This research aims to devise a distinct mathematical key for individual identification and recognition. This key, represented through signals, is constructed using Lagrange polynomials derived from the skeletal points. Consequently, we present this key as a novel fingerprint categorized within physiological fingerprints. It's crucial to highlight that the primary application of this fingerprint is for remote individual identification, specifically excluding any bodily masking. Subsequently, we implement an artificial intelligence model, specifically a Convolutional Neural Network (CNN), for the automated detection of individuals. The proposed CNN is trained on an extensive dataset comprising 10000 real-world cases and augmented data. Our skeletal fingerprint recognition system demonstrates superior performance compared to other physiological fingerprints, achieving a remarkable 98% accuracy in detecting individuals at a distance.