Patents by Inventor Stephane Gentric
Stephane Gentric has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20230289565Abstract: A method for the secure use of a first neural network on an input datum, the method including the implementation, by data processing device of a terminal, of the following steps: (a) constructing a second neural network corresponding to the first neural network, into which is inserted, at the input of a target layer of the first neural network, at least one auto-encoder neural network trained to add a parasitic noise to its input; (b) using the second neural network on the input datum.Type: ApplicationFiled: March 6, 2023Publication date: September 14, 2023Applicant: IDEMIA IDENTITY & SECURITY FRANCEInventors: Hervé CHABANNE, Linda GUIGA, Vincent DESPIEGEL, Stephane GENTRIC
-
Publication number: 20230097143Abstract: A method including: for each image forming part of a plurality of images showing an individual, applying processing to the image so as to produce a biometric template relating to the individual; calculating an average template constituting an average of the biometric templates produced; modifying a chosen image from the plurality of images into a modified image, the modification being adapted so that an error between the average template and a biometric template produced by applying the processing to the modified image is smaller than an error between the average template and the biometric template that has been produced by applying the processing to the chosen image.Type: ApplicationFiled: September 26, 2022Publication date: March 30, 2023Applicant: IDEMIA IDENTITY & SECURITY FRANCEInventor: Stéphane GENTRIC
-
Patent number: 11386716Abstract: The invention relates to a method of biometric recognition by means of an artificial intelligence unit (5) that has access to a memory (3) containing at least one reference image of a body portion of a user and that is arranged to compare it with at least one image that has been captured of the same body portion of a candidate for recognition, the method comprising the step of submitting training images to the artificial intelligence unit, the training images presenting body portions similar to those of the reference image, the artificial intelligence unit being taught to reject them, and the method comprising the additional step of submitting at least one anti-drift image to the artificial intelligence unit, the artificial intelligence unit being taught to accept it. The invention also relates to an associated installation.Type: GrantFiled: August 20, 2020Date of Patent: July 12, 2022Assignee: IDEMTA IDENTITY & SECURITY FRANCEInventors: Laurent Mercier, Stéphane Gentric, Aurélien Fenals, Olivier Heurtier, Laurent Kerautret
-
Patent number: 11074330Abstract: A biometric recognition method comprising the step of calculating a similarity score between a candidate biometric vector and a reference biometric vector, at least one of the two biometric vectors being quantified.Type: GrantFiled: July 12, 2019Date of Patent: July 27, 2021Assignee: IDEMIA IDENTITY & SECURITY FRANCEInventors: Jonathan Milgram, Stéphane Gentric
-
Patent number: 11062008Abstract: A biometric recognition method, comprising the step of calculating a similarity score of a candidate biometric vector with a reference biometric vector. At least one of the biometric vectors is extracted using at least one neural network.Type: GrantFiled: July 12, 2019Date of Patent: July 13, 2021Assignee: IDEMIA IDENTITY & SECURITY FRANCEInventors: Jonathan Milgram, Stéphane Gentric, Franck Maurin
-
Publication number: 20210056334Abstract: The invention relates to a method of biometric recognition by means of an artificial intelligence unit (5) that has access to a memory (3) containing at least one reference image of a body portion of a user and that is arranged to compare it with at least one image that has been captured of the same body portion of a candidate for recognition, the method comprising the step of submitting training images to the artificial intelligence unit, the training images presenting body portions similar to those of the reference image, the artificial intelligence unit being taught to reject them, and the method comprising the additional step of submitting at least one anti-drift image to the artificial intelligence unit, the artificial intelligence unit being taught to accept it. The invention also relates to an associated installation.Type: ApplicationFiled: August 20, 2020Publication date: February 25, 2021Inventors: Laurent MERCIER, Stéphane GENTRIC, Aurélien FENALS, Olivier HEURTIER, Laurent KERAUTRET
-
