Unsupervised Classification of Intrusive Igneous Rock Thin Section Images using Edge Detection and Colour Analysis
This addresses the labor-intensive task of rock classification for geologists by automating the process, though it is incremental as it builds on existing image analysis techniques.
The study tackled the problem of classifying intrusive igneous rock thin section images by developing an unsupervised method using edge detection and color analysis, achieving precision rates of 90% to 100%.
Classification of rocks is one of the fundamental tasks in a geological study. The process requires a human expert to examine sampled thin section images under a microscope. In this study, we propose a method that uses microscope automation, digital image acquisition, edge detection and colour analysis (histogram). We collected 60 digital images from 20 standard thin sections using a digital camera mounted on a conventional microscope. Each image is partitioned into a finite number of cells that form a grid structure. Edge and colour profile of pixels inside each cell determine its classification. The individual cells then determine the thin section image classification via a majority voting scheme. Our method yielded successful results as high as 90% to 100% precision.