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 comprises an identifier, and corresponds for example to a banknote, a box of drugs, a luxury product, etc.
• the identifier comprises a set of characters, for example alphanumeric, kenji, etc.
• the identifier is a serial number.
• the protection comprises at least one of:
• the identifier can be individual, that is to say specific to a given sensitive product.
• the identifier may also be generic, that is to say specific to a set of sensitive products, for example a batch of drugs.
• banknotes which are sensitive products among the most complex in terms of security, will be described below, the invention can be implemented for any other sensitive product.
• banknotes include a set of security features, such as signs, watermarks, security thread, hologram, etc. which are incorporated in or on the banknotes during their manufacture.
• the invention relates to a first object, a method for verifying the authenticity of a sensitive product, said sensitive product comprising an identifier.
• a remote server comprising a database comprising a set of original digital images of sensitive products, at least one of:
• step (1120) of extracting an optical fingerprint from the test digital image and step (1000) of extracting an optical fingerprint from the original digital image comprising at least one of:
• a step (1030) of metrology A step (1010) of defining a set of remarkable points on the original digital image and on the digital test image of the sensitive product can be provided, each remarkable point being defined as a set of at least one pixel, c ' 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, according to at least one predefined direction and a predefined distance around said set of at least one pixel .
• the step (1020) for calculating local collisions consists, for at least one remarkable point, in calculating a set of local histograms in a determined subset of the digital test image or the original digital image. said subset comprising said remarkable point.
• the metrology step (1030) consists in calculating the distance between a first remarkable point and a second remarkable point on at least one of the original digital image and the digital test image of the sensitive product.
• the comparison step (1150) is short-circuited according to the value of the validity attribute.
• the acquisition step (1100) is implemented by means of a sensor of an optical objective 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 a 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.
• FIG. 1 illustrates an embodiment of a sensitive product in the form of a banknote
• FIG. 2 illustrates, on an enlargement of a portion of a sensitive product identifier, in the present case a bank note serial number, a set of arrows representing the distance between remarkable points for the calculation of metrology according to the invention, and
• FIG. 3 illustrates an embodiment of the method according to the invention.
• a sensitive product 100 in this case a banknote (specimen) is illustrated in Figure 1.
• the banknote is planar and rectangular.
• X or horizontal, means the direction of the length of the banknote and Y, or vertical, the direction of the width of said banknote.
• the bank note comprises a set of security elements, in particular graphic or optical.
• the bank note comprises in particular a security thread 130, which is integrated in the paper pulp of said banknote and which is visible optically by a local contrast effect.
• the position of a security thread is not necessarily the same between two bank notes of the same cash value.
• it can be provided that it includes a graphic window whose width is that of said ticket, whose length is at most that of said ticket, and in the plane of said ticket, 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 bank note also includes a watermark 110, illustrated in particular by the number "20" in Figure 1 and which is optically visible by a local contrast effect.
• the sensitive product comprises an identifier 120, typically composed of alphanumeric characters, for example incremented, and in this case a serial number.
• the identifier is not printed in offset. Generally, it is printed with a dark ink, in this case black, on a light background.
• the identifier defines a first plane and the background defines a background, it is visible optically by a local contrast effect.
• the identifier can be recognized by optical character recognition.
• the sensitive product is at least partially flat, that is to say that it is plane or comprises at least one plane 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.
• the sensitive product and its packaging are thus indistinctly considered.
• the planar surface supporting the identifier comprises at least one of the following characteristics:
• a step of making a digital image of said sensitive product that is to say at least of the flat surface supporting said identifier.
• the image produced is in high definition and stored in a secure database.
• Said digital image is called "original digital image", by difference to a
• 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 defined graphically by a set of printing points.
• the ink used for printing is dark, usually black.
• the background tint on which each character is printed is lighter than that of the ink, so that the character is legible on said background by virtue of 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 graphic security or decor elements; and each pattern 150 of the bottom of the sensitive product has a local contrast effect.
