One-Class Classification with Subgaussians

Madany Mamlouk, Amir, Kim, Jan T., Barth, Erhardt, Brauckmann, Michael and Martinetz, Thomas (2003) One-Class Classification with Subgaussians. In: Pattern Recognition. Lecture Notes in Computer Science, 2781 . Springer Verlag, Berlin Heidelberg, DEU, pp. 346-353. ISBN 978-3-540-40861-1

Full text not available from this repository.

Abstract

If a simple and fast solution for one-class classification is required, the most common approach is to assume a Gaussian distribution for the patterns of the single class. Bayesian classification then leads to a simple template matching. In this paper we show for two very different applications that the classification performance can be improved significantly if a more uniform subgaussian instead of a Gaussian class distribution is assumed. One application is face detection, the other is the detection of transcription factor binding sites on a genome. As for the Gaussian, the distance from a template, i.e., the distribution center, determines a pattern’s class assignment. However, depending on the distribution assumed, maximum likelihood learning leads to different templates from the training data. These new templates lead to significant improvements of the classification performance.

Item Type: Book Section
Faculty \ School: Faculty of Science > School of Computing Sciences
Related URLs:
Depositing User: Vishal Gautam
Date Deposited: 23 Jul 2011 17:45
Last Modified: 22 Apr 2020 10:20
URI: https://ueaeprints.uea.ac.uk/id/eprint/22642
DOI: 10.1007/978-3-540-45243-0_45

Actions (login required)

View Item View Item