Method and server for facilitating providing food information
By adding visual markers to food packaging and using image processing technology to generate enhanced image data, the problem of difficult access to information on food packaging has been solved, achieving convenient information access and easy readability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- TETRA LAVAL HOLDINGS & FINANCE SA
- Filing Date
- 2021-06-30
- Publication Date
- 2026-07-21
AI Technical Summary
In existing technologies, information on food packaging is difficult to access, especially for people with impaired vision, and the small print size makes reading difficult.
By adding visual markers to food packaging and using the user's device camera to capture real image data, combined with a human image database and spatial reference points to generate enhanced image data, a convenient way to obtain food information is provided.
It can obtain food information without identifying the packaging location, supports easy-to-read large text display, is suitable for small packaging, reduces reading difficulties for people with poor eyesight, and reduces the risk of accidentally ingesting allergenic foods.
Smart Images
Figure CN115735232B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to software technology in the food processing and packaging industry. More specifically, it relates to methods and servers for facilitating the provision of food information. Background Technology
[0002] Today, in the food processing industry, by law, product information is provided on food packaging in the form of printed text. This type of information can be important to consumers. For example, it may contain information about the product's contents, which may be important regarding food preferences or allergies. It may also contain information about expiration dates, which may be important regarding the product's condition.
[0003] However, this type of information is often difficult to obtain. Multiple sides of the food packaging typically need to be examined before the information can be located. Furthermore, the small font size can make it difficult for people with impaired vision, such as the elderly, to read.
[0004] In view of the above, it is necessary to improve the way food information is presented to consumers so that they can better understand the food provided in the packaging. Summary of the Invention
[0005] One object of the present invention is to overcome, at least in part, one or more of the aforementioned limitations of the prior art. In particular, one object is to provide a method for facilitating the provision of food information.
[0006] It is generally recognized that the use of enhanced image data allows for the facilitation of food information delivery. The possibility of adding artificial image data to real image data enables consumers who cannot read or otherwise access food information printed on packaging to obtain that information, which in turn can reduce the risk of foods containing, for example, nuts being consumed by consumers with nut allergies.
[0007] According to a first aspect, a method for facilitating the provision of food information is provided, the method comprising: providing food packaging, wherein the food packaging may provide visual markings; capturing real image data describing the visual markings via a camera of a user device; extracting marking data from the real image data; retrieving artificial image data linked to the marking data from an artificial image database, wherein the artificial image data may describe at least one food component of the food held in the food packaging; determining artificial image spatial reference points based on the visual markings; generating enhanced image data by combining the real image data, the artificial image data, and the artificial image spatial reference points; and providing the enhanced image data to the screen of the user device.
[0008] Visual markers should be interpreted as recognizable marks of a predetermined size. They can be simple shapes or complex images.
[0009] Food components should be interpreted as the ingredients of a food. As a non-limiting example, a food component can be water, sugar, or salt. It can also be in processed or unprocessed form, such as crushed tomatoes or fresh tomatoes.
[0010] Artificial image data can also be text and / or a combination of text and images. For example, artificial image data could include an image describing three oranges, which could be multiple oranges used to produce juice held in the packaging. Alternatively, artificial image data could be the text "3 oranges," which could be presented next to the packaging in the enhanced image data. Another option is that both the three oranges and the text are displayed next to the packaging in the enhanced image data.
[0011] Food may include one food component, an example of which is milk. Food may also include multiple food components, an example of which is baking soda, which may include food components such as carbonated water, sugar, flavorings, and food coloring.
[0012] The proposed method offers the advantage of acquiring food information without needing to identify its location on the packaging. Furthermore, it allows for product visualization without opening the packaging. Because the food information is confined to the space available for printing on food packaging, this method enables the use of large, easily readable text in smaller packages.
[0013] The method may further include extracting spatial measurement data from real image data, wherein the spatial measurement data is linked to measurements of food packaging and / or visual markings; performing spatial calibration of artificial image data by comparing the spatial measurement data with spatial reference data linked to food packaging and / or linked to visual markings provided by a spatial reference database, thereby generating calibrated artificial image data, wherein real image data, calibrated artificial image data, and artificial image spatial reference points are combined to produce enhanced image data.
[0014] In other words, spatial measurement data can be described as geometric measurements of an object determined from an image of the object. Conversely, spatial reference data can be described as geometric measurements determined by measuring the actual object.
