Comparative Analysis of Basic Self-Organizing Map and Neocognitron for Handwritten Character Recognition

Draganov, Ivo R. and Popova, Antoaneta A. (2007) Comparative Analysis of Basic Self-Organizing Map and Neocognitron for Handwritten Character Recognition. In: "International Scientific Conference on Information, Communication and Energy Systems and Technologies ICEST" (24-27 June 2007) hosted in Ohrid, Macedonia, 2007, 24-27 June 2007, Ohrid, Macedonia.

[thumbnail of ICEST2007_2_8.pdf]
Preview
Text
ICEST2007_2_8.pdf

Download (213kB) | Preview

Abstract

In this paper we present a comparative analysis of the performance both as accuracy and time consumption of two
neural network classifiers for handwritten character recognition – a basic self organizing map and neocognitron proposed by Kohonen and Fukushima respectively. The results of our study are found useful for characters and pseudo-characters recognition as a certain stage of processing in a whole handwriting recognition system.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: character, pseudo-character, word, handwriting recognition, self-organizing map, neocognitron
Subjects: Scientific Fields (Frascati) > Engineering and Technology > Electrical engineering, electronic engineering,information engineering
Divisions: Faculty of Technical Sciences
Depositing User: ICEST
Date Deposited: 18 Mar 2020 17:13
Last Modified: 18 Mar 2020 17:13
URI: https://eprints.uklo.edu.mk/id/eprint/2698

Actions (login required)

View Item View Item