EP3577635B1 - Method for verifying the authenticity of a sensitive product - Google Patents

Method for verifying the authenticity of a sensitive product Download PDF

Info

Publication number
EP3577635B1
EP3577635B1 EP18705689.0A EP18705689A EP3577635B1 EP 3577635 B1 EP3577635 B1 EP 3577635B1 EP 18705689 A EP18705689 A EP 18705689A EP 3577635 B1 EP3577635 B1 EP 3577635B1
Authority
EP
European Patent Office
Prior art keywords
digital image
distinctive
sensitive product
original digital
point
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
EP18705689.0A
Other languages
German (de)
French (fr)
Other versions
EP3577635A1 (en
Inventor
Marc Pic
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Surys SA
Original Assignee
Surys SA
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Surys SA filed Critical Surys SA
Publication of EP3577635A1 publication Critical patent/EP3577635A1/en
Application granted granted Critical
Publication of EP3577635B1 publication Critical patent/EP3577635B1/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
    • G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
    • G07D7/20—Testing patterns thereon
    • G07D7/202—Testing patterns thereon using pattern matching
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
    • G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
    • G07D7/20—Testing patterns thereon
    • G07D7/202—Testing patterns thereon using pattern matching
    • G07D7/206—Matching template patterns

Definitions

  • a sensitive product includes an identifier, and corresponds for example to a bank note, a box of medicines, a luxury product, etc.
  • the identifier includes a set of characters, for example alphanumeric, kenji, etc.
  • the identifier is a serial number.
  • the identifier can be individual, that is to say specific to a given sensitive product.
  • the identifier can also be generic, that is to say specific to a set of sensitive products, for example a batch of medicines.
  • banknotes include a set of security elements, for example such as signs, watermarks, security thread, hologram, etc. which are incorporated in or on the banknotes during their manufacture.
  • US2012/324534 discloses the verification of a security document by comparing the scanned fingerprint of the person with that in the database.
  • US2014/055824 discloses verification of security documents with holograms.
  • WO2015/042485 discloses the verification of security documents by comparison of printed patterns.
  • An authentication solution is proposed here with simple and common optical equipment, allowing anyone to verify the authenticity of a sensitive product, in particular a bank note, in visible light.
  • the invention concerns, according to a first its objects, a method of verifying the authenticity of a sensitive product, as claimed in claim 1.
  • a step (1010) can be provided consisting of defining a set of remarkable points on the original digital image and on the test digital image of the sensitive product, each remarkable point being defined as a set of at least one pixel, that is, that is to say a single pixel or a set of adjacent pixels in pairs for which the contrast gradient is greater than a predefined threshold value, in at least one predefined direction and a predefined distance around said set of at least one pixel .
  • the step (1020) of calculating local collisions consists, for at least one remarkable point, of calculating a set of local histograms in a determined subset of the test digital image or the original digital image, said sub-set. -set comprising said remarkable point.
  • the metrology step (1030) consists of calculating the distance between a first remarkable point and a second remarkable point on at least one of the original digital image and the test digital image of the sensitive product.
  • a step (1040) can be provided consisting of associating in the database each original digital image with a plurality of corresponding attributes, said attributes comprising at least one of: the coordinates of remarkable points, the distances between certain remarkable points , contrast gradient values around remarkable points, or other notable characteristics such as mathematical moments of certain parts of the image.
  • a step (1050) can be provided consisting of associating, in the database, a validity attribute with at least one of the original digital images.
  • the comparison step (1150) is bypassed depending on the value of the validity attribute.
  • the acquisition step (1100) is implemented using a sensor of an optical lens of a communicating object.
  • said subset of the test digital image or the original digital image has a predetermined geometric shape whose value of the surface is predetermined or function of a predetermined gradient of contrast, color or intensity around said remarkable point.
  • the invention relates to a computer program comprising program code instructions for executing the steps of the method according to the invention, when said program is executed on a computer.
  • a sensitive product 100 in this case a bank note (specimen) is illustrated on the figure 1 .
  • the banknote is flat and rectangular.
  • the banknote includes a set of security elements, in particular graphic or optical.
  • the banknote notably comprises a security thread 130, which is integrated into the paper pulp of said banknote and which is optically visible by a local contrast effect.
  • the position of a security thread is not necessarily the same between two banknotes of the same monetary value.
  • a security thread when manufacturing a bank note, it can be provided that it includes a graphic window whose width is that of said note, whose length is at most that of said note, and in the plane of said note, within which the position of the security thread is random, said security thread being generally rectilinear, and in particular in the direction of the width of the note.
  • the banknote also includes a watermark 110, illustrated in particular by the number “20” on the figure 1 and which is optically visible by a local contrast effect.
  • the sensitive product includes an identifier 120, typically composed of alphanumeric characters, for example incremented, and in this case a serial number. Particularly for banknotes, the identifier is not printed offset. Generally, it is printed with dark ink, in this case black, on a light background.
  • the identifier defines a foreground and the background defines a background, it is optically visible by a local contrast effect.
  • the identifier can be recognized by optical character recognition.
  • the sensitive product is at least partially planar, that is to say it is planar or comprises at least one planar face supporting said identifier.
  • the flat surface supporting said identifier is a surface on which said identifier is integrated, affixed, glued, printed, etc. either directly on the sensitive product, or on the packaging of said sensitive product, in particular on the part of the packaging covering said surface.
  • a step is provided consisting of producing a digital image of said sensitive product, that is to say at least of the flat face supporting said identifier.
  • the image produced is in high definition and stored in a secure database.
  • Said digital image is called an “original digital image”, as opposed to a “test digital image” described later.
  • a step is provided consisting of optically recognizing (OCR) the characters of the identifier in the original digital image of a sensitive product, typically using a scanner.
  • OCR optically recognizing
  • optically recognized identifier is recorded in digital format and associated with the original digital image of said sensitive product in the database, which allows for example indexing thereof.
  • each character of the identifier is graphically defined by a set of printing points.
  • the ink used for printing is dark, usually black.
  • the color of the background on which each character is printed is lighter than that of the ink, so that the character is readable on said background thanks to a local contrast effect.
  • the background on which the identifier is printed is not uniform and may include a set of patterns 150, which may be security or decorative graphic elements; and each pattern 150 of the background of the sensitive product presents a local contrast effect.
  • the identifier is unique. However, for various reasons, it happens that several sensitive products have the same identifier, for example several bank notes of the same monetary value have the same serial number. It is estimated that a maximum of twenty banknotes of the same monetary value can have the same serial number.
  • two banknotes presenting the same identifier in fact present a set of at least one difference in at least one of the security elements or the background.
  • the position of the identifier on the background is different, or the pattern of the background is different, etc.
  • each sensitive product is actually graphically unique. It therefore has a fingerprint, that is to say a set of attributes (notably optical, graphic and geometric) which give it its uniqueness.
  • a fingerprint that is to say a set of attributes (notably optical, graphic and geometric) which give it its uniqueness.
  • the (optical) fingerprint of the sensitive product can be extracted from the original digital image to identify and authenticate said sensitive product as described later.
  • a step 1000 is provided consisting of extracting at least one optical imprint from the original digital image of the sensitive product scanned, that is to say calculating the attributes which contribute to its unique character, from the digital image in the database or before its storage therein. We can then associate said fingerprint with said original digital image in the database.
  • each original digital image is associated 1040 with a plurality of corresponding attributes, all of the attributes of a given original image making it possible to characterize it at least in part.
  • the attributes include, for example, the coordinates of remarkable points (described below), the distances between certain remarkable points, contrast gradient values around the remarkable points, etc. or other notable characteristics such as mathematical moments of certain parts of the image as described below.
  • the extraction of the fingerprint of the sensitive product is implemented automatically and preferably comprises at least one of the steps among: a local collision calculation step and a metrology step.
  • a step 1010 consisting of defining, or identifying, a set of remarkable points on the digital image (original or test) of the sensitive product.
  • a remarkable point is defined as a point in the digital image of the sensitive product, that is to say a pixel or a set of adjacent pixels two by two, for which the contrast gradient, according to a predefined direction and distance , is greater than a predefined threshold value.
  • the predefined direction is horizontal and/or vertical.
  • a first notable point belongs to the foreground.
  • a first remarkable point is a printing point of a character of the identifier.
  • a second remarkable point belongs to the foreground or the background (fond).
  • a second remarkable point is a point on the outline of a graphic element of the background pattern.
  • a set of remarkable points can be defined or identified according to the FAST algorithm (for Features from Accelerated Segment Test in English), for example such as described in the article by Edward Rosten and Tom Drummond “Machine learning for high-speed corner detection” (2006) published at https://www.edwardrosten.com/work/rosten_2006_machine.pdf.
  • a step 1020 of calculating local collisions can be provided on the original digital image of the sensitive product.
  • the step of calculating local collisions consists, for at least one remarkable point, of calculating a set of local histograms in a determined subset of the digital image, said subset being a part of the digital image which comprises said remarkable point, which has a predetermined geometric shape and whose surface value is predetermined or a function of a predetermined gradient of contrast, color or intensity around said remarkable point.
  • any predetermined geometric shape can be provided. This is recorded in a memory.
  • the surface value of the predetermined shape can also be predetermined and stored in said memory.
  • the geometric shape is a circle centered on said remarkable point, and whose radius is a function of the chosen gradient, which simplifies the calculations and therefore increases the processing speed.
  • Local histograms are calculated in a number of predetermined directions.
  • SIFT Scale Invariant Feature Transform
  • SURF Speeded Up Robust Features
  • the detection of points is based on the differences of the Gaussians (DoG) obtained by calculating the difference between each pair of images smoothed by a Gaussian filter, by varying the sigma parameter each time (i.e. the deviation standard) of the filter.
  • DoG can be calculated for different scale levels allowing the notion of scale space to be introduced.
  • the detection of potential areas of points of interest / remarkable points is carried out by searching for the extrema according to the plane of the dimension of the image (x,y) and the plane of the scale factor. Then a filtering step is necessary to remove irrelevant points, for example by eliminating points whose contrast is too low.
  • the calculation of the SIFT descriptor is carried out on an area around each point of interest, for example 16x16 pixels, subdivided into 4x4 zones of 4x4 pixels. On each of the 16 zones, a histogram of the gradient orientations based on 8 intervals is then calculated. The concatenation of the 16 histograms gives a descriptor vector of 128 values.
  • the method consists of using the determinant of the Hessian matrix, calculating an approximation of the second derivatives of the Gaussians of the image through filters at different scales using masks of different sizes (for example 9x9, 15x15, 21x21, ).
  • the principle is based on the sums of the responses of the horizontal and vertical Haar wavelets as well as their norms.
  • the circular description area is again divided into 16 regions.
  • a wavelet analysis is performed on each region in order to construct the final descriptor.
  • the latter is made up of the sum of the gradients in x and y as well as the sum of their respective norm for all 16 regions.
  • the descriptor vector is thus made up of 64 values which represent properties extracted both in normal space and in that of magnitude scales.
  • Each subset corresponds to a single fingerprint.
  • a metrology step 1030 consisting of calculating the distance between a first remarkable point and a second remarkable point on the original digital image of the sensitive product.
  • the distance between the first remarkable point and the second remarkable point is greater than a first threshold value recorded in a memory, and less than a second threshold value recorded in said memory.
  • the first threshold value ensures that the two remarkable points are not too close to each other; the second threshold value ensures that the two remarkable points are not too far from each other.
  • the first remarkable point is located on one of the characters of the identifier of the sensitive product.
  • the second remarkable point is located on a security wire of said sensitive product.
  • the second remarkable point is located on an edge of said sensitive product or on an edge of the face supporting said identifier.
  • the second remarkable point located on the contour of a pattern of the background of the face supporting said identifier.
  • the distance between two remarkable points is illustrated by a double arrow.
  • the first remarkable points are located on the character outline of the identifier, in this case the digits 04 of the serial number of a bank note; and at the other end of the double arrows, the second remarkable points are located on the outline of a character in the background (in this case the letter R which appears slightly in the background, with guilloches).
  • the previous variants can be combined with each other. We can calculate the distance between a first and a second remarkable point, and calculate the distance between the first remarkable point and a third remarkable point different from the second.
  • the first remarkable point and the second remarkable point are aligned on a horizontal straight line, or on a vertical straight line, so that the distance is calculated in the horizontal direction and/or in the vertical direction, in one direction or in the 'other, the horizontal and the vertical being defined typically by the reading direction.
  • At least one of the distances calculated for the sensitive product is recorded and associated with the original digital image of said sensitive product in the database.
  • a step 1100 is provided for acquiring a digital image of said sensitive product, typically using an optical lens of a communicating object, said sensitive product being preferably planar and comprising a surface supporting an identifier. Said digital image is called a “test digital image”.
  • communicating object we mean any object, preferably portable, equipped with an optical lens, a processor and a memory, and capable of establishing communication, radio or otherwise, with the database.
  • the communicating object is a mobile phone, a smart phone - or Smartphone by Anglicism, a PDA, a tablet, etc., a personal computer or an automatic bank note sorter.
  • test image of said sensitive product comprising said identifier then undergoes a digital processing step, which aims to compare said test image to a corresponding original digital image and which can be implemented on the communicating object or, preferably, on a remote server.
  • the remote server is the server hosting the database, or a server in communication with it and with the communicating object, which limits the risks of hacking the communicating object.
  • the digital processing step includes an optical character recognition (OCR) step 1110 consisting of recognizing the characters of the identifier of said sensitive product.
  • OCR optical character recognition
  • a step 1140 is then provided consisting of identifying in the database a set of at least one original digital image corresponding to the characters of the optically recognized identifier.
  • the digital processing state also includes a step 1120 consisting of extracting an optical print from the test digital image, in a manner identical to the extraction of an optical print from the original digital image, that is to say according to steps 1010, 1020, 1030 previously described.
  • the optical fingerprint of the test digital image is then compared 1150 to each optical fingerprint of the set of at least one original digital image. If several optical fingerprints of the digital test image are calculated, it can be planned to compare each optical fingerprint of the digital test image with each optical fingerprint of the original digital image.
  • a value of said attribute means that the sensitive product at the origin of said original digital image is considered to be invalid, for example because it has been withdrawn from circulation or declared stolen.
  • the comparison step is short-circuited as a function of the value of said attribute, that is to say if the sensitive product at the origin of said original digital image is considered to be invalid.
  • the calculation of local collisions can advantageously be carried out on a support (bank note, packaging) that is wrinkled or whose edges are damaged.