• the background patterns for example represent alphanumeric characters, graphic symbols, an image, etc. which most often depends on the field of use, for example the fiduciary domain (banknotes), or the field of pharmaceutical product packaging.
• the background may comprise at least one of the graphic elements (security or not) among:
• At least one inscription preferably in security ink, for example optically variable
• At least one background impression possibly more or less monochromatic
• an assembly of at least one hologram or a visible security element for example a variable ink
• the identifier is unique. However, for different reasons, it happens that several sensitive products have the same identifier, for example several banknotes of the same cash value have the same serial number. It is estimated that a maximum of twenty bank notes of the same cash value may have the same serial number.
• two bank notes having the same identifier actually have a set of at least one difference by at least one of the security elements or the background.
• the position of the identifier on the bottom is different, or the background pattern is different, etc.
• each sensitive product is actually graphically unique. It therefore has a print, that is to say a set of attributes (including optical, graphic and geometric) that 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 of extracting at least one optical impression of the original digital image of the scanned sensitive product that is to say to calculate the attributes that contribute to the uniqueness of it, from the digital image in the database or before storage in it. It is then possible to associate said fingerprint with said original digital image in the database.
• each original digital image is associated with a plurality of corresponding attributes, the set of attributes of a given original image making it possible to characterize at least part of it.
• the attributes include, for example, the coordinates of remarkable points (described hereinafter), the distances between certain remarkable points, contrast gradient values around the remarkable points, and so on. or other notable features such as mathematical moments of parts of the image as described below.
• the moments of Zernike are very useful for the modeling of optical systems, they represent well the wavefronts and the transformations that these they undergo during the crossing of dioptres or reflection on mirrors. They are very useful for the representation of the properties of the images.
• the first degrees of the Zernike moments represent the inclinations and global orientation changes of the wavefront
• the second degrees represent astigmaties or defocalisations
• the third degrees represent the coma aberrations
• the fourth degrees represent the spherical deformations. etc.
• Binary descriptors are known, for example:
• BRISK Binary robust invariant scalable keypoints.
• the extraction of the imprint of the sensitive product is implemented automatically and preferably comprises at least one of: a local collisions calculation step and a metrology step.
• step 1010 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, i.e. a pixel or set of adjacent pixels in pairs, for which the contrast gradient, in a predefined direction and distance , is greater than a predefined threshold value.
• the predefined direction is horizontal and / or vertical.
• a first remarkable point belongs to the foreground.
• a first remarkable point is a point of impression of a character of the identifier.
• a second remarkable point belongs to the foreground or the background.
• 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 algorithm FAST (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_mach i ne. pdf.
• FAST for Features from Accelerated Segment Test in English
• 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 geometrical 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 one is saved in a memory.
• the value of the surface of the predetermined shape may also be predetermined and recorded in said memory.
• the geometric shape is a circle centered on the said remarkable point, and whose radius is a function of the chosen gradient, which simplifies the calculations and thus increases the processing speed.
• Local histograms are calculated according to a number of predetermined directions.
• each scanned sensitive product is registered and associated in the database with at least one of:
• SIFT Scale Invariant Feature Transform
• SURF Speeded Up Robust Features
• the detection of points is based on the differences of the Gaussian (DoG) obtained by calculating the difference between each pair of images smoothed by a Gaussian filter, varying from each time the sigma parameter (ie the standard deviation) of the filter.
• DoGs can be calculated for different scale levels to introduce the notion of scale space.
• the detection of the potential areas of points of interest / remarkable points is carried out by looking for the extrema according to the plane of the dimension of the image (x, y) and the plane of the scale factor.
