Abstract:
A method is described for quick recognition of a person (in particular, a user of a POS or Cashpoint/ATM service) by means of identification codes derivable from biometric data. Such method comprises the phases of registering at least one user, and of recognizing a registered user, from a plurality of registered users, by means of a respective recognition event. Each user registration event comprises the steps of acquiring from the user to be registered at least one biometric datum correlated to a configuration of the user's blood vessels; then, encoding, by means of a coding procedure, the at least one acquired biometric datum into a respective registration identification code of the user to be registered; then, associating such registration identification code to the user to be registered; lastly, registering the user as a registered user, and registering the associated registration identification code as the registration identification code of the registered user. Each recognition event of a registered user, from a plurality of registered users, comprises the steps of acquiring from the user to be recognized the aforementioned at least one biometric datum correlated to a configuration of the user's blood vessels; then, encoding, by means of the aforementioned coding procedure, the at least one acquired biometric datum into a respective recognition identification code of the user to be registered; then, preparing, on the basis of said registration identification codes registered, a comparison set comprising a plurality of comparison identification codes; then, comparing the recognition identification code with each of such plurality of comparison identification codes; then, estimating, for each of such comparisons, a respective matching level; lastly, recognizing or refusing recognition of the user to be recognized, on the basis of the estimated matching levels. Each of the comparisons between the recognition identification code and one of the comparison identification codes comprises processing performed by applying at least one learning algorithm.