| Presentation | 2014-01-24 Object recognition by the selection of visual words according to each category using frequency histograms Tatsunori TOMURA, Yasukuni MORI, Ikuo MATSUBA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The general object recognition is a task that enables a computer to recognize an object and scene in images. In this paper, we propose a method that selects visual words for each category which are useful for classification. The required amount of reconstruction process of visual words is small compared to traditional methods in case of an appearance of a new category, because visual words for each category are constructed by images belonging to only one category. When generating histograms using visual words and images of the same category, the average of the appearance frequency of each visual word is distinct. Visual words for each category can be classified into features related to the object or noises. It is considered that visual words which have a high average of appearance frequency are features related to the object, and those which have a low average are noises. The noises may cause misclassification of images. Therefore, the proposed method selects visual words with a high average of appearance frequency to reduce noises. An evaluation experiment was performed in order to confirm the effectiveness of the proposed method. The results showed a better classification rate than the conventional method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | generic object recognition / visual words for each category / bag of features / local features |
| Paper # | PRMU2013-112,MVE2013-53 |
| Date of Issue |
| Conference Information | |
| Committee | MVE |
|---|---|
| Conference Date | 2014/1/16(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 | Media Experience and Virtual Environment (MVE) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Object recognition by the selection of visual words according to each category using frequency histograms |
| Sub Title (in English) | |
| Keyword(1) | generic object recognition |
| Keyword(2) | visual words for each category |
| Keyword(3) | bag of features |
| Keyword(4) | local features |
| 1st Author's Name | Tatsunori TOMURA |
| 1st Author's Affiliation | Graduate School of Advanced Integration Science, Chiba University() |
| 2nd Author's Name | Yasukuni MORI |
| 2nd Author's Affiliation | Graduate School of Advanced Integration Science, Chiba University |
| 3rd Author's Name | Ikuo MATSUBA |
| 3rd Author's Affiliation | Graduate School of Advanced Integration Science, Chiba University |
| Date | 2014-01-24 |
| Paper # | PRMU2013-112,MVE2013-53 |
| Volume (vol) | vol.113 |
| Number (no) | 403 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |