Abstract: The invention relates to a papillary print sensor comprising an acquisition surface (14) extending over a length L, a light source (11) configured to emit a light pulse, a sheet (12) adapted to propagate light rays by reflection on the first face (12a) and the second face (12b), which defines a critical angle (?c), and an imager (13), wherein the thickness (e) of the sheet is less than a thickness emax=L/2×tan(?c), such that a first part of the light rays (20b, 20c) is propagated without reflection on the acquisition surface (14) while a second part of the light rays (20a, 20d) is reflected towards said acquisition surface (14) after reflection on the second face (12), and the imager (13) is configured to acquire a first image during the reception of the first part of the light rays and a second image during the reception of the second part of the light rays.

Abstract: The present invention relates to a method for performing a biometric function between a client (1) and a server (2), the server (2) being connected to a biometric database and an alphanumeric database, characterized in that the method comprises performing, by a processing unit (11) of the client (1), steps of: (a) identifying a sequence of elementary blocks defined by the biometric function, each elementary block performing a given operation on said biometric database and/or said alphanumeric database implemented by a processing unit (21) of the server (2); (b) requesting the execution, by the processing unit (21) of the server (2), of the identified sequence of elementary blocks.

Abstract: A method for selecting an image of a fingerprint for identifying an individual is described. The method includes: acquiring a current image comprising a fingerprint and segmenting said fingerprint; determining a value representing a stability of said current image; determining a value representing the sharpness of said current image; determining a score, said score being a combination of said value representing a stability, of said value representing a sharpness and of a number of segmented fingerprints; and selecting said current image for identifying said individual in the case where said score is higher than a first threshold value, and otherwise storing said current image in memory as best image in the case where the score thereof is higher than a best score value, and repeating this method.

Abstract: The present invention relates to a parameter training method for a convolutional neural network, CNN, for classifying data, the method comprising the implementation by data processing means (11c) of servers (1a, 1b, 1c) of steps of: (a1) Obtaining parameters of a set of at least one first CNN; (a2) For a first CNN of said set: Training, based on a database of already-classified public training data, parameters of a final representation block (B) of a second CNN corresponding to the first selected CNN to which said representation block (B) has been added; Retraining, based on a database of already-classified confidential training data of a secondary server (1a, 1b), parameters of the second CNN; Transmitting to the main server (1c) parameters of a third CNN corresponding to the second CNN without a final representation block (B); (a3) Replacing a first CNN of said set of first CNNs with the third CNN; (a4) Aggregating said set of at least one first CNN into a fourth CNN.

Abstract: A biometric data processing method implemented by a proof entity and a verification entity that are connected. The proof entity has a candidate biometric data, a reference biometric data, cryptographic footprints of the reference biometric data, and the candidate biometric data. The verification entity has a set of cryptographic footprints of reference biometric data of authorized users. The method includes generating the proof entity of a zero-knowledge proof of the fact that the candidate biometric data and the reference biometric data match. Transmitting to the verification entity the zero-knowledge proof of the cryptographic footprints of the candidate biometric data and the reference biometric data. Verifying that the zero-knowledge proof is valid, and the received cryptographic footprint of the reference biometric data belongs to the set of cryptographic footprints of reference biometric data in the possession of the verification entity.

Abstract: The invention proposes a method of authentication of an electronic identity device (1) presented by an individual, the method being characterized in that it comprises the implementation of steps of: (b) Reception by data processing means (21) of a server (2) of an acquired image of said electronic identity device (1), the image representing at least one personal visual element of the individual and a dynamic verification code that are visible on said electronic identity device (1), said dynamic verification code containing at least one item of reference information representative of an expected appearance of said visual element; (c) Extraction, by analysis of said acquired image by the data processing means (21) of the server (2), of: an item of candidate information representative of the appearance of said visual element as represented in the acquired image; the reference information representative of the expected appearance of said visual element contained in said dynamic verification code as represente

Abstract: Method for capturing a thermal pattern by a sensor comprising a plurality of pixels each comprising a heat-sensitive measuring element, the method comprising, for each pixel: heating the measuring element; first reading of the electrical charges outputted by the pixel during a first measurement duration and giving a first measurement value x1; second reading of the electrical charges outputted by the pixel during a second measurement duration and giving a second measurement value x2; calculating a difference x1??·x2, where ? is a positive real number, and wherein more than half of the heating duration is implemented during the first measurement duration and less than half of the heating duration is implemented during the second measurement duration.

Abstract: The present invention relates to a method of segmenting an input image representing at least one biometric trait, by means of a convolutional neural network, CNN, the method being characterized in that it comprises the implementation, by data processing means (21) of a client (2), of steps of (b) generating, by means of a first subnetwork of said CNN, referred to as a specialization block, a confidence mask associated with a ridge orientation map of the at least one biometric trait represented by said input image, referred to as a RFM mask; said RFM mask being applied to at least the input image so as to obtain a focused input image; (c) segmenting, by means of a second subnetwork of said CNN, referred to as a segmentation block, the focused input image.

Abstract: A method for extracting a signature of a fingerprint shown on a source image is described. For this purpose, the source image is transformed into the frequency domain. One or more ridge frequencies are next determined by means of a convolutional neural network applied to said transformed image, n being an integer greater than or equal to 1. The source image is normalized in response to said n ridge frequencies determined. One or more signatures of said fingerprint are finally extracted from said n normalized images.