Description

DOMAINE DE L'INVENTIONFIELD OF THE INVENTION

La présente invention concerne le domaine de la protection des produits sensibles contre les contrefaçons. Au sens de la présente invention, un produit sensible comprend un identifiant, et correspond par exemple à un billet de banque, une boite de médicaments, un produit de luxe, etc.The present invention relates to the field of protection of sensitive products against counterfeiting. For the purposes of the present invention, a sensitive product includes an identifier, and corresponds for example to a bank note, a box of medicines, a luxury product, etc.

L'identifiant comprend un ensemble de caractères, par exemple alphanumériques, kenji, etc. Par exemple, l'identifiant est un numéro de série.The identifier includes a set of characters, for example alphanumeric, kenji, etc. For example, the identifier is a serial number.

La protection comprend au moins l'un parmi :

  • le marquage d'un produit sensible et/ou de son emballage grâce audit identifiant, et
  • la vérification dudit marquage, où par « vérification » on entend indistinctement vérification ou authentification.
The protection includes at least one of:
  • the marking of a sensitive product and/or its packaging using said identifier, and
  • the verification of said marking, where by “verification” we mean verification or authentication without distinction.

L'identifiant peut être individuel, c'est-à-dire spécifique à un produit sensible donné. L'identifiant peut aussi être générique, c'est-à-dire spécifique à un ensemble de produits sensibles, par exemple un lot de médicaments.The identifier can be individual, that is to say specific to a given sensitive product. The identifier can also be generic, that is to say specific to a set of sensitive products, for example a batch of medicines.

Par souci de concision, seul le cas des billets de banque, qui sont les produits sensibles parmi les plus complexes en termes de sécurité, sera décrit ci-après, l'invention pouvant être mise en oeuvre pour tout autre produit sensible.For the sake of brevity, only the case of bank notes, which are among the most complex sensitive products in terms of security, will be described below, the invention being able to be implemented for any other sensitive product.

L'authenticité des billets de banque est essentielle dans la vie économique. Les billets de banque comprennent un ensemble d'éléments de sécurité, par exemple tels que signes, filigranes, fil de sécurité, hologramme, etc. qui sont incorporés dans ou sur les billets lors de leur fabrication.The authenticity of banknotes is essential in economic life. Banknotes include a set of security elements, for example such as signs, watermarks, security thread, hologram, etc. which are incorporated in or on the banknotes during their manufacture.

Pour vérifier l'authenticité d'un billet de banque, il convient donc de vérifier l'authenticité de certains de ces éléments de sécurité, que ce soit sans équipement, avec des outils d'aide à l'authentification, ou avec une machine d'authentification.To verify the authenticity of a bank note, it is therefore appropriate to verify the authenticity of some of these security elements, whether without equipment, with authentication tools, or with a machine. 'authentication.

À cet effet, on connaît certaines méthodes d'authentification publiées par exemple par la Banque de France à l'adresse Internet : https://www.banque-france.fr/la-banque-de-france/billets-et-pieces/notre-monnaie-leuro/authentifier-les-billets-en-eur/comment-authentifier-les-billets.html. For this purpose, we know certain authentication methods published for example by the Banque de France at the Internet address: https://www.banque-france.fr/la-banque-de-france/billets-et-pieces/notre-coin-leuro/authentifier-les-billets-en-eur/comment-authentifier-les-billets. html.

Diverses méthodes sont ainsi proposées, elles se basent notamment sur le toucher, l'observation en lumière ultraviolette ou en lumière visible, notamment à l'aide d'une loupe, ainsi que sur la manipulation d'un billet de banque afin de contrôler notamment l'aspect diffractant de l'hologramme en réaction avec un changement des conditions d'observations.Various methods are thus proposed, they are based in particular on touch, observation in ultraviolet light or in visible light, in particular using a magnifying glass, as well as on the manipulation of a bank note in order to control in particular the diffracting appearance of the hologram in reaction to a change in observation conditions.

US2012/324534 divulgue la vérification d'un document de sécurité par comparaison de l'empreinte scannée de la personne avec celle dans la base de données. US2012/324534 discloses the verification of a security document by comparing the scanned fingerprint of the person with that in the database.

