Face Recognition Methods Based on Feedforward Neural Networks, Principal Component Analysis and Self-Organizing Map
In this contribution, human face as biometric is considered. Original method of feature extraction from image data is introduced using MLP (multilayer perceptron) and PCA (principal component analysis). This method is used in human face recognition system and results are compared to face recognition...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Spolecnost pro radioelektronicke inzenyrstvi
2007-04-01
|
Series: | Radioengineering |
Subjects: | |
Online Access: | http://www.radioeng.cz/fulltexts/2007/07_01_51_57.pdf |
_version_ | 1811228241805967360 |
---|---|
author | J. Pavlovicova M. Oravec |
author_facet | J. Pavlovicova M. Oravec |
author_sort | J. Pavlovicova |
collection | DOAJ |
description | In this contribution, human face as biometric is considered. Original method of feature extraction from image data is introduced using MLP (multilayer perceptron) and PCA (principal component analysis). This method is used in human face recognition system and results are compared to face recognition system using PCA directly, to a system with direct classification of input images by MLP and RBF (radial basis function) networks, and to a system using MLP as a feature extractor and MLP and RBF networks in the role of classifier. Also a two-stage method for face recognition is presented, in which Kohonen self-organizing map is used as a feature extractor. MLP and RBF network are used as classifiers. In order to obtain deeper insight into presented methods, also visualizations of internal representation of input data obtained by neural networks are presented. |
first_indexed | 2024-04-12T09:54:55Z |
format | Article |
id | doaj.art-fcee978c489042c1a324cfa65ea890e8 |
institution | Directory Open Access Journal |
issn | 1210-2512 |
language | English |
last_indexed | 2024-04-12T09:54:55Z |
publishDate | 2007-04-01 |
publisher | Spolecnost pro radioelektronicke inzenyrstvi |
record_format | Article |
series | Radioengineering |
spelling | doaj.art-fcee978c489042c1a324cfa65ea890e82022-12-22T03:37:43ZengSpolecnost pro radioelektronicke inzenyrstviRadioengineering1210-25122007-04-011615157Face Recognition Methods Based on Feedforward Neural Networks, Principal Component Analysis and Self-Organizing MapJ. PavlovicovaM. OravecIn this contribution, human face as biometric is considered. Original method of feature extraction from image data is introduced using MLP (multilayer perceptron) and PCA (principal component analysis). This method is used in human face recognition system and results are compared to face recognition system using PCA directly, to a system with direct classification of input images by MLP and RBF (radial basis function) networks, and to a system using MLP as a feature extractor and MLP and RBF networks in the role of classifier. Also a two-stage method for face recognition is presented, in which Kohonen self-organizing map is used as a feature extractor. MLP and RBF network are used as classifiers. In order to obtain deeper insight into presented methods, also visualizations of internal representation of input data obtained by neural networks are presented.www.radioeng.cz/fulltexts/2007/07_01_51_57.pdfBiometricsface recognitionneural networksPCAmultilayer perceptronradial-basis function networkself-organizing mapvisualizationLDAkernels |
spellingShingle | J. Pavlovicova M. Oravec Face Recognition Methods Based on Feedforward Neural Networks, Principal Component Analysis and Self-Organizing Map Radioengineering Biometrics face recognition neural networks PCA multilayer perceptron radial-basis function network self-organizing map visualization LDA kernels |
title | Face Recognition Methods Based on Feedforward Neural Networks, Principal Component Analysis and Self-Organizing Map |
title_full | Face Recognition Methods Based on Feedforward Neural Networks, Principal Component Analysis and Self-Organizing Map |
title_fullStr | Face Recognition Methods Based on Feedforward Neural Networks, Principal Component Analysis and Self-Organizing Map |
title_full_unstemmed | Face Recognition Methods Based on Feedforward Neural Networks, Principal Component Analysis and Self-Organizing Map |
title_short | Face Recognition Methods Based on Feedforward Neural Networks, Principal Component Analysis and Self-Organizing Map |
title_sort | face recognition methods based on feedforward neural networks principal component analysis and self organizing map |
topic | Biometrics face recognition neural networks PCA multilayer perceptron radial-basis function network self-organizing map visualization LDA kernels |
url | http://www.radioeng.cz/fulltexts/2007/07_01_51_57.pdf |
work_keys_str_mv | AT jpavlovicova facerecognitionmethodsbasedonfeedforwardneuralnetworksprincipalcomponentanalysisandselforganizingmap AT moravec facerecognitionmethodsbasedonfeedforwardneuralnetworksprincipalcomponentanalysisandselforganizingmap |