Image Processing and Machine Learning Approaches for Petrographic Thin Section Analysis (Russian)

2017 ◽  
Author(s):  
Semen Budennyy ◽  
Alexey Pachezhertsev ◽  
Alexander Bukharev ◽  
Artem Erofeev ◽  
Dmitry Mitrushkin ◽  
...  
Keyword(s):  
Machine Learning ◽  
Image Processing ◽  
Thin Section ◽  
Learning Approaches ◽  
Thin Section Analysis ◽  
Petrographic Thin Section ◽  
Section Analysis

Image Processing and Machine Learning Approaches for Petrographic Thin Section Analysis

2017 ◽  
Author(s):  
Semen Budennyy ◽  
Alexey Pachezhertsev ◽  
Alexander Bukharev ◽  
Artem Erofeev ◽  
Dmitry Mitrushkin ◽  
...  
Keyword(s):  
Machine Learning ◽  
Image Processing ◽  
Thin Section ◽  
Learning Approaches ◽  
Thin Section Analysis ◽  
Petrographic Thin Section ◽  
Section Analysis

scholarly journals Facies And Diagenesis Of Tabalar And Tendehantu Carbonate Formation In Mangkalihat Peninsula Area: An Outcrop Preliminary Study To Oligocene – Miocene Reservoir Candidate Prospect

2012 ◽  
Vol 7 (2) ◽  
pp. 78-91
Author(s):  
Risman Adhitiya ◽  
Merza Media Adeyosfi ◽  
Syahreza S. Angkasa ◽  
Felix Sihombing
Keyword(s):  
Thin Section ◽  
Carbonate Rock ◽  
Carbonate Formation ◽  
Data Compilation ◽  
Sample Data ◽  
Preliminary Study ◽  
Thin Section Analysis ◽  
Fair Poor ◽  
Petrographic Thin Section ◽  
Section Analysis

Mangkalihat peninsula is located between Kutai and Tarakan basins, which known as two Hydro Carbon (HC) Prolific basins in Eastern Borneo. The petroleoum system in this area is poorly known because of the different system between Kutai and Tarakan Basin. The field study is focusing in the eastern part of Mangkalihat Peninsula, where The Tabalar and Tendehantu Formation are exposed. The data compilation is from outcrop, thin section and plug sample which permeability and porosity values were measured by Klickenberg method. Outcrop analysis showed that Tendehantu Formation can be divided into two lithofacies, whileTabalar Formation has only one lithofacies. The petrographic thin section analysis showed three microfacies from the two formations. Pore destruction caused by diagenesis can de indicated with the presence of bladed and equant cement in vuggy pores, while the diagenetical development of porosity is marked by the microfracturing that was assumed to be formed by compaction and deep burial and matrix dissolution in some of the samples. Petrography and plug sample data integration shows the quality value of those carbonate rock as a reservoir from the permeability and porosity parameter. Based on the microfacies grouping showed in three microfacies, the porosity value is 5.26 - 17.32 % (tight to good), and permeability value is 0.041 – 7.27mD (fair – poor). The carbonate rock quality is influenced by the whole diagenetic processes that happened in each lithofacies.

scholarly journals Analysis of the Nosema Cells Identification for Microscopic Images

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3068
Author(s):  
Soumaya Dghim ◽  
Carlos M. Travieso-González ◽  
Radim Burget
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Image Processing ◽  
Deep Learning ◽  
The Other ◽  
Support Vector ◽  
Learning Approaches ◽  
Microscopic Images ◽  
Trained Neural Network ◽  
Nosema Disease

The use of image processing tools, machine learning, and deep learning approaches has become very useful and robust in recent years. This paper introduces the detection of the Nosema disease, which is considered to be one of the most economically significant diseases today. This work shows a solution for recognizing and identifying Nosema cells between the other existing objects in the microscopic image. Two main strategies are examined. The first strategy uses image processing tools to extract the most valuable information and features from the dataset of microscopic images. Then, machine learning methods are applied, such as a neural network (ANN) and support vector machine (SVM) for detecting and classifying the Nosema disease cells. The second strategy explores deep learning and transfers learning. Several approaches were examined, including a convolutional neural network (CNN) classifier and several methods of transfer learning (AlexNet, VGG-16 and VGG-19), which were fine-tuned and applied to the object sub-images in order to identify the Nosema images from the other object images. The best accuracy was reached by the VGG-16 pre-trained neural network with 96.25%.

Sign in / Sign up

Export Citation Format

Share Document