US2014/055824 divulgue la vérification des documents de sécurité avec des hologrammes. US2014/055824 discloses verification of security documents with holograms.

WO2015/042485 divulgue la vérification des documents de sécurité par comparaison des motifs imprimés. WO2015/042485 discloses the verification of security documents by comparison of printed patterns.

Il est proposé ici une solution d'authentification avec un équipement optique simple et courant, permettant à quiconque de vérifier l'authenticité d'un produit sensible, en particulier un billet de banque, en lumière visible.An authentication solution is proposed here with simple and common optical equipment, allowing anyone to verify the authenticity of a sensitive product, in particular a bank note, in visible light.

RESUME DE L'INVENTIONSUMMARY OF THE INVENTION

Plus précisément, l'invention concerne selon un premier ses objets, un procédé de vérification de l'authenticité d'un produit sensible, tel que revendiqué dans la revendication 1.More precisely, the invention concerns, according to a first its objects, a method of verifying the authenticity of a sensitive product, as claimed in claim 1.

On peut prévoir une étape (1010) consistant à définir un ensemble de points remarquables sur l'image numérique originale et sur l'image numérique test du produit sensible, chaque point remarquable étant défini comme un ensemble d'au moins un pixel, c'est-à-dire un pixel unique ou un ensemble de pixels adjacents deux à deux pour lequel le gradient de contraste est supérieur à une valeur seuil prédéfinie, selon au moins une direction prédéfinie et une distance prédéfinie autour dudit ensemble d'au moins un pixel.A step (1010) can be provided consisting of defining a set of remarkable points on the original digital image and on the test digital image of the sensitive product, each remarkable point being defined as a set of at least one pixel, that is, that is to say a single pixel or a set of adjacent pixels in pairs for which the contrast gradient is greater than a predefined threshold value, in at least one predefined direction and a predefined distance around said set of at least one pixel .

L'étape (1020) de calcul de collisions locales consiste, pour au moins un point remarquable, à calculer un ensemble d'histogrammes locaux dans un sous-ensemble déterminé de l'image numérique test ou de l'image numérique originale, ledit sous-ensemble comprenant ledit point remarquable.The step (1020) of calculating local collisions consists, for at least one remarkable point, of calculating a set of local histograms in a determined subset of the test digital image or the original digital image, said sub-set. -set comprising said remarkable point.

L'étape (1030) de métrologie consiste à calculer la distance entre un premier point remarquable et un deuxième point remarquable sur au moins l'une parmi l'image numérique originale et l'image numérique test du produit sensible.The metrology step (1030) consists of calculating the distance between a first remarkable point and a second remarkable point on at least one of the original digital image and the test digital image of the sensitive product.

On peut prévoir une étape (1040) consistant à associer dans la base de données chaque image numérique originale à une pluralité d'attributs correspondants, lesdits attributs comprenant au moins l'un parmi : les coordonnées de points remarquables, les distances entre certains points remarquables, des valeurs de gradient de contraste autour des points remarquables, ou encore d'autres caractéristiques notables comme des moments mathématiques de certaines parties de l'image.A step (1040) can be provided consisting of associating in the database each original digital image with a plurality of corresponding attributes, said attributes comprising at least one of: the coordinates of remarkable points, the distances between certain remarkable points , contrast gradient values around remarkable points, or other notable characteristics such as mathematical moments of certain parts of the image.

On peut prévoir une étape (1050) consistant à associer, dans la base de données, un attribut de validité à l'une au moins des images numériques originales.A step (1050) can be provided consisting of associating, in the database, a validity attribute with at least one of the original digital images.

De préférence, l'étape de comparaison (1150) est court-circuitée en fonction de la valeur de l'attribut de validité.Preferably, the comparison step (1150) is bypassed depending on the value of the validity attribute.

Dans un mode de réalisation, l'étape d'acquisition (1100) est mise en oeuvre grâce à un capteur d'un objectif optique d'un objet communicant.In one embodiment, the acquisition step (1100) is implemented using a sensor of an optical lens of a communicating object.

Dans un mode de réalisation, ledit sous-ensemble de l'image numérique test ou de l'image numérique originale présente une forme géométrique prédéterminée dont la valeur de la surface est prédéterminée ou fonction d'un gradient prédéterminé de contraste, de couleur ou d'intensité autour dudit point remarquable.In one embodiment, said subset of the test digital image or the original digital image has a predetermined geometric shape whose value of the surface is predetermined or function of a predetermined gradient of contrast, color or intensity around said remarkable point.

Selon un autre de ses objets, l'invention concerne un programme d'ordinateur comprenant des instructions de code de programme pour l'exécution des étapes du procédé selon l'invention, lorsque ledit programme est exécuté sur un ordinateur.According to another of its objects, the invention relates to a computer program comprising program code instructions for executing the steps of the method according to the invention, when said program is executed on a computer.

D'autres caractéristiques et avantages de la présente invention apparaîtront plus clairement à la lecture de la description suivante donnée à titre d'exemple illustratif et non limitatif et faite en référence aux figures annexées.Other characteristics and advantages of the present invention will appear more clearly on reading the following description given by way of illustrative and non-limiting example and made with reference to the appended figures.

DESCRIPTIF DES DESSINSDESCRIPTION OF THE DRAWINGS

  • la figure 1 illustre un mode de réalisation d'un produit sensible sous forme de billet de banque,there figure 1 illustrates an embodiment of a sensitive product in the form of a bank note,
  • la figure 2 illustre, sur un agrandissement d'une partie d'un identifiant de produit sensible, en l'espèce un numéro de série de billet de banque, un ensemble de flèches représentant la distance entre points remarquables pour le calcul de métrologie selon l'invention, etthere figure 2 illustrates, on an enlargement of a part of a sensitive product identifier, in this case a bank note serial number, a set of arrows representing the distance between remarkable points for the metrology calculation according to the invention, And
  • la figure 3 illustre un mode de réalisation du procédé selon l'invention.there Figure 3 illustrates an embodiment of the method according to the invention.
DESCRIPTION DETAILLEEDETAILED DESCRIPTION Produit sensibleSensitive product

Un produit sensible 100, en l'espèce un billet de banque (spécimen) est illustré sur la figure 1. Le billet de banque est plan et rectangulaire. Par convention, on entend par X, ou horizontal, le sens de la longueur du billet de banque et par Y, ou verticale, le sens de la largeur dudit billet de banque.A sensitive product 100, in this case a bank note (specimen) is illustrated on the figure 1 . The banknote is flat and rectangular. By convention, we mean by X, or horizontal, the direction of the length of the banknote and by Y, or vertical, the direction of the width of said banknote.

Comme exposé préalablement le billet de banque comprend un ensemble d'éléments de sécurité, en particulier graphiques ou optiques.As previously explained, the banknote includes a set of security elements, in particular graphic or optical.

Parmi les éléments de sécurité, le billet de banque comprend notamment un fil de sécurité 130, qui est intégré dans la pâte à papier dudit billet de banque et qui est visible optiquement par un effet local de contraste.Among the security elements, the banknote notably comprises a security thread 130, which is integrated into the paper pulp of said banknote and which is optically visible by a local contrast effect.

La position d'un fil de sécurité n'est pas nécessairement la même entre deux billets de banque de même valeur numéraire. Par exemple, lors de la fabrication d'un billet de banque, on peut prévoir que celui-ci comprend une fenêtre graphique dont la largeur est celle dudit billet, dont la longueur est au maximum celle dudit billet, et dans le plan dudit billet, à l'intérieur de laquelle la position du fil de sécurité est aléatoire, ledit fil de sécurité étant généralement rectiligne, et en particulier dans le sens de la largeur du billet.The position of a security thread is not necessarily the same between two banknotes of the same monetary value. For example, when manufacturing a bank note, it can be provided that it includes a graphic window whose width is that of said note, whose length is at most that of said note, and in the plane of said note, within which the position of the security thread is random, said security thread being generally rectilinear, and in particular in the direction of the width of the note.

Le billet de banque comprend également un filigrane 110, illustré notamment par le nombre « 20 » sur la figure 1 et qui est visible optiquement par un effet local de contraste.The banknote also includes a watermark 110, illustrated in particular by the number “20” on the figure 1 and which is optically visible by a local contrast effect.

Le produit sensible comprend un identifiant 120, typiquement composé de caractères alphanumériques, par exemple incrémentés, et en l'espèce un numéro de série. En particulier pour les billets de banque, l'identifiant n'est pas imprimé en offset. Généralement, il est imprimé avec une encre sombre, en l'espèce noire, sur un fond clair.The sensitive product includes an identifier 120, typically composed of alphanumeric characters, for example incremented, and in this case a serial number. Particularly for banknotes, the identifier is not printed offset. Generally, it is printed with dark ink, in this case black, on a light background.

L'identifiant définit un premier plan et le fond définit un arrière-plan, il est visible optiquement par un effet local de contraste.The identifier defines a foreground and the background defines a background, it is optically visible by a local contrast effect.

En outre, l'identifiant peut être reconnu par reconnaissance optique de caractères.Additionally, the identifier can be recognized by optical character recognition.