• the SIFT descriptor is calculated on an area around each point of interest, for example 16x16 pixels, subdivided into 4x4 areas 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 in using the determinant of the Hessian matrix, to calculate an approximation of the second derivatives of Gaussians of the image by means of filters at different scales by using masks different sizes (eg 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 area of description is divided again into 16 regions. A wavelet analysis is performed on each region to construct the final descriptor.
• the latter consists of the sum of the x and y gradients as well as the sum of their respective norms for all 16 regions.
• the descriptor vector thus consists of 64 values that represent properties extracted both in the normal space and in that of the size scales.
• the ORB algorithm which is a method for accelerating the processing with respect to the SIFT algorithm and which is based on a remarkable FAST point detector described above, and local property descriptors of BRIEF binary test type, for example as described at http://www.vision.cs.chubu.ac.jp/CV-R/pdf/Rublee iccv2011.pdf.
• Each subset corresponds to a single footprint. It is possible to store the fingerprint of each selected subset in the database.
• the distance between the first remarkable point and the second remarkable point is greater than a first threshold value stored in a memory, and less than a second threshold value recorded in said memory.
• the first threshold value makes it possible to guarantee that the two remarkable points are not too close to each other; the second threshold value makes it possible to guarantee that the two remarkable points not too far apart 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 thread of said sensitive product.
• the second remarkable point is located on a border of said sensitive product or on a border of the face supporting said identifier.
• the second remarkable point located on the contour of a pattern of the bottom 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 numbers 04 of the serial number of a banknote; and at the other end of the double arrows, the second remarkable points are located on the outline of a character of the bottom (in this case the letter R which appears slightly in the background, with guilloches).
• the previous variants are combinable with each other.
• One 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 line, or on a vertical line, so that the distance is calculated in the horizontal direction and / or in the vertical direction, in one direction or in the other direction. 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 for acquiring a digital image of said sensitive product is provided, typically by means of an optical objective of a communicating object, said sensitive product preferably being plane and comprising a surface supporting an identifier. Said digital image is called "digital test image”.
• communicating object any object, preferably portable, equipped with an optical lens, a processor and a memory, and capable of establishing a 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 sorting machine banknotes.
• the test image of said sensitive product comprising said identifier then undergoes a digital processing step, which aims at comparing said test image with 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 risk of piracy of the communicating object.
• the digital processing step comprises an optical character recognition (OCR) step 1110 of recognizing the characters of the identifier of said sensitive product.
• OCR optical character recognition
• the digital processing state also includes a step 1120 of extracting an optical fingerprint from the test digital image, in a manner identical to extracting an optical fingerprint from the original digital image, i.e. 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 impressions of the test digital image are calculated, it can be expected to compare each optical fingerprint of the test digital image with each optical fingerprint of the original digital image.
• a signal whose value is a function of the result of the comparison.
• a binary signal is provided whose one of the binary values means that the comparison is positive, that is to say that the print of the test image is equal to the print of the original image, and the other binary value means that the comparison is negative.
• a validity attribute means that the sensitive product at the origin of said original digital image is considered invalid, for example because it has been removed from circulation or has been stolen.
• the comparison step is short-circuited according to the value of said attribute, ie if the sensitive product at the origin of said original digital image is considered to be invalid.
• the calculation of local collisions can be advantageously carried out on a support (banknote, packaging) wrinkled or whose edges are damaged.

Landscapes

• Engineering & Computer Science (AREA)
• Computer Vision & Pattern Recognition (AREA)
• Physics & Mathematics (AREA)
• General Physics & Mathematics (AREA)
• Image Analysis (AREA)
• Editing Of Facsimile Originals (AREA)
• Inspection Of Paper Currency And Valuable Securities (AREA)
• Facsimiles In General (AREA)

Applications Claiming Priority (2)

Publications (2)

Family

ID=58632451

Family Applications (1)

Country Status (3)

Family Cites Families (3)

• 2017
  • 2017-01-31 FR FR1750810A patent/FR3062509B1/fr active Active
• 2018
  • 2018-01-29 EP EP18705689.0A patent/EP3577635B1/de active Active
  • 2018-01-29 WO PCT/FR2018/050200 patent/WO2018142054A1/fr active Search and Examination

Also Published As

Similar Documents

Legal Events