The size and morphology of precipitated barium sulphate crystals have been quantified by semi-automated image analysis. Using a set of six bi-dimensional shape descriptors and a pseudo-3D parameter and with the help of statistical tools such as principal component analysis and factorial discriminant analysis, it is possible to discriminate the various habits of barite, found in literature or obtained in our experiments under various operational conditions (single or double feed, feed injection position, feed rates) related to macro and micromixing. By examination of sets of at least 80 crystals per sample, the effect of these conditions on the shape and size of barite have been evaluated.