# US 10,990,845 B2 · Method of augmented authentification of a material subject > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,990,845 B2 - Document ID: US10990845B2 - Status: Granted - Kind: B2 - Application number: 16/302,255 - Filed: 2017-05-17 - Published: 2019-09-12 - Granted: 2021-04-27 - Earliest claimed: 2016-05-17 - Assignees: Kerquest - Applicants: Kerquest - Inventors: Yann Boutant; Thierry Fournel - Web page: https://patentgrep.com/patent/US10990845B2 ## CPC - H04N 1/32144: {embedded in the image data, i.e. enclosed or integrated in the image, e.g. watermark, super-imposed logo or stamp} - G06F 18/22: Matching criteria, e.g. proximity measures - G06V 10/758: {Involving statistics of pixels or of feature values, e.g. histogram matching} - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Disclosed is a method for determining a relational imprint between two images including the following steps: —the implementation of a first image and of a second image, —a phase of calculating vectors of similarity between tiles belonging respectively to the first and second images, the similarity vectors forming a field of imprint vectors, the field of imprint vectors including at least one haphazard region disordered in the sense of an entropy criterion, —a phase of recording in the guise of relational imprint of a representation of the calculated field of imprint vectors. Also disclosed is a method for authenticating a candidate image with respect to an authentic image implementing the method for determining a relational imprint. ## Claims ### Claim 1 A method for determining a relational imprint between two images, the method comprising: obtaining an image of a material subject and a selected reference image different from the material subject image; calculating vectors of similarity between tiles belonging to the material subject image and the selected reference image, respectively, by a similarity indicator and a similarity rank, the similarity indicator and the similarity rank being selected to obtain a field of imprint vectors, formed by the vectors of similarity, the field of imprint vectors comprising at least one disordered region in the sense of an entropy criterion; and recording as a relational imprint a representation of the at least one disordered region of the obtained field of imprint vectors. ### Claim 2 (depends on 1) The method according to claim 1, wherein the calculating the similarity vectors comprises: determining a mark common to the material subject image and the selected reference image, determining, in one of the material subject image and the selected reference image, a set of reference tiles each associated with at least one reference point having coordinates in a common reference system, searching, in the other one of the material subject image and the selected reference image, for concordance tiles that are each matched with a reference tile with which the respective concordance tiles have a degree of similarity and are each associated with at least one reference point having coordinates in the common reference system, and calculating coordinates of each of the similarity vectors based on coordinates of reference points of each of the reference tiles and each of the associated concordance tiles. ### Claim 3 (depends on 2) The method according to claim 2, wherein the reference tiles are predetermined based on a specific grid of reference tiles. ### Claim 4 (depends on 2) The method according to claim 2, wherein the searching for the concordance tiles uses, for each of the reference tiles, calculating a series of similarity indices between the portion of the one image corresponding to said respective reference tile and an inspection portion of the other image, the inspection portion being displaced in the other image for calculating each similarity index and by selecting as a concordance tile associated with said respective reference tile, the inspection portion having a specific degree of similarity with said reference tile. ### Claim 5 (depends on 2) The method according to claim 2, wherein the searching for concordance tiles comprises: determining, for the other image, a set of inspection tiles, for each of the reference tiles: calculating a series of similarity indices, each similarity index being calculated between the portion of the one image corresponding to said reference tile and the portion of the other image corresponding to an inspection tile, the inspection tile being different for each calculation of similarity index, and selecting, as one of the concordance tiles associated with said reference tile, the inspection tile having a specific degree of similarity with said reference tile. ### Claim 6 (depends on 5) The method according to claim 5, wherein the determining the sets of reference and inspection tiles is performed by implementing a characteristic detection and description algorithm. ### Claim 7 (depends on 1) The method according to claim 1, wherein the similarity vectors are calculated in the plane or a two-dimensional space. ### Claim 8 (depends on 1) The method according to claim 1, further comprising, before calculating the similarity vectors, transforming one or more of the one image and the other image. ### Claim 9 (depends on 8) The method according to claim 8, wherein the transforming is a registration. ### Claim 10 (depends on 1) The method according to claim 1, further comprising, before the calculating the similarity vectors, determining one of at least of the following parameters: size, shape, position of one or more of the reference tiles and the concordance tiles, order of use of the one image and the other image, and size and shape of an evaluation window to determine an existence of a disordered region. ### Claim 11 (depends on 1) The method according to claim 1, wherein the calculating the field of imprint vectors comprises: calculating a plurality of fields of intermediate similarity vectors between one of the two images and the other image having undergone a transformation that is different from an intermediate similarity vector to the other, and comparing the fields of intermediate similarity vectors between each other and keeping, as a field of imprint similarity vectors, the field of intermediate similarity vectors having a similarity optimum, maximum or minimum. ### Claim 12 (depends on 1) The method according to claim 1, further comprising, before the recording, decomposing the field of similarity vectors into at least one regular portion and one disordered portion including allocating each of the similarity vectors to either one of the regular and disordered portions according to a regional entropy criterion. ### Claim 13 (depends on 12) The method according to claim 12, wherein, when a local similarity