Automated Mineral Classification and Measurement Using Machine Learning and Image Analysis

Automated Sample Analysis

Light microscopes are used daily in the evaluation of mining samples to assess the performance of the recovery process, and during exploration for new resources. Operators must perform a rigorous and accurate evaluation of samples daily, a task that can prove arduous and consume a reasonable proportion of the day. With ZEN Intellesis, and ZEN Image Analysis, the classification and measurement of the mineralogy is automatically performed, thus freeing the operator to concentrate on the interpretation of the data and their other tasks.

ZEN Intellesis in combination with ZEN Image Analysis offer advanced machine learning, trainable on site, to differentiate mineralogy for object classification and measurement; resulting in faster time to results and efficiency improvements.

Figure 1: Reflected light image acquired with ZEISS Axiolab 5. Sample of milled copper ore mounted in a resin block and previously prepared for SEM analysis. Remnants of a carbon coating remain on some surfaces

Consistent Sample Evaluation

Quality monitoring is a continuous process reliant on feeding data into an information loop from which operational decisions are made. Evidence gathered over time forms the basis for strategic planning. Reliable, consistent data is imperative in such a situation. Unlike human operators, the ZEN Intellesis and Image Analysis modules do not tire on long days and promise consistent results sample after sample.

Figure 2: Artificial color map following Intellesis classification. Despite the challenges presented by sample preparation, e.g., the impossibility of obtaining a transmitted light image, surface scratches, and gauges, Intellesis automatically classifies the individual constituents of this image. Resin in light grey, gangue in dark grey, pyrite in brown, chalcopyrite in orange, and chalcocite in blue.