A bulk solid material may be defined as a collection of particles or granules, the properties of which are descriptive of the whole (e. g. bulk composition) as well as of individual particles (e. g. particle mineralogy, particle size and shape). The particle and bulk properties of granular materials have a very significant effect on the performance of bulk solid handling plants. Referring to an operating plant, an appropriate sampling methodology has to be applied to collect a set representative of the whole. Different analytical techniques to characterize particulate solids and to determine their properties can be employed in order to compare their results and efficiency. In this work, chemical and imaging-based analyses were applied and compared, in order to define the relevant information to set up an automatic recognition procedure, by utilizing a proper classification algorithm. The results obtained on applying a traditional physical separation and a new approach were matched in terms of efficiency. The data are to be applied to check on-line monitoring procedures related to silicate raw materials.