Statistical methods for segmentation and quantification of minerals in ore microscopy

Köse, Cemal; Alp, İbrahi̇m; İkibaş, Cevat

doi:10.1016/j.mineng.2012.01.008

Cited by 19 publications

(9 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These mineral surfaces are generally acquired from the polished section of particles (Figure 1) settled in epoxy resin. The use of a polished section is quite common for (i) automatic identification/quantification of rockforming minerals [1][2][3][4][5][6][7] and (ii) prediction of the mineral liberation spectrum, i.e. distribution of a selected mineral phase in a population of particles [8][9][10][11][12].…”

Section: Using Random Forest Tree Classification For Evaluating Vertical Cross-sections In Epoxy Blocks To Get Unbiased Estimates For 3d mentioning

confidence: 99%

Using Random Forest Tree Classification for Evaluating Vertical Cross-Sections in Epoxy Blocks to Get Unbiased Estimates for 3D Mineral Map

Camalan

Çavur²

2021

Politeknik Dergisi

View full text Add to dashboard Cite

show abstract

Section: Using Random Forest Tree Classification For Evaluating Vertical Cross-sections In Epoxy Blocks To Get Unbiased Estimates For 3d mentioning

confidence: 99%

Using Random Forest Tree Classification for Evaluating Vertical Cross-Sections in Epoxy Blocks to Get Unbiased Estimates for 3D Mineral Map

Camalan

Çavur²

2021

Politeknik Dergisi

View full text Add to dashboard Cite

show abstract

“…2D images can be digitized on polished sections of particles by an ore microscope [18] or backscattered electron (BSE) imaging [19,20] on a scanning electron microscope (SEM). The optical micrographs can be evaluated with various image processing methods [11,[21][22][23][24][25][26] for the construction of a 2D mineral map on particles. However, the reflected light imaging in ore microscopy generates indistinguishable images of siliceous nonopaque minerals and epoxy resin as the reflected light spectra of the transparent minerals and epoxy resin are very similar [27].…”

Section: Introductionmentioning

confidence: 99%

Development of a supervised classification method to construct 2D mineral mapson backscattered electron images

Camalan¹,

Çavur²

2020

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

The Mineral Liberation Analyzer (MLA) can be used to obtain mineral maps from backscattered electron (BSE) images of particles. This paper proposes an alternative methodology that includes random forest classification, a prospective machine learning algorithm, to develop mineral maps from BSE images. The results show that the overall accuracy and kappa statistic of the proposed method are 97% and 0.94, respectively, proving that random forest classification is accurate. The accuracy indicators also suggest that the proposed method may be applied to classify minerals with similar appearances under BSE imaging. Meanwhile, random forest predicts fewer middling particles with binary and ternary composition, but the MLA predicts more middling particles only with ternary composition. These discrepancies may arise because the MLA, unlike random forest, may also measure the elemental compositions of mineral surfaces below the polished section.

show abstract

“…Mikroskobik görüntülerin hızlı, güvenilir ve doğru bir şekilde ölçümü ve analizi son zamanlarda özellikle boyut küçültme optimizasyonu ve modifikasyonu çalışmalarında da büyük önem taşımaktadır. Tam otomatik sistemler mineral analiz çalışanlarının iş yükünü büyük ölçüde azaltmaktadır [11]. Clemex gibi bazı görüntü analiz sistemleri ile minerallerin genişlik, uzunluk, alan, gerçek uzunluk, yüzde olarak miktarları, çevre, yuvarlaklık, en büyük en küçük ve ortalama çap miktarları, serbestleşme ve bağlı danelerin oranları ve dane çapı dağılım aralıkları gibi özelliklerin belirlenmesi mümkündür [9].…”

Section: Gi̇ri̇ş (Introduction)unclassified

İleri̇ Mi̇kroskopi̇ Yöntemleri̇ İle Parlak Kesi̇t Anali̇zleri̇

Karaman¹,

Şahinoğlu²,

Alp³

et al. 2017

NWSA

Self Cite

View full text Add to dashboard Cite

İLERİ MİKROSKOPİ YÖNTEMLERİ İLE PARLAK KESİT ANALİZLERİ ÖZBu çalışmanın amacı pirit içeren kayaçların parlak kesit analizlerini, yeni bir teknik olan trinoküler araştırma mikroskobuna entegre clemex görüntü analiz sistemi ve motorize tabla kullanarak yapmaktır. Motorize tabla ile bütün kesitin patern oluşturarak taranması mümkün olmuştur. Clemex görüntü analiz sistemi ile çok kısa sürede analizler yapılabilmiştir. Bu nedenle manuel olarak yapılan analizlere göre daha güvenilir ve daha hızlı olduğu anlaşılmıştır. Çalışılan kayaçlardaki pirit oranı (%0.09-%2.13) ve pirite ait en küçük (24µm), en büyük (895µm) ve ortalama dane çapları (48µm-132µm)hesaplanmıştır. Sonuç olarak daha kısa sürede daha doğru sonuçlar alma açısından motorize tabla ve clemex gibi sistemlerin kullanılmasının önem taşıdığı anlaşılmıştır.Anahtar Kelimeler: Clemex, Motorize Tabla, Parlak Kesit, Pirit, Kayaç ANALYSES OF POLISHED SECTION VIA ADVANCED MICROSCOPY METHODS ABSTRACTThe aim of this study is to perform polished section analyses of rocks that contain pyrite with clemex image analysis system and motorized table which are integrated into the trinocular research microscope that is a new technique. It was possible to pattern scanning the entire cross section with the motorized table. With the clemex image analysis system, very short time analyzes were possible. For this reason, it is understood that it is more reliable and faster than the manual analysis. The rate of pyrite (0.09%-2.13%) in the rocks studied and the smallest (24µm), largest (895µm) and average grain diameters (48µm-132µm) of pyrite were calculated. Consequently, it was understood that the importance of using the systems such as motorized table and clemex in terms of getting more accurate results in a short time.

show abstract

Statistical methods for segmentation and quantification of minerals in ore microscopy

Cited by 19 publications

References 58 publications

Using Random Forest Tree Classification for Evaluating Vertical Cross-Sections in Epoxy Blocks to Get Unbiased Estimates for 3D Mineral Map

Using Random Forest Tree Classification for Evaluating Vertical Cross-Sections in Epoxy Blocks to Get Unbiased Estimates for 3D Mineral Map

Development of a supervised classification method to construct 2D mineral mapson backscattered electron images

İleri̇ Mi̇kroskopi̇ Yöntemleri̇ İle Parlak Kesi̇t Anali̇zleri̇

Contact Info

Product

Resources

About