Machine vision for the quality assessment of emulsions in pharmaceutical processing

Abstract

Emulsion quality evaluation using machine vision techniques depends on the efficiency of the image segmentation algorithms. Two different machine vision techniques are investigated to determine their competency in detecting droplets from in-process microscopic images of a cream emulsion. Histogram-based segmentation shows promising potential compared to edge and symmetry detection. A statistical study of the droplet characteristics was conducted. The results demonstrate that the histogram-based approach is more proficient in the progressive analysis of droplet evolution during emulsification. A real-time integration of the technique is proposed, as a soft sensor, to predict the optimum process time and to increase manufacturing efficiency in chemical industries.