Le produit sensible est au moins partiellement plan, c'est-à-dire qu'il est plan ou comprend au moins une face plane supportant ledit identifiant. Typiquement, la surface plane supportant ledit identifiant est une surface sur laquelle ledit identifiant est intégré, apposé, collé, imprimé, etc. soit directement sur le produit sensible, soit sur l'emballage dudit produit sensible, notamment sur la partie de l'emballage recouvrant ladite surface.The sensitive product is at least partially planar, that is to say it is planar or comprises at least one planar face supporting said identifier. Typically, the flat surface supporting said identifier is a surface on which said identifier is integrated, affixed, glued, printed, etc. either directly on the sensitive product, or on the packaging of said sensitive product, in particular on the part of the packaging covering said surface.

Au sens de la présente invention, on considère donc indistinctement le produit sensible et son emballage.For the purposes of the present invention, we therefore consider the sensitive product and its packaging without distinction.

De préférence, la surface plane supportant l'identifiant comprend au moins l'une des caractéristiques suivantes :

  • elle est non uniformément monochromatique,
  • elle comprend au moins un élément graphique (de sécurité ou de décor).
Preferably, the flat surface supporting the identifier comprises at least one of the following characteristics:
  • it is non-uniformly monochromatic,
  • it includes at least one graphic element (safety or decoration).

ScanScan

Après la fabrication d'un produit sensible, et de préférence avant sa mise en service / dans le commerce, on prévoit une étape consistant à réaliser une image numérique dudit produit sensible, c'est-à-dire au moins de la face plane supportant ledit identifiant.After the manufacture of a sensitive product, and preferably before its putting into service/in commerce, a step is provided consisting of producing a digital image of said sensitive product, that is to say at least of the flat face supporting said identifier.

De préférence l'image réalisée est en haute définition et stockée dans une base de données sécurisée.Preferably the image produced is in high definition and stored in a secure database.

Ladite image numérique est dite « image numérique originale », par différence à une « image numérique test » décrite ultérieurement.Said digital image is called an “original digital image”, as opposed to a “test digital image” described later.

Reconnaissance de caractèresCharacter recognition

On prévoit une étape consistant à reconnaître optiquement (OCR) les caractères de l'identifiant dans l'image numérique originale d'un produit sensible, typiquement grâce un scanner.A step is provided consisting of optically recognizing (OCR) the characters of the identifier in the original digital image of a sensitive product, typically using a scanner.

L'identifiant reconnu optiquement est enregistré sous format numérique et associé à l'image numérique originale dudit produit sensible dans la base de données, ce qui permet par exemple une indexation de celle-ci.The optically recognized identifier is recorded in digital format and associated with the original digital image of said sensitive product in the database, which allows for example indexing thereof.

Sur le produit sensible, chaque caractère de l'identifiant est défini graphiquement par un ensemble de points d'impression. L'encre utilisée pour l'impression est sombre, en général noire. La teinte du fond sur lequel est imprimé chaque caractère est plus claire que celle de l'encre, de sorte que le caractère est lisible sur ledit fond grâce à un effet local de contraste.On the sensitive product, each character of the identifier is graphically defined by a set of printing points. The ink used for printing is dark, usually black. The color of the background on which each character is printed is lighter than that of the ink, so that the character is readable on said background thanks to a local contrast effect.

Le fond sur lequel l'identifiant est imprimé n'est pas uniforme et peut comprendre un ensemble de motifs 150, qui peuvent être des éléments graphiques de sécurité ou de décor ; et chaque motif 150 du fond du produit sensible présente un effet local de contraste.The background on which the identifier is printed is not uniform and may include a set of patterns 150, which may be security or decorative graphic elements; and each pattern 150 of the background of the sensitive product presents a local contrast effect.

Les motifs du fond représentent par exemple des caractères alphanumériques, des symboles graphiques, une image, etc. qui dépend le plus souvent du domaine d'utilisation, par exemple le domaine fiduciaire (billets de banque), ou le domaine de l'emballage de produit pharmaceutique. Par exemple, le fond peut comprendre au moins l'un des éléments graphiques (de sécurité ou non) parmi :

  • au moins un filigrane ;
  • des impressions offset ;
  • au moins un hologramme 140 ;
  • au moins un fil de sécurité ;
  • au moins une inscription, de préférence en encre de sécurité par exemple optiquement variable ;
  • au moins une impression de fond (éventuellement plus ou moins monochromatique) ;
  • des inscriptions légales (par exemple la composition, en particulier chimique) ;
  • un ensemble d'au moins un logo ;
  • un ensemble d'au moins un hologramme ou un élément de sécurité visible (par exemple une encre variable) ;
  • etc.
The background patterns represent, for example, alphanumeric characters, graphic symbols, an image, etc. which most often depends on the field of use, for example the fiduciary field (bank notes), or the field of pharmaceutical product packaging. For example, the background may include at least one of the graphic elements (security or not) from:
  • at least one watermark;
  • offset printing;
  • at least one hologram 140;
  • at least one safety thread;
  • at least one inscription, preferably in security ink, for example optically variable;
  • at least one background print (possibly more or less monochromatic);
  • legal inscriptions (for example composition, in particular chemical);
  • a set of at least one logo;
  • a set of at least one hologram or a visible security element (for example variable ink);
  • etc.

De préférence, l'identifiant est unique. Toutefois, pour différentes raisons, il arrive que plusieurs produits sensibles présentent un même identifiant, par exemple plusieurs billets de banque de même valeur numéraire présentent un même numéro de série. On estime qu'au maximum une vingtaine de billets de banque de même valeur numéraire peuvent présenter un même numéro de série.Preferably, the identifier is unique. However, for various reasons, it happens that several sensitive products have the same identifier, for example several bank notes of the same monetary value have the same serial number. It is estimated that a maximum of twenty banknotes of the same monetary value can have the same serial number.

Cependant, même si deux produits sensibles présentent un même identifiant, en réalité d'autres éléments graphiques de la face supportant ledit identifiant diffèrent.However, even if two sensitive products have the same identifier, in reality other graphic elements of the face supporting said identifier differ.

Par exemple, deux billets de banque présentant un même identifiant présentent en fait un ensemble d'au moins une différence par l'un au moins des éléments de sécurité ou le fond. Par exemple, la position de l'identifiant sur le fond est différente, ou le motif du fond est différent, etc.For example, two banknotes presenting the same identifier in fact present a set of at least one difference in at least one of the security elements or the background. For example, the position of the identifier on the background is different, or the pattern of the background is different, etc.

Ainsi, vus globalement, les deux produits sensibles qui présentent un même identifiant sont en réalité graphiquement différents.Thus, seen globally, the two sensitive products which present the same identifier are in reality graphically different.

Ainsi, chaque produit sensible est en réalité graphiquement unique. Il possède donc une empreinte, c'est-à-dire un ensemble d'attributs (notamment optiques, graphiques et géométriques) qui lui confèrent son unicité. A l'instar d'une empreinte digitale, l'empreinte (optique) du produit sensible peut être extraite de l'image numérique originale pour identifier et authentifier ledit produit sensible comme décrit ultérieurement.Thus, each sensitive product is actually graphically unique. It therefore has a fingerprint, that is to say a set of attributes (notably optical, graphic and geometric) which give it its uniqueness. Like a fingerprint, the (optical) fingerprint of the sensitive product can be extracted from the original digital image to identify and authenticate said sensitive product as described later.

EmpreinteFootprint

On prévoit une étape 1000 consistant à extraire au moins une empreinte optique de l'image numérique originale du produit sensible scanné, c'est-à-dire à calculer les attributs qui concourent au caractère unique de celui-ci, à partir de l'image numérique dans la base de données ou avant son stockage dans celle-ci. On peut alors associer ladite empreinte à ladite image numérique originale dans la base de données.A step 1000 is provided consisting of extracting at least one optical imprint from the original digital image of the sensitive product scanned, that is to say calculating the attributes which contribute to its unique character, from the digital image in the database or before its storage therein. We can then associate said fingerprint with said original digital image in the database.

Ainsi, dans la base de données, chaque image numérique originale est associée 1040 à une pluralité d'attributs correspondants, l'ensemble des attributs d'une image originale donnée permettant de caractériser au moins en partie celle-ci.Thus, in the database, each original digital image is associated 1040 with a plurality of corresponding attributes, all of the attributes of a given original image making it possible to characterize it at least in part.

Les attributs comprennent par exemple les coordonnées de points remarquables (décrits ci-après), les distances entre certains points remarquables, des valeurs de gradient de contraste autour des points remarquables, etc. ou encore d'autres caractéristiques notables comme des moments mathématiques de certaines parties de l'image comme décrit ci-après.The attributes include, for example, the coordinates of remarkable points (described below), the distances between certain remarkable points, contrast gradient values around the remarkable points, etc. or other notable characteristics such as mathematical moments of certain parts of the image as described below.