Patent number: 10636262Abstract: Method for monitoring individuals in a place equipped with cameras, the method including the steps of: detecting representative characteristics of an individual in a first zone of the place; detecting representative characteristics of an individual in at least a second zone and comparing these representative characteristics with representative characteristics previously stored in order to determine whether the individual detected in the second zone has been detected in other zones; confirming the determination from a topography of the place by checking consistency of a path of the individual from one zone to another and of the time model by comparing temporal detection information on the representative characteristics in the zones. Device for implementing this method.Type: GrantFiled: March 11, 2016Date of Patent: April 28, 2020Assignee: Idemia Identity & SecurityInventors: Olivier Beiler, Pierre Escamilla, Stephane Gentric
-
Publication number: 20200019691Abstract: A biometric recognition method comprising the step of calculating a similarity score between a candidate biometric vector and a reference biometric vector, at least one of the two biometric vectors being quantified.Type: ApplicationFiled: July 12, 2019Publication date: January 16, 2020Inventors: Jonathan MILGRAM, Stéphane GENTRIC
-
Publication number: 20200019689Abstract: A biometric recognition method, comprising the step of calculating a similarity score of a candidate biometric vector with a reference biometric vector. At least one of the biometric vectors is extracted using at least one neural network.Type: ApplicationFiled: July 12, 2019Publication date: January 16, 2020Inventors: Jonathan MILGRAM, Stéphane GENTRIC, Franck MAURIN
-
Patent number: 10403076Abstract: The invention relates to a method for securing a document including a visual element, carried out by a processing unit comprising processing means, the method comprising generation, from the visual element, of a reference security datum, and storage of the reference security datum, wherein the reference security datum is generated by means of an algorithm configured so as to generate: for any image acquired from the visual element, a security datum whereof the differences relative to the reference security datum are less than a determined threshold, and for any image acquired on a different visual element, a security datum whereof the differences relative to the reference security datum are greater than said threshold.Type: GrantFiled: February 9, 2017Date of Patent: September 3, 2019Assignee: SAFRAN IDENTITY & SECURITYInventors: Herve Chabanne, Jean-Christophe Fondeur, Stephane Gentric, Erik Van Dijk
-
Patent number: 10332016Abstract: The invention concerns a method to compare two data obtained from a sensor or interface, carried out by processing means of a processing unit, the method comprising the computing of a similarity function between two feature vectors of the data to be compared, characterized in that each feature vector of a datum is modelled as the summation of Gaussian variables, said variables comprising: a mean of a class to which the vector belongs, an intrinsic deviation, and an observation noise of the vector, each feature vector being associated with a quality vector comprising information on the observation noise of the feature vector, and in that the similarity function is computed from the feature vectors and associated quality vectors.Type: GrantFiled: November 3, 2015Date of Patent: June 25, 2019Assignee: IDEMIA IDENTITY & SECURITYInventors: Julien Bohne, Stephane Gentric
-
Patent number: 10078782Abstract: A method for identifying and/or authenticating an individual by a system including a storage device storing at least one binary code of a reference iris and a binary code of an associated reference mask: acquisition of an image of an eye of the individual, segmentation of the acquired image to isolate a region containing the texture of the iris and determine an associated mask, division of the region and the mask into N2 concentric rings, normalization of the region, determination of a binary iris code IC and a binary code of mask IM matching at least one ring of the iris with a ring of the reference iris to minimize a matching distance between the acquired image and the reference image, computation of the minimized matching distance, identification and/or authentication of the individual if the minimized matching distance is less than a predetermined threshold.Type: GrantFiled: June 13, 2016Date of Patent: September 18, 2018Assignee: MORPHOInventors: Emine Krichen, Pierre Gacon, Stephane Gentric
-
Publication number: 20180158177Abstract: System for processing images including a main neural network, preferably convolution-based (CNN), and at least one preprocessing neural network, preferably convolution-based, upstream of the main neural network, for carrying out before processing by the main neural network at least one parametric transformation f, differentiable with respect to its parameters, this transformation being applied to at least part of the pixels of the image and being of the form p?=f(V(p),?) where p is a processed pixel of the original image or of a decomposition of this image, p? the pixel of the transformed image or of its decomposition, V(p) is a neighborhood of the pixel p, and ? a vector of parameters, the preprocessing neural network having at least part of its learning which is performed simultaneously with that of the main neural network.Type: ApplicationFiled: December 5, 2017Publication date: June 7, 2018Inventors: Sarah Lannes, Vincent Despiegel, Yann Raphaël Lifchitz, Stephane Gentric
