PIPP: Person Identification from Palm-surface Polygons

Automatic person identification from palmprint images is a well-established technology in biometrics. In biometrics, a person is identified based on some characteristic parameters. Characterization of the palmprint images is done mainly using principal lines, wrinkles, and ridges. In this paper, we have proposed a person identification method based on a novel set of geometric features highlighting the characteristics of the palm surface as biometric behavior. Performance of the proposed method has been evaluated on publicly available palm-image datasets, and the results establish the applicability of the method. On VERA left-hand, right-hand, and COEP image datasets, the proposed method shows 96.5%, 97.5%, and 95.3% accuracy, respectively.