Object recognition from 2D images using Kohonen self-organized feature maps

Heba Lakany, E.G Schukat-Talamazzini, H Niemann, M.A.R Ghonaimy

Research output: Contribution to journalArticle

Abstract

In this paper, we propose an algorithm for recognition of objects from 2D images. The algorithm is neural network based. It uses Kohonen self-organised feature maps (SOFM) as a vector quantiser whose performance is compared to that of EM technique. A codebook is designed using SOFM and a simple labelling procedure is used to label the feature vectors, then the labelled training data set of di erent objects are recognised by the resilient propagation network. The algorithm is applied to 2D images of industrial objects.
LanguageEnglish
Pages301-308
Number of pages8
JournalPattern Recognition and Image Analysis
Volume7
Issue number3
Publication statusPublished - 1997

Fingerprint

Object recognition
Labeling
Labels
Neural networks

Keywords

  • 2D images
  • Kohonen
  • self organized feature maps

Cite this

Lakany, H., Schukat-Talamazzini, E. G., Niemann, H., & Ghonaimy, M. A. R. (1997). Object recognition from 2D images using Kohonen self-organized feature maps. Pattern Recognition and Image Analysis, 7(3), 301-308.
Lakany, Heba ; Schukat-Talamazzini, E.G ; Niemann, H ; Ghonaimy, M.A.R. / Object recognition from 2D images using Kohonen self-organized feature maps. In: Pattern Recognition and Image Analysis. 1997 ; Vol. 7, No. 3. pp. 301-308.
@article{04694583edcb4e45ad9ff350c952ffa5,
title = "Object recognition from 2D images using Kohonen self-organized feature maps",
abstract = "In this paper, we propose an algorithm for recognition of objects from 2D images. The algorithm is neural network based. It uses Kohonen self-organised feature maps (SOFM) as a vector quantiser whose performance is compared to that of EM technique. A codebook is designed using SOFM and a simple labelling procedure is used to label the feature vectors, then the labelled training data set of di erent objects are recognised by the resilient propagation network. The algorithm is applied to 2D images of industrial objects.",
keywords = "2D images, Kohonen, self organized feature maps",
author = "Heba Lakany and E.G Schukat-Talamazzini and H Niemann and M.A.R Ghonaimy",
year = "1997",
language = "English",
volume = "7",
pages = "301--308",
journal = "Pattern Recognition and Image Analysis",
issn = "1054-6618",
publisher = "Springer",
number = "3",

}

Lakany, H, Schukat-Talamazzini, EG, Niemann, H & Ghonaimy, MAR 1997, 'Object recognition from 2D images using Kohonen self-organized feature maps' Pattern Recognition and Image Analysis, vol. 7, no. 3, pp. 301-308.

Object recognition from 2D images using Kohonen self-organized feature maps. / Lakany, Heba; Schukat-Talamazzini, E.G; Niemann, H; Ghonaimy, M.A.R.

In: Pattern Recognition and Image Analysis, Vol. 7, No. 3, 1997, p. 301-308.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Object recognition from 2D images using Kohonen self-organized feature maps

AU - Lakany, Heba

AU - Schukat-Talamazzini, E.G

AU - Niemann, H

AU - Ghonaimy, M.A.R

PY - 1997

Y1 - 1997

N2 - In this paper, we propose an algorithm for recognition of objects from 2D images. The algorithm is neural network based. It uses Kohonen self-organised feature maps (SOFM) as a vector quantiser whose performance is compared to that of EM technique. A codebook is designed using SOFM and a simple labelling procedure is used to label the feature vectors, then the labelled training data set of di erent objects are recognised by the resilient propagation network. The algorithm is applied to 2D images of industrial objects.

AB - In this paper, we propose an algorithm for recognition of objects from 2D images. The algorithm is neural network based. It uses Kohonen self-organised feature maps (SOFM) as a vector quantiser whose performance is compared to that of EM technique. A codebook is designed using SOFM and a simple labelling procedure is used to label the feature vectors, then the labelled training data set of di erent objects are recognised by the resilient propagation network. The algorithm is applied to 2D images of industrial objects.

KW - 2D images

KW - Kohonen

KW - self organized feature maps

UR - http://pleiades.online/contents/patrec/patrec3_97v7cont.htm

M3 - Article

VL - 7

SP - 301

EP - 308

JO - Pattern Recognition and Image Analysis

T2 - Pattern Recognition and Image Analysis

JF - Pattern Recognition and Image Analysis

SN - 1054-6618

IS - 3

ER -

Lakany H, Schukat-Talamazzini EG, Niemann H, Ghonaimy MAR. Object recognition from 2D images using Kohonen self-organized feature maps. Pattern Recognition and Image Analysis. 1997;7(3):301-308.