[0015] The advantage of generating calibrated artificial data is that the enhanced image data can be scaled to fit the real image data.
[0016] The method may further include, in the step of providing food packaging, providing additional food packaging, wherein the additional food packaging may provide additional visual markings, wherein real image data describes the visual markings and the additional visual markings, wherein marking data may be based on the visual markings and the additional visual markings, wherein artificial image data may describe at least one food component of the food held in the food packaging and at least one additional food component of the additional food held in the additional food packaging, and wherein artificial image spatial reference points may be based on the visual markings and the additional visual markings.
[0017] The advantage of providing additional packaging is that it allows the mixture of foods kept in the food packaging to be shown in enhanced image data.
[0018] Spatial measurement data can be linked to measurements of food packaging, additional food packaging, visual markings and / or additional visual markings, and spatial reference data can be linked to food packaging, additional food packaging, visual markings and / or additional visual markings.
[0019] The advantage of doing this is that, in the case of additional food packaging, the enhanced image data can be calibrated to both the food packaging and the additional food packaging.
[0020] The method may also include providing a physical container, such as a bowl, wherein the real image data can further describe the physical container; determining the geometric data of the physical container in the real image data; generating adjusted artificial image data by adjusting the artificial image data based on the geometric data of the physical container; and generating enhanced image data by combining the real image data, the adjusted artificial image data, and the artificial image spatial reference points.
[0021] Geometric data can be determined by comparing spatial reference data linked to food packaging and / or visual markers with the physical container.
[0022] Visual markings can be provided along with QR codes on the side of food packaging. This can be advantageous because visual markings and QR codes can be captured in the same image.
[0023] The QR code can be configured to launch an application on the user's device. Launching the application on the user's device could mean opening a webpage in the user's web browser. This could be an advantage, as the application does not need to be pre-installed.
[0024] The QR code can also be configured to instruct the user to move the camera backward when the code is scanned near the camera. This allows for a wider field of view.
[0025] QR codes can include unique identifiers for food packaging. This can be advantageous because food information related to specific packaging, such as expiration dates, can be provided within enhanced image data.
[0026] Visual markings may be incorporated into the decoration of food packaging. The decoration of food packaging should be interpreted as the printed surface of the packaging that provides consumer-oriented information, such as the product name. This can be advantageous because it eliminates the need to print additional markings on the food packaging. In other words, the printing process does not need to be altered. Furthermore, by having less non-consumer-oriented information (such as barcodes), more space on the packaging can be used for consumer-oriented information. Additionally, by "hiding" the visual markings within the decoration, the risk of counterfeit products or other types of fraud is reduced. In other words, it is more difficult to copy or improperly modify if the location and manner in which the visual markings are presented on the packaging are not explicitly stated.
[0027] Artificial image data can describe the food in a first form, and the food can be held in the food packaging in a second form. The first volume of the food in the first form can differ from the second volume of the food in the second form. Describing the food in different forms can be advantageous because it allows, for example, a user to see how full the bowl will be after the food has been processed, which helps the user choose a bowl.
[0028] Human-generated image data can be geographically dependent on the user's device. This can be an advantage, as different enhanced image data can be provided based on the location of the food packaging.
[0029] Human-generated image data can be based on a user's profile. This profile can include user-defined settings for different food components. This can be advantageous because it allows for the provision of food information relevant to a specific user. For example, it could be information about food components that the user might be allergic to. Another advantage is that users can select the information they want presented. For example, they might want to know the ingredients of a food and its origin, or they might want to know its nutritional value and expiration date. Otherwise, finding specific information would be difficult and time-consuming.
[0030] According to a second aspect, a server configured to facilitate the provision of food information is provided. The server may include a transceiver, a control unit, and a memory.
[0031] The transceiver can be configured to receive tagged data and send enhanced image data to the screen of the user device.
[0032] The control unit can be configured to perform a retrieval function, which is configured to retrieve artificial image data linked to labeled data from an artificial image database, wherein the artificial image data describes at least one food component of the food held in food packaging; a determination function, which is configured to determine artificial image spatial reference points based on visual labels; and a first generation function, which is configured to generate enhanced image data by combining real image data, artificial image data, and artificial image spatial reference points.
[0033] The control unit can also be configured to perform an extraction function, which is configured to extract spatial measurement data from real image data, wherein the spatial measurement data can be linked to the measurement of visual markers; and a second generation function, which is configured to generate calibrated artificial image data by performing spatial calibration of the artificial image data by comparing the spatial measurement data with spatial reference data linked to visual markers provided by a spatial reference database.
