Abstract—This study developed an automatic classification system based on deep learning to detect visual elements in Baum test images, namely crown, stem, steambasis, and roots. Using the YOLOv8 algorithm, the model was trained on a dataset that was systematically annotated based on a psychological symbolic framework. The labeling process focused on representative and easily recognizable visual features. Evaluation results show that the model can identify elements with high accuracy and stable performance. This system supports more objective and efficient interpretation in the context of psychological assessment. However, final interpretation still requires expert validation. Limitations include the small size of the dataset and the lack of complex visual features. Further research is recommended to expand the dataset, apply expert cross-validation, and explore more advanced model architectures.
 
Keywords—detection, interpretation, psychometrics, Baum test, YOLOV8


Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).