Polynomial regression, area and length based filtering to remove misclassified pixels acquired in the crack segmentation process of 2D X-ray CT images of tested plaster specimens

Ujjal Kumar Bhowmik; Tyler Cork; Nick W. Hudyma

doi:10.1109/CSCI.2015.141

Polynomial regression, area and length based filtering to remove misclassified pixels acquired in the crack segmentation process of 2D X-ray CT images of tested plaster specimens

Ujjal Kumar Bhowmik, Tyler Cork, Nick W. Hudyma

Civil Engineering Department

Catholic University of America

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

Abstract

This work presents an effective and robust technique to remove misclassified pixels acquired in the crack segmentation process of 2D X-ray CT images of tested plaster specimens. Cracks have distinct properties, such as they are fairly piece-wise linear, and they have certain area and length ratios, which can be used to remove misclassified pixels from cracks segments. In this paper, a combination of polynomial regression and area-based, length-based filtering scheme is applied to remove undesired pixels from the 2D CT images of plaster specimen. With the help of experimental results the effectiveness and robustness of the proposed technique are verified.

Original language	English
Title of host publication	Proceedings - 2015 International Conference on Computational Science and Computational Intelligence, CSCI 2015
Editors	Quoc-Nam Tran, Leonidas Deligiannidis, Hamid R. Arabnia
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	437-442
Number of pages	6
ISBN (Electronic)	9781467397957
DOIs	https://doi.org/10.1109/CSCI.2015.141
State	Published - 2 Mar 2016
Event	International Conference on Computational Science and Computational Intelligence, CSCI 2015 - Las Vegas, United States Duration: 7 Dec 2015 → 9 Dec 2015

Publication series

Name	Proceedings - 2015 International Conference on Computational Science and Computational Intelligence, CSCI 2015

Conference

Conference	International Conference on Computational Science and Computational Intelligence, CSCI 2015
Country/Territory	United States
City	Las Vegas
Period	7/12/15 → 9/12/15

Keywords

Area-based filtering
Computed tomography (CT)
Length-based filtering
Local entropy based thresholding
Polynomial regression based filtering

Access to Document

10.1109/CSCI.2015.141

Cite this

Bhowmik, U. K., Cork, T., & Hudyma, N. W. (2016). Polynomial regression, area and length based filtering to remove misclassified pixels acquired in the crack segmentation process of 2D X-ray CT images of tested plaster specimens. In Q.-N. Tran, L. Deligiannidis, & H. R. Arabnia (Eds.), Proceedings - 2015 International Conference on Computational Science and Computational Intelligence, CSCI 2015 (pp. 437-442). Article 7424132 (Proceedings - 2015 International Conference on Computational Science and Computational Intelligence, CSCI 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CSCI.2015.141

Bhowmik, Ujjal Kumar ; Cork, Tyler ; Hudyma, Nick W. / Polynomial regression, area and length based filtering to remove misclassified pixels acquired in the crack segmentation process of 2D X-ray CT images of tested plaster specimens. Proceedings - 2015 International Conference on Computational Science and Computational Intelligence, CSCI 2015. editor / Quoc-Nam Tran ; Leonidas Deligiannidis ; Hamid R. Arabnia. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 437-442 (Proceedings - 2015 International Conference on Computational Science and Computational Intelligence, CSCI 2015).

@inproceedings{533921aa98c045ee904e6c49771aed0e,

title = "Polynomial regression, area and length based filtering to remove misclassified pixels acquired in the crack segmentation process of 2D X-ray CT images of tested plaster specimens",

abstract = "This work presents an effective and robust technique to remove misclassified pixels acquired in the crack segmentation process of 2D X-ray CT images of tested plaster specimens. Cracks have distinct properties, such as they are fairly piece-wise linear, and they have certain area and length ratios, which can be used to remove misclassified pixels from cracks segments. In this paper, a combination of polynomial regression and area-based, length-based filtering scheme is applied to remove undesired pixels from the 2D CT images of plaster specimen. With the help of experimental results the effectiveness and robustness of the proposed technique are verified.",

keywords = "Area-based filtering, Computed tomography (CT), Length-based filtering, Local entropy based thresholding, Polynomial regression based filtering",

author = "Bhowmik, {Ujjal Kumar} and Tyler Cork and Hudyma, {Nick W.}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; International Conference on Computational Science and Computational Intelligence, CSCI 2015 ; Conference date: 07-12-2015 Through 09-12-2015",

year = "2016",

month = mar,

day = "2",

doi = "10.1109/CSCI.2015.141",

language = "English",

series = "Proceedings - 2015 International Conference on Computational Science and Computational Intelligence, CSCI 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "437--442",

editor = "Quoc-Nam Tran and Leonidas Deligiannidis and Arabnia, {Hamid R.}",

booktitle = "Proceedings - 2015 International Conference on Computational Science and Computational Intelligence, CSCI 2015",

