Novel feature recognition neural network and its application to character recognition

Basit Hussain, Mansur R. Kabuka

Research output: Contribution to journalArticle

56 Citations (Scopus)

Abstract

This paper presents a Feature Recognition Network for pattern recognition that learns the patterns by remembering their different segments. The base algorithm for this network is a Boolean net algorithm that we developed during our past research. Simulation results show that the network can recognize patterns after significant noise, deformation, translation and even scaling. The network is compared to existing popular networks used for the same purpose, especially Neocognitron. The network is also analyzed as regards to interconnection complexity and information storage/retrieval.

Original languageEnglish
Pages (from-to)98-106
Number of pages9
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume16
Issue number1
DOIs
StatePublished - Jan 1 1994

Fingerprint

Feature Recognition
Character recognition
Character Recognition
Neural Networks
Neural networks
Pattern recognition
Data storage equipment
Interconnection
Pattern Recognition
Retrieval
Scaling
Simulation

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Novel feature recognition neural network and its application to character recognition. / Hussain, Basit; Kabuka, Mansur R.

In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 16, No. 1, 01.01.1994, p. 98-106.

Research output: Contribution to journalArticle

@article{120c522fadb548a4b3127ff7e3cd01b1,
title = "Novel feature recognition neural network and its application to character recognition",
abstract = "This paper presents a Feature Recognition Network for pattern recognition that learns the patterns by remembering their different segments. The base algorithm for this network is a Boolean net algorithm that we developed during our past research. Simulation results show that the network can recognize patterns after significant noise, deformation, translation and even scaling. The network is compared to existing popular networks used for the same purpose, especially Neocognitron. The network is also analyzed as regards to interconnection complexity and information storage/retrieval.",
author = "Basit Hussain and Kabuka, {Mansur R.}",
year = "1994",
month = "1",
day = "1",
doi = "10.1109/34.273711",
language = "English",
volume = "16",
pages = "98--106",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",
number = "1",

}

TY - JOUR

T1 - Novel feature recognition neural network and its application to character recognition

AU - Hussain, Basit

AU - Kabuka, Mansur R.

PY - 1994/1/1

Y1 - 1994/1/1

N2 - This paper presents a Feature Recognition Network for pattern recognition that learns the patterns by remembering their different segments. The base algorithm for this network is a Boolean net algorithm that we developed during our past research. Simulation results show that the network can recognize patterns after significant noise, deformation, translation and even scaling. The network is compared to existing popular networks used for the same purpose, especially Neocognitron. The network is also analyzed as regards to interconnection complexity and information storage/retrieval.

AB - This paper presents a Feature Recognition Network for pattern recognition that learns the patterns by remembering their different segments. The base algorithm for this network is a Boolean net algorithm that we developed during our past research. Simulation results show that the network can recognize patterns after significant noise, deformation, translation and even scaling. The network is compared to existing popular networks used for the same purpose, especially Neocognitron. The network is also analyzed as regards to interconnection complexity and information storage/retrieval.

UR - http://www.scopus.com/inward/record.url?scp=0028196492&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028196492&partnerID=8YFLogxK

U2 - 10.1109/34.273711

DO - 10.1109/34.273711

M3 - Article

VL - 16

SP - 98

EP - 106

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 1

ER -