Using genetic algorithm feature selection in neural classification systems for image pattern recognition: Fid-Bau Portal

Fachinformationsdienst BAUdigital

A platform for research: civil engineering, architecture and urbanism

Using genetic algorithm feature selection in neural classification systems for image pattern recognition

Margarita R. Gamarra A. / Christian G. Quintero M.

Pattern recognition performance depends on variations during extraction, selection and classification stages. This paper presents an approach to feature selection by using genetic algorithms with regard to digital image recognition and quality control. Error rate and kappa coefficient were used for evaluating the genetic algorithm approach Neural networks were used for classification, involving the features selected by the genetic algorithms. The neural network approach was compared to a K-nearest neighbor classifier. The proposed approach performed better than the other methods.

Access

Page navigation

Document information

Export, share and cite

Using genetic algorithm feature selection in neural classification systems for image pattern recognition

Margarita R. Gamarra A. / Christian G. Quintero M.

Pattern recognition performance depends on variations during extraction, selection and classification stages. This paper presents an approach to feature selection by using genetic algorithms with regard to digital image recognition and quality control. Error rate and kappa coefficient were used for evaluating the genetic algorithm approach Neural networks were used for classification, involving the features selected by the genetic algorithms. The neural network approach was compared to a K-nearest neighbor classifier. The proposed approach performed better than the other methods.

Using genetic algorithm feature selection in neural classification systems for image pattern recognition

Margarita R. Gamarra A. / Christian G. Quintero M.

Pattern recognition performance depends on variations during extraction, selection and classification stages. This paper presents an approach to feature selection by using genetic algorithms with regard to digital image recognition and quality control. Error rate and kappa coefficient were used for evaluating the genetic algorithm approach Neural networks were used for classification, involving the features selected by the genetic algorithms. The neural network approach was compared to a K-nearest neighbor classifier. The proposed approach performed better than the other methods.

Access

Page navigation

Document information

Export, share and cite

Document information

Title:

Using genetic algorithm feature selection in neural classification systems for image pattern recognition

Contributors:

Margarita R. Gamarra A. (author) / Christian G. Quintero M. (author)

Published in:

Ingeniería e Investigación, Vol 33, Iss 1, Pp 52-58 (2013)

Publication date:

2013

ISSN:

0120-5609 , 2248-8723

Type of media:

Article (Journal)

Type of material:

Electronic Resource

Language:

Unknown

Keywords:

Feature vector , genetic algorithm , neural network , pattern recognition. , Engineering (General). Civil engineering (General) , TA1-2040

Metadata by DOAJ is licensed under CC BY-SA 1.0

Similar titles

Feature Selection for a Neural Network Damage Diagnostic using a Genetic Algorithm

Manson, G. / Worden, K. | British Library Conference Proceedings | 2006

Feature selection using a genetic algorithm-based hybrid approach

Luis Felipe Giraldo / Edilson Delgado Trejos / Juan Carlos Riaño et al. | DOAJ | 2006

Free access

Image and Pattern Recognition Using Wavelet Neural Networks

Wang, A.-m. / Liu, T.-f. / Wang, X. | British Library Online Contents | 2002

Feature selection of fabric defects based on genetic algorithm

Yao, G. / Zhong, X. / Liang, J. et al. | British Library Online Contents | 2009

Recognition of MEMS Microstructure Feature Based on Pattern Analysis and Classification

Hu, K. / Jiang, X.Q. / Liu, X.J. | British Library Online Contents | 2008