De nombreux moments peuvent être utilisés, par exemple au moins l'un parmi :

  • Les moments de Zernike, par exemple décrits à l'adresse liris.cnrs.fr/Documents/Liris-3770.pdf sont très utiles pour la modélisation de systèmes optiques, ils représentent bien les fronts d'onde et les transformations que ceux-ci subissent lors de la traversée de dioptres ou de la réflexion sur des miroirs. Ils sont très utiles pour la représentation des propriétés des images. Typiquement les premiers degrés des moments de Zernike représentent les inclinaisons et les changements d'orientation globaux du front d'onde, les seconds degrés représentent des astigmaties ou des défocalisations, les troisièmes degrés représentent les aberrations de coma, les quatrièmes degrés représentent les déformations sphériques, etc.
  • Les moments de Hu, qui sont construits sur des moments centraux et qui sont invariants en échelle, par exemple tels que décrit dans M. K. Hu, "Visual Pattern Recognition by Moment Invariants", IRE Trans. Info. Theory, vol. IT-8, pp.179-187, 1962 .
Many moments can be used, for example at least one of:
  • Zernike moments, for example described at liris.cnrs.fr/Documents/Liris-3770.pdf, are very useful for modeling optical systems, they represent wave fronts and the transformations that these undergo when crossing diopters or reflecting on mirrors. They are very useful for representing image properties. Typically the first degrees of Zernike moments represent global tilts and orientation changes of the wavefront, the second degrees represent astigmatisms or defocuses, the third degrees represent coma aberrations, the fourth degrees represent spherical deformations , etc.
  • The moments of Hu, which are built on central moments and which are scale invariant, for example as described in MK Hu, “Visual Pattern Recognition by Moment Invariants”, IRE Trans. Info. Theory, vol. IT-8, pp.179-187, 1962 .

A titre alternatif des moments mathématiques, on peut aussi utiliser des descripteurs dits « binaires » en ce qu'ils sont basés sur des échantillons de motif sur lequel on a le choix de la zone à échantillonner, que l'on traite pour mesurer l'orientation du motif afin de le recaler (la méthode pour déterminer l'orientation étant choisie) et qui permet enfin de comparer des paires d'échantillons par exemple dans une logique d'arbre binaire (la façon d'organiser les comparaisons étant choisie).As an alternative to mathematical moments, we can also use so-called “binary” descriptors in that they are based on pattern samples on which we have the choice of the area to be sampled, which we process to measure the orientation of the pattern in order to register it (the method for determining the orientation being chosen) and which finally makes it possible to compare pairs of samples for example in a binary tree logic (the way of organizing the comparisons being chosen).

De tels descripteurs binaires sont connus, par exemple :

  • Sous l'acronyme BRIEF (Binary robust independent elementary features en anglais) de la méthode ORB (pour Orientated FAST and Rotated BRIEF en anglais), décrits par exemple à l'adresse https://gilscvblog.com/2013/10/04/a-tutorial-on-binary-descriptors-part-3-the-orb-descriptor/ ;
  • Sous l'acronyme BRISK, et décrits par exemple dans l'article Leutenegger, Stefan, Margarita Chli, and Roland Y. Siegwart. "BRISK: Binary robust invariant scalable keypoints." Computer Vision (ICCV), 2011 IEEE International Conférence on. IEEE, 2011 .) ; et
  • Sous l'acronyme FREAK et décrits par exemple dans l'article Alahi, Alexandre, Raphael Ortiz, and Pierre Vandergheynst. "Freak: Fast retina keypoint." Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conférence on. IEEE, 2012 .
Such binary descriptors are known, for example:
  • Under the acronym BRIEF (Binary robust independent elementary features) of the ORB method (for Orientated FAST and Rotated BRIEF), described for example at https://gilscvblog.com/2013/10/04/ a-tutorial-on-binary-descriptors-part-3-the-orb-descriptor/ ;
  • Under the acronym BRISK, and described for example in the Leutenegger article, Stefan, Margarita Chli, and Roland Y. Siegwart. “BRISK: Binary robust invariant scalable keypoints.” Computer Vision (ICCV), 2011 IEEE International Conference on. IEEE, 2011 .); And
  • Under the acronym FREAK and described for example in the article Alahi, Alexandre, Raphael Ortiz, and Pierre Vandergheynst. "Freak: Fast retina keypoint." Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 2012 .

L'extraction de l'empreinte du produit sensible est mise en oeuvre automatiquement et comprend de préférence au moins l'une des étapes parmi : une étape de calcul de collisions locales et une étape de métrologie.The extraction of the fingerprint of the sensitive product is implemented automatically and preferably comprises at least one of the steps among: a local collision calculation step and a metrology step.

Points remarquablesNotable points

On peut prévoir une étape 1010 consistant à définir, ou identifier, un ensemble de points remarquables sur l'image numérique (originale ou test) du produit sensible.We can provide a step 1010 consisting of defining, or identifying, a set of remarkable points on the digital image (original or test) of the sensitive product.

Un point remarquable est défini comme un point de l'image numérique du produit sensible, c'est-à-dire un pixel ou un ensemble de pixels adjacents deux à deux, pour lequel le gradient de contraste, selon une direction et une distance prédéfinies, est supérieur à une valeur seuil prédéfinie.A remarkable point is defined as a point in the digital image of the sensitive product, that is to say a pixel or a set of adjacent pixels two by two, for which the contrast gradient, according to a predefined direction and distance , is greater than a predefined threshold value.

De préférence, la direction prédéfinie est horizontale et/ou verticale.Preferably, the predefined direction is horizontal and/or vertical.

De préférence, un premier point remarquable appartient au premier plan. En l'espèce, un premier point remarquable est un point d'impression d'un caractère de l'identifiant. Par exemple un deuxième point remarquable appartient au premier plan ou à l'arrière-plan (fond). En l'espèce, un deuxième point remarquable est un point sur le contour d'un élément graphique du motif du fond.Preferably, a first notable point belongs to the foreground. In this case, a first remarkable point is a printing point of a character of the identifier. For example, a second remarkable point belongs to the foreground or the background (fond). In this case, a second remarkable point is a point on the outline of a graphic element of the background pattern.

Par exemple, un ensemble de points remarquables peut être défini ou identifié selon l'algorithme FAST (pour Features from Accelerated Segment Test en anglais) par exemple tel que décrit dans l'article de Edward Rosten et Tom Drummond « Machine learning for high-speed corner détection » (2006) publié à l'adresse https://www.edwardrosten.com/work/rosten_2006_machine.pdf.For example, a set of remarkable points can be defined or identified according to the FAST algorithm (for Features from Accelerated Segment Test in English), for example such as described in the article by Edward Rosten and Tom Drummond “Machine learning for high-speed corner detection” (2006) published at https://www.edwardrosten.com/work/rosten_2006_machine.pdf.

Collisions localesLocal collisions

On peut prévoir une étape 1020 de calcul de collisions locales sur l'image numérique originale du produit sensible.A step 1020 of calculating local collisions can be provided on the original digital image of the sensitive product.

L'étape de calcul de collisions locales consiste, pour au moins un point remarquable, à calculer un ensemble d'histogrammes locaux dans un sous-ensemble déterminé de l'image numérique, ledit sous-ensemble étant une partie de l'image numérique qui comprend ledit point remarquable, qui présente une forme géométrique prédéterminée et dont la valeur de la surface est prédéterminée ou fonction d'un gradient prédéterminé de contraste, de couleur ou d'intensité autour dudit point remarquable.The step of calculating local collisions consists, for at least one remarkable point, of calculating a set of local histograms in a determined subset of the digital image, said subset being a part of the digital image which comprises said remarkable point, which has a predetermined geometric shape and whose surface value is predetermined or a function of a predetermined gradient of contrast, color or intensity around said remarkable point.

On peut prévoir toute forme géométrique prédéterminée. Celle-ci est enregistrée dans une mémoire. La valeur de la surface de la forme prédéterminée peut également être prédéterminée et enregistrée dans ladite mémoire. Avantageusement, la forme géométrique est un cercle centré sur ledit point remarquable, et dont le rayon est fonction du gradient choisi, ce qui simplifie les calculs donc augmente la vitesse de traitement.Any predetermined geometric shape can be provided. This is recorded in a memory. The surface value of the predetermined shape can also be predetermined and stored in said memory. Advantageously, the geometric shape is a circle centered on said remarkable point, and whose radius is a function of the chosen gradient, which simplifies the calculations and therefore increases the processing speed.

Les histogrammes locaux sont calculés selon un nombre de directions prédéterminées.Local histograms are calculated in a number of predetermined directions.

De préférence, on enregistre et associe dans la base de données à chaque produit sensible numérisé au moins l'un des éléments parmi :

  • la valeur des histogrammes locaux,
  • la façon dont ont été calculées les collisions locales, et
  • la position (coordonnées) des points remarquables.
Preferably, at least one of the elements among:
  • the value of local histograms,
  • how local collisions were calculated, and
  • the position (coordinates) of the remarkable points.

Par exemple, on peut calculer et enregistrer dans la base de données l'une au moins des propriétés du sous-ensemble déterminé parmi :

  • des descripteurs de contour ou de forme,
  • des indices de forme ou de texture,
  • des caractéristiques colorimétriques,
  • des caractéristiques de motif.
For example, we can calculate and record in the database at least one of the properties of the subset determined from:
  • contour or shape descriptors,
  • cues of shape or texture,
  • colorimetric characteristics,
  • pattern characteristics.

Par exemple, on peut utiliser l'algorithme dit SIFT pour "Scale Invariant Feature Transform" en anglais ou l'algorithme dit SURF pour "Speeded Up Robust Features" en anglais, qui sont tous deux des descripteurs locaux qui consistent, dans un premier temps, à détecter un certain nombre de points d'intérêt dans l'image, pour ensuite calculer un descripteur décrivant localement l'image autour de chaque point d'intérêt. La qualité du descripteur est mesurée par sa robustesse aux changements possibles que peut subir une image, en l'occurrence le changement d'échelle et la rotation.For example, we can use the so-called SIFT algorithm for "Scale Invariant Feature Transform" in English or the so-called SURF algorithm for "Speeded Up Robust Features" in English, which are both local descriptors which consist, initially , to detect a certain number of points of interest in the image, to then calculate a descriptor locally describing the image around each point of interest. The quality of the descriptor is measured by its robustness to possible changes that an image may undergo, in this case change of scale and rotation.

