Using more than 1000 thin section photos of ancient (Phanerozoic) carbonates from different marine environments (pelagic to shallow-water) a new numerical methodology, based on digitized images ofthin sections, is proposed here. In accordance with the Dunham classification, it allows the user to automatically identify carbonate textures unaffected by post-depositional modifications (recrystallization, dolomitization, meteoric dissolution and so on). The methodology uses, as input, 256 grey-tone digital image and by image processing gives, as output, a set of23 values ofnumerical features measured on the whole image including the ‘‘white areas’’ (calcite cement). A multi-layer perceptron neural network takes as input this features and gives, as output, the estimated class. We used 532 images of thin sections to train the neural network, whereas to test the methodology we used 268 images taken from the same photo collection and 215 images from San Lorenzello carbonate sequence (Matese Mountains, southern Italy), Early Cretaceous in age. This technique has shown 93.3% and 93.5% ofaccuracy to classify automatically textures ofcarbonate rocks using digitized images on the 268 and 215 test sets, respectively. Therefore, the proposed methodology is a further promising application to the geosciences allowing carbonate textures ofmany thin sections to be identified in a rapid and accurate way. A MATLAB-based computer code has been developed for the processing and display of images

Textural identification of carbonate rocks by image processing and neural network. A new methodology

AMODIO, Sabrina;
2005-01-01

Abstract

Using more than 1000 thin section photos of ancient (Phanerozoic) carbonates from different marine environments (pelagic to shallow-water) a new numerical methodology, based on digitized images ofthin sections, is proposed here. In accordance with the Dunham classification, it allows the user to automatically identify carbonate textures unaffected by post-depositional modifications (recrystallization, dolomitization, meteoric dissolution and so on). The methodology uses, as input, 256 grey-tone digital image and by image processing gives, as output, a set of23 values ofnumerical features measured on the whole image including the ‘‘white areas’’ (calcite cement). A multi-layer perceptron neural network takes as input this features and gives, as output, the estimated class. We used 532 images of thin sections to train the neural network, whereas to test the methodology we used 268 images taken from the same photo collection and 215 images from San Lorenzello carbonate sequence (Matese Mountains, southern Italy), Early Cretaceous in age. This technique has shown 93.3% and 93.5% ofaccuracy to classify automatically textures ofcarbonate rocks using digitized images on the 268 and 215 test sets, respectively. Therefore, the proposed methodology is a further promising application to the geosciences allowing carbonate textures ofmany thin sections to be identified in a rapid and accurate way. A MATLAB-based computer code has been developed for the processing and display of images
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11367/20367
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 87
  • ???jsp.display-item.citation.isi??? 61
social impact