| Presentation | 2004/2/13 Pattern Recognition Using Average Patterns of Categorical K-Nearest Neighbors Seiji HOTTA, Senya KIYASU, Sueharu MIYAHARA, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The typical non-parametric method of pattern recognition "κ-nearest neighbor rule (κNN)" is carried out by counting the labels of the κ-nearest training samples to a test sample. This method collects the κ-nearest neighbors without taking into account a category and outputs the category of the test sample by using only the labels of training sets. This paper presents a classifier that outputs the category of a test sample based on the distance between the test sample and the average patterns, which are calculated using the κ-nearest neighbors belonging to individual categories. A kernel method can be applied to this classifier for improving recognition rates. Performance of the proposed method is examined using handwritten digit patterns and artificial sets of patterns. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | κ-nearest neighbor / average pattern / kernel method / handwritten digit recognition |
| Paper # | TL2003-69,PRMU2003-255 |
| Date of Issue |
| Conference Information | |
| Committee | TL |
|---|---|
| Conference Date | 2004/2/13(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 | Thought and Language (TL) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Pattern Recognition Using Average Patterns of Categorical K-Nearest Neighbors |
| Sub Title (in English) | |
| Keyword(1) | κ-nearest neighbor |
| Keyword(2) | average pattern |
| Keyword(3) | kernel method |
| Keyword(4) | handwritten digit recognition |
| 1st Author's Name | Seiji HOTTA |
| 1st Author's Affiliation | Department of Computer and Information Sciences, Nagasaki University() |
| 2nd Author's Name | Senya KIYASU |
| 2nd Author's Affiliation | Department of Computer and Information Sciences, Nagasaki University |
| 3rd Author's Name | Sueharu MIYAHARA |
| 3rd Author's Affiliation | Department of Computer and Information Sciences, Nagasaki University |
| Date | 2004/2/13 |
| Paper # | TL2003-69,PRMU2003-255 |
| Volume (vol) | vol.103 |
| Number (no) | 657 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |