Assessment of segmentation methods for pore detection in cellular concrete images

Juan Fernando Gaviria-Hdz, Leidy Johanna Medina, Carlos Mera, Lina Chica, Lina María Sepúlveda-Cano

Resultado de la investigación: Capítulo del libro/informe/acta de congresoContribución a la conferenciaInvestigaciónrevisión exhaustiva

Resumen

In the last years the use of cellular concretes has been extended due to the rise in the ratio strength/weight reached. Porosity is a property that must be taken into account because it is associated directly to the performance of a cellular concrete. The mercury porosimetry and vacuum saturation are test used to concrete porosity. However, these tests are expensive, and it requires a careful preparation of samples. Another way to determine porosity and pore distribution over concrete is reconstruction using high-resolution images from microscopy. As an alternative, in this work we compare traditional edge detection methods and fractional derivate method to detect the pores in images taken from a flat sample of cellular concrete. The experiments show that the method based on fractional derivate is more accurate to detect the pores, which is the first step to estimate total porosity of cellular concrete through non-specialized images.

Idioma originalInglés
Título de la publicación alojada2019 22nd Symposium on Image, Signal Processing and Artificial Vision, STSIVA 2019 - Conference Proceedings
EditorialInstitute of Electrical and Electronics Engineers Inc.
ISBN (versión digital)9781728114910
DOI
EstadoPublicada - 1 abr 2019
Evento22nd Symposium on Image, Signal Processing and Artificial Vision, STSIVA 2019 - Bucaramanga, Colombia
Duración: 24 abr 201926 abr 2019

Serie de la publicación

Nombre2019 22nd Symposium on Image, Signal Processing and Artificial Vision, STSIVA 2019 - Conference Proceedings

Conferencia

Conferencia22nd Symposium on Image, Signal Processing and Artificial Vision, STSIVA 2019
PaísColombia
CiudadBucaramanga
Período24/04/1926/04/19

Huella dactilar

Concretes
Porosity
Mercury (metal)
Edge detection
Image resolution
Microscopic examination
Vacuum
Experiments

Citar esto

Gaviria-Hdz, J. F., Medina, L. J., Mera, C., Chica, L., & Sepúlveda-Cano, L. M. (2019). Assessment of segmentation methods for pore detection in cellular concrete images. En 2019 22nd Symposium on Image, Signal Processing and Artificial Vision, STSIVA 2019 - Conference Proceedings [8730220] (2019 22nd Symposium on Image, Signal Processing and Artificial Vision, STSIVA 2019 - Conference Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/STSIVA.2019.8730220
Gaviria-Hdz, Juan Fernando ; Medina, Leidy Johanna ; Mera, Carlos ; Chica, Lina ; Sepúlveda-Cano, Lina María. / Assessment of segmentation methods for pore detection in cellular concrete images. 2019 22nd Symposium on Image, Signal Processing and Artificial Vision, STSIVA 2019 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. (2019 22nd Symposium on Image, Signal Processing and Artificial Vision, STSIVA 2019 - Conference Proceedings).
@inproceedings{180c29e935784b71a894fc3159640e15,
title = "Assessment of segmentation methods for pore detection in cellular concrete images",
abstract = "In the last years the use of cellular concretes has been extended due to the rise in the ratio strength/weight reached. Porosity is a property that must be taken into account because it is associated directly to the performance of a cellular concrete. The mercury porosimetry and vacuum saturation are test used to concrete porosity. However, these tests are expensive, and it requires a careful preparation of samples. Another way to determine porosity and pore distribution over concrete is reconstruction using high-resolution images from microscopy. As an alternative, in this work we compare traditional edge detection methods and fractional derivate method to detect the pores in images taken from a flat sample of cellular concrete. The experiments show that the method based on fractional derivate is more accurate to detect the pores, which is the first step to estimate total porosity of cellular concrete through non-specialized images.",
keywords = "Cellular concrete, Fractional Derivative, Pore segmentation, Porosity estimation",
author = "Gaviria-Hdz, {Juan Fernando} and Medina, {Leidy Johanna} and Carlos Mera and Lina Chica and Sep{\'u}lveda-Cano, {Lina Mar{\'i}a}",
year = "2019",
month = "4",
day = "1",
doi = "10.1109/STSIVA.2019.8730220",
language = "Ingl{\'e}s",
series = "2019 22nd Symposium on Image, Signal Processing and Artificial Vision, STSIVA 2019 - Conference Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2019 22nd Symposium on Image, Signal Processing and Artificial Vision, STSIVA 2019 - Conference Proceedings",
address = "Estados Unidos",