Pour l'algorithme SIFT, décrit notamment dans la publication D. Lowe. Object récognition from local scale-invariant features. IEEE International Conférence on Computer Vision, pages 1150-1157, 1999 , la détection des points est basée sur les différences des gaussiennes (DoG) obtenues par le calcul de la différence entre chaque couple d'images lissées par un filtre gaussien, en variant à chaque fois le paramètre sigma (c'est à dire la déviation standard) du filtre. Les DoG peuvent être calculé pour différents niveaux d'échelle permettant d'introduire la notion de l'espace d'échelle. La détection des potentielles zones de points d'intérêt / points remarquables s'effectue en recherchant les extrema selon le plan de la dimension de l'image (x,y) et le plan du facteur d'échelle. Ensuite une étape de filtrage est nécessaire pour supprimer les points non pertinents, en éliminant par exemple les points dont le contraste est trop faible.For the SIFT algorithm, described in particular in the publication D. Lowe. Object recognition from local scale-invariant features. IEEE International Conference on Computer Vision, pages 1150-1157, 1999 , the detection of points is based on the differences of the Gaussians (DoG) obtained by calculating the difference between each pair of images smoothed by a Gaussian filter, by varying the sigma parameter each time (i.e. the deviation standard) of the filter. The DoG can be calculated for different scale levels allowing the notion of scale space to be introduced. The detection of potential areas of points of interest / remarkable points is carried out by searching for the extrema according to the plane of the dimension of the image (x,y) and the plane of the scale factor. Then a filtering step is necessary to remove irrelevant points, for example by eliminating points whose contrast is too low.

Le calcul du descripteur SIFT s'effectue sur une zone autour de chaque point d'intérêt par exemple de 16x16 pixels, subdivisée en 4x4 zones de 4x4 pixels. Sur chacune des 16 zones, un histogramme des orientations du gradient basé sur 8 intervalles est alors calculé. La concaténation des 16 histogrammes donne un vecteur descripteur de 128 valeurs.The calculation of the SIFT descriptor is carried out on an area around each point of interest, for example 16x16 pixels, subdivided into 4x4 zones of 4x4 pixels. On each of the 16 zones, a histogram of the gradient orientations based on 8 intervals is then calculated. The concatenation of the 16 histograms gives a descriptor vector of 128 values.

Pour l'algorithme SURF, décrit notamment dans la publication H. Bay, T. Tuylelaars, and L. Van Gool. Surf : Speeded up robust features. European Conférence on Computer Vision, pages 404-417, 2006 , la méthode consiste à utiliser le déterminant de la matrice Hessienne, à calculer une approximation des dérivées secondes des gaussiennes de l'image par le biais de filtres à différentes échelles en utilisant des masques de différentes tailles (par exemple 9x9, 15x15, 21x21, ...). Pour le calcul de l'orientation des points et les descripteurs autour des points, le principe est basé sur les sommes des réponses des ondelettes de Haar horizontales et verticales ainsi que leurs normes. La zone circulaire de description est divisée là encore en 16 régions. Une analyse en ondelettes est effectuée sur chaque région afin de construire le descripteur final. Ce dernier est constitué de la somme des gradients en x et en y ainsi que de la somme de leur norme respective pour l'ensemble des 16 régions. Le vecteur descripteur est ainsi constitué de 64 valeurs qui représentent des propriétés extraites à la fois dans l'espace normal et dans celui des échelles de grandeur.For the SURF algorithm, described in particular in the publication H. Bay, T. Tuylelaars, and L. Van Gool. Surfing: Speeded up robust features. European Conference on Computer Vision, pages 404-417, 2006 , the method consists of using the determinant of the Hessian matrix, calculating an approximation of the second derivatives of the Gaussians of the image through filters at different scales using masks of different sizes (for example 9x9, 15x15, 21x21, ...). For the calculation of the orientation of the points and the descriptors around the points, the principle is based on the sums of the responses of the horizontal and vertical Haar wavelets as well as their norms. The circular description area is again divided into 16 regions. A wavelet analysis is performed on each region in order to construct the final descriptor. The latter is made up of the sum of the gradients in x and y as well as the sum of their respective norm for all 16 regions. The descriptor vector is thus made up of 64 values which represent properties extracted both in normal space and in that of magnitude scales.

A titre alternatif à l'algorithme SIFT, on peut utiliser l'un des algorithmes parmi :

  • l'algorithme ASIFT pour Affine-SIFT. C'est une méthode de comparaison d'images qui permet d'intégrer dans la prise en compte les transformations affines sur l'image et qui, en l'espèce, peut servir à compenser les déformations dues à l'orientation du plan du produit sensible dans l'espace (en particulier un billet de banque). Une telle méthode est décrite par exemple à l'adresse http://www.ipol.im/pub/art/2011/my-asift/ ; et
  • l'algorithme ORB, qui est une méthode destinée à accélérer les traitements vis-à-vis de l'algorithme SIFT et qui est basé sur un détecteur de points remarquables de type FAST décrite ci-dessus, et des descripteurs de propriétés locales de type test binaires BRIEF, par exemple tel que décrit à l'adresse http://www.vision.cs.chubu.ac.jp/CV-R/pdf/Rublee_iccv2011.pdf.
As an alternative to the SIFT algorithm, one of the algorithms can be used among:
  • the ASIFT algorithm for Affine-SIFT. It is a method of comparing images which allows affine transformations on the image to be taken into account and which, in this case, can be used to compensate for deformations due to the orientation of the plane of the product. sensitive in space (in particular a bank note). Such a method is described for example at http://www.ipol.im/pub/art/2011/my-asift/ ; And
  • the ORB algorithm, which is a method intended to accelerate processing with respect to the SIFT algorithm and which is based on a detector of remarkable points of the FAST type described above, and descriptors of local properties of the type BRIEF binary tests, for example as described at http://www.vision.cs.chubu.ac.jp/CV-R/pdf/Rublee_iccv2011.pdf .

A chaque sous-ensemble correspond une seule empreinte. On peut prévoir de stocker l'empreinte de chaque sous-ensemble sélectionné dans la base de données.Each subset corresponds to a single fingerprint. We can plan to store the fingerprint of each selected subset in the database.

MétrologieMetrology

On peut prévoir une étape 1030 de métrologie consistant à calculer la distance entre un premier point remarquable et un deuxième point remarquable sur l'image numérique originale du produit sensible.We can provide a metrology step 1030 consisting of calculating the distance between a first remarkable point and a second remarkable point on the original digital image of the sensitive product.

De préférence, la distance entre le premier point remarquable et le deuxième point remarquable est supérieure à une première valeur seuil enregistrée dans une mémoire, et inférieure à une deuxième valeur seuil enregistrée dans ladite mémoire.Preferably, the distance between the first remarkable point and the second remarkable point is greater than a first threshold value recorded in a memory, and less than a second threshold value recorded in said memory.

La première valeur seuil permet de garantir que les deux points remarquables ne soient pas trop près l'un de l'autre ; la deuxième valeur seuil permet de garantir que les deux points remarquables pas trop éloignés l'un de l'autre.The first threshold value ensures that the two remarkable points are not too close to each other; the second threshold value ensures that the two remarkable points are not too far from each other.

De préférence, le premier point remarquable est situé sur un des caractères de l'identifiant du produit sensible.Preferably, the first remarkable point is located on one of the characters of the identifier of the sensitive product.

Dans une première variante, le deuxième point remarquable est situé sur un fil de sécurité dudit produit sensible.In a first variant, the second remarkable point is located on a security wire of said sensitive product.

Dans une deuxième variante, le deuxième point remarquable est situé sur une bordure dudit produit sensible ou sur une bordure de la face supportant ledit identifiant.In a second variant, the second remarkable point is located on an edge of said sensitive product or on an edge of the face supporting said identifier.

Dans une troisième variante, le deuxième point remarquable situé sur le contour d'un motif du fond de la face supportant ledit identifiant.In a third variant, the second remarkable point located on the contour of a pattern of the background of the face supporting said identifier.

Sur la figure 2, la distance entre deux points remarquables est illustrée par une double flèche. A une extrémité des doubles flèches, les premiers points remarquables sont situés sur le contour de caractères de l'identifiant, en l'espèce les chiffres 04 du numéro de série d'un billet de banque ; et à l'autre extrémité des doubles flèches, les deuxièmes point remarquables sont situés sur le contour d'un caractère du fond (en l'espèce la lettre R qui apparaît légèrement en arrière-plan, avec des guilloches).On the figure 2 , the distance between two remarkable points is illustrated by a double arrow. At one end of the double arrows, the first remarkable points are located on the character outline of the identifier, in this case the digits 04 of the serial number of a bank note; and at the other end of the double arrows, the second remarkable points are located on the outline of a character in the background (in this case the letter R which appears slightly in the background, with guilloches).

Les variantes précédentes sont combinables entre elles. On peut calculer la distance entre un premier et un deuxième point remarquable, et calculer la distance entre le premier point remarquable et un troisième point remarquable différent du deuxième.The previous variants can be combined with each other. We can calculate the distance between a first and a second remarkable point, and calculate the distance between the first remarkable point and a third remarkable point different from the second.