[0034] The real image data can further describe the physical container. The control unit can also be configured to perform a second determining function, which is configured to determine the geometric data of the physical container in the real image data; a third generating function, which is configured to generate adjusted artificial image data by adjusting the artificial image data based on the geometric data of the physical container; and a fourth generating function, which is configured to generate enhanced image data by combining real image data, adjusted artificial image data, and artificial image spatial reference points.
[0035] In addition to the attributes mentioned above, other attributes can be added and used in combination with or separately from the attributes mentioned above.
[0036] Other objects, features, aspects, and advantages of the invention will become apparent from the following detailed description and the accompanying drawings. Unless otherwise expressly stated, the same features and advantages described with respect to one aspect also apply to the other aspects. Attached Figure Description
[0037] Embodiments of the invention will now be described by way of example with reference to the accompanying schematic diagrams, wherein...
[0038] Figure 1 This is a schematic diagram showing a system used to facilitate the provision of food information;
[0039] Figure 2A Examples of scenes with real image data are shown;
[0040] Figure 2B and 2C Two examples of scenes with enhanced image data are shown;
[0041] Figure 3 This is a flowchart illustrating the steps of a method for facilitating the provision of food information;
[0042] Figures 4A to 4C It shows different ways of providing visual markings on food packaging;
[0043] Figure 5 The server is displayed and is configured to facilitate the provision of food information. Detailed Implementation
[0044] Figure 1 This is a schematic diagram illustrating a system 100 used to facilitate the provision of food information. Food packaging 102 may be provided. Food packaging 102 can hold food. Food may include one or more food components. In this example, additional food packaging 122 is also provided with additional visual markings 124. It may also be multiple additional food packages. In the case of multiple food packages, two or more food packages may hold the same food. They may also hold different foods.
[0045] Physical container 126 may also be provided, as shown in this example. It may also be one of multiple physical containers provided. Physical container 126 may be a bowl, pot, glassware, or any other physical container capable of holding food. Physical container 126 may differ from food packaging 102.
[0046] Food packaging 102 may have visual markings 104. It may also have a QR code 402. About Figures 4A to 4C Visual marker 104 and QR code 402 are further described.
[0047] System 100 may also include user equipment 108. The user equipment may be a mobile device, such as a smartphone, tablet, or any other electronic device suitable for this purpose. It may also be smart glasses, in which a screen is integrated into the lenses of the glasses.
[0048] User equipment 108 may include camera 106. Camera 106 may be provided as an external camera connected to user equipment 108 in an appropriate manner.
[0049] User equipment 108 may include screen 110. Even if screen 110 is shown as part of user equipment 108, it may also be provided as an external screen and connected to user equipment 108 in an appropriate manner.
[0050] The camera 106 of the user equipment 108 can be used to capture real-world image data. This real-world image data can describe one or more visual markings 104 provided on the food packaging 102. The real-world image data can further describe one or more food packages. It can also describe one or more physical containers.
[0051] Tag data 112 can be extracted from real image data via user device 108. Tag data 112 can be used to retrieve artificial image data 114 linked to tag data 112 from artificial image database 116. Artificial image database 116 can be provided locally on user device 108. It can also be provided to user device 108 from an external source. Artificial image data 114 can be an illustration of the food components included in a food package. In other words, it can be an illustration of the contents of food package 102. It can also be an illustration or video related to food package 102, such as a guide on how to open the food package. It can also be an illustration related to the maker, such as a company mascot or logo.
[0052] Artificial image spatial reference points can be determined. These reference points can be determined based on the position of visual marker 104.
[0053] Augmented image data can be generated by combining real image data, artificial image data, and artificial image spatial reference points. Augmented image data can be interpreted as images displaying real-life objects (such as food packaging or physical containers) and animated objects from an artificial image database. Artificial image spatial reference points can be used to align the real image data and the artificial image data. In a simpler version of System 100, the step of determining the artificial image spatial reference points can be skipped. Instead, a pre-determined reference point (such as the center of the screen) can be used to determine where to place the artificial image data.
[0054] Enhanced image data can be provided to the screen 110 of user device 108.
