Spectral and spatial classification of earthquake images by support vector selection and adaptation

Gulşen Taşkin Kaya; Okan K. Ersoy; Mustafa E. Kamaşak

doi:10.1109/SOCPAR.2010.5686099

Spectral and spatial classification of earthquake images by support vector selection and adaptation

Purdue University

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

5 Citations (Scopus)

Abstract

The aim of this study is to extract homogenous and edge regions from a post-earthquake Quickbird satellite image with high resolution and to combine this spatial information with spectral information in classification of earthquake damage. In order to extract the homogenous and edge regions from the image, a spatial filtering approach and Canny filter were used. A novel method called support vector selection and adaptation (SVSA) was used in classification of earthquake damage. Pixel and texture-based classification were separately carried out in order to show their comparative classification performance. For implementation, a small region from city of Bam in Iran was selected.

Original language	English
Title of host publication	Proceedings of the 2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010
Pages	194-197
Number of pages	4
DOIs	https://doi.org/10.1109/SOCPAR.2010.5686099
Publication status	Published - 2010
Event	2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010 - Cergy-Pontoise, France Duration: 7 Dec 2010 → 10 Dec 2010

Publication series

Name	Proceedings of the 2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010

Conference

Conference	2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010
Country/Territory	France
City	Cergy-Pontoise
Period	7/12/10 → 10/12/10

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 11 Sustainable Cities and Communities

Access to Document

10.1109/SOCPAR.2010.5686099

Cite this

Kaya, G. T., Ersoy, O. K., & Kamaşak, M. E. (2010). Spectral and spatial classification of earthquake images by support vector selection and adaptation. In Proceedings of the 2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010 (pp. 194-197). Article 5686099 (Proceedings of the 2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010). https://doi.org/10.1109/SOCPAR.2010.5686099

Kaya, Gulşen Taşkin ; Ersoy, Okan K. ; Kamaşak, Mustafa E. / Spectral and spatial classification of earthquake images by support vector selection and adaptation. Proceedings of the 2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010. 2010. pp. 194-197 (Proceedings of the 2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010).

@inproceedings{9d32ceef54354db48a187c31521e8861,

title = "Spectral and spatial classification of earthquake images by support vector selection and adaptation",

abstract = "The aim of this study is to extract homogenous and edge regions from a post-earthquake Quickbird satellite image with high resolution and to combine this spatial information with spectral information in classification of earthquake damage. In order to extract the homogenous and edge regions from the image, a spatial filtering approach and Canny filter were used. A novel method called support vector selection and adaptation (SVSA) was used in classification of earthquake damage. Pixel and texture-based classification were separately carried out in order to show their comparative classification performance. For implementation, a small region from city of Bam in Iran was selected.",

author = "Kaya, \{Gul{\c s}en Ta{\c s}kin\} and Ersoy, \{Okan K.\} and Kama{\c s}ak, \{Mustafa E.\}",

year = "2010",

doi = "10.1109/SOCPAR.2010.5686099",

language = "English",

isbn = "9781424478958",

series = "Proceedings of the 2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010",

pages = "194--197",

booktitle = "Proceedings of the 2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010",

note = "2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010 ; Conference date: 07-12-2010 Through 10-12-2010",

}

Kaya, GT, Ersoy, OK & Kamaşak, ME 2010, Spectral and spatial classification of earthquake images by support vector selection and adaptation. in Proceedings of the 2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010., 5686099, Proceedings of the 2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010, pp. 194-197, 2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010, Cergy-Pontoise, France, 7/12/10. https://doi.org/10.1109/SOCPAR.2010.5686099

Spectral and spatial classification of earthquake images by support vector selection and adaptation. / Kaya, Gulşen Taşkin; Ersoy, Okan K.; Kamaşak, Mustafa E.
Proceedings of the 2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010. 2010. p. 194-197 5686099 (Proceedings of the 2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010).

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

TY - GEN

T1 - Spectral and spatial classification of earthquake images by support vector selection and adaptation

AU - Kaya, Gulşen Taşkin

AU - Ersoy, Okan K.

AU - Kamaşak, Mustafa E.

PY - 2010

Y1 - 2010

N2 - The aim of this study is to extract homogenous and edge regions from a post-earthquake Quickbird satellite image with high resolution and to combine this spatial information with spectral information in classification of earthquake damage. In order to extract the homogenous and edge regions from the image, a spatial filtering approach and Canny filter were used. A novel method called support vector selection and adaptation (SVSA) was used in classification of earthquake damage. Pixel and texture-based classification were separately carried out in order to show their comparative classification performance. For implementation, a small region from city of Bam in Iran was selected.

AB - The aim of this study is to extract homogenous and edge regions from a post-earthquake Quickbird satellite image with high resolution and to combine this spatial information with spectral information in classification of earthquake damage. In order to extract the homogenous and edge regions from the image, a spatial filtering approach and Canny filter were used. A novel method called support vector selection and adaptation (SVSA) was used in classification of earthquake damage. Pixel and texture-based classification were separately carried out in order to show their comparative classification performance. For implementation, a small region from city of Bam in Iran was selected.

UR - https://www.scopus.com/pages/publications/79951498095

U2 - 10.1109/SOCPAR.2010.5686099

DO - 10.1109/SOCPAR.2010.5686099

M3 - Conference contribution

AN - SCOPUS:79951498095

SN - 9781424478958

T3 - Proceedings of the 2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010

SP - 194

EP - 197

BT - Proceedings of the 2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010

T2 - 2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010

Y2 - 7 December 2010 through 10 December 2010

ER -

Kaya GT, Ersoy OK, Kamaşak ME. Spectral and spatial classification of earthquake images by support vector selection and adaptation. In Proceedings of the 2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010. 2010. p. 194-197. 5686099. (Proceedings of the 2010 International Conference of Soft Computing and Pattern Recognition, SoCPaR 2010). doi: 10.1109/SOCPAR.2010.5686099

Spectral and spatial classification of earthquake images by support vector selection and adaptation

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this