Method and device for evaluating sealing performance of carton package

Abstract

A method (800) for evaluating a seal (200, 202) of a carton package (114) arranged to contain a food product (FP) is disclosed. The seal (200, 202) is produced using an ultrasonic sealing technique, the method comprising: capturing (802) an image data set (500) depicting the seal (200, 202), where the image data set (500) comprises a first subset of data (600) associated with a first color channel and a second subset of data (602) associated with a second color channel, an adhesive section (702a, 702b) is identified (804) by using the first subset of data (600), and a non-adhesive section (704) is identified (806) by using the second subset of data (602).

Description

Technical Field

[0001] The present invention relates to food packaging technology. More particularly, the present invention relates to evaluating the sealability of carton packages made by using ultrasonic sealing technology. Background Art

[0002] Today, it is well known that heat induction sealing is used to form the seals, sometimes also called welds, in carton packaging. In roll-fed carton filling machines, it is common practice to form a tube by sealing the opposite ends of a web of packaging material together. Usually, this step is called longitudinal sealing. Once the tube is formed, the food (e.g., milk) is fed into the tube from above. At the lower end of the tube, a transverse seal is made. By making two transverse seals simultaneously and cutting between the two seals, a bag containing the food is formed from the lower end of the tube. In a subsequent step, these bags can be formed into, for example, a brick-shaped package by folding the bag.

[0003] Since induction heat sealing requires a layer in the packaging material that generates heat in response to the magnetic field generated by the inductor of the transverse heat sealing device, other sealing technologies have been developed in order to also be able to provide reliable and effective sealing for packaging materials without, for example, an aluminum layer. One such technology is ultrasonic sealing. Rather than generating heat by inducing eddy currents in the packaging material, which causes the inner and outer plastic layers of the packaging material to melt, ultrasonic sealing devices generate heat by using ultrasonic waves that interact with the plastic material to generate heat.

[0004] To protect the food contained in the package, both the longitudinal seal and the two transverse seals (one at the upper end and one at the lower end of the package) should be made in such a way that the food is not released from the package, and should also prevent bacteria, germs or other microorganisms from entering the package. In order to be able to provide cost-effective packaging, thousands of packages are produced every hour. Due to the high speed, there is less room for making reliable seals. In other words, in order to be able to generate sufficient heat in the transverse sealing area of ​​the package while still meeting the time constraints required to provide high speeds, the combined packaging materials and the settings of the transverse sealing equipment should be appropriately set. In addition, in order to ensure that the packages produced have reliable transverse seals, samples are regularly taken for quality assessment.

[0005] Quality assessment can be performed in different ways. Today, manually assessing the seal using a microscope is a common practice. By using a microscope in combination with a quality checklist, it is possible to detect deviations in the packaging that could be caused by incorrect settings of the transverse sealing equipment or packaging materials that do not meet the set requirements. Once quality issues have been identified, the transverse sealing equipment and packaging materials can be further analyzed in detail.

[0006] Today's quality assessments, with very few exceptions, identify the risk that the seal of the package does not protect the food from the surrounding environment and that there is a risk of leakage. However, as the speed of the filling machine increases, less and less time is available for transverse sealing of the package, which in turn increases the risk of insufficient sealing. In addition, increased cost-efficiency requirements (which lead to, for example, thinner layers of packaging material) may also increase the risk of insufficient sealing. In addition, increased environmental requirements (which make certain materials such as aluminum foil less suitable for use, for example) can also lead to an increased risk of insufficient sealing. Therefore, even if the sealing equipment of the filling machine is reliable, the growing need also leads to the fact that these reliable sealing equipment is preferably combined with a reliable seal quality assessment to ensure that situations that lead to insufficient sealing can be identified when they occur. Once identified, action can be taken, which has the positive effect of reducing the risk of insufficient transport packaging and also reducing product waste. Summary of the invention

[0007] It is an object of the present invention to at least partially overcome one or more of the above limitations of the prior art. In particular, it is an object of the present invention to provide a reliable and cost-effective method for evaluating the seal of a carton package.

[0008] According to a first aspect, there is provided a method for evaluating a seal of a carton package arranged to contain a food product, wherein the seal is produced by using an ultrasonic sealing technique, the method comprising:

[0009] capturing an image data set depicting the seal, wherein the image data set includes a first data subset associated with a first color channel and a second data subset associated with a second color channel,

[0010] identifying the adhesion segment by using the first data subset, and

[0011] Non-adherent segments are identified using the second data subset.

[0012] The advantage of using different subsets to identify adhered segments (i.e., segments where the first and second sides of the packaging material are adhered to each other, e.g., because the plastic layers on both sides have melted and merged together) is that both adhered segments and non-adhered segments are clearly identified. In other words, non-adhered segments are not considered as any segment that is not an adhered segment. By using this approach and actively determining adhered and non-adhered segments, a more reliable seal quality assessment can be achieved.

[0013] Another advantage is speed. Unlike commonly used methods for induction heat seal quality assessment, in which the imprints formed by the inductor coil ridges are identified, the method proposed herein exploits the fact that no such imprints need to be identified when evaluating ultrasonic seals.

[0014] Since the heat generation achieved by using ultrasonic sealing technology is different from the heat generation achieved by using induction heat sealing technology, the packaging material is less mechanically affected by the ultrasonic sealing technology because there is less contact between the sealing device and the packaging material. Therefore, a reliable seal assessment can be performed by analyzing the first and second subsets related to different color channels, because these color channels in turn may be related to the impact on light when passing through the adhesive segment and the non-adhesive segment, respectively.

[0015] The method may further include:

[0016] identifying a seal section by using the first data subset and the second data subset, wherein the seal section corresponds to a top fin, a bottom fin, or a longitudinal seal section of the carton package,

[0017] The adhesive section and the non-adhesive section are both contained in the sealing section.

[0018] The advantage of using different subsets of the image data set to identify the adhered and non-adhered segments is that the two can be combined at a later stage to provide a reliable identification of the sealed segment. An adhered segment can be a segment where both sides of the packaging material merge together. On the other hand, a non-adhered segment can be a segment where both sides of the packaging material abut each other but do not merge together. The non-adhered segment can be used to extract feature lines, such as product lines and cut lines, by using the average value of the lines formed by the edges of the adhered and non-adhered segments. In this way, a more robust line fitting is achieved.

[0019] The image dataset may be captured by using a camera positioned on a first side of a seal of the package, the method further comprising:

[0020] The seal is illuminated by using a light source provided on a second side of the seal, wherein the second side of the seal is opposite to the first side of the seal, such that light emitted from the light source passes through the seal of the package into the camera.

[0021] The light provided may be natural light, diffuse light, or polarized light. Since different types of light may be associated with different benefits, the image data set may include a series of image data sets captured with natural light, diffracted light, and polarized light. For all light options, a first and a second data subset may be captured.

[0022] The light source is one or more light emitting diodes (LEDs) that emit light having at least one specific frequency, wherein a first frequency range of a first color channel and / or a second frequency range of a second color channel is set based on the at least one specific frequency of the one or more LEDs.

[0023] The advantage of using LEDs is that they can be manufactured in a cost-effective manner and can also be manufactured to produce light with a specific frequency.

[0024] The first frequency range of the first color channel and / or the second frequency range of the second color channel are set based on properties of the packaging material.

[0025] By adapting the light source to the specific details of the packaging material, a more reliable assessment of seal quality can be achieved.

[0026] The image dataset may be captured in multiple versions, wherein the multiple versions have different light settings, wherein the light settings include one or more specific frequencies of light emitted from the light source and / or one or more amplitudes of light emitted from the light source.

[0027] As shown above, in addition to the multiple versions, different types of light can also be used.

[0028] The packaging material may include a non-metallic light blocking layer, wherein the non-metallic light blocking layer is a cellulose-based light blocking layer, and the cellulose-based light blocking layer is suitable for blocking light having a frequency that causes microbial growth and / or vitamin loss in the food contained in the carton packaging.

[0029] The advantage of using a non-metallic photoresist layer is that it can reduce the impact of packaging materials on the environment.

[0030] The method may further include:

[0031] providing a reference object next to a seal of the carton package, wherein the reference object has a reference length and / or a reference width,

[0032] identifying a reference object depicted in the image data,

[0033] The absolute length and / or the absolute width of the adhered section and / or the non-adhered section is determined by using the reference length and / or the reference width.

