关键词:图像挖掘; 维度灾难; 形式背景; 概念格; 属性约简; 数据降维
Image feature data dimension reduction based on concept lattices
LUO Weia, WANG Lia, AI Lib, WANG Yue-hanga
(a. School of Computer Science & Engineering, b. School of Science, University of Science & Technology Liaoning, Anshan Liaoning 114051, China)
Abstract:High-dimensional image feature data is an obstacle for image mining. In order to reduce the image feature data dimension, this paper introduced a dimension reduction algorithm based on concept lattices. In this algorithm, calculated the concept lattices of the image formal, which was transformed from the HSV color feature, and then reduced the attributes of the concept lattice. The experiment results prove that this method is efficient, and it outperforms the principal component analysis (PCA).
Key words:image mining; curse of dimensionality; formal context; concept lattices; attribute reduction; data dimension reduction......