Hierarchical k-nearest neighbor classification using feature and observation space information

Ryosuke Kubota; Eiji Uchino; Noriaki Suetake

doi:10.1587/elex.5.114

LETTER

Hierarchical k-nearest neighbor classification using feature and observation space information

Ryosuke Kubota, Eiji Uchino, Noriaki Suetake

著者情報

キーワード: k-nearest neighbor classification, pixel classification, image segmentation, learning vector quantization

ジャーナルフリー

2008 年 5 巻 3 号 p. 114-119

DOI https://doi.org/10.1587/elex.5.114

詳細

抄録

A novel hierarchical k-nearest neighbor classification method using the feature and observation space information is proposed. The present method performs a fine classification when a pair of the spatial coordinate of the observation data in the observation space and its corresponding feature vector in the feature space is provided.

責任著者(Corresponding author)

J-STAGEへの登録はこちら（無料）