[0055] Optionally, a spatial reference database 120 may be provided. The spatial reference database 120 may provide spatial reference data 118 linked to food packaging 102 and / or visual markers 104. The spatial reference data may be the geometric dimensions of the food packaging or visual markers. To determine the type of packaging described, this information can be linked to visual markers or other codes provided on the packaging. By knowing the type of packaging (e.g., Tetra Brik 1000ml Slim), spatial reference data linked to the described packaging can be retrieved. The advantage of using packaging for spatial alignment instead of visual markers is that the packaging is larger, and thus different spatial reference points can be placed further apart, which can provide improved spatial alignment of artificial and real image data.
[0056] Spatial measurement data can be extracted from real image data. As mentioned above, the spatial measurement data can be linked to measurements of food packaging 102 and / or to measurements of visual markers 104. Calibrated artificial image data can be generated by comparing the spatial measurement data with spatial reference data.
[0057] Enhanced image data can be generated using real image data, calibrated artificial image data, and artificial image spatial reference points. In this way, the dimensions of artificial objects can be calibrated to match the dimensions of food packaging 102 and / or visual markers 104.
[0058] When the physical container 126 is provided in real image data, the geometric data of the physical container 126 can be determined, for example, by comparing the physical container 126 with spatial reference data of the food packaging 102 and / or visual markers 104.
[0059] Figure 2A A scenario based on real image data is illustrated by way of example. In this example, food packaging 102 with visual marker 104 and physical container 126 are visualized.
[0060] Figure 2B A scene based on enhanced image data is illustrated by way of example. It shows food held in food packaging 102, but in a first form 202 within a physical container 126. It can also be as follows: Figure 2C The second form 205 shown indicates that, Figure 2C The same food packaging 102 and the same food are shown, but in a second form 204 with a different volume. The first and second forms can be interpreted as processed and unprocessed forms of the food.
[0061] As an example, food packaging 102 could be cream packaging. Figure 2B In the image, the cream is visualized as unwhipped cream. Figure 2C In this context, the cream is visualized as whipped cream. In this case, the first form 202 of the product has a smaller volume than the second form 204.
[0062] As another example, food packaging 102 could be orange juice packaging. The first form could be unprocessed oranges. The second form could be a processed form of orange juice. In this case, the product in the first form has a larger volume than the product in the second form.
[0063] Although not in Figures 2A to 2C While any of these images may be shown, enhanced image data can depict multiple food packages or food components within the same scene. This can be used to illustrate the mixing of two food products.
[0064] As another example, food can be described by its individual food components.
[0065] Figure 3 This is a flowchart illustrating the steps of method 300 for promoting the provision of food information.
[0066] In the first step 302, food packaging may be provided, wherein the food packaging may have visual markings.
[0067] In the second step 304, the real image data describing the visual markers can be captured by the camera of the user device.
[0068] In the third step 308, labeled data can be extracted from the real image data.
[0069] In the fourth step 310, artificial image data linked to the labeled data can be retrieved from an artificial image database, wherein the artificial image data can describe at least one food component of the food held in the food packaging.
[0070] Alternatively, steps three and four can be skipped by checking whether the tagged data has been retrieved at step 306. In this case, method 300 can be repeated continuously to obtain a real-time feed of enhanced image data on the user's device screen. In other words, step three may only need to be performed once. Furthermore, step four may only need to be performed once.
[0071] In step 512, artificial image spatial reference points can be determined based on visual markers.
[0072] In step 614, enhanced image data can be generated by combining real image data, artificial image data, and artificial image spatial reference points.
[0073] In step 7, 316, the enhanced image data can be provided to the screen of the user device.
[0074] Optionally, in step 318, spatial measurement data can be extracted from real image data, wherein the spatial measurement data can be linked to measurements of food packaging and / or measurements of visual markings.
[0075] Optionally, in the ninth step 320, spatial calibration of the artificial image data can be performed by comparing the spatial measurement data with spatial reference data linked to food packaging and / or linked to visual markers provided by a spatial reference database to generate calibrated artificial image data.
[0076] Optionally, in step 614, enhanced image data can be generated by combining real image data, calibrated artificial image data, and artificial image spatial reference points.
[0077] Optionally, in the first step 302, 322 additional food packaging may be provided, wherein the additional food packaging may have additional visual markings.
[0078] The real image data can describe visual markers and additional visual markers.
[0079] The labeled data can be based on visual tags and additional visual tags.
[0080] The artificial image data can describe at least one food component of the food retained in the food packaging and at least one additional food component of the additional food retained in the additional food packaging.
[0081] Artificial image spatial reference points can be based on visual markers and additional visual markers.
