A Classifier Based on Distance between Test Samples and Average Patterns of Categorical Nearest Neighbors
抄録
application/pdf
The recognition rate of the typical nonparametric method "k-Nearest Neighbor rule (kNN)" is degraded when the dimensionality of feature vectors is large. Another nonparametric method "linear subspace methods" cannot represent the local distribution of patterns, so recognition rates decrease when pattern distribution is not normal distribution. This paper presents a classifier that outputs the class of a test sample by measuring the distance between the test sample and the average patterns, which are calculated using nearest neighbors belonging to individual categories. A kernel method can be applied to this classifier for improving its recognition rates. The performance of those methods is verified by experiments with handwritten digit patterns and two class artificial ones.
text
Ninth International Workshop on Frontiers in Handwriting Recognition (IWFHR'04), 26-29 Oct. 2004
Ninth International Workshop on Frontiers in Handwriting Recognition (IWFHR'04) pp. 45-50 ; 2004
収録刊行物
-
- Proceedings of the 9th Int’l Workshop on Frontiers in Handwriting Recognition (IWFHR-9 2004)
-
Proceedings of the 9th Int’l Workshop on Frontiers in Handwriting Recognition (IWFHR-9 2004) 45-50, 2004
IEEE Computer Society Press
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1050855522046917504
-
- NII論文ID
- 120006981377
-
- HANDLE
- 10069/16322
-
- 本文言語コード
- en
-
- 資料種別
- conference paper
-
- データソース種別
-
- IRDB
- CiNii Articles