Figure 3.

Figure 3. The Vision Transformer model, with a random crop and voting strategy, achieves an F-score of 0.91.

(A) Schematic flowchart of the inputs, Vision Transformer model, and growth size classification. Two different inputs were fed to the model. Input #1 was the original palmskin images; Input #2 had random cropping, a data augmentation technique, applied to the palmskin images to generate a larger set of imaging data for the model. (B) Schematic flowchart of the isometric cropping and voting. Isometric cropping was used in the test dataset, and voting was used to consolidate all size predictions based on each sub-crop. (C, D) Confusion matrix and F-scores for the “No voting” and “Voting” conditions. Scores above 0.7 are shown in black for ease of visualization.