2D-page texture classification using support vector machines and genetic algorithms an hybrid approach for texture image analysis

Carlos Fernandez-Lozano; Jose A. Seoane; Pablo Mesejo; Youssef S.G. Nashed; Stefano Cagnoni; Julian Dorado

2D-page texture classification using support vector machines and genetic algorithms an hybrid approach for texture image analysis

Carlos Fernandez-Lozano, Jose A. Seoane, Pablo Mesejo, Youssef S.G. Nashed, Stefano Cagnoni, Julian Dorado

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Scopus citations

Abstract

In this paper, a novel texture classification method from two-dimensional electrophoresis gel images is presented. Such a method makes use of textural features that are reduced to a more compact and efficient subset of characteristics by means of a Genetic Algorithm-based feature selection technique. Then, the selected features are used as inputs for a classifier, in this case a Support Vector Machine. The accuracy of the proposed method is around 94%, and has shown to yield statistically better performances than the classification based on the entire feature set. We found that the most decisive and representative features for the textural classification of proteins are those related to the second order co-occurrence matrix. This classification step can be very useful in order to discard over-segmented areas after a protein segmentation or identification process.

Original language	English (US)
Title of host publication	BIOINFORMATICS 2013 - Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms
Pages	5-14
Number of pages	10
State	Published - 2013
Event	International Conference on Bioinformatics Models, Methods and Algorithms, BIOINFORMATICS 2013 - Barcelona, Spain Duration: Feb 11 2013 → Feb 14 2013

Publication series

Name	BIOINFORMATICS 2013 - Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms

Other

Other	International Conference on Bioinformatics Models, Methods and Algorithms, BIOINFORMATICS 2013
Country/Territory	Spain
City	Barcelona
Period	2/11/13 → 2/14/13

Keywords

Electrophoresis
Feature selection
Genetic algorithm
Support vector machines
Texture analysis

ASJC Scopus subject areas

Biomedical Engineering
Health Informatics
Modeling and Simulation

Cite this

Fernandez-Lozano, C., Seoane, J. A., Mesejo, P., Nashed, Y. S. G., Cagnoni, S., & Dorado, J. (2013). 2D-page texture classification using support vector machines and genetic algorithms an hybrid approach for texture image analysis. In BIOINFORMATICS 2013 - Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms (pp. 5-14). (BIOINFORMATICS 2013 - Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms).

Fernandez-Lozano, Carlos ; Seoane, Jose A. ; Mesejo, Pablo et al. / 2D-page texture classification using support vector machines and genetic algorithms an hybrid approach for texture image analysis. BIOINFORMATICS 2013 - Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms. 2013. pp. 5-14 (BIOINFORMATICS 2013 - Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms).

@inproceedings{3028fa29f31242b1b024575b462ce8d5,

title = "2D-page texture classification using support vector machines and genetic algorithms an hybrid approach for texture image analysis",

abstract = "In this paper, a novel texture classification method from two-dimensional electrophoresis gel images is presented. Such a method makes use of textural features that are reduced to a more compact and efficient subset of characteristics by means of a Genetic Algorithm-based feature selection technique. Then, the selected features are used as inputs for a classifier, in this case a Support Vector Machine. The accuracy of the proposed method is around 94%, and has shown to yield statistically better performances than the classification based on the entire feature set. We found that the most decisive and representative features for the textural classification of proteins are those related to the second order co-occurrence matrix. This classification step can be very useful in order to discard over-segmented areas after a protein segmentation or identification process.",

keywords = "Electrophoresis, Feature selection, Genetic algorithm, Support vector machines, Texture analysis",

author = "Carlos Fernandez-Lozano and Seoane, {Jose A.} and Pablo Mesejo and Nashed, {Youssef S.G.} and Stefano Cagnoni and Julian Dorado",

year = "2013",

language = "English (US)",

isbn = "9789898565358",

series = "BIOINFORMATICS 2013 - Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms",

pages = "5--14",

booktitle = "BIOINFORMATICS 2013 - Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms",

note = "International Conference on Bioinformatics Models, Methods and Algorithms, BIOINFORMATICS 2013 ; Conference date: 11-02-2013 Through 14-02-2013",

}

Fernandez-Lozano, C, Seoane, JA, Mesejo, P, Nashed, YSG, Cagnoni, S & Dorado, J 2013, 2D-page texture classification using support vector machines and genetic algorithms an hybrid approach for texture image analysis. in BIOINFORMATICS 2013 - Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms. BIOINFORMATICS 2013 - Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms, pp. 5-14, International Conference on Bioinformatics Models, Methods and Algorithms, BIOINFORMATICS 2013, Barcelona, Spain, 2/11/13.

2D-page texture classification using support vector machines and genetic algorithms an hybrid approach for texture image analysis. / Fernandez-Lozano, Carlos; Seoane, Jose A.; Mesejo, Pablo et al.
BIOINFORMATICS 2013 - Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms. 2013. p. 5-14 (BIOINFORMATICS 2013 - Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - 2D-page texture classification using support vector machines and genetic algorithms an hybrid approach for texture image analysis

AU - Fernandez-Lozano, Carlos

AU - Seoane, Jose A.

AU - Mesejo, Pablo

AU - Nashed, Youssef S.G.

AU - Cagnoni, Stefano

AU - Dorado, Julian

PY - 2013

Y1 - 2013

N2 - In this paper, a novel texture classification method from two-dimensional electrophoresis gel images is presented. Such a method makes use of textural features that are reduced to a more compact and efficient subset of characteristics by means of a Genetic Algorithm-based feature selection technique. Then, the selected features are used as inputs for a classifier, in this case a Support Vector Machine. The accuracy of the proposed method is around 94%, and has shown to yield statistically better performances than the classification based on the entire feature set. We found that the most decisive and representative features for the textural classification of proteins are those related to the second order co-occurrence matrix. This classification step can be very useful in order to discard over-segmented areas after a protein segmentation or identification process.

AB - In this paper, a novel texture classification method from two-dimensional electrophoresis gel images is presented. Such a method makes use of textural features that are reduced to a more compact and efficient subset of characteristics by means of a Genetic Algorithm-based feature selection technique. Then, the selected features are used as inputs for a classifier, in this case a Support Vector Machine. The accuracy of the proposed method is around 94%, and has shown to yield statistically better performances than the classification based on the entire feature set. We found that the most decisive and representative features for the textural classification of proteins are those related to the second order co-occurrence matrix. This classification step can be very useful in order to discard over-segmented areas after a protein segmentation or identification process.

KW - Electrophoresis

KW - Feature selection

KW - Genetic algorithm

KW - Support vector machines

KW - Texture analysis

UR - http://www.scopus.com/inward/record.url?scp=84878002778&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878002778&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84878002778

SN - 9789898565358

T3 - BIOINFORMATICS 2013 - Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms

SP - 5

EP - 14

BT - BIOINFORMATICS 2013 - Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms

T2 - International Conference on Bioinformatics Models, Methods and Algorithms, BIOINFORMATICS 2013

Y2 - 11 February 2013 through 14 February 2013

ER -

Fernandez-Lozano C, Seoane JA, Mesejo P, Nashed YSG, Cagnoni S, Dorado J. 2D-page texture classification using support vector machines and genetic algorithms an hybrid approach for texture image analysis. In BIOINFORMATICS 2013 - Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms. 2013. p. 5-14. (BIOINFORMATICS 2013 - Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms).

2D-page texture classification using support vector machines and genetic algorithms an hybrid approach for texture image analysis

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this