De préférence, le premier point remarquable et le deuxième point remarquable sont alignés sur une droite horizontale, ou sur une droite verticale, de sorte que la distance est calculée selon la direction horizontale et/ou selon la direction verticale, dans un sens ou dans l'autre, l'horizontale et la verticale étant définies typiquement par le sens de lecture.Preferably, the first remarkable point and the second remarkable point are aligned on a horizontal straight line, or on a vertical straight line, so that the distance is calculated in the horizontal direction and/or in the vertical direction, in one direction or in the 'other, the horizontal and the vertical being defined typically by the reading direction.

De préférence, au moins l'une des distances calculées pour le produit sensible est enregistrée et associée à l'image numérique originale dudit produit sensible dans la base de données.Preferably, at least one of the distances calculated for the sensitive product is recorded and associated with the original digital image of said sensitive product in the database.

FonctionnementFunctioning

Pour vérifier l'authenticité d'un produit sensible, en particulier une fois celui-ci mis en service / dans le commerce, on prévoit une étape 1100 d'acquisition d'une image numérique dudit produit sensible, typiquement grâce un objectif optique d'un objet communicant, ledit produit sensible étant de préférence plan et comprenant une surface supportant un identifiant. Ladite image numérique est dite « image numérique test ».To verify the authenticity of a sensitive product, in particular once it has been put into service/in commerce, a step 1100 is provided for acquiring a digital image of said sensitive product, typically using an optical lens of a communicating object, said sensitive product being preferably planar and comprising a surface supporting an identifier. Said digital image is called a “test digital image”.

Par « objet communicant » on entend tout objet, de préférence portable, équipé d'un objectif optique, d'un processeur et d'une mémoire, et susceptible d'établir une communication, radio ou autre, avec la base de données. Typiquement, l'objet communicant est un téléphone portable, un téléphone intelligent - ou Smartphone par anglicisme, un PDA, une tablette, etc., un ordinateur individuel ou une trieuse automatique de billets de banque.By “communicating object” we mean any object, preferably portable, equipped with an optical lens, a processor and a memory, and capable of establishing communication, radio or otherwise, with the database. Typically, the communicating object is a mobile phone, a smart phone - or Smartphone by Anglicism, a PDA, a tablet, etc., a personal computer or an automatic bank note sorter.

L'image test dudit produit sensible comprenant ledit identifiant subit alors une étape de traitement numérique, qui vise à comparer ladite image test à une image numérique originale correspondante et qui peut être mis en oeuvre sur l'objet communicant ou, de préférence, sur un serveur distant. Typiquement le serveur distant est le serveur hébergeant la base de données, ou un serveur en communication avec celle-ci et avec l'objet communicant, ce qui limite les risques de piratage de l'objet communiquant.The test image of said sensitive product comprising said identifier then undergoes a digital processing step, which aims to compare said test image to a corresponding original digital image and which can be implemented on the communicating object or, preferably, on a remote server. Typically the remote server is the server hosting the database, or a server in communication with it and with the communicating object, which limits the risks of hacking the communicating object.

L'étape de traitement numérique comprend une étape 1110 de reconnaissance optique de caractères (OCR) consistant à reconnaître les caractères de l'identifiant dudit produit sensible.The digital processing step includes an optical character recognition (OCR) step 1110 consisting of recognizing the characters of the identifier of said sensitive product.

On prévoit une étape 1130 consistant à envoyer au serveur distant au moins l'un parmi :

  • les caractères de l'identifiant reconnu optiquement, et
  • ladite image numérique test.
A step 1130 is provided consisting of sending to the remote server at least one of:
  • the characters of the optically recognized identifier, and
  • said test digital image.

Après connexion dudit objet communicant à la base de données, on prévoit alors une étape 1140 consistant à identifier dans la base de données un ensemble d'au moins une image numérique originale correspondant aux caractères de l'identifiant reconnu optiquement.After connection of said communicating object to the database, a step 1140 is then provided consisting of identifying in the database a set of at least one original digital image corresponding to the characters of the optically recognized identifier.

L'état de traitement numérique comprend également une étape 1120 consistant à extraire une empreinte optique de l'image numérique test, de manière identique à l'extraction d'une empreinte optique de l'image numérique originale, c'est-à-dire selon les étapes 1010, 1020, 1030 précédemment décrites.The digital processing state also includes a step 1120 consisting of extracting an optical print from the test digital image, in a manner identical to the extraction of an optical print from the original digital image, that is to say according to steps 1010, 1020, 1030 previously described.

L'empreinte optique de l'image numérique test est alors comparée 1150 à chaque empreinte optique de l'ensemble d'au moins une image numérique originale. Si plusieurs empreintes optiques de l'image numérique test sont calculées, on peut prévoir de comparer chaque empreinte optique de l'image numérique test avec chaque empreinte optique de l'image numérique orignale.The optical fingerprint of the test digital image is then compared 1150 to each optical fingerprint of the set of at least one original digital image. If several optical fingerprints of the digital test image are calculated, it can be planned to compare each optical fingerprint of the digital test image with each optical fingerprint of the original digital image.

De préférence, on prévoit alors d'émettre un signal dont la valeur est fonction du résultat de la comparaison. Par exemple, on prévoit un signal binaire dont l'une des valeurs binaires signifie que la comparaison est positive, c'est-à-dire que l'empreinte de l'image test est égale à l'empreinte de l'image originale, et l'autre valeur binaire signifie que la comparaison est négative.Preferably, we then plan to emit a signal whose value depends on the result of the comparison. For example, we provide a binary signal of which one of the binary values means that the comparison is positive, that is to say that the fingerprint of the test image is equal to the fingerprint of the original image, and the other binary value means the comparison is negative.

Le risque d'obtenir une comparaison positive entre l'empreinte d'une image numérique originale provenant d'un produit sensible original et l'empreinte d'une image numérique test provenant d'un faux produit sensible créé par exemple par photocopie est extrêmement faible du fait de l'ensemble des éléments de sécurité, et notamment du fil de sécurité dans le cas des billets de banque.The risk of obtaining a positive comparison between the fingerprint of an original digital image from an original sensitive product and the fingerprint of a test digital image coming from a false sensitive product created for example by photocopy is extremely low due to all the security elements, and in particular the security thread in the case of bank notes.

Dans le cas des billets de banque, on estime le risque de comparaison positive par erreur (similarité accidentelle entre deux billets sur le type de caractéristiques mesurées) à 1/13 000 000 000.In the case of banknotes, the risk of positive comparison by error (accidental similarity between two banknotes based on the type of characteristics measured) is estimated at 1/13,000,000,000.

On peut prévoir d'associer 1050, dans la base de données, un attribut dit de validité pour chaque image numérique originale. Par exemple, une valeur dudit attribut signifie que le produit sensible à l'origine de ladite image numérique originale est considéré comme étant non valide, par exemple parce qu'il a été retiré de la mise en circulation ou déclaré volé. De préférence, l'étape de comparaison est court-circuitée en fonction de la valeur dudit attribut, c'est-à-dire si le produit sensible à l'origine de ladite image numérique originale est considéré comme étant non valide.We can plan to associate 1050, in the database, a so-called validity attribute for each original digital image. For example, a value of said attribute means that the sensitive product at the origin of said original digital image is considered to be invalid, for example because it has been withdrawn from circulation or declared stolen. Preferably, the comparison step is short-circuited as a function of the value of said attribute, that is to say if the sensitive product at the origin of said original digital image is considered to be invalid.

Grâce à l'invention, le calcul des collisions locales peut être avantageusement réalisé sur un support (billet de banque, emballage) froissé ou dont les bords sont abîmés.Thanks to the invention, the calculation of local collisions can advantageously be carried out on a support (bank note, packaging) that is wrinkled or whose edges are damaged.

Nomenclature

100
Produit sensible
110
Filigrane
120
Identifiant du produit sensible, par exemple numéro de billet de banque
130
Fil de sécurité
140
Hologramme
150
Motif du fond
1000
Extraction d'une empreinte optique de l'image numérique originale
1010
Définition d'un ensemble de points remarquables sur l'image numérique originale et sur l'image numérique test
1020
Calcul de collisions locales sur l'image numérique originale et/ou sur l'image numérique test
1030
Étape de métrologie sur l'image numérique originale et/ou sur l'image numérique test
1040
Association dans la base de données à chaque image numérique originale d'une pluralité d'attributs correspondants
1050
Association dans la base de données, d'un attribut de validité à l'une au moins des images numériques originales
1100
Acquisition d'une image numérique test dudit produit sensible
1110
Reconnaissance optique des caractères de l'identifiant du produit sensible
1120
Extraction d'une empreinte optique de l'image numérique test
1130
Envoi à un serveur distant
1140
Identification dans la base de données d'au moins une image numérique originale correspondant à l'image numérique test
1150
Comparaison des empreintes de l'image numérique test et de l'image numérique originale
Nomenclature
100
Sensitive product
110
Watermark
120
Sensitive product identifier, e.g. bank note number
130
Safety wire
140
Hologram
150
Background pattern
1000
Extraction of an optical fingerprint from the original digital image
1010
Definition of a set of remarkable points on the original digital image and on the test digital image
1020
Calculation of local collisions on the original digital image and/or on the test digital image
1030
Metrology step on the original digital image and/or on the test digital image
1040
Association in the database with each original digital image of a plurality of corresponding attributes
1050
Association in the database of a validity attribute with at least one of the original digital images
1100
Acquisition of a digital test image of said sensitive product
1110
Optical recognition of sensitive product identifier characters
1120
Extraction of an optical print from the digital test image
1130
Sending to a remote server
1140
Identification in the database of at least one original digital image corresponding to the test digital image
1150
Comparison of fingerprints from the test digital image and the original digital image

