RECOGNITION OF LOCAL CAPITAL USING SYMMETRIC TWO-DIMENSIONAL LINEAR DISCRIMINANT ANALYSIS
Abstract
Statistical pattern recognition is a system that aims to classify a number of objects to a number of categories or classes. Given a data matrix A, A = {Π1, Π2,…, Πk} where Πi consist of ni point data of ith class then patterns in each classes can classify and separate distance of within and between-class in datasets. In this paper, Symmetric Two-Dimensional Linear Discriminant Analysis proposed to maximize the between-class scatter matrices (Sb) and minimize the within-class scatter matrices (Sw), and can recognition the symmetric capital letter by hand writing such as A, B, C, D, E, H, I, K, M, O, S, U, V, W and Y by using ADL2-D algorithm.
Moraref