ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Isolated digit recognition using a NeuralTree

Shah, S (1996) Isolated digit recognition using a NeuralTree. In: of 1996 International Conference on Neural Information Processing. ICONIP '96, 24-27 Sept. 1996, Hong Kong, pp. 470-474.

Full text not available from this repository. (Request a copy)

Abstract

Classification trees and neural networks are two popular approaches to pattern recognition problems. Both these approaches are combined in NeuralTree which uses a multilayer perceptron (MLP) at each decision node of binary classification tree to extract nonlinear features. NeuralTree exploits the power of tree classification using appropriate local features obtained by trained neural networks at internal nodes. This approach has been successfully applied to recognize hand-written isolated digits. The proposed method achieves significant decrease in error-rate compared to other classical methods and the size of NeuralTree classifier is also small compared to that of Classification and Regression Tree (CART)

Item Type: Conference Paper
Additional Information: Copyright of this article belongs to Springer-Verlag.
Keywords: character recognition;feature extraction;multilayer perceptrons
Department/Centre: Division of Electrical Sciences > Electrical Engineering
Date Deposited: 31 Aug 2007
Last Modified: 10 Jan 2012 05:26
URI: http://eprints.iisc.ernet.in/id/eprint/10759

Actions (login required)

View Item View Item