A Dimension Reduction Method for High-Dimensional Image Patterns Using Relational Discriminant Analysis

Relational Discriminant Analysis를 이용한 고차원 영상패턴의 차원축소

Relational discriminant analysis is a way of representing an object based on the dissimilarity measures among the prototypes extracted from feature vectors instead of the vectors themselves. Thus, by appropriately selecting a few number of representatives and by defining the dissimilarity measure, in this paper we propose a method of reducing the dimensionality and getting to achieve a better classification performance in both speed and accuracy. Our experimental results demonstrate that the proposed mechanism increases the performance as compared with the conventional approaches for samples involving artificial data sets.