| Presentation | 2014-05-22 Hybrid Aggregation of Sparse Coded Discriptors for Food Image Recognition Riko KUSUMOTO, Xian-Hua HAN, Yen-Wei CHEN, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In Recent year, with the increasing of unhealthy diets which will threaten people's life due to the various resulted risks such as heart stroke, liver trouble and so on, the maintaining for healthy life has attracted much attention and then how to manage the dietary life is becoming more and more important. In this research, we aim to construct an auto-recognition system of food images and keep the daily food-log records which will contribute to manage dietary life. In order to achieve the acceptable recognition performance of the food images, we propose to apply a sparse model, instead of vector quantization in the widely used Bag-of-Features (BOF) model, to code local descriptors extracted from the food images for reducing information loss, and use the spatial pyramid matching for integrating spatial information into the image representation vector. Furthermore, a hybrid aggregation strategy called as top-ranked average pooling (TRAP), instead of average or max pooling, is explored for constructing the compact vector for image representation. Experiments validate that our proposed framework can significantly improve the recognition performance compared to the conventional BOF on two food datasets. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Image Recognition / Sparse Coding / Pooling / Food Image |
| Paper # | SIP2014-1,IE2014-1,PRMU2014-1,MI2014-1 |
| Date of Issue |
| Conference Information | |
| Committee | SIP |
|---|---|
| Conference Date | 2014/5/15(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 | Signal Processing (SIP) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Hybrid Aggregation of Sparse Coded Discriptors for Food Image Recognition |
| Sub Title (in English) | |
| Keyword(1) | Image Recognition |
| Keyword(2) | Sparse Coding |
| Keyword(3) | Pooling |
| Keyword(4) | Food Image |
| 1st Author's Name | Riko KUSUMOTO |
| 1st Author's Affiliation | Ritsumeikan University() |
| 2nd Author's Name | Xian-Hua HAN |
| 2nd Author's Affiliation | Ritsumeikan University |
| 3rd Author's Name | Yen-Wei CHEN |
| 3rd Author's Affiliation | Ritsumeikan University |
| Date | 2014-05-22 |
| Paper # | SIP2014-1,IE2014-1,PRMU2014-1,MI2014-1 |
| Volume (vol) | vol.114 |
| Number (no) | 39 |
| Page | pp.pp.- |
| #Pages | 5 |
| Date of Issue | |