Breadcrumb

 
 

Handwritten digit classification using cascading neural network ensembles

Title:

Handwritten digit classification using cascading neural network ensembles

Zaramian, Nancy (2006) Handwritten digit classification using cascading neural network ensembles. Masters thesis, Concordia University.

[img]
Preview
PDF - Accepted Version
1772Kb

Abstract

In the problem of handwritten digit classification, difficulties are encountered when there is ambiguity among the digits to be classified. It is desirable to detect this confusion and either reject the classification or attempt to make a better decision using post-processing methods. In the proposed method, a cascading neural network model is used to do the latter. Each level contains an ensemble of neural networks trained on different features. This generates classifiers that complement each other and help identify samples that are difficult to classify. Experiments were done on the MNIST database. This database has 60000 training images and 10000 test images that contain segmented handwritten digits. The results from the experiment show an improvement in the classification accuracy with the addition of each level of neural networks. Out of the 10000 test images 2206 of the samples were rejected from the cascading neural network model and were sent to post-processing. Among the 7794 of the accepted samples not sent to post-processing, only 52 were falsely classified. The overall classification rate of the system, including post-processing is 96.58%

Divisions:Concordia University > Faculty of Engineering and Computer Science > Computer Science and Software Engineering
Item Type:Thesis (Masters)
Authors:Zaramian, Nancy
Pagination:viii, 57 leaves : ill. ; 29 cm.
Institution:Concordia University
Degree Name:M. Comp. Sc.
Program:Computer Science and Software Engineering
Date:2006
Thesis Supervisor(s):Suen, Ching Y and Fevens, Thomas
ID Code:8891
Deposited By:Concordia University Libraries
Deposited On:18 Aug 2011 14:38
Last Modified:18 Aug 2011 14:38
Related URLs:
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Document Downloads

More statistics for this item...

Concordia University - Footer