PalmPrint: A System of Deep Learning Approaches for Dermatoglyphics and Cognitive Personality Insights

In today’s world, everyone wants to know how children learn and what their learning and personality types are. Each person is unique and has certain skills. The sooner these talents are discovered, the better. In order to maximize their potential, this establishes interests at a young age. In order to identify the areas in which they are most likely to succeed, it also analyzes personality traits. By automating the process of identifying personality and learning types, this paper aims to simplify a lengthy and laborious procedure. Our study offers a novel method for identifying personality traits and learning styles from fingerprints. It is known that both the formation of the brain and fingerprints are influenced by the environment and genes, but they occur simultaneously during fetal development. Therefore, we can determine personality traits, various forms of intelligence, and innate talents by looking at fingerprints. Scanned fingerprints will be the input for the suggested system. These will be filtered and turned into black-and-white pictures. The fingerprints will then be filtered using Gabor filtering, dimension reduced using Principal Component Analysis (PCA), and trained using a Convolutional Neural Network, which correctly classifies the fingerprints into seven classes. The system will be evaluated using the Grad-CAM algorithm, which will produce a comprehensive report that suggests personality traits and learning styles based on the results.