Testing additive linear discriminant analysis on pattern recognition

• Main Author: Lum, Kwai Thiam.
• Other Authors: School of Electrical and Electronic Engineering
• Format: Final Year Project
• Language: English
• Published: 2010
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
• Online Access: http://hdl.handle.net/10356/41468
• Institution: Nanyang Technological University

In this dissertation, we investigate the pattern recognition performance of Additive Linear Discriminant Analysis (ALDA) with dataset from UIC. In search of a technique that extracts the most relevant information in different set of features to form the basis vectors, Fisher proposed the Fisher’s Linear Discriminant Analysis (LDA) that finds the eigenvectors of the covariance matrix of this set of features. Each set of features can then be represented exactly by a linear combination of eigenvector, or approximately, by a subset eigenvector of best those that account for the most variance within the features database characterized by its eigenvalues. Additive Linear Discriminant Analysis is a similar technique which will be discussed and tested on some well known databases in this report.