-
Publication number: 20170236355Abstract: The invention relates to a method for securing a document including a visual element, carried out by a processing unit comprising processing means, the method comprising generation, from the visual element, of a reference security datum, and storage of the reference security datum, wherein the reference security datum is generated by means of an algorithm configured so as to generate: for any image acquired from the visual element, a security datum whereof the differences relative to the reference security datum are less than a determined threshold, and for any image acquired on a different visual element, a security datum whereof the differences relative to the reference security datum are greater than said threshold.Type: ApplicationFiled: February 9, 2017Publication date: August 17, 2017Inventors: Herve CHABANNE, Jean-Christophe FONDEUR, Stephane GENTRIC, Erik VAN DIJK
-
Publication number: 20160364611Abstract: The present invention relates to a method for identifying and/or authenticating an individual comprising the following steps performed by a system comprising a storage device storing at least one binary code of a reference iris and a binary code of an associated reference mask: acquisition 101 of an image of an eye of the individual, segmentation 102 of the acquired image of the eye so as to isolate a region containing the texture of the iris and determine an associated mask, division 103 of said region containing the iris texture and of said mask into N2 of concentric rings, normalization 104 of said region containing the texture of the iris and of said mask of Cartesian coordinates in polar coordinates, determination 105 of a binary iris code IC of size equal to N2*P*F and a binary code of mask IM associated by application of F Gabor filters to each position of P positions of each ring, matching 106 at least one ring of the iris of the acquired image with a ring of the reference iris so as to minimize a maType: ApplicationFiled: June 13, 2016Publication date: December 15, 2016Inventors: Emine KRICHEN, Pierre GACON, Stephane GENTRIC
-
Publication number: 20160267758Abstract: Method for monitoring individuals in a place equipped with cameras, the method including the steps of: detecting representative characteristics of an individual in a first zone of the place; detecting representative characteristics of an individual in at least a second zone and comparing these representative characteristics with representative characteristics previously stored in order to determine whether the individual detected in the second zone has been detected in other zones; confirming the determination from a topography of the place by checking consistency of a path of the individual from one zone to another and of the time model by comparing temporal detection information on the representative characteristics in the zones. Device for implementing this method.Type: ApplicationFiled: March 11, 2016Publication date: September 15, 2016Inventors: Olivier BEILER, Pierre ESCAMILLA, Stephane GENTRIC
-
Publication number: 20160125308Abstract: The invention concerns a method to compare two data obtained from a sensor or interface, carried out by processing means of a processing unit, the method comprising the computing of a similarity function between two feature vectors of the data to be compared, characterized in that each feature vector of a datum is modelled as the summation of Gaussian variables, said variables comprising: a mean of a class to which the vector belongs, an intrinsic deviation, and an observation noise of the vector, each feature vector being associated with a quality vector comprising information on the observation noise of the feature vector, and in that the similarity function is computed from the feature vectors and associated quality vectors.Type: ApplicationFiled: November 3, 2015Publication date: May 5, 2016Inventors: Julien Bohne, Stephane Gentric
-
Patent number: 8345933Abstract: A procedure for identifying a person with a data acquisition device (202) that is configured for capturing the image of their eyelashes (102, 104). The captured image is compared with eyelash images in a database.Type: GrantFiled: April 6, 2007Date of Patent: January 1, 2013Assignee: MorphoInventors: Martin Cottard, Stéphane Gentric
-
Publication number: 20090097715Abstract: A procedure for identifying a person with a data acquisition device (202) that is configured for capturing the image of their eyelashes (102, 104). The captured image is compared with eyelash images in a database.Type: ApplicationFiled: April 6, 2007Publication date: April 16, 2009Applicant: Sagem SecuriteInventors: Martin Cottard, Stephane Gentric