The presence of shadows, holes, and gaps on soil images collected under natural conditions has a significant negative impact on machine vision classification of soil species. And the sample size for machine vision-based soil species identification is generally insufficient due to the high cost of acquiring and labeling soil photographs. A soil species classification method is presented based on subgraph selection to address above problems. The proposed approach first constructs an optimal model to select the centers of soil subgraph according to the principles of local shadow minimization and spatial distance maximization. And then creates a soil sub-image dataset on the basis of a center set obtained by iteratively updating a distance matrix utilizing above optimization model. Experimental results demonstrate that soil subgraph datasets established by the subgraph selection algorithm exhibit excellent performance on three ResNet models with different depths. ResNet-18 performs best when setting the adaptive factor α to 1 and the sub-image size is 224, with a validation set classification accuracy of 9248% and a test set classification accuracy of 9295%. In addition, it is 4665% superior than the best classification result of the soil species classification model rained with the original soil image dataset. These prove that the accuracy of soil classification based on the subgraph selection algorithm is promoted and the algorithm is effective.