Claims (10)

  1. Method for verifying the authenticity of a sensitive product, said sensitive product comprising an identifier comprising a set of characters, characterized in that the method comprises steps consisting in:
    - acquiring (1100) a test digital image comprising said identifier of said sensitive product;
    - optically recognizing (1110) characters of said identifier,
    - defining (1010) a set of distinctive points on the original digital image and on the test digital image of the sensitive product, a distinctive point being defined as a point of the digital image of the sensitive product, that is to say a pixel or a set of two-by-two adjacent pixels, for which the contrast gradient is greater than a predefined threshold value in at least one predefined direction and at a predefined distance around said set of at least one pixel,
    - extracting (1120) an optical fingerprint of the test digital image,
    - sending (1130), to a remote server comprising a database comprising a set of original digital images of sensitive products, at least one from among:
    ∘ the optically recognized characters of the identifier,
    ∘ the optical fingerprint of the extracted test digital image, and
    ∘ said test digital image,
    - identifying (1140), in the database, a set of at least one original digital image corresponding to said test digital image,
    - extracting (1000) an optical fingerprint of the corresponding original digital image, and
    - comparing (1150) the optical fingerprint of the test digital image and the optical fingerprint of the original digital image,
    wherein:
    - the step (1120) consisting in extracting an optical fingerprint of the test digital image is implemented in an identical manner to the step (1000) consisting in extracting an optical fingerprint of the original digital image,
    the extraction step (1000, 1120) comprising at least one of the steps from among:
    - a step (1020) of calculating local collisions, consisting in calculating, for at least one distinctive point, a set of local histograms in a determined subset of the digital image, said subset being part of the digital image which comprises said distinctive point, and
    - a metrology step (1030) consisting in calculating the distance between a first distinctive point and a second distinctive point on the original digital image or on the test digital image.
  2. Method according to Claim 1, wherein,
    for the step (1020) of calculating local collisions, said subset which comprises said distinctive point has a predetermined geometrical shape the value of the area of which is predetermined or a function of a predetermined contrast, colour or intensity gradient around said distinctive point.
  3. Method according to Claim 2, wherein the geometrical shape is a circle centred around said distinctive point.
  4. Method according to any one of the preceding claims, wherein, for the metrology step (1030), the distance between the first distinctive point and the second distinctive point is greater than a first threshold value stored in a memory and less than a second threshold value stored in said memory.
  5. Method according to any one of Claims 2 to 4, comprising a step (1040) consisting in associating, in the database, each original digital image with a plurality of corresponding attributes, said attributes comprising at least one from among: the coordinates of distinctive points, the distances between certain distinctive points, and values of contrast gradient around distinctive points or else other distinctive features such as mathematical moments of certain parts of the image.
  6. Method according to any one of the preceding claims, comprising a step (1050) consisting in associating, in the database, a validity attribute with at least one of the original digital images.
  7. Method according to Claim 6, wherein the comparison step (1150) is bypassed depending on the value of the validity attribute.
  8. Method according to any one of the preceding claims, wherein the acquisition step (1100) is implemented using a sensor of an optical lens of a communicating object.
  9. Method according to any one of the preceding claims, further comprising a step consisting in associating said optical fingerprint of the original digital image with said original digital image in the database; and
    steps consisting in storing and associating, in the database, with each digitized sensitive product, at least one of the elements from among:
    - the value of the local histograms,
    - the way in which the local collisions were calculated, and
    - the position of the distinctive points.
  10. Method according to any one of the preceding claims, wherein a first distinctive point is a printing point of a character of the identifier and a second distinctive point belongs to the foreground or to the background.
EP18705689.0A 2017-01-31 2018-01-29 Method for verifying the authenticity of a sensitive product Active EP3577635B1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
FR1750810A FR3062509B1 (en) 2017-01-31 2017-01-31 PROCESS FOR VERIFYING THE AUTHENTICITY OF A SENSITIVE PRODUCT.
PCT/FR2018/050200 WO2018142054A1 (en) 2017-01-31 2018-01-29 Method for verifying the authenticity of a sensitive product.

Publications (2)

Publication Number Publication Date
EP3577635A1 EP3577635A1 (en) 2019-12-11
EP3577635B1 true EP3577635B1 (en) 2024-02-28

Family

ID=58632451

Family Applications (1)

Application Number Title Priority Date Filing Date
EP18705689.0A Active EP3577635B1 (en) 2017-01-31 2018-01-29 Method for verifying the authenticity of a sensitive product

Country Status (3)

Country Link
EP (1) EP3577635B1 (en)
FR (1) FR3062509B1 (en)
WO (1) WO2018142054A1 (en)

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR2952738B1 (en) * 2009-11-17 2012-01-13 Advestigo METHOD AND SYSTEM FOR AUTOMATICALLY CONTROL AND AUTHENTICITY OF IDENTITY DOCUMENT
FR2973137B1 (en) * 2011-03-25 2015-07-24 Hologram Ind METHOD AND SYSTEM FOR AUTHENTICATING A SECURE DOCUMENT
JP2016535375A (en) * 2013-09-20 2016-11-10 モバイル、サーチ、セキュリティ、リミテッド、ライアビリティ、カンパニーＭｏｂｉｌｅ Ｓｅａｒｃｈ Ｓｅｃｕｒｉｔｙ Ｌｌｃ Certificate and document authentication system

Also Published As

Publication number Publication date
WO2018142054A1 (en) 2018-08-09
FR3062509B1 (en) 2020-10-23
EP3577635A1 (en) 2019-12-11
FR3062509A1 (en) 2018-08-03

Similar Documents

Publication Publication Date Title
US11423641B2 (en) Database for detecting counterfeit items using digital fingerprint records
TW201305969A (en) Method and apparatus for authentication of a coin or other manufactured item
CA3000153A1 (en) Analysis process for a structure document capable of being deformed
EP3311333B1 (en) Pairing of images of postal articles with descriptors of singularities of the gradient field
Centeno et al. Identity Document and banknote security forensics: a survey
Remya Revi et al. Image forgery detection using deep textural features from local binary pattern map
Vaishnavi et al. Recognizing image splicing forgeries using histogram features
EP3577635B1 (en) Method for verifying the authenticity of a sensitive product
FR3109831A1 (en) Method for verifying a barcode.
EP3210166B1 (en) Method of comparing digital images
Sabeena et al. Digital Image Forgery Detection Using Local Binary Pattern (LBP) and Harlick Transform with classification
WO2020144225A1 (en) Method for processing digital images
WO2020025790A1 (en) Method for securing a bottle and verifying the bottle
Hardani et al. Identify the authenticity of rupiah currency using k nearest neighbor (K-NN) algorithm
Xu et al. Coin recognition method based on SIFT algorithm
EP3956809A1 (en) Image processing method for an identity document
Rahman et al. A statistical approach for offline signature verification using local gradient features
CN113343955B (en) Face recognition intelligent tail box application method based on depth pyramid
EP4091098A1 (en) Method for processing a candidate image
WO2023099571A1 (en) Method and device for authenticating printed codes
WO2021209412A1 (en) Method for detecting an attack by presentation for fingerprints
Sánchez-Rivero et al. Authenticity Assessment of Cuban Banknotes by Combining Deep Learning and Image Processing Techniques
Vhanmane et al. A Survey on Accurate and Efficient Image Forgery Detection Using SIFT Descriptor to Improve Detection Accuracy
Elbarrany et al. BuckTracker: System For Multi Banknotes Tracking
Sambare et al. Document Verification System and Validation Against QR Codes

Legal Events

Date Code Title Description
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: UNKNOWN

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE

PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20190709

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

AX Request for extension of the european patent

Extension state: BA ME

DAV Request for validation of the european patent (deleted)
DAX Request for extension of the european patent (deleted)
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: EXAMINATION IS IN PROGRESS

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: EXAMINATION IS IN PROGRESS

17Q First examination report despatched

Effective date: 20210825

GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: GRANT OF PATENT IS INTENDED

INTG Intention to grant announced

Effective date: 20230414

GRAJ Information related to disapproval of communication of intention to grant by the applicant or resumption of examination proceedings by the epo deleted

Free format text: ORIGINAL CODE: EPIDOSDIGR1

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: EXAMINATION IS IN PROGRESS

INTC Intention to grant announced (deleted)
GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: GRANT OF PATENT IS INTENDED

INTG Intention to grant announced

Effective date: 20230929

GRAS Grant fee paid

Free format text: ORIGINAL CODE: EPIDOSNIGR3

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE PATENT HAS BEEN GRANTED

AK Designated contracting states

Kind code of ref document: B1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

REG Reference to a national code

Ref country code: GB

Ref legal event code: FG4D

Free format text: NOT ENGLISH

REG Reference to a national code

Ref country code: CH

Ref legal event code: EP

REG Reference to a national code

Ref country code: DE

Ref legal event code: R096

Ref document number: 602018065813

Country of ref document: DE

REG Reference to a national code

Ref country code: IE

Ref legal event code: FG4D

Free format text: LANGUAGE OF EP DOCUMENT: FRENCH