[0082] Spatial measurement data can be linked to measurements of food packaging, additional food packaging, visual markings, and / or additional visual markings. Furthermore, spatial reference data can be linked to food packaging, additional food packaging, visual markings, and / or additional visual markings.
[0083] Optionally, in the first step 302, 324 physical containers can be provided, wherein the real image data further describes the physical containers. Optionally, in the tenth step, the geometric data of the physical containers in the real image data can be determined. Optionally, in the eleventh step, adjusted artificial image data can be generated by adjusting the artificial image data based on the geometric data of the physical containers. Optionally, in the sixth step 314, enhanced image data can be generated by combining the real image data, the adjusted artificial image data, and the artificial image spatial reference points.
[0084] Optionally, in the tenth step, geometric data is determined by comparing spatial reference data linked to food packaging and / or linked to visual markers with the physical container.
[0085] Figures 4A to 4C An example of how visual marking 104 can be set on food packaging 102 is shown. Visual marking 104 can be provided together with a QR code 402 (e.g., a QR code) or separately.
[0086] Figure 4A An example is shown where visual markers 104 are provided next to a QR code 402 on one side of the food packaging 102. They can be placed on either side of the food packaging 102.
[0087] Figure 4B An example is shown where visual marker 104 is provided within QR code 402.
[0088] Figure 4CAn example is shown where visual markings 104 are included in the decoration 404 of food packaging 102. In other words, visual markings 104 may be, for example, a mark already printed on the food packaging 104.
[0089] Figure 5 A schematic diagram of server 500 is shown. Server 500 is configured to facilitate the provision of food information. Server 500 includes transceiver 502, control unit 504, and memory 508.
[0090] Transceiver 502 is configured to communicate with other devices. Transceiver 502 can be configured to receive tag data and send enhanced image data to the screen of a user equipment.
[0091] Control circuitry 504 can be configured to control the functions and operations of server 500. Control circuitry 504 may include processor 506, such as a central processing unit (CPU). Processor 506 can be configured to execute program code stored in memory 508 to perform the functions and operations of server 500.
[0092] The control circuit 504 can perform a retrieval function 510, which is configured to retrieve artificial image data linked to labeled data from an artificial image database, wherein the artificial image data can describe at least one food component of the food held in food packaging.
[0093] Control circuit 504 can perform determination function 512, which is configured to determine artificial image spatial reference points based on visual markers.
[0094] The control circuit 504 can perform a first generation function 514, which is configured to generate enhanced image data by combining real image data, artificial image data, and artificial image spatial reference points.
[0095] Optionally, the control circuit 504 may perform an extraction function 516 configured to extract spatial measurement data from real image data, wherein the spatial measurement data is linked to measurements of visual markers and / or packaging described in the real image data.
[0096] Optionally, the control circuit 504 may perform a second generation function 518, which is configured to perform spatial calibration of the artificial image data by comparing the spatial measurement data with spatial reference data linked to visual markers and / or packaging provided by a spatial reference database, in order to generate calibrated artificial image data.
[0097] Optionally, the control circuit 504 may perform a second determining function 520, which is configured to determine the geometric data of the physical container in the real image data.
[0098] Optionally, the control circuit 504 may perform a third generation function 522, which is configured to generate adjusted artificial image data by adjusting the geometric data of the artificial image data based on the physical container.
[0099] Optionally, the control circuit 504 may perform a fourth generation function 524, which is configured to generate enhanced image data by combining real image data, adjusted artificial image data, and artificial image spatial reference points.
[0100] Optionally, the control circuit 504 can be configured to extract labeled data from real image data via a second extraction function.
[0101] Server 500 can be set up within the user's device.
[0102] As can be seen from the above description, although various embodiments of the present invention have been described and illustrated, the present invention is not limited thereto, but may also be implemented in other ways within the scope of the subject matter defined in the following claims.
Claims
1. A method (300) for facilitating the provision of food information, comprising: Provide food packaging (102), wherein the food packaging (102) is provided with visual markings (104). Provide (324) physical containers (126), The user equipment (108) captures real image data describing the visual marker (104) and the physical container (126) using its camera (106). Extract labeled data from the real image data (112). Artificial image data (114) linked to the labeled data (112) is retrieved from the artificial image database (116), wherein the artificial image data (114) describes at least one food component of the food held in the food packaging (102). Artificial image spatial reference points are determined based on the visual markers (104). Determine the geometric data of the physical container (126) in the real image data. Adjusted artificial image data is generated by adjusting the artificial image data (114) based on the geometric data of the physical container (126), and Enhanced image data is generated by combining the real image data, the adjusted artificial image data, and the artificial image spatial reference points. The enhanced image data is provided to the screen (110) of the user equipment (108).
2. The method according to claim 1, wherein the method further comprises: Spatial measurement data is extracted from the real image data, wherein the spatial measurement data is linked to the measurement of the food packaging (102) and / or the measurement of the visual marker (104). Spatial calibration of the artificial image data (114) is performed by comparing the spatial measurement data with spatial reference data (118) provided by the spatial reference database (120) that is linked to the food packaging (102) and / or linked to the visual markers (104), to generate calibrated artificial image data. The enhanced image data is generated by combining the real image data, the calibrated artificial image data, and the artificial image spatial reference points.
3. The method according to claim 1 or 2, wherein the step of providing (302) food packaging (102) further includes providing additional food packaging (122), wherein the additional food packaging (122) is provided with additional visual markings (124). The real image data described therein describes the visual marker (104) and the additional visual marker (124). The tag data (112) is based on the visual tag (104) and the additional visual tag (124). The artificial image data (114) described at least one food component of the food retained in the food package (102) and at least one additional food component of the additional food retained in the additional food package (122). The artificial image spatial reference point is based on the visual marker (104) and the additional visual marker (124).
4. The method according to claim 1 or 2, wherein the spatial measurement data is linked to the measurement of the food packaging (102), the measurement of the additional food packaging (122), the measurement of the visual marker (104), and / or the measurement of the additional visual marker (124), and The spatial reference data is linked to the food packaging (102), the additional food packaging (122), the visual marker (104), and / or the additional visual marker (124).
5. The method according to claim 1 or 2, wherein the physical container (126) comprises a bowl.
6. The method according to claim 1 or 2, wherein the geometric data is determined by comparing spatial reference data linked to the food packaging (102) and / or linked to the visual marker (104) with the physical container (126).
7. The method according to claim 1 or 2, wherein the visual mark (104) is disposed together with the QR code (402) on one side of the food packaging (102), wherein the QR code (402) is configured to launch an application on the user device (108).
8. The method according to claim 7, wherein, The QR code (402) includes a QR code.
9. The method according to claim 7, wherein the QR code (402) includes a unique identifier of the food packaging (102).
10. The method according to claim 1 or 2, wherein the visual mark (104) is included in the decoration (404) of the food packaging (102).
11. The method according to claim 1 or 2, wherein, The artificial image data (114) describes the food in a first form (202), and the food is held in the food packaging in a second form (204), wherein the first volume of the food in the first form (202) is different from the second volume of the food in the second form (204).
12. The method according to claim 1 or 2, wherein the artificial image data (114) depends on the geographic location of the user equipment (108).
13. The method according to claim 1 or 2, wherein the artificial image data (114) depends on the user's profile, wherein the profile includes user setting data for different food components.
14. A server (500) configured to facilitate the provision of food information, the server (500) including a transceiver (502), a control unit (504) and a memory (508). in, The transceiver (502) is configured to: Receive tag data (112). Send enhanced image data to the screen (108) of the user device. The control unit (504) is configured to perform: A retrieval function (510) is configured to retrieve artificial image data (114) linked to the labeled data (112) from an artificial image database (116), wherein the artificial image data (114) describes at least one food component held in the food packaging (102); The determination function (512) is configured to determine an artificial image spatial reference point based on visual markers (104), wherein the visual markers (104) are described by real image data captured by the user device's camera. A second determining function (520) is configured to determine the geometric data of a physical container (126) in real image data, which also describes the physical container (126). A third generation function (522) is configured to generate adjusted artificial image data by adjusting the artificial image data (114) based on the geometric data of the physical container (126), and The fourth generation function (524) is configured to generate enhanced image data by combining the real image data, the adjusted artificial image data (114), and the artificial image spatial reference point.
15. The server (500) of claim 14, wherein the control unit (504) is further configured to perform: Extraction function (516), configured to extract spatial measurement data from the real image data, wherein the spatial measurement data is linked to the measurement of the visual marker (104), The second generation function (518) is configured to perform spatial calibration of the artificial image data (114) by comparing the spatial measurement data with spatial reference data (118) provided by the spatial reference database (120) that is linked to the visual markers (104), in order to generate calibrated artificial image data.