}

Gaviria-Hdz, JF, Medina, LJ, Mera, C, Chica, L & Sepúlveda-Cano, LM 2019, Assessment of segmentation methods for pore detection in cellular concrete images. En 2019 22nd Symposium on Image, Signal Processing and Artificial Vision, STSIVA 2019 - Conference Proceedings., 8730220, 2019 22nd Symposium on Image, Signal Processing and Artificial Vision, STSIVA 2019 - Conference Proceedings, Institute of Electrical and Electronics Engineers Inc., Bucaramanga, Colombia, 24/04/19. https://doi.org/10.1109/STSIVA.2019.8730220

Assessment of segmentation methods for pore detection in cellular concrete images. / Gaviria-Hdz, Juan Fernando; Medina, Leidy Johanna; Mera, Carlos; Chica, Lina; Sepúlveda-Cano, Lina María.

2019 22nd Symposium on Image, Signal Processing and Artificial Vision, STSIVA 2019 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. 8730220 (2019 22nd Symposium on Image, Signal Processing and Artificial Vision, STSIVA 2019 - Conference Proceedings).

Resultado de la investigación: Capítulo del libro/informe/acta de congresoContribución a la conferenciaInvestigaciónrevisión exhaustiva

TY - GEN

T1 - Assessment of segmentation methods for pore detection in cellular concrete images

AU - Gaviria-Hdz, Juan Fernando

AU - Medina, Leidy Johanna

AU - Mera, Carlos

AU - Chica, Lina

AU - Sepúlveda-Cano, Lina María

PY - 2019/4/1

Y1 - 2019/4/1

N2 - In the last years the use of cellular concretes has been extended due to the rise in the ratio strength/weight reached. Porosity is a property that must be taken into account because it is associated directly to the performance of a cellular concrete. The mercury porosimetry and vacuum saturation are test used to concrete porosity. However, these tests are expensive, and it requires a careful preparation of samples. Another way to determine porosity and pore distribution over concrete is reconstruction using high-resolution images from microscopy. As an alternative, in this work we compare traditional edge detection methods and fractional derivate method to detect the pores in images taken from a flat sample of cellular concrete. The experiments show that the method based on fractional derivate is more accurate to detect the pores, which is the first step to estimate total porosity of cellular concrete through non-specialized images.

AB - In the last years the use of cellular concretes has been extended due to the rise in the ratio strength/weight reached. Porosity is a property that must be taken into account because it is associated directly to the performance of a cellular concrete. The mercury porosimetry and vacuum saturation are test used to concrete porosity. However, these tests are expensive, and it requires a careful preparation of samples. Another way to determine porosity and pore distribution over concrete is reconstruction using high-resolution images from microscopy. As an alternative, in this work we compare traditional edge detection methods and fractional derivate method to detect the pores in images taken from a flat sample of cellular concrete. The experiments show that the method based on fractional derivate is more accurate to detect the pores, which is the first step to estimate total porosity of cellular concrete through non-specialized images.

KW - Cellular concrete

KW - Fractional Derivative

KW - Pore segmentation

KW - Porosity estimation

UR - http://www.scopus.com/inward/record.url?scp=85068066499&partnerID=8YFLogxK

U2 - 10.1109/STSIVA.2019.8730220

DO - 10.1109/STSIVA.2019.8730220

M3 - Contribución a la conferencia

T3 - 2019 22nd Symposium on Image, Signal Processing and Artificial Vision, STSIVA 2019 - Conference Proceedings

BT - 2019 22nd Symposium on Image, Signal Processing and Artificial Vision, STSIVA 2019 - Conference Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Gaviria-Hdz JF, Medina LJ, Mera C, Chica L, Sepúlveda-Cano LM. Assessment of segmentation methods for pore detection in cellular concrete images. En 2019 22nd Symposium on Image, Signal Processing and Artificial Vision, STSIVA 2019 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. 8730220. (2019 22nd Symposium on Image, Signal Processing and Artificial Vision, STSIVA 2019 - Conference Proceedings). https://doi.org/10.1109/STSIVA.2019.8730220