}

Bhowmik, UK, Cork, T & Hudyma, NW 2016, Polynomial regression, area and length based filtering to remove misclassified pixels acquired in the crack segmentation process of 2D X-ray CT images of tested plaster specimens. in Q-N Tran, L Deligiannidis & HR Arabnia (eds), Proceedings - 2015 International Conference on Computational Science and Computational Intelligence, CSCI 2015., 7424132, Proceedings - 2015 International Conference on Computational Science and Computational Intelligence, CSCI 2015, Institute of Electrical and Electronics Engineers Inc., pp. 437-442, International Conference on Computational Science and Computational Intelligence, CSCI 2015, Las Vegas, United States, 7/12/15. https://doi.org/10.1109/CSCI.2015.141

Polynomial regression, area and length based filtering to remove misclassified pixels acquired in the crack segmentation process of 2D X-ray CT images of tested plaster specimens. / Bhowmik, Ujjal Kumar; Cork, Tyler; Hudyma, Nick W.
Proceedings - 2015 International Conference on Computational Science and Computational Intelligence, CSCI 2015. ed. / Quoc-Nam Tran; Leonidas Deligiannidis; Hamid R. Arabnia. Institute of Electrical and Electronics Engineers Inc., 2016. p. 437-442 7424132 (Proceedings - 2015 International Conference on Computational Science and Computational Intelligence, CSCI 2015).

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

TY - GEN

T1 - Polynomial regression, area and length based filtering to remove misclassified pixels acquired in the crack segmentation process of 2D X-ray CT images of tested plaster specimens

AU - Bhowmik, Ujjal Kumar

AU - Cork, Tyler

AU - Hudyma, Nick W.

PY - 2016/3/2

Y1 - 2016/3/2

N2 - This work presents an effective and robust technique to remove misclassified pixels acquired in the crack segmentation process of 2D X-ray CT images of tested plaster specimens. Cracks have distinct properties, such as they are fairly piece-wise linear, and they have certain area and length ratios, which can be used to remove misclassified pixels from cracks segments. In this paper, a combination of polynomial regression and area-based, length-based filtering scheme is applied to remove undesired pixels from the 2D CT images of plaster specimen. With the help of experimental results the effectiveness and robustness of the proposed technique are verified.

AB - This work presents an effective and robust technique to remove misclassified pixels acquired in the crack segmentation process of 2D X-ray CT images of tested plaster specimens. Cracks have distinct properties, such as they are fairly piece-wise linear, and they have certain area and length ratios, which can be used to remove misclassified pixels from cracks segments. In this paper, a combination of polynomial regression and area-based, length-based filtering scheme is applied to remove undesired pixels from the 2D CT images of plaster specimen. With the help of experimental results the effectiveness and robustness of the proposed technique are verified.

KW - Area-based filtering

KW - Computed tomography (CT)

KW - Length-based filtering

KW - Local entropy based thresholding

KW - Polynomial regression based filtering

UR - http://www.scopus.com/inward/record.url?scp=84964490257&partnerID=8YFLogxK

U2 - 10.1109/CSCI.2015.141

DO - 10.1109/CSCI.2015.141

M3 - Conference contribution

AN - SCOPUS:84964490257

T3 - Proceedings - 2015 International Conference on Computational Science and Computational Intelligence, CSCI 2015

SP - 437

EP - 442

BT - Proceedings - 2015 International Conference on Computational Science and Computational Intelligence, CSCI 2015

A2 - Tran, Quoc-Nam

A2 - Deligiannidis, Leonidas

A2 - Arabnia, Hamid R.

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - International Conference on Computational Science and Computational Intelligence, CSCI 2015

Y2 - 7 December 2015 through 9 December 2015

ER -

Bhowmik UK, Cork T, Hudyma NW. Polynomial regression, area and length based filtering to remove misclassified pixels acquired in the crack segmentation process of 2D X-ray CT images of tested plaster specimens. In Tran QN, Deligiannidis L, Arabnia HR, editors, Proceedings - 2015 International Conference on Computational Science and Computational Intelligence, CSCI 2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 437-442. 7424132. (Proceedings - 2015 International Conference on Computational Science and Computational Intelligence, CSCI 2015). doi: 10.1109/CSCI.2015.141

Polynomial regression, area and length based filtering to remove misclassified pixels acquired in the crack segmentation process of 2D X-ray CT images of tested plaster specimens

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this