Abstract Macroscopic images of callus colonies and microscopic images from suspension cultures of anthocyanin-producing Ajuga cells were analyzed by machine vision to appraise culture productivity (pigment accumulation and cell growth). Callus culture mass was accurately estimated using data from simultaneous capture of top and side view images. A comparison of several alternative regression models determined that this performance data could be obtained reliably without interrupting the culture cycle to weigh cell colonies. The best regression models could predict callus mass in the 2.12–5.95 g fresh weight range with a maximum error less than 11%. For suspension culture analysis, the detailed RGB (red-green-blue) information captured in each of the color microscopic images did not allow separation of pigmented cells and cell aggregates from non-pigmented entities and background in the medium, however, conversion of RGB data to the HSI (hue-saturation-intensity) coordinate system permitted clear separation of object classes based on a combination of dimensional and photometric information. Further segmentation using saturation and intensity characteristics of the HSI values allowed categorization of low, medium, and highly-pig- mented cells and aggregates in the mixed suspension, and machine vision data was able to track both biomass accumulation and anthocyanin pigment formation over time as verified by mass and spectrophotometric analysis of the same cultures.