Fig. 7From: DeepCob: precise and high-throughput analysis of maize cob geometry using deep learning with an application in genebank phenomicsClustering of individual images by their heterogeneity of maize cob traits within images. Clustering approaches with the extracted cob traits. A First two principal components showing the average color of individual cobs (\(n=\mathrm{19,867}\) cobs) (left) and average cob color per analyzed image (\(n=\mathrm{3,302}\) images) (right). The colors of each dot reflect the average RGB values (i.e., the color) of each cob, or image, respectively. B PCA plots showing clusters identified with the multivariate clustering methods CLARA (left) and \(k\)-means clustering (right). C Distribution of cob traits within each method and clusterBack to article page