AUTOMATED IMAGE-ANALYSIS OF ICE THIN-SECTIONS - INSTRUMENTATION, METHODS AND EXTRACTION OF STEREOLOGICAL AND TEXTURAL PARAMETERS

Image-analysis procedures have been developed for a simple PC-based system to evaluate the textural features of ice thin sections automatically. The method yields parameters that describe both ice crystals and pores in an objective, reproducible manner. Specimens are recorded in linearly and circularly polarized light (ice grains) as well as in transmitted and incident plain light (pores) under standardized conditions. After preparative filtering, images are segmented through union of two Sobel-filtered images (ice crystals/grain boundaries) or through thresholding (ice crystals/pores). The quantification of texture is based on the evaluation of image contrast as well as on linear analysis and non-linear transforms to obtain information on grain-sizes and their distribution. In the study of ice pores, stereological effects of finite section thickness have to be corrected. The discussion focuses on errors involved in automated textural analysis and the glaciological yield of measured and derived parameters.