Abstract:
A method for the quick recognition of a person (particularly, a user of a POS or cash dispenser/ATM service), by means of identification codes derivable from biometric data, is described. Such a method comprises the steps of registering at least one user, and recognizing a registered user, out of a plurality of registered users, through a respective recognition event. Each registration event of a user to be registered comprises the steps of acquiring from the user at least one biometric datum related to a configuration of blood vessels of the user; then, encoding, by a coding procedure, the at least one acquired biometric datum into a respective registration identification code of the user; then, associating such registration identification code to the user to be registered; finally, registering the user as a registered user, and registering the associated registration identification code as a registration identification code of the registered user. Each recognition event of a registered user, among a plurality of registered users, comprises the steps of acquiring from the user to be recognized the above- mentioned at least one biometric datum related to a configuration of blood vessels of the user; then, encoding, by the above-mentioned coding procedure, the at least one acquired biometric datum into a respective recognition identification code of the user to be recognized; then, preparing, based on said registered registration identification codes, 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; finally, recognizing or refusing recognition of the user to be recognized based on the estimated matching levels. The above-mentioned step of preparing a comparison set comprises defining the comparison set starting from the overall set of all the registration identification codes of the plurality of already registered users, and using, on such overall set, classification and grouping techniques on the registration identification codes.
Abstract:
It is described a method for optimized processing of data structures, by electronic processing means (10) comprising a programmable processing device (11) and at least one processor (12), by carrying out operations on coded data contained in the data structures. The method first comprises the step of programming the programmable processing device (11), so that it is capable of autonomously carrying out a predetermined plurality of basic operations on one or more of the data structures at issue, so that each of such basic operations is managed as a pre-programmed primitive operation. Then, the method comprises the following steps, carried out by the at least one processor (12): receiving in input (step S1) a flow of coded data (D) belonging to one of said data structures, and a request r of an operation on such coded data (D); then, recognizing (step S2) the data structure (DS) of the received data flow and the requested operation (O); then, determining (step S3), based on the received data structure DS and the requested operation (O), whether to perform the requested operation (O) or to get the programmable processing device (11) to carry out the requested operation. If the at least one processor determines, based, e.g. , on predetermined rules stored therein, that the requested operation (O) has to be performed by the programmable processing device (11), the method comprises the further steps of sending (step S4) to the programmable processing device (11), by the at least one processor (12), the flow of coded data (D) and a piece of information about the recognized data structure (DS) and about the requested operation (O); then, executing the requested operation (O) on the received data flow (D), by the programmable processing device (11), autonomously, based on the basic operations pre-programmed therein; finally, providing, by the programmable processing device (11), the obtained result (R).
Abstract:
A method for the quick recognition of a person (particularly, a user of a POS or ATM service, or of an access service to a subway station), by means of identification codes derivable from biometric data, is described. Such a method comprises the steps of registering at least one user, and recognizing a registered user, among a plurality of registered users, through a respective recognition event. Each user registration event comprises the steps of acquiring from the user at least one biometric datum, and of encoding, through a coding procedure, the acquired biometric datum into a respective registration identification code of the user; then, associating such registration identification code to the user to be registered; finally, registering the user as a registered user, and registering the associated registration identification code as a registration identification code of the registered user. Then, the method comprises the step of preparing and associating to each of the recognition terminals (10) a respective comparison set, comprising a plurality of comparison identification codes, each of which corresponds to a registration identification code of a respective user registered in a previous registration event. Such a step comprises the selection of the comparison identification codes, among the registered identification codes, for each of the recognition terminals, based on a comparison between localization information of the registered users and the known localization of the recognition terminal (10). The method then comprises the step of recognizing a registered user, among a plurality of registered users, by one of the recognition terminals, through a respective recognition event. Each recognition event provides for acquiring from the user to be recognized the same at least one biometric datum acquired in the registration step; then, encoding the at least one acquired biometric datum, through the coding procedure, into a respective recognition identification code of the user to be recognized, and comparing the recognition identification code with each of the comparison identification codes; finally, estimating, for each comparison, a respective matching level, and recognizing or refusing recognition of the user, based on the estimated matching levels.
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.
Abstract:
A system (1) for making a teleconference between at least one first and at least one second speaker (I1, I2), present in a first (S1) and a second (S2) teleconference sites remote from one another, connectable by a telecommunications network (NW), is described. In each of the teleconference sites (S1, S2), the system comprises corresponding transceiver means (10, 20), configured to transmit to the other site generated electronic signals, and to receive electronic signals generated in the other site. The system (1) further comprises (connected to the transceiver means) first (11) and second (21) acquisition means, configured to acquire an image of the first and second (I1, I2) speakers, and to generate the above-mentioned electronic signals based on the acquired image. The system (1) then comprises corresponding first (12) and second (22) remote image displaying means (connected to the transceiver means to receive the electronic signals generated in the other site) configured to process such electronic signals so as to display, based thereon, the image of the remote speaker. The first remote image displaying means (12) comprise processing means (121), provided with an electronic screen (122), configured to display the image of the remote speaker in a displaying window (125) present in the electronic screen in a predetermined position. The first acquisition means (11) are arranged adjacent to the electronic screen (121) and the displaying window (125), so that the acquired image of the first speaker (I1), while he/she looks at the image (32) of the second speaker in the displaying window (125), is similar to or substantially identical to the image that would be acquired if the first speaker (11 ) would look at the first acquisition means (11). The second displaying means (22) comprise a displaying screen (221), having shape and dimensions suitable to contain an image (31) projected life-size of the first speaker (I1).
Abstract:
A method for the quick recognition of a person (particularly, a user of a POS or cash dispenser/ATM service), by means of identification codes derivable from biometric data, is described. Such a method comprises the steps of registering at least one user, and recognizing a registered user, out of a plurality of registered users, through a respective recognition event. Each registration event of a user to be registered comprises the steps of acquiring from the user at least one biometric datum of the user; then, encoding, by a coding procedure, the at least one acquired biometric datum into a respective registration identification code of the user; then, associating such registration identification code to the user to be registered; finally, registering the user as a registered user, and registering the associated registration identification code as a registration identification code of the registered user. Each recognition event of a registered user, among a plurality of registered users, comprises the steps of acquiring from the user to be recognized the above- mentioned at least one biometric datum of the user; then, encoding, by the above- mentioned coding procedure, the at least one acquired biometric datum into a respective recognition identification code of the user to be recognized; then, preparing, based on said registered registration identification codes, 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; finally, recognizing or refusing recognition of the user to be recognized based on the estimated matching levels. Each of the comparisons between the recognition identification code and one of the comparison identification codes comprises a processing operation carried out by applying at least one trained algorithm. The method further provides for further training the at least one trained algorithm upon the recognition event.