optimum is selected at an order equal to one, for a local rank, the respective similarity vector is added either into the disordered component of the field of imprint vector, or into the regular component of the field of imprint vectors, according to whether or not the respective similarity vector fulfills the regional entropy criterion, the null vector then being added into the regular component, or into the disordered component, respectively. ### Claim 14 (depends on 1) The method according to claim 1, further comprising compressing the field of imprint vectors and recording a compression result as a relational imprint. ### Claim 15 (depends on 1) The method according to claim 1, further comprising using, as a relative or relational signature of the material subject image with respect to the reference image, a digital representation of the relational imprint. ### Claim 16 (depends on 1) The method according to claim 1, wherein the recording the relational imprint is associated with the recording of at least one of the images used. ### Claim 17 (depends on 1) The method according to claim 1, further comprising one of visually, sonorously, and tactily representing the relational imprint. ### Claim 18 (depends on 2) The method according to claim 2, wherein the reference tiles are predetermined based on a set of distinct unitary tiles, of regular or non-regular shape, size and position, with or without overlapping. ### Claim 19 (depends on 2) The method according to claim 2, wherein the reference tiles are auto-adaptively predetermined by implementing an algorithm of characteristic detection and description. ### Claim 20 (depends on 5) The method according to claim 5, wherein the degree of similarity corresponds to the similarity rank of the inspection tile retained as the concordance tile in the set of inspection tiles. ### Claim 21 (depends on 15) The method according to claim 15, wherein the relational signature is recorded for later use. ### Claim 22 (depends on 15) The method according to claim 15, further comprising: calculating a first relational imprint of the material subject image with respect to the reference image, a registration of the material subject image with respect to the reference image being based on the first relation imprint; and subsequently calculating a second relational imprint of the registered material subject image with respect to the reference image, the second relation imprint being used for determining the relational signature. ### Claim 23 (depends on 15) The method according to claim 15, further comprising: calculating a first relational imprint of the material subject image with respect to the reference image, a registration of the material subject image with respect to the reference image being based on the first relational imprint; subsequently calculating a second relational imprint of the registered material subject image with respect to the reference image, a registration of the registered material subject image with respect to the reference image being based on the second relation imprint; and subsequently calculating a third relational imprint of the registered material subject image with respect to the reference image, the third relation imprint being used to determine the relational signature. ### Claim 24 (depends on 18) The method according to claim 18, wherein the method used in a visual cryptography scheme. ### Claim 25 (depends on 1) The method according to claim 1, wherein the relational imprint is recorded as a list of sets of similarity vectors linked to the respective reference points, according to a class to which the sets of similarity vectors belong. ### Claim 26 (depends on 1) The method according to claim 1, further comprising using, as a relational stimulus of the material subject image with respect to the reference image, a cognitive conditioning of the relational imprint. ### Claim 27 (depends on 1) A method of unitary authentication of material subjects, each of the material subjects to be authenticated belonging to families of subjects comprising an authentication zone, with an essentially random, intrinsic continuous medium structure, a same reference image being used to authenticate a set of material subjects, the method comprising: determining, for each of the material subjects, a relational imprint between the reference image and at least one image of an authentication zone of the material subject according to the method of claim 1; determining, from each of the relational imprints, a relational signature; recording the relational signature in association with the reference image, as a set of authentic relational signatures; authenticating a candidate material subject comprising: determining, for a relational imprint between the reference image and an image of an authentication zone of the candidate material subject according to the method of claim 1, determining, from the relational imprint between the reference image and the image of the authentication zone of the candidate material subject, a candidate relational signature of the candidate material subject, and comparing the candidate relational signature with the relational signatures of the set of authentic relational signatures and considering the candidate material subject as authentic when the candidate relational signature is similar, according to a threshold level, to one of the relational signatures of the set of the authentic relational signatures. ### Claim 28 (depends on 26) The method of unitary authentication according to claim 26, wherein the material subject image is registered with respect to the reference image. ### Claim 29 (depends on 24) The method of unitary authentication according to claim 24, wherein a position of the authentication zone on the material subjects is recorded. ### Claim 30 (depends on 24) The method of unitary authentication according to claim 24, wherein images of the material subjects are recorded. ### Claim 31 (depends on 24) The method of unitary authentication according to claim 24, wherein each of the relational signatures is recorded in association with the respective image of the corresponding material subject, and after the authenticating, the recorded image corresponding to the relational signature of the authenticated material subject is compared to the candidate image of the material subject in order to check integrity. ### Claim 32 (depends on 24) The method of unitary authentication according to claim 24, where the authenticating of the candidate subject is conducted using an electronic device comprising a visualization touch screen and being configured to allow a modification of visualization magnification of the images and/or displacement of said images by the displacement of two points of contact on the touch screen.