Bootstrapping for efficient handwritten digit recognition

Saradhi, Vijaya V and Murty, Narasimha M (2001) Bootstrapping for efficient handwritten digit recognition. In: Pattern Recognition, 34 (5). pp. 1047-1056.

PDF Bootstrapping_for_efcient.pdf Restricted to Registered users only Download (201kB) | Request a copy

Abstract

In this paper we present two algorithms for selecting prototypes from the given training data set. Here, we employ the bootstrap technique to preprocess the data. We compare the proposed algorithms with the condensed nearest-neighbor algorithm which is order dependent and a genetic-algorithm-based prototype selection scheme which is order independent.Algorithms proposed in this paper are found to be better than the condensed nearest neighbor and prototype selection methods in terms of classification accuracy.

Item Type:	Journal Article
Publication:	Pattern Recognition
Publisher:	Elsevier Science
Additional Information:	Copyright belongs to Elsevier Science Ltd.
Keywords:	Bootstrapping;Redundancy removal;Condensed nearest neighbor;Prototype selection;Genetic algorithms;Thresholding;Classification accuracy
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	08 Dec 2008 12:39
Last Modified:	19 Sep 2010 04:53
URI:	http://eprints.iisc.ac.in/id/eprint/16620

Actions (login required)

View Item