<![CDATA[This study explores the clustering of personality similarities among vocational school students based on their Wartegg Test results, utilizing Convolutional Neural Networks (CNN) for feature extraction and the DBSCAN algorithm for clustering. The Wartegg Test, an image-based projective test long used in psychology, presents challenges in terms of cost and time, especially for lower middle-class schools and large-scale student applications. Pre-trained CNN models, VGG16 and ResNet50, were used to extract high-dimensional feature vectors from digitized test images, which were then reduced using Principal Component Analysis (PCA) to optimize clustering. DBSCAN effectively identified clusters of students with similar personality traits without predefined cluster numbers, achieving meaningful results as validated by the DBCV metric. ResNet50 outperformed VGG16 with a higher DBCV score of 0.6997, highlighting its superior capability to capture complex image patterns. The clustering results revealed two dominant groups and a minimal presence of noise, representing unique personality traits. This work contributes to computational psychological profiling in education using AI-based techniques, offering a scalable and objective approach to personality analysis. This study lies in the integration of image-based projective psychological tests with deep learning-based feature extraction and density-based clustering, bridging psychology and computer science.]]>
Copyrights © 2026
