Abstract
Plant shape, an important factor in soybean plant breeding, is currently evaluated visually by soybean plant breeders, often making judgment unstable and subjective. The purpose of our study was to create procedure for objectively evaluating soybean plant shape. Features of shape were determined by image analysis. Tree-based models based on recursive partitioning were then used to categorize shapes into three classes -- “good”, “fair” and ”poor”-- or two classes ”good”and ”not good.”Classification results based on tree-based models demonstrated highly acceptable predictability. Although model-based performance attained approximately the same discriminatory level as conventional linear discriminant function, it had the distinct advantage of outstanding interpretability, with shape parameters in the best predictive tree-based model coinciding with those selected empirically by expert breeders.
