| Presentation | 2013-03-15 Object Discovery from Images with Multiple Objects based on Co-occurring Graphs Takayuki NANBU, Hisashi KOGA, Toshinori WATANABE, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Although the BoF (Bag-of-Features)model has succeeded in automatic object discovery, it still has some drawbacks: For example, the BoF model does not represent the spatial relation between feature points. Moreover, decision of the proper vocabulary size is difficult. Xia and Hancock propose a graph-based object discovery algorithm in order to overcome these drawbacks. However, their algorithm assumes that each image contains only one object. In this paper, we propose a new graph-based object discovery method which deals with images including multiple objects. Our algorithm classifies the SIFT features out of the images into clusters based on the results of the SIFT matching. Here, because our clustering method does not require the number of the clusters as its input, we do not have to determine the vocabulary size. Then, the object models are acquired as the set of co-occurring edges, relying on the observation that the similar graph patterns occurs frequently in multiple object instances of the same kind. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Object Discovery / Graph-based Image Processing / SIFT matching / Frequent Pattern Mining |
| Paper # | PRMU2012-209 |
| Date of Issue |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 2013/3/7(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 | Pattern Recognition and Media Understanding (PRMU) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Object Discovery from Images with Multiple Objects based on Co-occurring Graphs |
| Sub Title (in English) | |
| Keyword(1) | Object Discovery |
| Keyword(2) | Graph-based Image Processing |
| Keyword(3) | SIFT matching |
| Keyword(4) | Frequent Pattern Mining |
| 1st Author's Name | Takayuki NANBU |
| 1st Author's Affiliation | Graduate School of Infomation Systems, Univaersity of Electro-Communication() |
| 2nd Author's Name | Hisashi KOGA |
| 2nd Author's Affiliation | Graduate School of Infomation Systems, Univaersity of Electro-Communication |
| 3rd Author's Name | Toshinori WATANABE |
| 3rd Author's Affiliation | Graduate School of Infomation Systems, Univaersity of Electro-Communication |
| Date | 2013-03-15 |
| Paper # | PRMU2012-209 |
| Volume (vol) | vol.112 |
| Number (no) | 495 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |