A device, computer program and method

Abstract

A method of authenticating a picture printed on an object is disclosed. The method comprising; capturing an image of the printed picture; retrieving an authentic version of the picture; converting the captured image and the retrieved authentic version to the same subtractive colour model; comparing the converted captured image and the converted retrieved authentic version; and in the event that any differences, between at least a part of the converted captured image and a corresponding part of the converted retrieved authentic version are random, determine the printed picture is authentic.

Description

BACKGROUND Field of the Disclosure

[0001] The present technique relates to a device, computer program and method.Description of the Related Art

[0002] The "background" description provided herein is for the purpose of generally presenting the context of the disclosure. Work of the presently named inventors, to the extent it is described in the background section, as well as aspects of the description which may not otherwise qualify as prior art at the time of filing, are neither expressly or impliedly admitted as prior art against the present technique.

[0003] Over the past few years, secure high quality colour pictures on identity cards, passports and high value goods have been used. There have been several systems developed, including a system developed by Sony ®< using leuco dye.

[0004] Whilst the systems for printing these secure, high quality colour pictures have been developed, there is a need to produce a system or device that can easily detect when these printing systems have been used.

[0005] It is an aim of the disclosure to address this issue.SUMMARY

[0006] According to embodiments of the disclosure there is provided a method of authenticating a picture printed on an object, comprising; capturing an image of the printed picture; retrieving an authentic version of the picture; converting the captured image and the retrieved authentic version to the same subtractive colour model; comparing the converted captured image and the converted retrieved authentic version; and in the event that any differences, between at least a part of the converted captured image and a corresponding part of the converted retrieved authentic version are random, determine the printed picture is authentic.

[0007] The foregoing paragraphs have been provided by way of general introduction, and are not intended to limit the scope of the following claims. The described embodiments, together with further advantages, will be best understood by reference to the following detailed description taken in conjunction with the accompanying drawings.BRIEF DESCRIPTION OF THE DRAWINGS

[0008] A more complete appreciation of the disclosure and many of the attendant advantages thereof will be readily obtained as the same becomes better understood by reference to the following detailed description when considered in connection with the accompanying drawings, wherein: Figure 1 shows a system produced by Sony to make a secure, high quality colour picture Figure 2A shows a cross sectional view of the colour sheet seen in Figure 1 and Figure 2B shows how red is created on the colour sheet of Figure 2A; Figure 3 shows a device 100 according to embodiments of the disclosure; and Figures 4 to 11 show a process carried out by the device of Figure 3 according to embodiments of the disclosure. DESCRIPTION OF THE EMBODIMENTS

[0009] Referring now to the drawings, wherein like reference numerals designate identical or corresponding parts throughout the several views.

[0010] Numerous modifications and variations of the present disclosure are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims, the disclosure may be practiced otherwise than as specifically described herein.

[0011] Figure 1 shows a system produced by Sony to make a secure, high quality colour picture. This is explained in [1], the contents of which are hereby incorporated by reference. The colour picture is made from a thin stacked Cyan / Magenta / Yellow (C / M / Y) thermochromic leuco-dye sheet. The sheet is shown in cross-section in Figure 2A and 2B.

[0012] The sheet has a C / M / Y layer which absorbs non-infrared light of different wavelengths. When the thermochromic layers are irradiated by non-infrared laser light with different wavelengths of λ 1 / λ 2 / λ 3 the C / M / Y layer heats up independently of one another and turns into its coloured state. Figure 2B explains drawing a red colour on the sheet. When the laser lights with λ 2 and λ 3 are irradiated on the sheet, the M and Y thermochromic layers respectively absorb the laser light λ 2 and λ 3 and heat up turning into the M and Y coloured states resulting in a red image.

[0013] Referring to Figure 1, writing on the sheet is performed by three different laser diodes, each with a maximum power of 5W and a wavelength of λ 1 , λ 2 , and λ 3 respectively. The three lasers are aligned using dichroic mirrors to form a single beam that is focussed on the thermochromic layers. The beam is steered through an Fθ lens by an x-galvano mirror and is synchronised to a Y motorised linear stage, or an x-y galvano mirror without any motorised linear stage The laser power and focus is set so that the laser beam heats a respective layer above its melting point and the colour is set.

[0014] Embodiments of the disclosure relate to a method and device which is configured to test a picture and to detect when this writing process is used on the sheets shown in Figures 2A and 2B to create the picture.

[0015] Referring to Figure 3, a device 100 according to embodiments of the disclosure is shown. The device 100 includes a sensor 110. The sensor 110 may be composed of sensor circuitry which is, in embodiments, semiconductor circuitry. The sensor 110 is configured to capture an image of the picture under test. The picture may be on an identity card, a passport, product, or product logo or emblem, or product packaging, or the like. By confirming that the picture is produced using a particular technique, the authenticity of the underlying identity card or passport, or product.

[0016] In embodiments, the picture under test may be provided on a product whose provenance is to be confirmed. For example, the picture may be produced as a sticker which is placed on a product such as wine or food from a particular region. In the event that the food is genuine then the picture will be produced using the aforesaid technique.

[0017] The device 100, in embodiments, also includes communication circuitry 120. The communication circuitry 120 is configured in embodiments to provide, over a network, data in the event of a failed test. This data may include details of the failed picture, for example, a name or the person on the identity card or passport or a number uniquely defining the identity card or passport. In embodiments, the data may include details of a shop from which the product was purchased. The purpose of providing the data is to enable the appropriate Government Agency to respond to the failed test appropriately by cancelling an identity card or passport (in the event that it has been cloned) or to visit a shop which is selling counterfeit goods. Of course, the disclosure is not limited to this and other data may be provided over the network by the communication circuitry 120 instead of or in addition to the aforementioned data. The network may be a wired network, or a wireless network. For example, the communication circuitry 120 may allow data to be communicated over a cellular network such as a 5G network, or a Low Earth Orbit Satellite internet network or the like. This network may be a Wide Area Network such as the Internet or may be a Private Network.

[0018] The operation of the device 100 is, in embodiments, controlled by processing circuitry 105. The processing circuitry 105 may be formed from semiconductor material and may be an Application Specific Integrated Circuit or may operate under the control of software. In other words, the processing circuitry 105 may operate under the control of software instructions stored on storage medium 115. The processing circuitry 105 is thus connected to the sensor 110 and the communication circuitry 120.

[0019] Additionally connected to the processing circuitry 105 is the storage 115. The storage 115 may be semiconductor storage or optically or magnetically readable storage. The storage 115 is configured to store software code according to embodiments therein or thereon.

[0020] Although the aforesaid sensor 110, communication circuitry 120, processing circuitry 105 and storage 115 is described as functionally different, it is envisaged that, in embodiments, these may all form part of the same circuitry. In other words, the audio / video capturing device 100 may comprise circuitry to perform the various functional steps.

[0021] In embodiments, the device 100 may be a computer or automatic gates such as those found at a national border or may be a mobile telephone or other handheld computer carried by law enforcement officers (in the case of the image being printed on official documentation such as an identity card or driving licence) or may be a mobile telephone carried by a consumer in the case of checking the authenticity of a product purchased in a shop.

[0022] A process 400 according to embodiments carried out by the device 100 of Figure 3 will now be described with reference to Figures 4 to 10. Overall, the purpose of the process 400 is to determine whether the image on a product or identity card or passport or the like is created using the apparatus explained in reference to Figures 1 to 3.

[0023] The process 400 starts in step 405 where an image of the picture under test is taken by the sensor 110. The process then moves to step 410 where a check is made to determine if the picture under test is formed by dots or lines.

[0024] Referring to Figure 5, two images are shown. The first image 510 is formed by dots produced by a known printing process using dots pattern (such as using an inkjet printer or laser engraving systems) and the second image 520 is formed by lines produced using a modernlaser engraving process (although not necessarily the laser engraving process of present embodiments). As is evident, the first image 510 produced by known printing is comprised of dots and the second image 520 produced using a modern laser engraving process is comprised of lines. It is possible to identify this from the image by capturing the image using a macro zoom setting. This may be achieved using a macro zoom lens on the device 100 or by activating the macro mode (a digital macro zoom setting) on the device 100. Of course, the disclosure is not so limited and a lens may be placed over the image under test which magnifies the picture.

[0025] The captured image is checked by the processing circuitry 105 to determine whether the captured image is comprised of dots (known printing) or lines (modern laser engraving). In the event that the captured image is comprised of dots, the path to step 430 is followed and the process ends as will be explained later. In the event that the captured image is comprised of lines, the path to step 415 is followed.

[0026] By performing an initial check of the picture and determining whether it is made using a known printing process or a modern laser engraving process a large proportion of unauthorised pictures are identified which means that the later process steps are not required.

[0027] In step 415, a check is made to determine if the modern laser engraving process is different to the process of Figure 1. Figure 6 shows a plan view of two types of printing medium. A first type of printing medium 610 has a cyan, magenta and yellow layer in the same plane, in a continuous repeated sequence that may be recognised by computer vision or AI software. In other words, the medium has the colours formed in a single layer. However, a second type of printing medium 620 has a cyan, magenta and yellow layer in different layers. In other words, when looked from a plan view, the second type of printing medium is the same colour; the different colours are produced by activating the dyes at different layers. As noted above with reference to Figures 1 to 3, the printing medium from which the genuine image is produced is the second type. Accordingly, in step 415, a check is made to determine whether the printing medium is the first type (i.e. is not the same printing medium from which a genuine image is made). This is explained with reference to Figures 7, 8 and 9.

[0028] Figure 7 shows picture 705. This picture is a ladybird. This picture of the ladybird will be printed onto a printing medium (either the first type or the second type of printing medium noted above). The original picture of the ladybird will be stored in association with a unique identifier identifying the passport, identity card or sticker or the like. This stored picture is an authenticated version of the picture mentioned later. The authenticated version of the picture may be the original image, an authenticated copy of the original picture or a virtual image which is an image of a ground truth (i.e. an image known to be created using the same technique as being authenticated).

[0029] When the device 100 checks the printed picture, an image of the printed picture on the object (such as the passport, identity card or sticker) will be captured by the sensor 110. As will be appreciated by the skilled person, the captured image will be in the Red, Green, Blue (RGB) format. In embodiments, the device 100 converts the RGB image into a CMYK image. This may be achieved using known techniques which are applicable to Leuco dyes. As will be appreciated, CMYK is one type of colour model that is a so-called subtractive model which creates colours by removing colours from white light. Other examples of a subtractive model include CMY and RYB and the like.

[0030] On the other hand, the RGB model is an additive colour model that uses red, green and blue light to create colours by adding different intensities of light together.

[0031] Therefore, as will be appreciated, the captured image is converted to a subtractive model, which is, in embodiments, a CMYK model. The separate CMY channels are then analysed to determine if the captured image is printed on the first type of printing medium 610 or the second type of printing medium 620.

[0032] Figure 8 shows separate colour channels between an authentic version of the picture (top image 810) and when the picture is printed on the first type of medium (bottom image 820). Specifically, the top image 810 is an authentic version of the picture and its corresponding CMY channels and the bottom image 820 is an image of the picture being produced on the first type of printing medium and its corresponding CMY channels.

[0033] A known authentic version of the picture is retrieved as noted above. In embodiments, the communication circuitry 120 retrieves a version of the picture from a database containing authentic versions of pictures. For example, in the case of a passport or an identity card, a unique number identifying the passport or identity card is used to determine the record in which an authentic version of the picture is stored. The authentic version of the picture is then retrieved from that record. The authentic version is shown in the top image 810.

[0034] The processing circuitry 105 checks the format of the authentic version of the picture and if the authentic version is not in the colour format as the subtractive format as the already converted captured image, the processing circuitry 105 converts the retrieved picture into the same subtractive model (such as, in this case, CMYK format).

[0035] Figure 9 shows the top image 810 and the bottom image 820 of Figure 8 with sections highlighted by boxes in the corresponding CMY channels. The sections highlighted by the boxes show differences between the CMY channels for an authentic version of the picture and a picture printed on the printing medium.

[0036] As will be appreciated, the main differences occur in the areas of the printed picture that are light or white in colour. In other words, there is a pattern in the location of the main differences. In particular, where there is white area to the bottom right of the picture and across the eyes of the ladybird, there is more cyan, magenta and yellow colours in the CMY channels of the bottom image 820 that is printed on the first type of printing medium 610. Although we discuss white colours and light colours where the main differences occur, the disclosure is not so limited. In fact, colours with high light intensity (light colours) contrast with black and other dark colours which have low light intensity. The light coloured objects reflect a large proportion of the light that strikes them and in an RGB colour model, a light colour has high number for each of the red, blue and green component and similarly in the CMYK colour model, the value of each component is high. Therefore, a light colour is a colour that has a light intensity above a predetermined threshold.

[0037] This larger amount of cyan, magenta and yellow colour is because the different colours (CMYK) are located on the same layer on the first type of printing medium.

[0038] Although the above describes the main differences being found in areas where the picture is white or light coloured, the disclosure is not so limited. For example, if the picture has an area of cyan, then the area of cyan in the picture will highlight the presence of white, yellow and magenta as would be appreciated. Similarly, if there is an area of picture that is the same colour as one of lines in the coloured layer of the first type of printing medium, the other colours will be highlighted in that area.

[0039] So, in step 415 of Figure 4, the image captured by the sensor 110 is converted to a subtractive colour model such as CMYK and the different colour channels are analysed in areas of white or light colour on the printed picture. In the event that the amount of cyan, yellow and / or magenta is above a threshold, it is determined that the picture is provided on the first type of printing medium 610.

[0040] In embodiments, the threshold may be defined by a proportion of the total size of the white or light areas of the picture. In embodiments, if the proportion is 10% or more of the total size of the white or light areas of the picture then it is determined that the first type of printing medium has been used. Of course, the disclosure is not so limited and any proportion is envisaged. For example, the proportion may be with the range of 5% to 25% as the first type of printing medium is comprised of CMYK on the same layer. In other words, a maximum of 25% of the area of the first type of printing medium is comprised of any one of cyan, magenta, yellow or a key. Of course, the disclosure is not so limited and in embodiments, the areas or shape of the cyan, yellow and / or magenta may determine that the first type of printing medium 610 is used. Specifically, the cyan, yellow and magenta colours are provided in lines in the first type of printing medium. Accordingly, if the amount of cyan, yellow and / or magenta in the channels is in lines, then the printing medium is the first type of printing medium.

[0041] It should be noted that the above describes a pattern as finding areas of white or light colour in the picture, however, the disclosure is not so limited. Indeed, it is envisaged that any non-random pattern will indicate that the printing medium used for the picture is not the second type of printing medium and so will be notified to the user of the device 100. In order to establish whether the pattern of differences is random or not, a known pattern matching computer vision technique is used. Of course, other image processing techniques for identifying patterns are envisaged such as artificial intelligence techniques.

[0042] In the event that the printing medium is the first type of printing medium (i.e. a pattern to the differences is found), the path to step 430 is followed and the process ends. However, in the event that the printing medium is not the first type of printing medium, the path to step 420 is followed.

[0043] In step 420, a check is made to determine whether the picture is printed on the second type of material.

[0044] A comparison is made between the CMY channels of the authentic version y of the picture and the already converted image of the picture captured by the sensor 110. As can be seen in the CMY channels of the captured image, there are a small number of differences in the channels. These are highlighted by red boxes in the bottom image 1020. A check is made to determine if the differences are minor imperfections caused by the laser engraving process itself. In other words, a check is made to determine if the second type of printing medium is used but minor imperfections caused by the laser engraving process itself has caused these differences in the expected CMY channel (the top image 1010) and the actual CMY channel from the captured image (the bottom image 1020).

[0045] In embodiments, and as noted above, a check is made to determine if the differences form a pattern such as a difference where the picture is a certain colour or shade. As explained above, this pattern would be indicative of a different printing medium being used. Alternatively, the differences may not form a pattern and may be random in nature. This is indicative that the second type of printing medium was used but that minor imperfections have been caused by the printing process itself.

[0046] As already mentioned, it is possible to identify patterns of this nature using computer vision techniques such as pattern recognition. In particular, pattern recognition can be used to identify any patterns in the differences between the CMY colour channels of the top image 1010 and the bottom image 1020. In the event that no pattern is identified, it is determined that the second printing medium type is used.

[0047] Of course, the disclosure is not so limited and if the number of small differences are below a threshold, then it is decided that the second type of printing medium is used. For example, if there is less than 5% of the area of the picture with these differences, then it is decided that the second type of printing medium is used. Of course, another metric may be used to determine that the second type of printing medium is used such as the size of differences is below a threshold amount.

[0048] In the case that the processing circuitry 105 determines that the second type of printing medium is used, the 'yes' path to step 425 is followed where a positive indication is made to the user that the picture is genuine via a display or audible indicator. However, in the event that the processing circuitry 105 determines that the second type of printing medium is not used, the 'no' path is followed to step 430 where the process ends.

[0049] It is possible to uniquely identify the printed picture where the second type of printing medium is used. Specifically, as a small number of minor imperfections are generated when the picture is engraved on the second printing medium (see Figure 10), it is possible to identify the location of these imperfections. These imperfections will be unique to the printed picture. Information relating to the imperfections such as the location of the imperfections and the magnitude of the imperfections are, in embodiments, stored in a smartcontract on a blockchain. This provides a unique identity to the printed picture and may be associated with a product upon which printed picture is placed. Accordingly, it is possible to track the location of a particular product.

[0050] Although the foregoing has described comparing a retrieved authentic version of the picture with the captured image of the picture to determine a pattern of differences, it will be appreciated that the entire images do not need to be compared. By comparing a corresponding part of the two images, the time required to perform such analysis is reduced. In embodiments, a random selection of parts of the captured image and the corresponding parts of the authentic version of the picture are selected and their colour channels are analysed using the pattern recognition technique.

[0051] In embodiments, the captured image and / or the authentic version of the picture are mapped to a common co-ordinate system. This may be achieved in many ways. For example, the captured image may be resized automatically to be the same as the authentic version and placed in a common co-ordinate space. Of course other techniques exist as will be apparent. The purpose of the mapping to a common co-ordinate system means that the same parts of the captured image and the authentic version of the picture are compared.

[0052] Figure 11 shows a process 1100 according to embodiments of the disclosure. The process starts at 1105. The process then moves to step 1110 where an image of the printed picture is captured. The process moves to step 1115 when an authentic version of the picture is retrieved. The process moves to step 1120 where the captured image and the retrieved authentic version are converted to the same subtractive colour model. In embodiments, this shows the Leuco colour gamut (although the disclosure is not so limited). The process then moves to step 1125 where the converted captured image and the converted retrieved authentic version are compared. The process then moves to step 1130 where, in the event that any differences, which in embodiments may be optionally within a certain defined threshold, between at least a part of the converted captured image and a corresponding part of the converted retrieved authentic version are random, the printed picture is determined to be authentic.

[0053] In so far as embodiments of the disclosure have been described as being implemented, at least in part, by software-controlled data processing apparatus, it will be appreciated that a non-transitory machine-readable medium carrying such software, such as an optical disk, a magnetic disk, semiconductor memory or the like, is also considered to represent an embodiment of the present disclosure.

[0054] It will be appreciated that the above description for clarity has described embodiments with reference to different functional units, circuitry and / or processors. However, it will be apparent that any suitable distribution of functionality between different functional units, circuitry and / or processors may be used without detracting from the embodiments.

[0055] Described embodiments may be implemented in any suitable form including hardware, software, firmware or any combination of these. Described embodiments may optionally be implemented at least partly as computer software running on one or more data processors and / or digital signal processors. The elements and components of any embodiment may be physically, functionally and logically implemented in any suitable way. Indeed the functionality may be implemented in a single unit, in a plurality of units or as part of other functional units. As such, the disclosed embodiments may be implemented in a single unit or may be physically and functionally distributed between different units, circuitry and / or processors.

[0056] Although the present disclosure has been described in connection with some embodiments, it is not intended to be limited to the specific form set forth herein. Additionally, although a feature may appear to be described in connection with particular embodiments, one skilled in the art would recognize that various features of the described embodiments may be combined in any manner suitable to implement the technique.

[0057] Embodiments of the present technique can generally described by the following numbered clauses: 1. A method of authenticating a picture printed on an object, comprising; capturing an image of the printed picture; retrieving an authentic version of the picture; converting the captured image and the retrieved authentic version to the same subtractive colour model; comparing the converted captured image and the converted retrieved authentic version; and in the event that any differences, between at least a part of the converted captured image and a corresponding part of the converted retrieved authentic version are random, determine the printed picture is authentic. 2. A method according to clause 1, further comprising: comparing the captured image with the retrieved authentic version and in the event that the printed picture is printed using dots, determine the printed picture is not authentic. 3. A method according to clause 1 or 2, further comprising: randomly selecting the at least part of the converted captured image and the corresponding part of the converted retrieved authentic version. 4. A method according to clause 3, further comprising: assigning a common co-ordinate system to the captured image and the retrieved authentic version. 5. A method according to any preceding clause, wherein the at least part of the converted captured image and the corresponding part of the converted retrieved authentic version are white. 6. A method according to any preceding clause, wherein the differences are within a predetermined threshold. 7. A computer program product comprising computer readable instructions which, when loaded onto a computer, configures the computer to perform a method according to clauses 1 to 6. 8. A device for authenticating a picture printed on an object, comprising circuitry configured to; capture an image of the printed picture; retrieve an authentic version of the picture; convert the captured image and the retrieved authentic version to the same subtractive colour model; compare the converted captured image and the converted retrieved authentic version; and in the event that any differences, between at least a part of the converted captured image and a corresponding part of the converted retrieved authentic version are random, determine the printed picture is authentic. 9. A device according to clause 8, wherein the circuitry is further configured to: compare the captured image with the retrieved authentic version and in the event that the printed picture is printed using dots, determine the printed picture is not authentic. 10. A device according to clause 8 or 9, wherein the circuitry is further configured to: randomly select the at least part of the converted captured image and the corresponding part of the converted retrieved authentic version. 11. A device according to clause 10, wherein the circuitry is further configured to: assign a common co-ordinate system to the captured image and the retrieved authentic version. 12. A device according to any one of clause 8 to 11, wherein the at least part of the converted captured image and the corresponding part of the converted retrieved authentic version are white. 13. A device according to any one of clause 8 to 12, wherein the differences are within a predetermined threshold. [1] 'Photo-Quality Single Pixel Full-Colour Rewritable Sheets with Leuco Dyes' Kenichi Kurihara et. Al, The 26th International Display Workshops, 27-29 November 2019, Sapporo Convention Center.

Claims

1. A method of authenticating a picture printed on an object, comprising; capturing an image of the printed picture; retrieving an authentic version of the picture; converting the captured image and the retrieved authentic version to the same subtractive colour model; comparing the converted captured image and the converted retrieved authentic version; and in the event that any differences, between at least a part of the converted captured image and a corresponding part of the converted retrieved authentic version are random, determine the printed picture is authentic.

2. A method according to claim 1, further comprising: comparing the captured image with the retrieved authentic version and in the event that the printed picture is printed using dots, determine the printed picture is not authentic.

3. A method according to claim 1, further comprising: randomly selecting the at least part of the converted captured image and the corresponding part of the converted retrieved authentic version.

4. A method according to claim 3, further comprising: assigning a common co-ordinate system to the captured image and the retrieved authentic version.

5. A method according to claim 1, wherein the at least part of the converted captured image and the corresponding part of the converted retrieved authentic version are white.

6. A method according to claim 1, wherein the differences are within a predetermined threshold.

7. A computer program product comprising computer readable instructions which, when loaded onto a computer, configures the computer to perform a method according to claim 1.

8. A device for authenticating a picture printed on an object, comprising circuitry configured to; capture an image of the printed picture; retrieve an authentic version of the picture; convert the captured image and the retrieved authentic version to the same subtractive colour model; compare the converted captured image and the converted retrieved authentic version; and in the event that any differences, between at least a part of the converted captured image and a corresponding part of the converted retrieved authentic version are random, determine the printed picture is authentic.

9. A device according to claim 8, wherein the circuitry is further configured to: compare the captured image with the retrieved authentic version and in the event that the printed picture is printed using dots, determine the printed picture is not authentic.

10. A device according to claim 8, wherein the circuitry is further configured to: randomly select the at least part of the converted captured image and the corresponding part of the converted retrieved authentic version.

11. A device according to claim 10, wherein the circuitry is further configured to: assign a common co-ordinate system to the captured image and the retrieved authentic version.

12. A device according to claim 8, wherein the at least part of the converted captured image and the corresponding part of the converted retrieved authentic version are white.

13. A device according to claim 8, wherein the differences are within a predetermined threshold.

Images