Semi-automated porosity identification from thin section images using image analysis and intelligent discriminant classifiers

Ghiasi-Freez, Javad; Soleimanpour, Iman; Kadkhodaie, Ali; Ziaii, Mansour; Sedighi, Mahdi; Hatampour, Amir

doi:10.1016/j.cageo.2012.03.006

Cited by 42 publications

(42 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this work, three classifiers were used, namely RBF‐NN, support vector machine (SVM) and k ‐NN according to Anderson (1995), Corinna and Vapnik (1995), Lipo (2005), Ghiasi‐Freez et al . (2012) and Bizon et al . (2014).…”

Section: Experiments and Resultsmentioning

confidence: 96%

“…Previous studies have shown that a combination of multiple classifiers, rather than a single classifier, can provide for higher performance and accuracy (Woods et al, 1997;Kuncheva, 2001). Among others, radial basis function (RBF) neural network, support vector machine (SVM), and k-nearest neighbours (k-NN) have been used by researchers for pattern recognition purposes (Park, 1991;Corinna & Vapnik, 1995;Wang, 2005;Ghiasi-Freez et al, 2012;Bizon et al, 2014;Zhang, 2016;Sharifi et al, 2021). The results have been then fused (i.e.…”

Section: Figurementioning

confidence: 99%

“…6. In this work, three classifiers were used, namely RBF-NN, support vector machine (SVM) and k-NN according to Anderson (1995), Corinna and Vapnik (1995), Lipo (2005), Ghiasi-Freez et al (2012) and Bizon et al (2014). Accordingly, 190 and 60 objects from the catalogue (250 objects related to seven different pore types) were considered for training and testing the classifiers, respectively.…”

Section: Intelligent Pore Type Classificationmentioning

confidence: 99%

See 2 more Smart Citations

Intelligent pore type characterization: Improved theory for rock physics modelling

Sharifi

2022

Geophysical Prospecting

View full text Add to dashboard Cite

Thanks to the recent developments in both hardware and software capabilities of computers, intelligent rock physics modelling has emerged as an alternative to the conventional approach to the rock physics. Respecting the crucial contribution of the pore geometry into the rock physics modelling, I propose an accurate yet cost‐ and time‐efficient intelligent framework to measure pore space based on digital rock physics. In this method, total pore space was calculated after estimating the pore geometry through pattern recognition on thin section images captured through polarized‐light microscopy. Next, applying three different multi‐class classifiers (radial basis function, support vector machine and k‐nearest neighbours) for estimating pore type and aspect ratio, the best results were obtained using the fuzzy Sugeno integral, and the pore types were classified according to the most widely used pore type classification scheme. Next, an artificial neural network was applied to interpolate discrete data points (thin sections) into continuous profiles of pore type and aspect ratio. Subsequently, as a case study, the proposed approaches were applied to a real‐world carbonate reservoir for modelling the P‐ and S‐wave velocities through a rock physics model. Verifying the modelling results against ultrasonic and measured well‐logging data, the methodology showed promising performance at acceptable levels of uncertainty. The most significant advantage of the intelligent pore type quantification over the conventional methods was found to be its ability to estimate elastic properties with good accuracy. The key findings of this research include automatic detection of the pore types and aspect ratio, provision of a database of pore geometry, attenuation of uncertainty in pore type characterization and improvement of rock physics modelling in the absence of reliable S‐wave velocity data.

show abstract

Section: Experiments and Resultsmentioning

confidence: 96%

Section: Figurementioning

confidence: 99%

Section: Intelligent Pore Type Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent pore type characterization: Improved theory for rock physics modelling

Sharifi

2022

Geophysical Prospecting

View full text Add to dashboard Cite

show abstract

“…Connected pores can be seen by means of a blue penetrating liquid. Porosity is usually evaluated by a standard point counting technique, i.e., viewing polished thin sections under reflected light (Ghiasi-Freez et al, 2012) and counting the pores. In this study, however, a digital approach was used by digital scanning of the thin sections, as to evaluate and compare a more feasible and accurate method to identify pores in a thin section.…”

Section: Methodsmentioning

confidence: 99%

Comparison of pore space features by thin sections and X-ray microtomography

Alves

Lima

Assis

et al. 2014

Applied Radiation and Isotopes

View full text Add to dashboard Cite

Microtomographic (µCT) and thin section (TS) images were analyzed and compared regarding porosity and its distribution along the samples. The results show that µCT, although limited by its resolution, shows relevant information about the distribution of porosity and quantification of connected and non-connected pores. TS have no limitations concerning resolution, but are limited by the experimental data and can only give information about connected pores. These two methods have their own advantages but when paired together they are able to make for a more complete analysis.

show abstract

“…Based on their unique color, pores can be identified by threshold methods in the RGB or HSV color spaces [5,6]. In addition, pattern recognition and GIS-based methods are applied to extract the boundary and region of the pore as a polygon object, and, further, to quantitatively calculate its shape, orientation, type, and spatial distribution [7][8][9][10]. Moreover, the deep-learning methods classify the thin-section image pixel by pixel, which is called image semantic segmentation, creating the labeled output image, where every single labeled pixel represents a mineral class or pore [11,12].…”

Section: A Pore Information Extractionmentioning

confidence: 99%

Rock classification in petrographic thin section images based on concatenated convolutional neural networks

Zhu

et al. 2020

Earth Sci Inform

View full text Add to dashboard Cite

Rock classification plays an important role in rock mechanics, petrology, mining engineering, magmatic processes, and numerous other fields pertaining to geosciences. This study proposes a concatenated convolutional neural network (Con-CNN) method for classifying the geologic rock type based on petrographic thin sections. Herein, plane polarized light (PPL) and crossed polarized light (XPL) were used to acquire thin section images as the fundamental data. After conducting the necessary pre-processing analyses, the PPL and XPL images as well as their comprehensive image (CI) were incorporated in three convolutional neural networks (CNNs) comprising the same structure for achieving a preliminary classification; these images were developed by employing the fused principal component analysis (PCA). Subsequently, the results of the CNNs were concatenated by using the maximum likelihood detection to obtain a comprehensive classification result. Finally, a statistical revision was applied to fix the misclassification due to the proportion difference of minerals that were similar in appearance. In this study, 13 types of 92 rock samples, 196 petrographic thin sections, 588 images, and 63504 image patches were fabricated for the training and validation of the Con-CNN. The five-folds cross validation shows that the method proposed provides an overall accuracy of 89.97%, which facilitates the automation of rock classification in petrographic thin sections.

show abstract

Semi-automated porosity identification from thin section images using image analysis and intelligent discriminant classifiers

Cited by 42 publications

References 11 publications

Intelligent pore type characterization: Improved theory for rock physics modelling

Intelligent pore type characterization: Improved theory for rock physics modelling

Comparison of pore space features by thin sections and X-ray microtomography

Rock classification in petrographic thin section images based on concatenated convolutional neural networks

Contact Info

Product

Resources

About