Classifications

• • B—PERFORMING OPERATIONS; TRANSPORTING
  • B42—BOOKBINDING; ALBUMS; FILES; SPECIAL PRINTED MATTER
  • B42D—BOOKS; BOOK COVERS; LOOSE LEAVES; PRINTED MATTER CHARACTERISED BY IDENTIFICATION OR SECURITY FEATURES; PRINTED MATTER OF SPECIAL FORMAT OR STYLE NOT OTHERWISE PROVIDED FOR; DEVICES FOR USE THEREWITH AND NOT OTHERWISE PROVIDED FOR; MOVABLE-STRIP WRITING OR READING APPARATUS
  • B42D25/00—Information-bearing cards or sheet-like structures characterised by identification or security features; Manufacture thereof
  • B42D25/30—Identification or security features, e.g. for preventing forgery
  • B42D25/324—Reliefs
• • B—PERFORMING OPERATIONS; TRANSPORTING
  • B42—BOOKBINDING; ALBUMS; FILES; SPECIAL PRINTED MATTER
  • B42D—BOOKS; BOOK COVERS; LOOSE LEAVES; PRINTED MATTER CHARACTERISED BY IDENTIFICATION OR SECURITY FEATURES; PRINTED MATTER OF SPECIAL FORMAT OR STYLE NOT OTHERWISE PROVIDED FOR; DEVICES FOR USE THEREWITH AND NOT OTHERWISE PROVIDED FOR; MOVABLE-STRIP WRITING OR READING APPARATUS
  • B42D25/00—Information-bearing cards or sheet-like structures characterised by identification or security features; Manufacture thereof
  • B42D25/30—Identification or security features, e.g. for preventing forgery
  • B42D25/305—Associated digital information

Definitions

• a product comprising a marking pattern on a surface area for identifying the product
• This application relates to the field of product surface marking technologies for traceability and anti-counterfeiting purpose.
• Anticounterfeiting technology guide European Union Intellectual Property Office, 2021.
• these technologies add an element onto the item that is difficult to duplicate, or copy, or they characterize a specific physical or chemical feature of the item, similar to a fingerprint of the item.
• the challenge may be either technical, for instance on the reproduction of holograms, or require products which are not readily available on the market, such as rare isotopes or special inks.
• anti-counterfeiting features may be classified as overt technologies (visible, or more generally perceptible by the end user with his own body senses, without the need for specific detection equipment, such as for instance holograms on banknotes) or covert technologies (invisible, meaning imperceptible/non visually disturbing relative to the product design when observed with the naked eye, but detectable with a dedicated equipment).
• covert technologies are preferred for branded products because they do not interfere with the product surface artistic and/or marketing designs.
• Example of covert technologies include:
• Product markings Technologies such as digital watermarks and other covert marking technologies have been designed to better prevent the counterfeiting of product packages and security documents by electronic and digital means.
• the AlpVision Cryptoglyph exists in two flavors, either as a random or pseudorandom pattern of microdots printed with visible ink (WO0225599, W004028140), or as a distributed cloud of micro-holes in the varnish layer (W006087351).
• the distribution of microdots or micro-holes can be controlled with a secret cryptographic key to create a digital pattern which is added to the product surface area by a product marking technology.
• Authentication can be performed using conventional imaging devices, such as smartphones or off-the-shelf office scanners, in combination with dedicated signal processing software.
• Product markings comprise printing markings (e.g. printed by depositing ink dots or varnish droplets on the product surface at locations identified from a digital pattern bitmap, etc.), laser markings (e.g. engraved from a laser movement programming in accordance with a predefined pattern, etc.), chemical markings, mechanical embossing and/or its reverse debossing process, die-stamping, die casting, stamping, waterjet cutting, hologram and the like.
• digital marking to refer to digital marking patterns as data representations or command inputs to product marking which ultimately transfers the digital marking pattern into one or more structural features of a product surface.
• Surface fingerprints These technologies do not add any security element on the product, but rather use existing, intrinsic microscopic surface characteristics. For instance, a matte surface of a plastic injected product is an ideal candidate for the fingerprint solution. An image of the surface may be acquired during production and then compared to a later image capture from the product under inspection. Authentication can be performed using conventional imaging devices, such as smartphones or off-the-shelf office scanners, in combination with dedicated signal processing software. Examples of fingerprinting technologies are described for instance in US10332247. Note that in some specific cases, surface fingerprints may also be considered as an intrinsic product marking wherein a mold and/or printer and/or stamp creates a marking pattern on the product surface at the time of manufacturing rather than as an extra step postmanufacturing. Throughout this disclosure we use the terminology “physical marking” when the marking pattern is inherent to a physical manufacturing tool which changes one or more structural features on a product surface.
• the authentication of an object for any of the above technologies typically comprises a step of identifying, with a detector comprising a sensor adapted to the particular authentication technology employed for this object, whether the authentication technology can be retrieved from inspecting the object.
• the detector employs a camera for imaging the object surface.
• digital detection technologies have emerged which have facilitated the automation of this process and its generalization to non-specialized personnel, possibly also the general public, thanks to the use of digital signal processing algorithms embedded into software applications either embedded into the detector equipment (e.g., a smartphone) or executed on a computer in communication with the detector equipment (e.g., a scanner) through a communication network.
• the digital signal representation to characterize the object genuineness - for instance, by measuring a difference, a distance or a signal-to-noise ratio (SNR) between the captured digital signal representation and a template digital signal representation of a reference genuine object; or by extracting mathematical features from the digital signal representation which can be used by a classifier to discriminate between a fake and a genuine object - for instance, feature points or feature vectors; more generally, pattern detection methods as known in the art of image processing may be employed to match the captured object image to a reference genuine image pattern.
• SNR signal-to-noise ratio
• the present application is based on the finding that combinations of marking base patterns over a product surface can facilitate a traceability of the product.
• the material shape (as may be prepared by embossing or engraving, for instance with a laser) or the printing structure (based on ink or varnish deposit) of an area of the product surface is enhanced by a plurality of marking patterns using a pre-defined geometrical arrangement relative to the product surface, such that the marked product surface shape does not visually disturb the product surface artwork or marketing design, while each of the combined marking patterns remain individually detectable by a marking pattern sensor independently from the other marking patterns out of the combined marking patterns on the product surface shape.
• a product comprising a marking pattern on a surface area is proposed, the marking pattern encoding a marking identifier z for individually identifying the product out of a set of N products, a) wherein the marking pattern is composed of an overlay of k base patterns; b) wherein the k base patterns have been selected among a set of P base patterns, so that the number of possible combinations of k in P is lower or equal to the total number N of products to identify, each of the base patterns being identified by an index in ; c) and wherein the subset of the k indices in the set of P base patterns provides a bijective encoding of the marking identifier i.
• the base pattern is a random or pseudo random distribution of structural features with diffuse surface reflection, color and/or specular properties, that are invisible to a human observer when looking at the product’s surface area.
• the marking pattern is a random or pseudo random distribution of structural features with diffuse surface reflection, color and/or specular properties, that are invisible to a human observer when looking at the product’s surface area.
• each base pattern is detectable independently from the other base patterns by capturing an image of the marking pattern on the surface area with an optical detector and searching for the base pattern matching the captured marking pattern image.
• a computer-implemented method of detecting a product marking identifier z from a marking pattern marked on a product surface area comprises the steps of: a) capturing, with an optical sensor, an image of the surface area of a product marked with a marking pattern according to the above proposed marking method; b) inputting the image to a computer-based marking pattern detection system configured to
• Figure 1 is an abstract representation of a product surface shape modified with an overlay of marking patterns (overlay arrangement).
• Figure 2 is an abstract representation of a product surface shape modified with a juxtaposition of marking patterns (ordered arrangement).
• Figure 3 is an abstract representation of a product surface shape modified with an overlay of translated marking patterns.
• Figure 4a) and 4b) show an abstract representation of a possible translated marking pattern adapted not to lose the structural elements from the initial pattern which have been moved beyond the image pattern borders after translation.
• Figure 5 shows a) a reference pattern of pseudo-random, low-density distribution of dot structural features; b) the resulting overlay pattern obtained by translating the reference pattern of Figure 5a) with 10 different translation vectors and overlaying the resulting 10 translated marking patterns; and c) the 10 cross-correlation peaks of the reference pattern of Figure 5a) compared with its 10 translated overlaid patterns of Figure 5b).
• Figure 6 shows a digital pattern of a product combinatorial marking in accordance with a proposed embodiment.
• Figure 7) shows an abstract workflow of a product combinatorial marking method according to some of the proposed embodiments.
• Figure 8 shows an abstract workflow of an individual marking number detection and identification according to some of the proposed embodiments.
• Figure 9 shows enlarged images of exemplary combinatorial markings on shiny and printed product surfaces.
• product or “item” or “manufactured item” (used interchangeably) refer to a manufactured or an artisanal product.
• examples of products include, but are not limited to a luxury product, a pharmaceutical product, a cosmetics product, a food product, a tobacco product, a consumer electronics product, a sports product, a spare part product (e.g. automotive), a biomedical product, a coin, a bullion, a jewel, an artistic product, a banknote, a security document, a collectible card product, a precious metal, a watch, a leather product such as a bag.
• a product may also be a part of a manufactured object which is attached to or associated with this object, such as a component, a tag, a label, or a package.
• a product comprises at least one surface characterized by its shape and/or its structure which may be modified with a pattern by using various manufacturing or printing processes known in the art. Examples of modifications comprises changes of the diffuse properties, surface color and/or specular properties.
• product surfaces include, but are not limited to, an engraved surface, an embossed surface, a debossed surface, a metallized surface, a varnished surface, or a printed surface.
• the product surface may comprise a metallic area, a plastic area, a printed area, a painted area, or a natural material area such as stone, precious metal, vegetal fiber, wood, or leather.
• the product may be part of a batch of similarly manufactured products.
• the product is a manufactured product, a package of a manufactured product or a label of a manufactured product.
• the “marking identifier” or “marking number” is the identifier serving to parametrize the generation of the “marking pattern”.
• the marking identifier can be any product identifier or product count number which enables to uniquely identify a product i in a set of N products, for instance in relation with a serial number (SN) of the product (i.e., an individual or unique marking code or number), a number identifying a batch of products, or a signature or a copy of other data displayed on the product such the serial number, the batch number, the expiration date, a QR code or a Barcode.
• the marking identifier As a number varying from 1 to N, but it will be apparent to those skilled in the art of computing that it is possible to map such a marking number to any manufacturing product identifier such as a serial number, an alphanumerical code, a string of characters identifier, a datamatrix, a barcode, a QR-code or other product identifier codes used in the industry, possibly in combination with batch numbers or model numbers, as long as there is a 1-to-l mapping between the product identifier and a unique marking number z out of the total number of products N to be individually identified.
• the shape and/or structure of the product surface may be modified with the marking pattern, encoding a marking identifier z which can be used to match a product number or a product identifier.
• marking refers to the result of a physical modification of a surface condition. Marking may be applied at the end of a manufacturing process to change the visual appearance or certain optical properties of a surface area relative to its surrounding areas, for instance a surface area on a product, or a surface area on a product part in association with a product.
• physical modifications comprise modifications of the surface shape or structure by processes such as for instance engraving, etching, embossing, debossing, stamping, die casting, die stamping, water jetting, printing, varnishing, and the like.
• visual appearance or optical properties for covert markings comprise surface diffuse reflection, color and/or specular properties which are non-visually disturbing to the naked eye when looking at the product surface design.
• the “marking” can be part of the manufacture process, e.g., the mold or the die from which the product is produced can comprise the marking pattern which is transferred to the surface area of the product.
• the marking modifications may be additive (e.g. printing, embossing, varnishing) or subtractive (e.g. debossing, engraving, water jetting, not printing or not varnishing at some positions) relative to the product surface area.
• the marking modifications may also be neutral, for instance a change in color.
• structural feature refers to an elementary component inherent to the marking process.
• a structural feature physically modifies the shape or structure of a surface area in the marking process.
• a structural feature may correspond to a dot and a structural feature value may correspond to a colour code (e.g., for printing), a depth or thickness of the dot (e.g., for engraving, embossing, debossing, or varnishing), and/or a size of the dot.
• a structural feature may be an embossing or debossing elementary shape of a predefined geometry.
• structural features are chosen so that their marking onto the surface causes changes to the surface diffuse reflection, color and/or specular properties which are visually nondisturbing to the end user but can be detected with an optical detector.
• pattern refers to a one-dimensional (ID), a two-dimensional (2D) or a three- dimensional representation (3D) of the distribution of structural features along a line, within an area, or throughout a volume in the process of marking a product surface.
• a “base pattern” refers to a pre-defined distribution of structural features.
• a base pattern may be represented in a computer-implemented form (“digital base pattern”) as a bitmap, a vector (ID), a matrix (2D) or a tensor (3D or more) of structural feature values.
• a database of base patterns refers to a digital database of digital base patterns.
• a base pattern may be formed as a material arrangement of structural features (“physical base pattern”).
• An image of a base pattern can be individually captured with an optical sensor and identified with a computer-implemented detection method of the prior art.
• Some base patterns of the prior art are also designed with inherent statistical robustness, error detection or error correction encoding, so as to be detectable and identifiable even if parts of the base pattern are missing at detection time.
• a “marking pattern” refers to a product surface marking which is made of from one or more base patterns and/or from one or more geometrical arrangements of one or more base patterns, using a product marking technology as known in the industrial prior art.
• a manufacturing tool reproducing the marking pattern e.g. a stamp
• the marking may be integrated into a manufacturing process adapted to apply the marking pattern from a digital pattern command (e.g. variable printing manufacturing process).
• a “digital marking pattern” or an “encoding (digital) marking pattern” may be produced as a data representation of a vector, a matrix or a tensor by a computer-implemented method such as a data encoding algorithm.
• This digital representation may be used in the manufacturing process according to methods known in the art, for instance to print or to emboss a pattern or to guide laser engraving of a pattern at pre-determined coordinates along an x-axis, a y-axis and/or a z- axis relative to the surface area.
• Examples of 2D patterns suitable for use in a dot marking process comprise “image bitmaps”, wherein each pixel represents a dot and the bitmap is used to guide the pattern marking process.
• the term “density” refers to the ratio of the number of actual structural features relative to the number of possible structural features per surface area of the marking pattern. For instance, in the case of a digital marking pattern based on dots on a square matrix, the density may be calculated as the ratio of active dots over the total number of pixel positions in a bitmap of a predetermined size (where in this case active dots are used to guide the placement of the structural point features in the marking).
• Marking methods known in the art e.g. the Cryptoglyph methods from AlpVision and other covert technologies
• the density is determined in a way, such that when the marking pattern is applied to the product surface, it is not visually noticeable to a human observer.
• x-axis, y-axis and y-axis means axis with reference to the positioning of a marking pattern relative to a product surface area.
• a database of base patterns consists of P base patterns, wherein each base pattern is identified by its index in the database.
• a “marking pattern” or a “combinatorial marking pattern” is a distribution of structural features (as defined by a pattern) present on the product surface and has been applied (using a product marking technology) on the product surface as a part of product manufacturing method.
• the combinatorial marking pattern is applied on the surface area by embossing, debossing, die-stamping, water jetting, engraving, or by depositing ink dots or varnish droplets, or any suitable methods known for the skilled in the art of authentication features manufacturing.
• This combinatorial marking pattern is applied based on a combination, for instance an overlay, and/or a geometrical arrangement of base patterns, for instance an ordered juxtaposition, as a result of a computer-implemented method generating the combination and/or the geometrical arrangement of the base patterns (300) according to the present disclosure.
• any suitable automated machine for applying (marking) a distribution of structural features (a pattern) on the surface of a product receives a combinatorial marking pattern according to the disclosure and applies a corresponding marking on the product’s surface.
• any suitable automated machine for applying (marking) a distribution of structural features (a pattern) on the surface of a product receives a subset of k marking patterns according to the disclosure and applies for each of the of k marking patterns a combinatorial marking on the product’s surface.
• the combinatorial marking pattern for individually identifying the product is encoding a marking identifier i. It is understood that the base patterns need to be designed such that they can be combined in order to yield a unique identification number, according to requirements of combinatory coding.
• Figure 1 shows an abstract representation of a first possible embodiment in which the shape or the structure of a surface area 120 of a product 100 is modified by using an overlay of a plurality of base patterns 131, 132, 133 selected in a database 110 of P pre-defined patterns.
• a database 110 of pre-defined base patterns is established wherein each base pattern is indexed as 0, 1, 2, 3. . . , P-1.
• Each base pattern has its index in the database.
• digital base patterns and a digital database thereof are represented.
• the total number P of pre-defined base patterns in the database 110 is chosen such that the combination of a subset of k base patterns in the set of P pre-defined base patterns enables to identify, from the indices of the k base patterns in the set, a unique number in the range from 1 to N, where N is the number of products to be individually tracked out of the batch of products. As will be apparent to those skilled in the art of combinatorics, this corresponds to the binomial coefficient.
• Each individual product may then be identified by a marking number derived from a subset of k indices, for instance using a bijective function, a lookup table, a combinatorial numbering system such as combinadics, enumerative combinatorics, or other indexing encoding methods.
• the marking detection technique is able to detect that pattern 0 and 2 are retrieved on a product surface, then the corresponding unique marking number will be 1.
• a bijective function can be used for this purpose.
• a function as a lookup table matching each subset of indices of the k selected base patterns to a unique marking number z in the set of N possible product numbers.
• the P pre-defined base patterns are prepared with a low density of a random or pseudo-random distribution of structural elements suitable for marking the product surface without being visually disturbing (“invisible”) when the product user is looking at the product surface design.
• the combinatorial marking pattern composed of k base patterns is similarly non visually disturbing, or even invisible, to a human observer.
• employing a small number k of base patterns to overlay into a marking pattern on the product surface area may increase the detection robustness (separable detection of each pattern in the overlay) while preserving the invisibility of the resulting marking pattern.
• each of the k base patterns is arranged as a random or pseudo-random distribution of the structural features.
• Each of the k base patterns may be detected and identified independently from the other patterns (separable base patterns), using a pattern detection method.
• the combinatorial marking pattern is detected with an optical detector and identified using pattern detection methods based on image processing as known in the field of covert anticounterfeiting technologies (for instance, detection of microdots patterns printed with visible ink (WO0225599, W004028140), or detection of a distributed cloud of micro-holes in the varnish layer (W006087351)).
• each of the k base patterns may be a 2D AlpVision Cryptoglyph pattern, but it will be apparent to those skilled in the art that any other patterns from the field of covert anticounterfeiting technologies as used in current product manufacturing industries may be used as an alternative and/or in combination with the AlpVision Cryptoglyph pattern. Physical markings may also be detected.
• the density of structural elements shall be low enough to avoid significant overlap between any k separate base patterns in the set of P base patterns. This preserves the ability to individually discriminate, at retrieval stage, k base patterns out of a combined marking pattern formed by overlaying the k base patterns and used as the marking pattern at manufacturing stage.
• a statistical method such as for instance methods in relation with the Cryptoglyph technology from AlpVision, but other embodiments are also possible
• an empirical method such as using a trial and error test with different patterns
• a combination thereof may be used to this end in a preparatory stage to populate the database 110 with P pre-defined based patterns (in the case of digital markings) or (not illustrated) to prepare P manufacturing tools, each tool enabling to apply a pre-defined based pattern on the product marking surface (in the case of physical markings).
• a density of a base pattern is described for example on the digital base pattern bitmap as a ratio between active dots (representing marked areas) and total dots (representing the size of the digital pattern bitmap.
• the density ratio for each base pattern is less than 5% (very low density).
• the density ratio for each base pattern is less than 10% (low density).
• Very low density may be desired for structural features of a high contrast colour to remain invisible once printed over a white surface, for instance black, cyan or magenta dots for the base patterns, while low density may be enough for marking structural features of a lower contrast colour, for instance like grey nuances printed over a grey background surface.
• the marking pattern can have any density but is marked in such a manner that the structural features are invisible to the naked eye. For instance, if marking is done with yellow ink on a white background, or in black over a blackish surface, or in grey over a greyish surface, or even in varnish. Generally speaking, the marking should use a colour having a low contrast with the product surface on which the features are deposited, such that it is below the sensitivity of the human visual system.
• One way to quantify the invisibility is by using the colour difference AE as defined by International Commission on Illumination. According to the International Commission on Illumination a AE that is lower than 2 is considered as not perceptible. Many other approaches exist to quantify for measuring colour difference.
• the marking pattern an overlay of k base patterns, has a density below 50% and is marked in such a manner that the structural features are not obviously visible to the naked eye, for instance with a AE below 10.
• the k patterns are chosen such that the density of the marking pattern remains lower than 10% in order for the marking to stay invisible
• the marked base pattern on the surface area contains 5 to 50 structural features (marks) per 1 cm 2 per base pattern, and the density of the marking pattern contains 10 to 1000 structural features (marks) / 1 cm 2 as a result of an overlay combination of k base patterns into a combinatorial marking pattern.
• the structural features after physical marking on the product surface area, have a maximal size between 1-1000 pm in diameter. In another embodiment, after physical marking on the product surface area, the structural features have a size between 5-500 pm in diameter.
• base patterns are chosen such as they are separable to each other, to facilitate their detection in the detection process (separable base patterns).
• base patterns are chosen such that they are partially orthogonal.
• base patterns are chosen such that they are fully orthogonal.
• Other embodiments are also possible with non-orthogonal patterns, for instance by combining them with further geometrical transforms in the marking process to facilitate their separation at detection time. It is also possible to design base patterns such that the structural feature satisfies specific layout conditions, for instance minimum distance between two structural features.
• the product 100 is produced with an individual marking number, it is possible to select, with a computer-implemented method, a subset of k base patterns 131, 132, 133 out of the database 110 such that their individual indices enable to retrieve the product individual marking number.
• the base patterns and the database refer herein to a digital base patterns and database.
• the k base patterns 131, 132, 133 corresponding to indices 2,4 and 9 in the database 110 can be superposed (overlaid) to produce a combinatorial marking pattern on the surface area 120.
• the superposition of the k base patterns 131, 132, 133 into the combinatorial marking pattern virtually corresponds to a simple “stacking” geometrical arrangement along a z-axis perpendicular to the surface area.
• the subset of k base patterns 131, 132, 133 may be overlaid into a digital pattern (not represented) by a computer-implemented method (for instance, by an image processing overlaying method known in the art employing a digital bitmap representation of the base pattern, but other methods are also possible).
• the resulting digital pattern is then used to guide the surface shape or structure modification at manufacturing stage (virtual stacking).
• the combinatorial marking pattern is first prepared as a digital combinatorial pattern formed as an overlay of the subset of A: base patterns 131, 132, 133, and is directly applied on the product surface based on this digital combinatorial pattern using a digital product marking technology.
• the subset of &base patterns 131, 132, 133 may be directly used to serially overlay the k patterns modifications each from a pattern- dedicated physical marking method, for instance by selecting & base patterns 131, 132, 133 out of P possible patterns in a sequential marking process wherein a manufacturing tool corresponds to a base pattern (e.g., rolling stamp or multiple die stamps) (physical stacking).
• a manufacturing tool corresponds to a base pattern (e.g., rolling stamp or multiple die stamps) (physical stacking).
• the combinatorial marking pattern is progressively applied on the product surface by overlaying one by one the A: base patterns 131, 132, 133 using a physical product marking on the product surface.
• Both the virtual stacking and the physical stacking overlay marking embodiments enable to produce a combinatorial marking pattern on the product surface area 120 which is a mixture (e.g. an overlay) of A: base patterns 131, 132, 133.
• the digital marking pattern consists of the selected k base patterns (e.g., in the example of Figure 1), 3 patterns 131 indexed 2 in the database, 132 indexed 4 in the database, 133 indexed 9 in the database) that are aligned in x- axis and y-axis relative to the surface area, and arranged in z-axis to form an overlay of base patterns.
• the product wherein (non-ordered) geometrical arrangements are produced by overlaying base patterns along the z-axis perpendicular to the surface area.
• geometrical arrangement is understood as geometrical placement of the selected base patterns relative to the product surface area, such as overlaying base patterns.
• the product is identifiable by extracting from the combinatorial marking pattern on the surface area the base patterns which have formed the combinatorial marking pattern.
• the index of each extracted base pattern is retrieved in the database of base patterns by using a pattern matching method, and the series of retrieved indices of base patterns enable to uniquely and unambiguously identify the encoded marking number i.
• an optical detection device 150 is used to capture one or more images from the combinatorial marking pattern over the product surface area 120, and a computer-implemented method is used to individually extract the k base patterns from the one or more images, for instance by searching for the best image processing matchings against each of the P base patterns to select the k best matches.
• image matching methods are described for instance in US 10332247, but other pattern matching methods as known by those skilled in the art of image processing may also be used.
• the computer-implemented method can then retrieve the index of each of the k base patterns in the database (pattern 131 at index 2, pattern 132 at index 4, and pattern 133 at index 9 in the example of Figure 1) and decode accordingly the individual marking number of the product based on the retrieved indices by reversing the bijective function used in encoding, or using the lookup table from the encoding, in order to associate the non-ordered selection of k base patterns indices in the set of P base patterns to a marking number i.
• Figure 2 shows an abstract representation of a second possible embodiment in which the shape or the structure of a surface area 120 of a product 100 is modified by using a combinatorial marking pattern made of a plurality of geometrically ordered base patterns, for instance an array of juxtaposed base patterns over the product surface area 120.
• a database 110 of pre-defined base patterns is established wherein each base pattern is indexed as 0, 1, 2, 3..., P-1.
• the total number P of pre-defined base patterns in the database 110 is chosen such that the ordered arrangements of a subset of k base patterns in the set of P base patterns enables to identify, from the indices of the k base patterns in the set, a unique number z in the range from 1 to N, where N is the number of products to be individually tracked out of the batch of products. As will be apparent to those skilled in the art of combinatorics, this corresponds to the number of permutations of k in P.
• the P and k values should be chosen such p that their number of possible ordered arrangements (permutations) is at least equal to
• Each product may then be identified by a marking number z which can be derived as a bijective function from a subset of k indices in the database of base patterns and their respective geometrical arrangement orders, for instance using a bijective function, a lookup table, a combinatorial numbering system such as combinadics, enumerative combinatorics, or other indexing encoding methods.
• a function f that defines the set of patterns to be arranged for each identifier. With the previous example this function may be for instance defined as:
• a bijective function can be used for this purpose.
• a function as a lookup table matching each subset of indices of the k selected base patterns to a unique marking number z in the set of N possible product numbers.
• the product 100 is produced with an individual marking number
• the subset of k base patterns 131, 132, 133 may be virtually juxtaposed into a digital marking pattern (not represented) by a computer-implemented method, and the resulting digital marking pattern is then used to guide the modification on the product surface area 120 at manufacturing stage.
• a digital marking pattern not represented
• 100*100 pixels digital bitmap representations of 4 base patterns may be juxtaposed at 4 different positions into a 200*200 digital bitmap representation of the combinatorial marking pattern (virtual arrangement), which is then used for marking the surface area using a digital marking technology.
• the combinatorial marking pattern is first prepared as a digital combinatorial pattern formed as a geometrical arrangement, for instance a juxtaposition, of the subset of & base patterns 131, 132, 133, and is directly applied on the product surface based on this digital combinatorial pattern using a digital product marking technology.
• the subset of &base patterns may be directly used to physically juxtapose, one by one, the & base patterns modifications each from a pattern-dedicated physical marking method, for instance by selecting k stamps, moulds or manufacturing tools each representing a base pattern out of N possible patterns, in a serial marking process and positioning them one by one at a different position over the surface area 120 with an automated positioning mechanism (e.g robot arm, x-y table, conveyer belt, etc) (physical arrangement).
• the combinatorial marking pattern is progressively applied on the product surface by arranging one by one the &base patterns 131, 132, 133 at different marking positions relative to the surface area, for instance by juxtapositions, using a physical product marking on the product surface.
• Both the virtual and physical juxtaposition embodiments enable to produce a combinatorial marking pattern on the product surface area 120 which is an ordered geometrical arrangement of & base patterns 131, 132, 133.
• the number P of base patterns to match by the pattern detection method at the time of retrieving the product identifier the faster the detection.
• the number k of the subset of base patterns to geometrically arrange in an ordered way is chosen such that the combinatorial marking pattern made of the ordered geometrical arrangement of k base patterns fits into the surface area, as a function of the size of the area; and the size P of the set of base patterns is chosen as the smallest value such that their number of possible ordered arrangements (permutations) p] P k y is larger than or equal to the number N of products to be identified.
• the digital marking pattern consists of the selected & base patterns that are geometrically arranged in a non-overlapping, ordered way.
• the product wherein the digital marking pattern consists of the selected & base patterns that are geometrically arranged in non-overlapping way to form an array of side-by-side base patterns juxtaposed along the x-axis and/or along the y- axis.
• geometrical arrangement is understood as an ordered placement of the selected base patterns along an x-axis and/or a y-axis relative to the surface area, such as juxtaposing base patterns on the surface area.
• the juxtaposition example of Figure 2) is just one exemplary embodiment; other relative arrangements are also possible, for instance the k base patterns may be placed at different positions on the product’s surface area, separate by one or more non-marked areas, without being juxtaposed at adjacent positions.
• the position of each pattern as may be indicated by its x and/or y values in a coordinate system relative the product’s surface area, are enough to unambiguously indicate the geometrical arrangement order independently from the other geometrical arrangements.
• the patterns may also be rotated rather than translated relative to each other, and the coordinate system may be a polar coordinated system using the ray and angle values of each pattern to determine its geometrical arrangement order.
• the coordinate system may be anchored to a salient feature (for instance a brand logo placement) on the product’s surface so that the marking number encoding and decoding processes using the same combinatorial marking pattern refer to the same area at manufacturing and at detection time, but other solutions are also possible, for instance using automated semi-automated or manual registration or calibration methods.
• the order of the patterns into the array may for instance be defined from bottom to top, from left to right with reference to a horizontal x-axis and a vertical y-axis relative to the position of the surface area 120.
• an optical detection device 150 is used to capture one or more images from the product surface pattern 120 and a computer-implemented method is used to individually extract the k patterns as found onto the product surface area 120 according to the array position order.
• the computer-implemented method can then retrieve, from the individual placements of each base pattern from the combinatorial marking pattern on the product surface, the ordered indices of the base patterns in the database (sequence of indices 9, 0, 4, 2 in the example of Figure 2) and decode accordingly the individual marking number of the product based on the retrieved ordered indices, for instance by reversing the bijective function used in encoding or using the lookup table from the encoding.
• Other embodiments for ordering are also possible. Further embodiments - geometrical transforms of base patterns
• Figure 3 shows an abstract representation of a further possible embodiment for producing a combinatorial marking pattern in which the shape or the structure of a surface area 120 of a product 100 is modified by using a selection of geometrical transforms of a single predefined base pattern.
• Geometrical transforms may comprise as rotations, translations, scaling, warping, mirroring and/or a combination thereof.
• Geometrical transforms may also be specialized on sophisticated base patterns serving purposes such as increasing encoding space, introducing resilience to geometrical transformations, or allowing for the identification of rotations, translations, and scale.
• Such sophistication may consist for instance in adding shifted, rotated, or even mirrored versions of the base pattern. It is also possible to generate a base pattern with inherent geometrical properties to facilitate its retrieval with pattern matching methods from images captured by an optical sensor operating under different angles relative to the product surface area, for instance symmetries, such as rotational and/or central symmetries.
• the base pattern is translated 3 times to produce 3 different geometrical arrangements of the base patterns, indexed by the translation coordinates ((0,0), ⁇ 3,1 ⁇ , ⁇ 0,1 ⁇ ) along an x-axis and a y-axis reference relative to the surface area 120.
• the marking number of the product can be derived from the indices of the actual retrieved geometrical transforms identifiers (e.g. type of transforms, and/or coordinate values of the transformation) as a subset of j geometrical transforms selected out of a set of Q possible geometrical transforms of a base pattern.
• indices of the actual retrieved geometrical transforms identifiers e.g. type of transforms, and/or coordinate values of the transformation
• the combinatorial marking pattern is thus made of a subset of j geometrical transforms of a base pattern, such as rotations, translations, and scaling of the base pattern.
• 1 base pattern 131 is geometrically transformed to 3 transformed base patterns 1310, 1311, 1312).
• the base pattern may be pre-defined, for instance as an AlpVision Cryptoglyph digital pattern - but other embodiments are also possible - and the geometrical transforms of the pre-defined base pattern may be calculated on the fly at manufacturing time to produce a digital combinatorial marking suitable for marking the product surface with a digital marking technology.
• the combinatorial marking pattern consists of k elementary patterns, wherein each elementary pattern is selected in a set of P patterns, corresponding to all possibilities of applying j geometrical transforms selected out of Q possible geometrical transforms to each base pattern from a database of P predefined covert marking patterns.
• Other embodiments are also possible, for instance some base patterns may be more suitable to some geometrical transforms, so the number j of geometrical transforms may vary with each base pattern.
• a geometrical transform of index ⁇ 2,5 ⁇ is illustrated, corresponding to a translation of D*2 pixels (where D is a parameter defining the minimum number of pixels between 2 translated geometrical transforms of a base pattern in the digital marking pattern bitmap) along a horizontal axis (x-axis) and a translation of D*5 pixels along a vertical axis (y-axis).
• the total number P of pre-defined base patterns in the database 110 may be chosen such that the combined encoding of the indices of a subset of k base patterns in the set of P base patterns and of the j sets of coordinates selected out of Q possible geometrical transforms enables to identify a marking number in the range from 1 to N, where N is the number of products to be individually tracked out of the batch of products.
• the number of base patterns in the database is only 1 and the indexing encoding solely depends on the numbers of its actual and possible geometrical transforms, so as to accelerate the matching process at retrieval time.
• the geometrical transform of a base pattern may move some of its structural features beyond the borders of the product surface area 120 available space.
• the geometrical arrangement may employ pattern folding or wrap-around of the outside areas back into the regular base pattern area, for instance using the reconstruction scheme as illustrated on Figure 4b).
• this folded marking of products is particularly well suited when the geometrical transform is a translation along the x-axis and/or y-axis relative to the product surface are 120, and when the retrieval process uses cross-correlation to match to a base pattern reference, as the extraction of the cross-correlation calculated peaks enable to retrieve the number of translation steps along the x-axis as well as the y-axis (and thus the translation coordinates of the corresponding geometrical arrangements of the base pattern).
• the dashed square represents a translated base pattern and the parts exiting the base window represented by the black line are wrapped around. This wrap around has no impact on the cross-correlation signal of the translated base pattern with the original base pattern as recorded into the database 110 if the cross-correlation is computed using the Fourier transform.
• Figure 5 shows 5a) a base pattern; 5b) the combinatorial marking pattern formed by overlaying 10 translated and wrapped around versions of the base pattern using the following translations (10 out of 49 possibilities), with following 10 vectors noted ⁇ dx,dy ⁇ for each translation ⁇ ⁇ 0,0 ⁇ , ⁇ 0,1 ⁇ , ⁇ 0,4 ⁇ , ⁇ 3,1 ⁇ , ⁇ 3,6 ⁇ , ⁇ 4,2 ⁇ , ⁇ 5,0 ⁇ , ⁇ 5,1 ⁇ , ⁇ 5,6 ⁇ , ⁇ 6,6 ⁇ ⁇ ; and 5c) the cross-correlation of the base pattern and of the combined pattern showing 10 peaks corresponding to each translation vector.
• the resulting modification can remain visually non-disturbing for the end-user of the product when looking at the product design, as the number k of base patterns to be combined in the surface marking pattern can be chosen low enough to maintain the property of low-density, random or pseudorandom structural features distribution in the combined marking pattern without significant difference from the properties of each of the k individual patterns.
• the structural features for pattern marking may be chosen such that they are inherently imperceptible to the human eye for instance through changes in size and/or contrast. This is significant compared to a naive method of product serial number tracking.
• Example 1 Product surface overlays of 4 patterns out of a database of 72 patterns; the retrieval process only requires 72 matching comparisons;
• Example 2 Product surface overlays of 3 patterns out of a database of 183 patterns; the retrieval process only requires 183 matching comparisons;
• Example 3 Product surface juxtaposition of 4 patterns out of a database of 34 patterns; the retrieval process requires only 34 matching comparisons.
• Example 4 Product surface overlays of 10 patterns out of a database of 40 patterns; the retrieval process only requires 40 matching comparisons; this combination enables to index up to 847 million products (which would require 847 million pattern records and comparisons when using the prior art individual marking methods).
• Example 5 Product surface overlay of the same pattern with 10 different translations out of 49 possible translations; the retrieval process requires only 1 matching comparison, corresponding to over 8 billion combinations (which would require 8 billion pattern records and comparisons when using the prior art individual marking methods).
• Advantages of the proposed marking products and methods for traceability include but are not limited to: encoding larger numbers of product identifiers when compared to standard marking technologies encoding capacity; enabling a higher redundancy and better robustness for marking challenging product surfaces; decreased visibility as when compared to using the use of multiple markings with standard marking technologies.
• Figure 6 shows the digital bitmap corresponding to a combinatorial marking pattern of low density adapted from a set of geometrically arranged Cryptoglyph base patterns in accordance with the overlay embodiment of Figure 1.
• This combinatorial marking pattern is suitable for printing yellow dots or varnish dots on a 4cm*4cm surface area at serialization stage, at the end of a product package manufacturing process.
• Figure 7 shows a generic workflow of a combinatorial marking pattern embedding method employing a digital product marking method 710 suitable to embed onto the product surface a marking pattern. Dashed boxes and arrows show further optional steps.
• the ordered geometrical arrangement is a non-overlapping placement of the k base patterns distributed along an x-axis and/or y-axis according to their order, for instance a juxtaposition, for instance an array of k side-by-side base patterns juxtaposed along the x-axis and/or along the y-axis and wherein the coordinates of each base pattern in the array depends on its placement order in the juxtaposition geometrical arrangement.
• a suitable database of P base patterns can be prepared.
• a database of P base patterns is a database of P pre-defined base patterns, for instance AlpVision Cryptoglyph base patterns, but base patterns from other marking technologies may also be used as long as they can be combined into a combinatorial marking pattern while still being separable for later detection.
• the base patterns must be combined in way that they do not interfere with each other and allow for later detection and decoding (separable base patterns).
• the base patterns may be chosen as separable even when overlaid (e.g. embodiment of Figure 1) or they may be arranged geometrically in separate areas (e.g. in the embodiment Figure 2).
• the base patterns need to be designed such that they can be combined in order to yield a unique identification number, according to requirements of combinatory coding.
• Figure 8 shows a generic workflow of a pattern marking detection method to retrieve, from a product surface area comprising a combinatorial marking pattern according to the present disclosure, a product marking number z for individually identifying the product out of a set of N products.
• a computer-based method of detecting a product marking identifier z from a marking pattern marked on a product surface area comprising the steps of: a) capturing, with an optical sensor, an image of the surface area of a product marked with a marking pattern according to an overlay marking method of this disclosure; b) inputting the image to a computer-based marking pattern detection system configured to
• a computer-based method of detecting a product marking identifier z from a marking pattern marked on a product surface area comprising the steps of: a) capturing, with an optical sensor, an image of the surface area of a product marked with a marking pattern according to an ordered geometrical arrangement method of this disclosure; b) inputting the image to a computer-based marking pattern detection system configured to
• an optical sensor is a camera sensor configured on the detection device.
• the detection device is any suitable device known in the art, such as a smartphone.
• an optical detection device is a camera sensor configured on any smartphone.
• the optical sensor is a separate device from the detection device, and the optical sensor is in connection with the detection device through a communication network.
• the combinatorial marking pattern detection system (810) is configured as part of the detection device and the detection device contains a copy of the database 110 of base patterns (local pattern matching detection).
• the detection device also contains a copy of the lookup table used in encoding (local decoding).
• the combinatorial marking pattern detection system (810) is configured as part of a remote system (for instance a remote server) in connection with the detection device (for instance a smartphone with a camera sensor) through a communication network.
• the remote server which may be at the product manufacturer’s premises, contains a copy of the database 110 of base patterns (remote detection).
• the marking system employs a lookup table at the time of encoding the product identifier
• the remote server which may be at the product manufacturer’s premises, contains a copy of the lookup table to retrieve the product identifier from the indices of the matching base patterns (remote decoding).
• local detection may be combined with remote decoding (wherein the detection device sends the best matching indices to the remote server and the remote server returns the decoded identifier) or local decoding may be combined with remote detection (wherein the detection device sends the captured images to the remote server and the remote server returns the decoded based pattern indices, possibly with their arrangement order for instance in accordance with the embodiment of Figure 2).
• pattern matching technologies may be employed, including in particular those based on cross-correlation, on feature detectors (using Scale-Invariant Feature Transform for instance), or deep learning classifiers.
• these methods enable to search the best matching pattern out of a library of possible patterns to match to the image, but also to identify the pattern placement on the image and possibly to compensate for some geometrical transforms (in particular, translation compensation).
• some geometrical transforms in particular, translation compensation.
• the position of the cross-correlation signal peak enables to identify the translation of the pattern along a x-axis and/or a y-axis.
• steps of detecting a products’ marking number z include step b) that can be described as decoding a product marking number z from an image of the combinatorial marking pattern.
• the computer-based method of detecting and/or decoding a product marking number is executed with one or more processors of a computer-implemented digital marking pattern detection system (810).
• Elements of computer-implemented digital marking pattern detection system are known for the skilled in the art. Some (non-exhaustive) examples of pattern detection methods are described for instance in US10332247.
• the base patterns are designed with separable properties in accordance with the pattern matching method used in the detection step.
• the pattern matching method used in the detection step.
• a set Boi images B t are defined as “separable” and called “bases” if, for all possible set S of / ⁇ numbers, we have the property:
• Figure 9 shows experimental results for non-visually disturbing combinatorial markings on respectively a shiny product surface and a printed product surface.
• Figure 9a) shows an enlarged area of around 1cm* 1cm on a shiny printed product surface when using an AlpVision varnish dot marking method with the combinatorial pattern bitmap of Figure 6).
• Figure 9b) shows the further enlarged structural features corresponding to the low-density distribution varnish dot droplets on a 1mm* 1mm area of the product surface.
• Figure 9c) shows an enlarged area of around 1cm* 1cm on a printed product surface when using an AlpVision Cryptoglyph yellow dot markings according to the combinatorial pattern bitmap of Figure 6).
• Figure 9d shows the further enlarged structural features corresponding to the low-density distribution yellow dot droplets on a 1mm* 1mm area of the product surface (laboratory note: this image has been filtered to extract a blue component and map it to a grey level image for the purpose of patent illustration, as the structural features are otherwise invisible).
• the overlay embodiments e.g. Figure 1
• the ordered geometrical arrangements e.g. Figure 2
• the geometrical transforms e.g. Figure 3
• a combinatorial marking pattern made of j geometrical arrangements of k base patterns of structural features, wherein the term “geometrical arrangements” is to be understood as any of a geometrical transform of the base pattern and/or a geometrical placement relative to the surface area.
• geometrical arrangements provide additional diversity in possible combinations and/or permutations of base patterns into a combinatorial marking pattern to encode a marking number. This may be particularly advantageous in the case of a very large number of products.
• the individual product marking number combinatorial encoding method may thus jointly employ a first selection of k values among P possibilities for the pre-defined reference base patterns and a second set of j values among Q possibilities for their possible ordered and /or non-ordered geometrical arrangements, for instance using a lookup table, a combinatorial numbering system such as combinadics, enumerative combinatorics, or other indexing encoding methods.
• this may even comprise the addition of parity checks or error correction codes to increase the robustness of the encoding method to the noise induced by the physical marking process.
• Each individual product may then be identified from the combined encoding of the indices of a subset of & base patterns in the set of P patterns and of the geometrical transform coordinates of j geometrical arrangements of each base pattern in the set of Q possible geometrical arrangements of a base pattern.
• one of more processors of a computer- implemented digital marking pattern embedding system 700 may thus produce a combinatorial marking pattern encoding a marking number through the steps of:
• Acquiring predefined parameters comprising the total number of base patterns in a database 110 of base patterns, the number of possible geometrical arrangements of a base pattern, and/or the maximum number of combinable base patterns to produce a combinatorial marking pattern made of a subset of one or more geometrical arrangements of at least one base pattern selected in a subset of base patterns;
• the geometrical arrangements are defined and indexed along an x-axis, a y-axis, a z-axis, or a combination thereof, relative to a product surface area suitable for the product marking process, such that each geometrical arrangement of a base pattern over the product surface remains detectable independently from the other geometrical arrangements of base patterns in the combinatorial marking pattern.
• only one geometrical arrangement is predefined as an overlay of base patterns over the z-axis, and the base patterns are chosen in a database of base patterns which remain detectable from each other once overlaid into a combinatorial marking pattern (e.g. separable patterns or orthogonal patterns).
• a combinatorial marking pattern e.g. separable patterns or orthogonal patterns
• 4 geometrical arrangements are predefined as 4 possible positions in an array of 2*2 base patterns (x-axis coordinate and y-axis coordinate as geometrical arrangement indices) and the arrangement order (not just the combination) of a maximum number of 4 selected base pattern indices may be further used to encode the product marking number.
• only one reference base pattern is used (subset of 1 base pattern in a database of 1 single base pattern) and 3 geometrical arrangements may be chosen out of 16 possible translations (4 possible indices along x-axis * 4 possible indices along the 4 y-axis) to produce the combinatorial marking pattern.
• a combinatorial marking detection method may employ an optical detector adapted to capture an image 800 a product surface area comprising the combinatorial marking.
• the proposed method retrieves from the combinatorial marking image, with one of more processors of a computer-implemented digital marking pattern detection system 810, the product marking number through the steps of:

Landscapes

• Printing Methods (AREA)

Applications Claiming Priority (2)

Publications (1)

Family

ID=85036459

Family Applications (2)

Family Applications Before (1)

Country Status (3)

Families Citing this family (1)

Family Cites Families (4)

• 2023
  • 2023-01-10 EP EP23150941.5A patent/EP4400324A1/de not_active Withdrawn
• 2024
  • 2024-01-10 EP EP24700710.7A patent/EP4648973A1/de active Pending
  • 2024-01-10 WO PCT/EP2024/050423 patent/WO2024149774A1/en not_active Ceased
  • 2024-01-10 CN CN202480007352.1A patent/CN120500411A/zh active Pending

Also Published As

Similar Documents

Legal Events