Industrial-scale cultivation of plant cells for valuable product recovery (e.g. natural pigments, pharmaceutical compounds) can only be considered commercially-feasible when a fully-automated, predictable bioprocess is achieved. Automation of cell selection, quantification, and sorting procedures, and pinpointing of optimal microenvironmental regimes can be approached via machine vision. Macroscopic staging of Ajuga reptans callus masses (ranging between 2-6 g FW) permitted simultaneous rapid capture of top and side views. Area data used in a linear regression model yielded a reliable, non-destructive estimate of fresh mass. Suspension culture images from the same cell line were microscopically imaged at 4x (with an inverted microscope). Using color machine vision, the HSI (hue-saturation-intensity) coordinates were used to successfully separate pigmented cells and aggregates from non-pigmented cells, aggregates, and background debris. Time-course sampling of a routine suspension culture consistently allowed pigmented cells to be detected, and intensity could be correlated with the degree of pigmentation as verified using spectrophotometer analysis of parallel samples.