Mineral recognition in digital images of rocks: a new approach using multichannel classification

Digital image-analysis is used for counting (modal analysis) and measuring grains (texture and fabric analysis). Traditionally, minerals are visually recognized and manually outlined prior to digitizing and subsequent analysis. This limitation can be overcome by using multichannel methods of classification, in which the minerals in multichannel digital images are accurately recognized on the basis of their unique spectral or elemental signatures, established by a training stage prior to classification. The technique is applied here for the modal analysis of three-color, electro-optical images digitized using CCD video cameras and scanners, and multi-elemental X-ray maps acquired with an electron microprobe. In all three case studies of the analysis of plutonic igneous rocks, the resulting mineral modes are sufficiently precise to identify significant compositional heterogeneities between groups of samples and, in the case of X-ray element maps, to quantify the degree and type of alteration. -Authors