Support Vector Machines in Handwritten Digits Classification

Authors:
Urszula Markowska-Kaczmar;Pawel Kubacki
Affiliations:
Wroclaw University of Technology, Poland;Wroclaw University of Technology, Poland
Venue:
ISDA '05 Proceedings of the 5th International Conference on Intelligent Systems Design and Applications
Year:
2005

Citing 0
Cited 2

Letters: Adaptive binary tree for fast SVM multiclass classification

Neurocomputing
Consensus-Based Distributed Support Vector Machines

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

In the paper our approach to classify handwritten digits by using Support Vector Machines is described. Because of the unsatisfying, long time of training of SVM we propose to apply k-nearest neighbours algorithm with Manhattan distance to obtain reduced size of training set having a hope that this hybrid method does not make the significantly worse results of recognition. The aim of presented further experiments was to verify this assumption.