Robust GrayScale Distribution Estimation for Contactless Palmprint Recognition

More and more research have been developed very recently for automatic hand recognition. This paper proposes a new method for contactless hand authentication in complex images. Our system uses skin color and hand shape information for an accurate hand detection process. Then, the palm is extracted and characterized by a robust and normalized decomposition. During enrollment, a distribution estimation is used to defined the optimal discrimination of the palmprint features. Finally, some specific thresholds are defined to separate in test phase impostor and genuine users. The experimental results present an error rate of 1.5% with a population of 49 people.