Related Experiment Video
Updated: Jun 6, 2026
High Throughput Image-Based Phenotyping for Determining Morphological and Physiological Responses to Single and Combined Stresses in Potato
Published on: June 7, 2024
Image analysis optimisation for carotenoid and anthocyanin content prediction in carrots: addressing colour parameter
Alma C Verme1, Mark Melchior1, Jan H van den Berg1
1Brightlands Future Farming Institute, Department of Plant Envirogenetics, Faculty of Science and Engineering, Maastricht University, Venlo, Netherlands.
Introduction:
Colorimetric analysis of food using the CIELab/Ch colour space (i.e., from digital images of samples) is an accessible, non-destructive method for carotenoid and anthocyanin content prediction. Literature presents very well-fit, but rudimentary, models for pigment estimation (e.g., single/multiple linear regressions). However, standardised methods that statistically account for the high multicollinearity between CIELab/Ch colour parameters, varying light conditions and colour calibration, and samples with high genotypic variability are lacking.
Methods:
An image analysis optimisation was developed for the prediction of carotenoid and anthocyanin content of 16 carrot genotypes of different colours. Samples were photographed under six light conditions with a digital camera and image colour was calibrated before analysis with the CIELab/Ch colour space. Total pigment contents and individual carotenoid contents were analysed chemically via spectrophotometry and high-performance liquid chromatography, respectively. Partial least squares (PLS) regressions were used to assess the colour-pigment relationships to correct for high multicollinearity amongst the independent variables (CIELab/Ch colour parameters).
Results/Discussion:
The PLS models achieved satisfactory accuracy for the prediction of total carotenoid content (ca. R2 = 0.77) and total anthocyanin content (ca. R2 = 0.81) under all light conditions. The two models are suggested as robust approaches to total pigment prediction with multi-dimensional colour spaces, varying light conditions, and for a sample group of high genotypic variability. The carrot samples proved to have very high genetic diversity within each cultivar, resulting in unsatisfactory models for prediction of individual carotenoids (ca. R2 = 0.45) under the default light condition. However, all the results can be used to expand databases (towards artificial intelligence) and aid breeding programmes in search for higher concentrations of these interesting antioxidants for human health.