Abstract: A biometric inspection device including a housing provided with an acquisition interface, the device including an optical sensor for acquiring at least one image of a portion of the body of a candidate for inspection appearing before the acquisition interface. The optical sensor is configured so that the image also covers an internal zone of the housing situated outside the acquisition interface.

Abstract: A method for selecting an image of a fingerprint for identifying an individual is described. The method includes: acquiring a current image comprising a fingerprint and segmenting said fingerprint; determining a value representing a stability of said current image; determining a value representing the sharpness of said current image; determining a score, said score being a combination of said value representing a stability, of said value representing a sharpness and of a number of segmented fingerprints; and selecting said current image for identifying said individual in the case where said score is higher than a first threshold value, and otherwise storing said current image in memory as best image in the case where the score thereof is higher than a best score value, and repeating this method.

Abstract: A method for detecting bots in a user network (R), the method comprising the following steps: receiving (102) by a user terminal (2) an identifier (ID) associated with a network user account; transmitting (104), by the user terminal (2), the identifier (ID) to an access control system (3) configured to determine whether or not a mobile terminal owner has the right to access an area or service, the area or service being independent of the user network (R); transmitting (106), by the access control system (3) to the server (1), a representative data element supporting that the identifier (ID) has been received by the access control system (3); and using (108) by the server (1) the representative data element to determine whether the user of the account associated with the identifier (ID) is a bot or not.

Abstract: Method for controlling commands suitable to be processed by a peripheral (2) comprising the following steps implemented by a control circuit (6) connected to a communication bus (8), a command circuit (4) and the peripheral (3) also being connected to the communication bus (8): granting or refusing authorization to the command circuit (4) to transmit a command signal of the peripheral via the bus (8), detecting the possible transmission of the command signal for the peripheral by the command circuit via the bus (8), implementing protection measures (614) when the control circuit detects that the command signal has been transmitted as the control circuit has not granted authorization, or that the command signal has not been transmitted as the control circuit has granted authorization.

Abstract: The invention proposes a method for registering data from an individual's identity document (1), the method being characterized in that it comprises implementing by data processing means (21) of a server (2) the following steps: (A) Receipt of a photograph of said individual visible on said identity document (1), an optical reading data element of the identity document (1), and at least one personal data element of said individual; (B) Extraction by analysis of said photograph from reference information representative of the appearance of said photograph; (C) Generation of a random string, calculation of an encoded data element by applying an encoding procedure to said reference information representative of the appearance of said photograph and said random string; (D) Storage on the server (2) data storage means (22) of: Said encoded data element; A cryptographic imprint of a first concatenation of the optical reading data element of the identity document (1) and the random string; An encryption with a c

Abstract: Disclosed is a fraud detection method to authenticate that an object is formed of human skin. The method includes an object being placed on a home location on the surface of a propagation medium of a sensor, lighting the home location of the surface by a light source emitting light rays illuminating the home location forming with said surface a plurality of incidence angles encompassing a critical angle defined by the refraction index of the propagation medium and by a refraction index expected for authentic human skin, receipt by an imager of light rays from the surface, and acquisition of an image, and determining whether the object matches an authentic human finger based on the refraction index of said object, as a function of the spatial light distribution on the acquired image.

Abstract: A fingerprint detection device comprising a support having a bearing surface, a sensor arranged to capture an image of a dermatoglyph of a user's finger placed on the bearing surface, and an impedance-measuring electronic circuit connected to electrodes extending on the bearing surface, conductive tracks extending on the bearing surface between the electrodes and the impedance-measuring electronic circuit. At least two of the electrodes are connected to the impedance-measuring electronic circuit by at least two conductive tracks.

Abstract: This invention concerns a method of learning parameters of a convolutional neural network (CNN) through data processing means (11a, 11b, 11c) of at least one server (1a, 1b, 1c), for detecting items of interest visible in images, from at least one image learning database in which said items of interest, as well as characteristic geometric structures are already annotated, the CNN comprising an encoding layer for generating a representation vector of the detected items of interest, the method being characterized in that said representation vector comprises, for at least a first item of interest category to be detected, at least one descriptive value of at least a characteristic geometric structure of said first item of interest category. The present invention also relates to a process for detecting items of interest visible in an image and a method for associating items of interest visible in an image.

Abstract: The present invention concerns a method of classification of an input image representative of a biometric trait by means of a first convolutional neural network, CNN, characterized in that it comprises the implementation by data processing means (21) of a client (2) of steps of: (c) Estimation of a transformation parameter vector of said input image, by means of a second CNN, the parameters of the vector being representative of a geometric transformation enabling the biometric trait represented by the input image to be registered in a common reference frame; (d) Application to said input image of a transformation defined by said estimated transformation parameter vector, so as to obtain a registered input image; (e) Classification of the registered input image by means of the first CNN.

Abstract: A method of collecting biological material with the help of a mobile terminal, the method including the following steps: acquiring a first image and extracting a first candidate biometric dataset therefrom; comparing the candidate biometric dataset with reference biometric datasets and determining similarity scores; comparing the similarity scores with a first predetermined threshold; and when none of the similarity scores is greater than the first predetermined threshold, proceeding to collect biological material from the first dermatoglyph.

Abstract: A device for recognition from biometric characteristics extracted from at least one image of at least one iris of a candidate for recognition, the device having an image sensor with a field covering a capture zone in which at least one of the eyes of the candidate for recognition is intended to be located, and an illumination source of the capture zone, the illumination source emitting incident radiation in a wavelength range adapted to excite iris fluorescence and the sensor being arranged to be sensitive to iris fluorescence. Recognition method using such a device.