:Nihon Unisys, Ltd. |
| 3rd Author's Name | Hayato YAMANA |
| 3rd Author's Affiliation | Faculty of Science and Engineering, Waseda University:National Institute of Infomatics |
| Date | 2012-03-30 |
| Paper # | PRMU2011-268,HIP2011-96 |
| Volume (vol) | vol.111 |
| Number (no) | 500 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |