DESC:FIELD
The present disclosure generally relates to the field of product security and packaging. More particularly, the present disclosure relates to a system and method for uniquely identifying and authenticating products.
DEFINITIONS
As used in the present disclosure, the following terms are generally intended to have the meaning as set forth below, except to the extent that the context in which they are used indicate otherwise.
Product: The term “product” hereinafter refers to any article, item, or substance whose integrity is to be maintained. The term "product” also includes a security seal.
BACKGROUND
The background information herein below relates to the present disclosure but is not necessarily prior art.
Typically, a seal is designed to be used only once and is designed to leave a visual evidence of any tampering attempt. However, given enough time, resources and motivation, a skilled counterfeiter may completely replace an original seal with a duplicate seal rather than attempt to tamper with it. The same can be said for batch printing that is done on any product item. In the regulated pharmaceutical industry, in addition to the batch number, a unique identifier (ID) is printed on each item to be able to track each item individually. However, even these codes can easily be duplicated or reprinted by a counterfeiter. Today’s printing technologies such as Continuous Ink Jet, Thermal Ink Jet, Thermal Transfer Offset, Laser printers, Gravure printers, etc. have a limit on the resolution that can be achieved. This translates to minor differences in each print of the same text or artwork. These differences include but are not limited to:
1. difference in overall printing position with reference to some predefined fixed position on the body and/ or artwork of the seal or item, and
2. difference in the printing font, font size, printing quality, printer resolution, font styles, etc.
3. Missed or extra printing (misprinting) caused in the label area due to irregular or slight printing disparities which may be specific to the printer used on the original production line.
4. Visible printing disparities caused due to several other factors on the production line and printing material used, including but not limited to vibrations, speed, printing dimensions, printing material type, printing technology etc.
It is unviable, impractical, or nearly impossible for a counterfeiter to replicate the original print due to this.
These differences are there due to several reasons including, but not limited to, the printing technology used, the substrate material porosity and surface finish, vibrations on the printing line, etc. These differences mean each print can be uniquely identified by its fingerprint. Each seal or item has a unique serial number that is used to identify the seal or item. A counterfeiter may attempt to create a copy of an original seal/ item and reprint this unique ID on the copy. However, there is no system yet, which can detect the minor differences between each print to distinguish an original seal or item from any of its copies.
Therefore, there is a need for a system and method for uniquely identifying and authenticating products that alleviate the aforementioned drawbacks.
OBJECTS
Some of the objects of the present disclosure, which at least one embodiment herein satisfies, are as follows:
It is an object of the present disclosure to ameliorate one or more problems of the prior art or to at least provide a useful alternative.
An object of the present disclosure is to provide a system and method for uniquely identifying and authenticating products (i.e., items/articles or seals).
Another object of the present disclosure is to provide a system that uses Machine Learning (ML) techniques for checking the authenticity of a product.
Yet another object of the present disclosure is to provide a system that can detect minor differences in the printing of a unique serial number to differentiate between an original product and a fake product.
Other objects and advantages of the present disclosure will be more apparent from the following description when read in conjunction with the accompanying figures, which are not intended to limit the scope of the present disclosure.
SUMMARY
In accordance with one aspect of the invention, the present disclosure envisages a system for generation of unique fingerprints for a plurality of products on a production line. The system comprises a first repository, a first reference detection module, a first feature detection module, a first fingerprint generation module, and a data logging module. The first repository stores a pre-determined set of reference detection rules, a pre-determined set of feature detection rules, and a pre-determined set of fingerprint generation rules. The first reference detection module facilitates scanning of the products for which the fingerprints are to be generated and cooperates with the first repository to detect at least one fixed recognizable reference point on each of the products based on the pre-determined set of reference detection rules. The reference point is selected from the group consisting of a center of a barcode, a part of an artwork printed on the product’s packaging, and an edge or a corner of the product when the product is a seal. The first feature detection module cooperates with the first reference detection module and the first repository to detect at least one feature on each product based on the detected reference point and the pre-determined set of feature detection rules. The pre-determined set of feature detection rules includes rules for detecting the position of the feature based on the location of the fixed recognizable reference point on the product. Thereafter, the first feature detection module triggers capturing of an image of the detected feature in each product, wherein the feature includes at least one variable data printed on each product. The variable data can comprise any information that changes from one product to another or from one batch to another and is printed on the product or on the product’s packaging using thermal inkjet printer, continuous inkjet printer, laser printer, or any other printing techniques typically used for printing variable information. The first fingerprint generation module cooperates with the first feature detection module to receive the captured feature image corresponding to each product and further cooperates with the first repository to generate at least one unique fingerprint for each product by processing the corresponding feature image based on the pre-determined set of fingerprint generation rules. The data logging module cooperates with the first fingerprint generation module to store the generated fingerprints corresponding to the products in the first repository. The first reference detection module, the first feature detection module, the first fingerprint generation module, and the data logging module are implemented using one or more processor(s).
According to a second aspect of the present invention, the present disclosure provides a system for determining the authenticity of a product. The system comprises a second repository, a second reference detection module, a second feature detection module, a second fingerprint generation module, and a fingerprint matching module. The second repository stores a pre-determined set of reference detection rules, a pre-determined set of feature detection rules, and a list of unique identifiers corresponding to a plurality of original products, at least one pre-determined unique fingerprint, referred herein as “original fingerprint”, corresponding to each of the original products, and a pre-determined threshold matching percentage corresponding to each of the original fingerprints. The second reference detection module facilitates scanning of a product whose authenticity is to be determined. The product is referred to herein as “test product”. The second reference detection module cooperates with the second repository to detect at least one fixed recognizable reference point on the test product based on the pre-determined set of reference detection rules. The reference point is selected from the group consisting of a center of a barcode, a part of an artwork printed on the product’s packaging, and an edge or a corner of the product when the product is a seal. The second feature detection module cooperates with the second reference detection module and the second repository to detect at least one feature on the test product based on the detected reference point and the pre-determined set of feature detection rules. The pre-determined set of feature detection rules includes rules for detecting the position of the feature based on the location of the fixed recognizable reference point on the product. Further, the second feature detection module triggers capturing of an image of the detected feature in the test product, wherein the feature includes at least one variable data printed on each product. The variable data can comprise any information that changes from one product to another or from one batch to another and is printed on the product or on the product’s packaging using thermal inkjet printer, continuous inkjet printer, laser printer, or any other printing techniques typically used for printing variable information. The detected feature image so provided, is scaled or de-skewed to the original feature image size as during on-boarding in the first repository. It is then used to generate the fingerprint for the test product. The second fingerprint generation module cooperates with the second feature detection module to receive the captured feature image corresponding to the test product and further cooperates with the first repository to generate at least one unique fingerprint corresponding to the detected feature based on the received image of the feature and the pre-determined set of fingerprint generation rules. The fingerprint matching module obtains a unique identifier associated with the test product and extracts at least one original fingerprint corresponding to the unique identifier from the pre-determined set of fingerprints stored in the second repository. Thereafter, the fingerprint matching module generates a match percentage based on a comparison of the generated fingerprint and the extracted original fingerprint and further generates an outcome based on a comparison of the generated match percentage and the threshold match percentage. The second reference detection module, the second feature detection module, the second fingerprint generation module, and the fingerprint matching module are implemented using one or more processor(s).
In accordance with a third aspect of the present disclosure, the present disclosure envisages a method for generation of unique fingerprints for a plurality of products on a production line.
In accordance with a fourth aspect of the present disclosure, a method for determining the authenticity of a product is disclosed.
BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWING
A system and method for uniquely identifying and authenticating products of the present disclosure will now be described with the help of the accompanying drawing, in which:
Figure 1 illustrates a block diagram of a system for generation of unique fingerprints for products, in accordance with the present disclosure;
Figure 2 illustrates a block diagram of a system for determining the authenticity of products, in accordance with the present disclosure;
Figure 3 illustrates an image defining a position of a feature with respect to an edge of the product as detected by the systems of Figure 1 and Figure 2;
Figures 4A and 4B illustrate normal and high-resolution images of three exemplary products printed with the same variable data (i.e., unique serial number);
Figure 5A illustrates an exemplary image of a feature on a product broken down into 14 smaller images using a 7x2 grid for determination of the authenticity of the product;
Figure 5B illustrates a comparison of sub-grid images of an original product and a duplicate product for determining printing differences therebetween for determination of the authenticity of the products;
Figures 6A illustrates an image of a product to be authenticated having a logo and a seal printed with a variable data (i.e., a unique identifier);
Figure 6B illustrates the image of Figure 6A with a grid plotted on the seal;
Figure 6C illustrates an exemplary image of a pattern extracted from the image of Figure 6B;
Figure 6D illustrates an exemplary image depicting the extracted pattern of Figure 6C being resolved based on the intersection points between the grid and the identifier;
Figure 7 illustrates a flow diagram of a method for generation of unique fingerprints for products, in accordance with the present disclosure; and
Figures 8A and 8B illustrate a flow diagram of a method for determining the authenticity of products, in accordance with the present disclosure.
LIST OF REFERENCE NUMERALS
100, 200 System
102 First repository
104 First reference detection module
106 First feature detection module
108 First fingerprint generation module
108a First plotting module
108b First analyser
108c First fingerprint generator
110 Data logging module
202 Second repository
204 Second reference detection module
206 Second feature detection module
208 Second fingerprint generation module
208a Second plotting module
208b Second analyser
208c Second fingerprint generator
210 Fingerprint matching module
210a Identification module
210b Matching module
210c First comparator
210d Second comparator
DETAILED DESCRIPTION
Embodiments, of the present disclosure, will now be described with reference to the accompanying drawing.
Embodiments are provided so as to thoroughly and fully convey the scope of the present disclosure to the person skilled in the art. Numerous details, are set forth, relating to specific components, and methods, to provide a complete understanding of embodiments of the present disclosure. It will be apparent to the person skilled in the art that the details provided in the embodiments should not be construed to limit the scope of the present disclosure. In some embodiments, well-known processes, well-known apparatus structures, and well-known techniques are not described in detail.
The terminology used, in the present disclosure, is only for the purpose of explaining a particular embodiment and such terminology shall not be considered to limit the scope of the present disclosure. As used in the present disclosure, the forms "a,” "an," and "the" may be intended to include the plural forms as well, unless the context clearly suggests otherwise. The terms "comprises," "comprising," “including,” and “having,” are open ended transitional phrases and therefore specify the presence of stated features, integers, steps, operations, elements, modules, units and/or components, but do not forbid the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. The particular order of steps disclosed in the method and process of the present disclosure is not to be construed as necessarily requiring their performance as described or illustrated. It is also to be understood that additional or alternative steps may be employed.
When an element is referred to as being "mounted on," “engaged to,” "connected to," or "coupled to" another element, it may be directly on, engaged, connected or coupled to the other element. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed elements.
The terms first, second, third, etc., should not be construed to limit the scope of the present disclosure as the aforementioned terms may be only used to distinguish one element, component, region, layer, or section from another component, region, layer or section. Terms such as first, second, third etc., when used herein do not imply a specific sequence or order unless clearly suggested by the present disclosure.
Terms such as “inner,” “outer,” "beneath," "below," "lower," "above," "upper," and the like may be used in the present disclosure to describe relationships between different elements as depicted from the figures.
Typically, plastic seals are used to mechanically secure/seal transport boxes, containers, vehicle doors, trucks, trailers, warehouses, and the like. These seals are designed to be used only once and designed to leave a visual evidence of any tampering attempt. Each seal has a unique serial number that is used to identify the seal. However, a skilled counterfeiter may completely replace a plastic seal with a duplicate seal rather than attempt to tamper with it. The same can be said for batch printing that is done on any product item. In a regulated pharmaceutical industry, in addition to the batch number, a unique identifier (ID) is printed on each item to be able to track each item individually. However, even these codes can easily be duplicated or reprinted by a counterfeiter. The counterfeiter may do this by creating a copy of an original seal/item and reprinting this unique serial number on the copy (duplicate seal/item). Currently, there exists no means to detect such counterfeiting or identify whether a seal/item is an original seal/item or a duplicate seal/item.
In order to overcome the above-mentioned problem of the prior art, the present disclosure envisages systems and methods for uniquely identifying and authenticating products. The term ‘product’ as used herein refers to a security seal, an article, or an item to be sold.
Current printing technologies such as Continuous Ink Jet, Thermal Ink Jet, Thermal Transfer Offset, Laser printers, Gravure printers, etc. have a limit on the resolution that can be achieved. This translates to minor differences to each print of the same artwork on different products. These differences are there due to several reasons including, but not limited to, the printing technology used, the substrate material porosity and surface finish, vibrations on the printing line, etc. These differences mean each print can be uniquely identified by its fingerprint. The system and method of the present disclosure use this fingerprint to uniquely identify original products and distinguish them from duplicate products.
The systems (100, 200) and methods (300, 400) of the present disclosure are now being described in detail with reference to the Figure 1 through Figure 8B.
In accordance with one aspect, referring to Figure 1, the present disclosure provides a system 100 for generation of unique fingerprints for a plurality of products on a production line. The system 100 comprises a first repository 102, a first reference detection module 104, a first feature detection module 106, a first fingerprint generation module 108, and a data logging module 110. The first repository 102 is configured to store a pre-determined set of reference detection rules, a pre-determined set of feature detection rules, and a pre-determined set of fingerprint generation rules. The first reference detection module 104 is configured to facilitate scanning of the products for which the fingerprints are to be generated and further configured to cooperate with the first repository 102 to detect at least one fixed recognizable reference point on each of the products based on the pre-determined set of reference detection rules. The fixed recognizable reference point can be selected from the group consisting of, but not limited to, a center of a barcode, a part/point of an artwork printed on the product’s packaging, and an edge or a corner of the product when the product is a seal. The first feature detection module 106 is configured to cooperate with the first reference detection module 104 and the first repository 102 to detect at least one feature on each product based on the detected reference point and the pre-determined set of feature detection rules. The pre-determined set of feature detection rules includes rules for detecting the position of the feature based on the location of the fixed recognizable reference point on the product. In an exemplary embodiment, the feature detection rules define the position of the feature with reference to the edge of a seal. In another embodiment, the feature detection rules define the position of the feature with reference to a point in the artwork printed on an item. The first feature detection module 106 is further configured to trigger capturing of an image of the detected feature in each product, the feature including at least one variable data printed on each product. The first fingerprint generation module 108 is configured to cooperate with the first feature detection module 106 to receive the captured feature image corresponding to each product and is further configured to cooperate with the first repository 102 to generate at least one unique fingerprint for each product by processing the corresponding feature image based on the pre-determined set of fingerprint generation rules. The data logging module 110 is configured to cooperate with the first fingerprint generation module 108 to store the generated fingerprints corresponding to the products in the first repository 102.
In an embodiment, the first reference detection module 104 comprises a scanning module and a recognition module. The scanning module facilitates a user on the production line to scan the products for which the fingerprints are to be generated. The recognition module is triggered during the process of scanning to detect the at least one fixed recognizable reference point on each of the products based on the pre-determined set of reference detection rules. The reference point may be, for example, an edge of a plastic seal, a point in the artwork, or any other recognizable point on the product or product’s packaging. Accordingly, the pre-determined set of reference detection rules are rules for detecting/recognizing the edge of the plastic seal, or detecting/recognizing the artwork and the reference point in the artwork or any other recognizable point on the product or product’s packaging. The rules may be discovered using machine learning techniques and/or manually pre-fed into the first repository 102.
Additionally, the recognition module can be configured to recognize the category and/or brand of the product being scanned and accordingly fetch the category/brand-specific reference detection rules from the first repository 102. In this case, the first repository 102 stores different reference detection rules for each category of product. The recognition module may use a pre-trained machine learning model to recognize the product category and/or brand and accordingly fetch the corresponding reference detection rules, to detect the reference point on the product or the product’s packaging.
The “artwork” referred to herein above may include a text in and around a visual code printed on the packaging, a brand logo, or a relative position and size of the visual code and the artwork, text, or brand logo printed on the packaging.
In one embodiment, the first fingerprint generation module 108 comprises a first plotting module 108a, a first analyser 108b, and a first fingerprint generator 108c. The first plotting module 108a is configured to receive the captured feature image corresponding to each product and is further configured to plot a pre-determined design on each feature image. The design can be a grid or a mesh comprising shapes selected from the group consisting of, but not limited to, polygon, circle, and ellipse or other random shapes. The first analyser 108b is configured to cooperate with the first plotting module 108a to identify a pattern in each feature by analysing the feature in the feature images with respect to the plotted design. The first fingerprint generator 108c is configured to generate the at least one unique fingerprint for each product based on the identified pattern using the pre-determined set of fingerprint generation rules.
In an embodiment, the first analyser 108b is configured to identify the pattern in each feature by at least one of the following techniques:
- dividing each feature image into sub-images based on the plotted design and detecting a pattern of variations in the printing of the feature parts in the sub-images;
- detecting a relative position of the feature parts in the sub-images with respect to the design; and
- detecting the number and positions of intersections between the feature parts in the sub-images and said design.
In an embodiment, the first fingerprint generator 108c is configured to generate one unique fingerprint for each sub-image of the feature image.
In an exemplary embodiment, the first plotting module 108a receives a captured feature image and plots a ‘k’ rows x ‘n’ columns grid on the feature image, thereby breaking down the feature image into ‘kn’ sub-images. The first analyser 108b identifies a pattern in each of the sub-images by analysing the feature parts in the sub-images with respect to the plotted design. The first fingerprint generator 108c generates a unique fingerprint for the product based on the identified pattern using the pre-determined set of fingerprint generation rules. Alternatively, the first fingerprint generator 108c may be configured to generate a unique fingerprint for each part of the feature in the sub-image based on the identified pattern using the pre-determined set of fingerprint generation rules. Accordingly, the pre-determined set of fingerprint generation rules includes rules for generating unique fingerprints based on the identified feature patterns.
In an alternate embodiment, the first fingerprint generation module 108 comprises an encrypting module configured to encrypt the feature images corresponding to each of the products using a pre-determined encryption technique to generate the at least one unique fingerprint for each product. In this embodiment, the pre-determined encryption technique can be selected from the group consisting of, but not limited to, bit level scrambling, cyclic shift and pixel swapping, DNA coding, chaotic maps, and compressed sensing.
The “variable data” as used herein comprises any information that changes from one product to another or from one batch to another and is printed on the product or on the product’s packaging using thermal inkjet printer, continuous inkjet printer, laser printer, or any other printing techniques typically used for printing variable information. The variable data may include a unique identifier, batch information, a data-matrix code, and the like.
The first reference detection module 104, the first feature detection module 106, the first fingerprint generation module 108, and the data logging module 110 are implemented using one or more processor(s).
The system 100 can be implemented in an edge device/electronic device such as a computer on a production line to scan products and generate unique fingerprints for them. Alternatively, one or more modules of the system 100 can be implemented on a remote server or cloud. The first reference detection module 104 may use an independent camera or a camera of the electronic device for scanning the products and capturing the feature images.
According to another aspect, referring to Figure 2, the present disclosure envisages a system 200 for determining the authenticity of products. The system 200 comprises a second repository 202, a second reference detection module 204, a second feature detection module 206, a second fingerprint generation module 208, and a fingerprint matching module 210. The second repository 202 is configured to store a pre-determined set of reference detection rules, a pre-determined set of feature detection rules, and a list of unique identifiers corresponding to a plurality of original products, at least one pre-determined unique fingerprint, referred herein as “original fingerprint”, corresponding to each of the original products, and a pre-determined threshold matching percentage corresponding to each of the original fingerprints. The unique identifiers, the unique fingerprints, and the threshold matching percentages may be stored in the second repository 202 in the form of a lookup table. The second reference detection module 204 is configured to facilitate scanning of a product whose authenticity is to be determined; the product is referred to herein as “test product”. The second reference detection module 204 is further configured to cooperate with the second repository 202 to detect at least one fixed recognizable reference point on the test product based on the pre-determined set of reference detection rules. The reference point is selected from the group consisting of a center of a barcode, a part of an artwork printed on the product’s packaging, and an edge or a corner of the product when the product is a seal. The second feature detection module 206 is configured to cooperate with the second reference detection module 204 and the second repository 202 to detect at least one feature on the test product based on the detected reference point and the pre-determined set of feature detection rules. The pre-determined set of feature detection rules includes rules for detecting the position of the feature based on the location of the fixed recognizable reference point on the product. In an exemplary embodiment, the feature detection rules define the position of the feature with reference to the edge of a seal. In another embodiment, the feature detection rules define the position of the feature with reference to a point of the artwork printed on an item. The second feature detection module 206 is further configured to trigger capturing of an image of the detected feature in the test product, wherein the feature includes at least one variable data printed on each product. The variable data can comprise, but is not limited to, any information that changes from one product to another or from one batch to another and is printed on the product or on the product’s packaging using thermal inkjet printer, continuous inkjet printer, laser printer, or any other printing techniques typically used for printing variable information. The variable data may include a unique identifier, batch information, a data-matrix code, and the like. The second feature detection module 206 can be further configured to scale or de-skew the detected feature image so provided to the original feature image size as during on-boarding in the first repository 102. The second fingerprint generation module 208 is configured to cooperate with the second feature detection module 206 to receive the captured feature image corresponding to the test product and is further configured to cooperate with the second repository 202 to generate at least one unique fingerprint corresponding to the detected feature based on the received image of the feature and the pre-determined set of fingerprint generation rules.
In an example, as shown in Figure 3, the product to be authenticated is a seal. The second reference detection module 204 scans the seal and detects the reference point i.e., the corner/edge of the seal. The second feature detection module 206 identifies the location of the feature/variable data (i.e., the unique identifier - 123456789) with respect to the detected corner/edge of the seal and captures an image of the detected feature. The detected feature image is scaled up or down or de-skewed to match the configured dimensions of feature image as used during on-boarding in the first repository, before generating the fingerprint for the test product.
The fingerprint matching module 210 is configured to obtain a unique identifier associated with the test product and extract at least one original fingerprint corresponding to the unique identifier from the pre-determined set of fingerprints stored in the second repository 202. In an embodiment, the unique identifier (ID) includes at least one of batch number or batch code of the product or any other unique code or number printed on the test product. The unique ID may be in the form of a number, an alphanumeric code, or a data matrix code. The fingerprint matching module 210 is further configured to generate a match percentage based on a comparison of the generated fingerprint and the extracted original fingerprint and is further configured to generate an outcome based on a comparison of the generated match percentage and the threshold matching percentage. In an embodiment, for generating the match percentage, the fingerprint matching module 210 uses one or more of the mathematical techniques such as Hausdorff-Distance, mean squared error (MSE), Normalized Root Mean Square Error (NRMSE), Structural Similarity, and Scale-invariant feature transform (SIFT).
In an embodiment, the fingerprint matching module 210 comprises an identification module 210a, a matching module 210b, a first comparator 210c, and a second comparator 210d. The identification module 210a is configured to obtain the unique identifier associated with the test product by scanning the test product. In an embodiment, the identification module (210a) is configured to use optical character recognition (OCR) techniques to read and obtain the unique identifier present in the variable data of the test product. Alternatively, the identification module 210a is configured to scan a data matrix code present in the variable data to obtain the unique identifier associated with the test product. The matching module 210b is configured to look up the unique identifier in the second repository 202 to obtain the at least one original fingerprint associated with the unique identifier and extract the original fingerprint. The first comparator 210c is configured to compare the generated fingerprint with the extracted original fingerprint to generate the match percentage, wherein the match percentage represents a matching proportion between the generated fingerprint and the pre-stored original fingerprint of the original product. The second comparator 210d is configured to compare the match percentage with the threshold matching percentage to generate either the outcome indicating that the test product is verified, if the match percentage is greater than or equal to the threshold percentage, or the outcome indicating that the test product is not verified, if the match percentage is less than the threshold percentage.
Like the first reference detection module 104, the second reference detection module 204 may also comprise a scanning module and a recognition module. The scanning module facilitates a user to scan the test product and the recognition module detects the at least one fixed recognizable reference point on the test product based on the pre-determined set of reference detection rules. As explained above, the reference point may be, for example, an edge of a plastic seal, a point in the artwork, or any other recognizable point on the product or product’s packaging. Accordingly, the pre-determined set of reference detection rules are rules for detecting/recognizing the edge of the plastic seal, or detecting/recognizing the artwork and the reference point in the artwork or any other recognizable point on the product or product’s packaging. The rules may be discovered using machine learning techniques and/or manually pre-fed into the second repository 202.
Additionally, the recognition module can be configured to recognize the category and/or brand of the product being scanned and accordingly fetch the category/brand-specific reference detection rules from the second repository 202. In this case, the second repository 202 stores different reference detection rules for each category of product. The recognition module may use a pre-trained machine learning model to recognize the product category and/or brand and accordingly fetch the corresponding reference detection rules, to detect the reference point on the product or the product’s packaging.
The “artwork” referred to herein above may include a text in and around a visual code printed on the packaging, a brand logo, or a relative position and size of the visual code and the artwork, text, or brand logo printed on the packaging.
In an embodiment, the second fingerprint generation module 208 comprises a second plotting module 208a, a second analyser 208b, and a second fingerprint generator 208c. The second plotting module 208a is configured to receive the captured feature image corresponding to the test product and is further configured to plot a pre-determined design on the feature image. The design can be a grid or a mesh comprising shapes selected from the group consisting of polygon, circle, and ellipse or other random shapes. The second analyser 208b is configured to cooperate with the second plotting module 208a to identify a pattern in the feature by analysing the feature in the feature image with respect to the plotted design. The second fingerprint generator 208c is configured to generate the at least one unique fingerprint based on the detected pattern using the pre-determined set of fingerprint generation rules, after scaling up or down or de-skewing the feature image as per original configuration of the feature image size used during on-boarding in the first repository.
In an embodiment, like the first analyser 108b, the second analyser 208b is configured to identify the pattern in the feature by:
- dividing the feature image into sub-images based on the plotted design and detecting a pattern of variations in the printing of the feature parts in said sub-images;
- detecting a relative position of the feature parts in the sub-images with respect to the design; and
- detecting the number and positions of intersections between the feature parts in the sub-images and the design.
The second fingerprint generator 208c is configured to generate one unique fingerprint for each sub-image of the feature image. Sometimes the product packaging may be damaged due to rough handling or during transportation. The feature (i.e., variable data) may be rubbed off or dust may accumulate on some part of this area. Due to this, the fingerprint may mismatch during verification leading to a false negative. To address this issue, the image of the variable data can be further divided into smaller images and a fingerprint may be created for each sub-image separately. For example, the image may be divided into two rows and 4 columns (8 sub-images). The resulting 8 fingerprints may be individually compared to their respective 8 original fingerprints. A threshold matching percentage may be set for each of these sub-images (for example, at least 70% or 80% match compared to the original) to verify the authenticity of the product at the time of verification. A second threshold matching percentage may be set, that checks how many sub-images match their original fingerprints within the tolerance set. For example, if the second threshold matching percentage is set at above 50%, then if 5 out of 8 sub-images match their respective originals (i.e., each of them matches their respective original fingerprints, above the threshold matching percentage) the product may be declared as genuine. This is done to reduce the number of false negatives (genuine product being declared as a fake) due to any damage the variable printing area may have suffered (due to dust accumulation, rough handling, transportation, etc.).
Alternatively, the second fingerprint generation module 208 comprises an encrypting module configured to encrypt the feature image corresponding to the test product using a pre-determined encryption technique to generate the unique fingerprint. The pre-determined encryption technique is selected from the group consisting of bit level scrambling, cyclic shift and pixel swapping, DNA coding, chaotic maps, and compressed sensing.
The second reference detection module 204, the second feature detection module 206, the second fingerprint generation module 208, and the fingerprint matching module 210 are implemented using one or more processor(s).
In one embodiment, the system 200 is implemented on an edge device i.e., in the device which is used to scan the test product (e.g., a laptop, a smartphone, or a tablet). The system 200 is implemented in the form of an application to facilitate the user to scan products and verify their authenticity. The second reference detection module 204 may use an independent camera or a camera of the user device for scanning the products and capturing the feature images. Alternatively, the second reference detection module 204 uses the user device camera to scan the image and for the authentication of the product.
In an alternate embodiment, the system 200 is at least partially implemented on a remote device such as a remote server or a cloud. For example, the second reference detection module 204 is implemented in the form of an application installed in the user device and the second feature detection module 206, the second fingerprint generation module 208, and the fingerprint matching module 210 are implemented on the cloud server. The second reference detection module 204 uses an independent camera or the device camera to capture the feature image and send the feature image to the second fingerprint generation module 208 for further processing, after the scale up or down or de-skewed of the feature image as per pre-defined configuration of the original feature image used during on-boarding of original product in first repository.
Thus, one or more of the first/second reference detection module 104/204, first/second feature detection module 106/206, first/second fingerprint generation module 108/208, and the fingerprint matching module 210 are stored on the edge device/electronic device. Alternatively, one or more of the first/second reference detection module 104/204, first/second feature detection module 106/206, first/second fingerprint generation module 108/208, and the fingerprint matching module 210 are located on a remote server and accessed by the electronic device via wireless communication means.
In yet another aspect, referring to Figure 7, the present disclosure envisages a method 300 for generation of unique fingerprints for a plurality of products on a production line. The method 300 comprises the following steps-
At step 302, a pre-determined set of reference detection rules, a pre-determined set of feature detection rules, and a pre-determined set of fingerprint generation rules are stored in a first repository 102.
At step 304, a first reference detection module 104 facilitates scanning of the products for which the fingerprints are to be generated.
At step 306, the first reference detection module 104 detects at least one fixed recognizable reference point on each of the products based on said pre-determined set of reference detection rules.
At step 308, a first feature detection module 106 detects at least one feature on each product based on the detected reference point and the pre-determined set of feature detection rules, the feature including at least one variable data printed on each product.
At step 310, the first feature detection module 106 triggers capturing of an image of the detected feature in each product.
At step 312, a first fingerprint generation module 108 receives the captured feature image corresponding to each product from the first feature detection module 106.
At step 314, the first fingerprint generation module 108 generates at least one unique fingerprint for each product by processing the corresponding feature image based on the pre-determined set of fingerprint generation rules.
At step 316, a data logging module 110 stores the generated fingerprints corresponding to the products in the first repository 102.
In accordance with another aspect of the present invention, referring to Figures 8A and 8B, a method 400 for determining the authenticity of products is envisaged. The method 400 comprises the following steps:
At step 402, a second repository 202 stores a pre-determined set of reference detection rules, a pre-determined set of feature detection rules, a pre-determined threshold matching percentage, and a list of unique identifiers corresponding to a plurality of original products and at least one pre-determined unique fingerprint corresponding to each of the original products.
At step 404, a second reference detection module 204 facilitates scanning of a product whose authenticity is to be determined, the product referred to herein as “test product”.
At step 406, the second reference detection module 204 detects at least one fixed recognizable reference point on the test product based on the pre-determined set of reference detection rules.
At step 408, a second feature detection module 206 detects at least one feature on the test product based on the detected reference point and the pre-determined set of feature detection rules, the feature including at least one variable data printed on each product.
At step 410, the second feature detection module 206 triggers capturing of an image of the detected feature in each product.
At step 412, a second fingerprint generation module 208 receives the captured feature image corresponding to the test product from the second feature detection module 206.
At step 414, the second fingerprint generation module 208 generates at least one unique fingerprint corresponding to the feature based on the received image of the detected feature and the pre-determined set of fingerprint generation rules.
At step 416, a fingerprint matching module 210 obtains a unique identifier associated with the test product.
At step 418, the fingerprint matching module 210 extracts the at least one original fingerprint corresponding to the unique identifier from the pre-determined set of fingerprints stored in the second repository 202.
At step 420, the fingerprint matching module 210 generates a match percentage based on a comparison of the generated fingerprint and the extracted original fingerprint.
At step 422, the fingerprint matching module 210 generates an outcome based on a comparison of the generated match percentage and said threshold matching percentage.
In an exemplary working embodiment, referring to Figure 4A, there are three seals printed with the same unique serial number. The seals are scanned and the images of unique serial numbers on each of the seals are obtained by the second feature detection module 206 as shown in Figure 4B. The second fingerprint generation module 208 receives and breaks down each of these images into 14 sub-images by plotting a 7x2 grid as shown in Figure 5A. The second fingerprint generation module 208 detects the unique pattern of parts of the serial number from each of the sub-images. For example, the pattern may a pattern of printing variations of the unique serial number in the sub-images as shown in the high-resolution image of Figure 5B; or the pattern may be positions and number of intersections of the serial number parts in the sub-images with the grid as shown in Figure 5A. As an example, the feature part “1” of the feature (unique serial number) printed on the seal shown in Figure 5A intersects with the plotted grid at one location only. Similarly, the feature part “2” of the feature intersects with the grid at two locations. In an embodiment, the second fingerprint generation module 208 generates a single fingerprint based on the detected pattern. Alternatively, the second fingerprint generation module generates 14 fingerprints for the 14 detected patterns associated with the 14 sub-images. Thereafter, the second fingerprint generation module 208 combines the 14 fingerprints using a mathematical function into one single fingerprint to determine the authenticity of the seal. Alternatively, these 14 fingerprints are used independently to determine the authenticity of the seal and generate a corresponding outcome. The generated outcome may be displayed on a display screen of an electronic device.
In another exemplary embodiment, referring to Figure 6A, the second reference detection module 204 detects a fixed recognizable reference point (i.e., a point in the logo) on the test product. As shown in Figure 6B, the second feature detection module 206 detects the feature (i.e., unique identifier “ABC123”) at a pre-defined position from the detected reference point. The second feature detection module 206 captures the at least one image of the detected feature. The second fingerprint generation module 208 plots a ‘k’ rows x ‘n’ columns grid on the feature image as shown in Figures 6B and detects the pattern which includes the number and position of intersections between grid and the feature parts as shown in Figures 6C and 6D.
When the grid plotting technique is used for fingerprint generation, the higher the grid dimension, the better is the accuracy of authentication, as it helps -
? to build redundancy; in case a portion of the item’s packaging or seal is damaged in transit, there is still sufficient information to match the fingerprint to the original fingerprint with a reasonable amount of confidence; and
? to increase resolution; the higher the number of sub-images, the better is the resolution, which in turn results in higher accuracy in the generation of the fingerprint by the first and second fingerprint generation modules (108, 208).
In an embodiment, the systems 100 and 200 include a converter to convert the images to greyscale before passing the images to the first and second feature detection modules (106, 206) to detect features by implementing the pre-determined set of feature detection rules (for e.g.., edge detection rules). This helps in increasing the contrast before the feature detection process is carried out, and thereby increases the feature detection accuracy.
In an embodiment, the systems (100, 200) use 1D or 2D code readers such as a barcode or a QR code reader to identify a batch or unique product identification. In this way, each batch will have a limited number of fingerprints (depending on the batch size). No two batches will have the same fingerprint since the printed batch number will change. If a unique code is printed on each pack, then there can only be one universally unique fingerprint for the pack. In the case of a unique code, the systems (100, 200) may also be configured to allow for a certain number of mismatches before a product is declared as a fake. Advantageously, the system (100, 200) can use OCR and a combination of the batch code and the unique code to efficiently identify and locate the original fingerprint from the repository (102, 202) for comparison.
In an embodiment, when each batch code is combined with the unique code, that forms a random code that is a universally unique combination. Thus, the length of the random code needs to be only as big as batch size. For example, if a production batch has 10,000 units, the random code needs to be no longer than 5 characters long. The second fingerprint generation module 208 uses techniques and methods such as image recognition, machine learning, and the like to resolve the extracted patterns into a unique fingerprint.
In summary, the systems (100, 200) are implemented in two main stages, namely:
Stage 1. preparation of product; and
Stage 2. authentication of the product.
In stage one, the original fingerprints for products (i.e., items or seals) are determined and stored in the first repository 102 as “pre-determined original fingerprints”. The product typically has a batch number printed in an alphanumeric form on the packaging. A unique alphanumeric code may also be printed in addition to the batch code. This printing is usually around some other recognizable artwork.
In stage two, the data in repository 102/202 is used for authentication. The user will use an application (mobile or web app) to scan the batch code to authenticate the product. The application will follow the steps i.e., recognize the logo/ artwork, use OCR to read the batch and/or unique code to find the schema and/or original fingerprint pattern/ number, and generate a fingerprint-based on a detected pattern of printing of batch and/or unique code.
Once the fingerprint of the product/unit being scanned is extracted, it is compared against the fingerprints within the batch schema (if there is no unique code). If there is a unique code, it is compared against the original fingerprint of that specific item. If a match is found the product is declared as genuine, else it is fake.
The “processor” used herein may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any device that manipulates signals based on operational instructions. Among other capabilities, the processor may be configured to fetch and execute the set of predetermined rules stored in the memory to control the operation of different modules/units of the system.
The present invention may be implemented with any combination of hardware and software. When implemented as a computer-implemented system, the present invention is implemented using means for performing all of the steps and functions described above. When implemented as software, the software code can be executed on any suitable processor or collection of processors, whether provided in a single computer or distributed among multiple computers. The present invention can also be included in an article of manufacture (e.g., one or more computer program products) having, for instance, non-transitory computer readable storage media. The storage media has the computer readable program code stored therein that is encoded with instructions for execution by a processor for providing and facilitating the mechanisms of the present invention. The article of manufacture can be included as part of a computer system or sold separately. The storage media can be any known media, such as computer memory, one or more optical discs, floppy discs, compact discs, magnetic tapes, flash memories, circuit configurations in Field Programmable Gate Arrays, or other semiconductor devices, or other tangible computer storage medium. The storage media can be transportable, such that the program or programs stored thereon can be loaded onto one or more different computers or other processors to implement various aspects of the present invention as discussed above.
The computer(s) used herein may be in any of several forms, such as a desktop computer, a tablet computer, or a laptop computer. Additionally, a computer may be any device with suitable processing capabilities, including a Personal Digital Assistant (PDA), a smartphone or any other suitable portable, mobile, or fixed electronic device.
The foregoing description of the embodiments has been provided for purposes of illustration and not intended to limit the scope of the present disclosure. Individual components of a particular embodiment are generally not limited to that particular embodiment, but, are interchangeable. Such variations are not to be regarded as a departure from the present disclosure, and all such modifications are considered to be within the scope of the present disclosure.
TECHNICAL ADVANCEMENTS AND ECONOMICAL SIGNIFICANCE
The present disclosure described herein above has several technical advantages including, but not limited to, the realization of, a system and method for uniquely identifying and authenticating products that:
? uses Machine Learning (ML) techniques to check the authenticity of a product; and
? can detect minor differences in the printing of a unique serial number to differentiate between an original product and a fake product.
The foregoing disclosure has been described with reference to the accompanying embodiments which do not limit the scope and ambit of the disclosure. The description provided is purely by way of example and illustration.
The embodiments herein and the various features and advantageous details thereof are explained with reference to the non-limiting embodiments in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.
The foregoing description of the specific embodiments so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.
The use of the expression “at least” or “at least one” suggests the use of one or more elements or ingredients or quantities, as the use may be in the embodiment of the disclosure to achieve one or more of the desired objects or results.
While considerable emphasis has been placed herein on the components and component parts of the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other changes in the preferred embodiment, as well as other embodiments of the disclosure, will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be interpreted merely as illustrative of the disclosure and not as a limitation.
,CLAIMS:WE CLAIM:
1. A system (100) for generation of unique fingerprints for a plurality of products on a production line, said system (100) comprising:
? a first repository (102) configured to store a pre-determined set of reference detection rules, a pre-determined set of feature detection rules, and a pre-determined set of fingerprint generation rules;
? a first reference detection module (104) configured to facilitate scanning of the products for which the fingerprints are to be generated and further configured to cooperate with said first repository (102) to detect at least one fixed recognizable reference point on each of the products based on said pre-determined set of reference detection rules;
? a first feature detection module (106) configured to cooperate with said first reference detection module (104) and said first repository (102) to detect at least one feature on each product based on the detected reference point and said pre-determined set of feature detection rules, said first feature detection module (106) further configured to trigger capturing of an image of the detected feature in each product, the feature including at least one variable data printed on each product;
? a first fingerprint generation module (108) configured to cooperate with said first feature detection module (106) to receive the captured feature image corresponding to each product and further configured to cooperate with said first repository (102) to generate at least one unique fingerprint for each product by processing the corresponding feature image based on said pre-determined set of fingerprint generation rules; and
? a data logging module (110) configured to cooperate with said first fingerprint generation module (108) to store the generated fingerprints corresponding to the products in said first repository (102),
wherein said first reference detection module (104), said first feature detection module (106), said first fingerprint generation module (108), and said data logging module (110) are implemented using one or more processor(s).
2. The system (100) as claimed in claim 1, wherein said first fingerprint generation module (108) comprises:
? a first plotting module (108a) configured to receive the captured feature image corresponding to each product and further configured to plot a pre-determined design on each feature image;
? a first analyser (108b) configured to cooperate with said first plotting module (108a) to identify a pattern in each feature by analysing the feature in the feature images with respect to the plotted design; and
? a first fingerprint generator (108c) configured to generate the at least one unique fingerprint for each product based on said identified pattern using said pre-determined set of fingerprint generation rules.
3. The system (100) as claimed in claim 2, wherein the plotted design is a grid or a mesh comprising shapes selected from the group consisting of polygon, circle, and ellipse or other random shapes.
4. The system (100) as claimed in claim 2, wherein said first analyser is configured to identify the pattern in each feature by at least one of the following techniques:
? dividing each feature image into sub-images based on the plotted design and detecting a pattern of variations in the printing of the feature parts in said sub-images;
? detecting a relative position of the feature parts in said sub-images with respect to said design; and
? detecting the number and positions of intersections between the feature parts in said sub-images and said design.
5. The system (100) as claimed in claim 4, wherein said first fingerprint generator (108c) is configured to generate one unique fingerprint for each sub-image of the feature image.
6. The system (100) as claimed in claim 1, wherein said first fingerprint generation module (108) comprises an encrypting module configured to encrypt the feature images corresponding to each of the products using a pre-determined encryption technique to generate the at least one unique fingerprint for each product.
7. The system (100) as claimed in claim 6, wherein the pre-determined encryption technique is selected from the group consisting of bit level scrambling, cyclic shift and pixel swapping, DNA coding, chaotic maps, and compressed sensing.
8. The system (100) as claimed in claim 1, wherein said variable data comprises any information that changes from one product to another or from one batch to another and is printed on the product or on the product’s packaging using thermal inkjet printer, continuous inkjet printer, laser printer, or any other printing techniques typically used for printing variable information.
9. The system (100) as claimed in claim 1, wherein said pre-determined set of feature detection rules include rules for detecting the position of the feature based on the location of the fixed recognizable reference point on the product.
10. The system (100) as claimed in claim 1, wherein the reference point is selected from the group consisting of a center of a barcode, a part of an artwork printed on the product’s packaging, and an edge or a corner of the product when the product is a seal.
11. A system (200) for determining the authenticity of products, said system (200) comprising:
? a second repository (202) configured to store a pre-determined set of reference detection rules, a pre-determined set of feature detection rules, and a list of unique identifiers corresponding to a plurality of original products, at least one pre-determined unique fingerprint, referred herein as “original fingerprint”, corresponding to each of the original products, and a pre-determined threshold matching percentage corresponding to each of the original fingerprints;
? a second reference detection module (204) configured to facilitate scanning of a product whose authenticity is to be determined, the product referred to herein as “test product”, said second reference detection module (204) further configured to cooperate with said second repository (202) to detect at least one fixed recognizable reference point on the test product based on said pre-determined set of reference detection rules;
? a second feature detection module (206) configured to cooperate with said second reference detection module (204) and said second repository (202) to detect at least one feature on the test product based on the detected reference point and said pre-determined set of feature detection rules, said second feature detection module (206) further configured to trigger capturing of an image of the detected feature in the test product, the feature including at least one variable data printed on each product;
? a second fingerprint generation module (208) configured to cooperate with said second feature detection module (206) to receive the captured feature image corresponding to the test product and further configured to cooperate with said second repository (202) to generate at least one unique fingerprint corresponding to the detected feature based on the received image of the feature and said pre-determined set of fingerprint generation rules; and
? a fingerprint matching module (210) configured to obtain a unique identifier associated with the test product and extract at least one original fingerprint corresponding to the unique identifier from the pre-determined set of fingerprints stored in said second repository (202), said fingerprint matching module (210) further configured to generate a match percentage based on a comparison of said generated fingerprint and said extracted original fingerprint and further generate an outcome based on a comparison of said generated match percentage and said threshold matching percentage,
wherein said second reference detection module (204), said second feature detection module (206), said second fingerprint generation module (208), and said fingerprint matching module (210) are implemented using one or more processor(s).
12. The system (200) as claimed in claim 11, wherein said fingerprint matching module (210) comprises:
? an identification module (210a) configured to obtain the unique identifier associated with the test product by scanning said test product;
? a matching module (210b) configured to look up the unique identifier in said second repository to obtain the at least one original fingerprint associated with the unique identifier and extract the original fingerprint;
? a first comparator (210c) configured to compare said generated fingerprint with said extracted original fingerprint to generate said match percentage, wherein said match percentage represents a matching proportion between said generated fingerprint and the pre-stored original fingerprint of the original product; and
? a second comparator (210d) configured to compare said match percentage with said threshold matching percentage to generate the outcome indicating:
- that the test product is verified, if said match percentage is greater than or equal to said threshold percentage; or
- that the test product is not verified, if said match percentage is less than said threshold percentage.
13. The system (200) as claimed in claim 12, wherein said identification module (210a) is configured to use optical character recognition (OCR) techniques to read and obtain the unique identifier present in the variable data of the test product.
14. The system (200) as claimed in claim 12, wherein said identification module (210a) is configured to scan a data matrix code present in the variable data to obtain the unique identifier associated with the test product.
15. The system (200) as claimed in claim 11, wherein said second fingerprint generation module (208) comprises:
? a second plotting module (208a) configured to receive the captured feature image corresponding to the test product and further configured to plot a pre-determined design on the feature image;
? a second analyser (208b) configured to cooperate with said second plotting module (208a) to identify a pattern in the feature by analysing the feature in the feature image with respect to the plotted design; and
? a second fingerprint generator (208c) configured to generate the at least one unique fingerprint based on said detected pattern using said pre-determined set of fingerprint generation rules.
16. The system (200) as claimed in claim 15, wherein the plotted design is a grid or a mesh comprising shapes selected from the group consisting of polygon, circle, and ellipse or other random shapes.
17. The system (200) as claimed in claim 15, wherein said second analyser (208b) is configured to identify the pattern in the feature by:
? dividing the feature image into sub-images based on the plotted design and detecting a pattern of variations in the printing of the feature parts in said sub-images;
? detecting a relative position of the feature parts in said sub-images with respect to said design; and
? detecting the number and positions of intersections between the feature parts in said sub-images and said design.
18. The system (200) as claimed in claim 15, wherein said second fingerprint generator (208c) is configured to generate one unique fingerprint for each sub-image of the feature image.
19. The system (200) as claimed in claim 11, wherein said second fingerprint generation module (208) comprises an encrypting module configured to encrypt the feature image corresponding to the test product using a pre-determined encryption technique to generate the unique fingerprint.
20. The system (200) as claimed in claim 19, wherein the pre-determined encryption technique is selected from the group consisting of bit level scrambling, cyclic shift and pixel swapping, DNA coding, chaotic maps, and compressed sensing.
21. The system (200) as claimed in claim 11, wherein said variable data comprises any information that changes from one product to another or from one batch to another and is printed on the product or on the product’s packaging using thermal inkjet printer, continuous inkjet printer, laser printer, or any other printing techniques typically used for printing variable information.
22. The system (200) as claimed in claim 11, wherein said pre-determined set of feature detection rules include rules for detecting the position of the feature based on the location of the fixed recognizable reference point on the product.
23. The system (200) as claimed in claim 11, wherein the reference point is selected from the group consisting of a center of a barcode, a part of an artwork printed on the product’s packaging, and an edge or a corner of the product when the product is a seal.
24. A method (300) for generation of unique fingerprints for a plurality of products on a production line, said method (300) comprising:
? storing (302), in a first repository (102), a pre-determined set of reference detection rules, a pre-determined set of feature detection rules, and a pre-determined set of fingerprint generation rules;
? facilitating (304), by a first reference detection module (104), scanning of the products for which the fingerprints are to be generated;
? detecting (306), by said first reference detection module (104), at least one fixed recognizable reference point on each of the products based on said pre-determined set of reference detection rules;
? detecting (308), by a first feature detection module (106), at least one feature on each product based on the detected reference point and said pre-determined set of feature detection rules, the feature including at least one variable data printed on each product;
? triggering (310), by said first feature detection module (106), capturing of an image of the detected feature in each product;
? receiving (312), by a first fingerprint generation module (108), the captured feature image corresponding to each product from said first feature detection module (106);
? generating (314), by said first fingerprint generation module (108), at least one unique fingerprint for each product by processing the corresponding feature image based on said pre-determined set of fingerprint generation rules; and
? storing (316), by a data logging module (110), the generated fingerprints corresponding to the products in said first repository (102).
25. A method (400) for determining the authenticity of products, said method (400) comprising:
? storing (402), in a second repository (202), a pre-determined set of reference detection rules, a pre-determined set of feature detection rules, a pre-determined threshold matching percentage, and a list of unique identifiers corresponding to a plurality of original products and at least one pre-determined unique fingerprint corresponding to each of the original products;
? facilitating (404), by a second reference detection module (204), scanning of a product whose authenticity is to be determined, the product referred herein as “test product”;
? detecting (406), by said second reference detection module (204), at least one fixed recognizable reference point on the test product based on said pre-determined set of reference detection rules;
? detecting (408), by a second feature detection module (206), at least one feature on the test product based on the detected reference point and said pre-determined set of feature detection rules, the feature including at least one variable data printed on each product;
? triggering (410), by said second feature detection module (206), capturing of an image of the detected feature in each product;
? receiving (412), by a second fingerprint generation module (208), the captured feature image corresponding to the test product from said second feature detection module (206);
? generating (414), by said second fingerprint generation module (208), at least one unique fingerprint corresponding to said feature based on the received image of the detected feature and said pre-determined set of fingerprint generation rules;
? obtaining (416), by a fingerprint matching module (210), a unique identifier associated with the test product;
? extracting (418), by said fingerprint matching module (210), the at least one original fingerprint corresponding to the unique identifier from the pre-determined set of fingerprints stored in said second repository (202);
? generating (420), by said fingerprint matching module (210), a match percentage based on a comparison of said generated fingerprint and said extracted original fingerprint; and
? generating (422), by said fingerprint matching module (210), an outcome based on a comparison of said generated match percentage and said threshold matching percentage.