[0034] The method may further include:

[0035] A substance such as ink is applied to the seal prior to capturing the image data set.

[0036] By applying a substance to the seal, the light does not pass through the adhesive section and the non-adherent section, but through the adhesive section to which the substance is applied and the non-adherent section to which the substance is applied. This has the advantage that the substance also affects the passage of light, and in different ways for different subsets. Therefore, by judiciously choosing the substance and the frequency of the light in combination with the properties of the packaging material, a reliable quality assessment of the seal can be made.

[0037] The image data set may further include a third data subset associated with a third color channel, and the method may further include:

[0038] By identifying the segments affected by the substance using the third data subset,

[0039] Therein, the step of identifying the sealing section is performed by using the first, second and third data subsets.

[0040] By using the third data subset and selecting the substance according to the third color channel linked to the data subset, it is easier to find the segment affected by the substance. The segment affected by the substance may be an adhesion segment.

[0041] The sealing section may comprise overlapping sub-sections, wherein the transverse seal and the longitudinal seal overlap.

[0042] The challenge with carton packages with longitudinal and transverse seals is that there are sections in the package where the longitudinal and transverse seals overlap. The three-layer packaging material presents challenges and the risk of insufficient sealing cannot be ignored. Therefore, reliable seal quality assessment is particularly important for packages with such overlapping sub-sections.

[0043] The method may further comprise, prior to the step of capturing the image dataset,

[0044] Remove the food contained in the packaging,

[0045] unfold the package so that the seal is exposed, and

[0046] The packaging is dissolved so that the cardboard layer of the packaging material is removed.

[0047] An advantage of removing the paperboard layer is that the remaining layer can be transparent, allowing light to pass through the seal.

[0048] According to a second aspect, there is provided an apparatus for evaluating a seal of a carton package arranged to contain a food product, wherein the seal is produced by using an ultrasonic sealing technique, the apparatus comprising:

[0049] a camera configured to capture an image data set depicting the seal, wherein the image data set includes a first data subset associated with a first color channel and a second data subset associated with a second color channel; and

[0050] A control unit including a processor and a memory is configured to identify adhered segments in the image data set by using the first data subset and to identify non-adhered segments in the image data set by using the second data subset.

[0051] The same advantages described above in connection with the first aspect also apply to this second aspect.

[0052] The device may also include:

[0053] a light source arranged to illuminate the sealing portion,

[0054] wherein the camera may be placed on a first side of a seal of the package and a light source is provided on a second side of the seal, wherein the second side of the seal is opposite to the first side of the seal,

[0055] Light emitted from the light source is thereby allowed to pass through the seal of the package and into the camera.

[0056] The light source is one or more light emitting diodes (LEDs) that emit light having at least one specific frequency, wherein a first frequency range of a first color channel and / or a second frequency range of a second color channel is set based on the at least one specific frequency of the one or more LEDs.

[0057] Other objects, features, aspects and advantages of the present invention will also become apparent from the following detailed description and accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Embodiments of the invention will now be described, by way of example, with reference to the accompanying schematic drawings, in which

[0059] Figure 1 A roll-fed filling machine is generally shown.

[0060] Figure 2 The packaging is shown in more detail.

[0061] Figure 3 The general concept of seal quality assessment is shown.

[0062] Figure 4 An apparatus for evaluating a seal is generally shown.

[0063] Figure 5 Shown by Figure 4 An example of an image dataset captured by the apparatus shown in FIG.

[0064] Figure 6 Shows Figure 5 The first, second and third subsets of the image dataset shown in .

[0065] Figure 7 Shows Figure 5 The image dataset shown in , where the extracted features are superimposed.

[0066] Figure 8 is a flow chart illustrating a method for evaluating a seal. DETAILED DESCRIPTION

[0067] refer to Figure 1, schematically shows a filling machine 100 (also called a packaging machine). As shown, a reel 102 of packaging material PM may be provided. The packaging material PM typically comprises a plurality of layers, such as a cardboard layer for providing stability and environmental benefits, an inner plastic layer for avoiding direct contact between the cardboard layer and the food FP, and an outer plastic layer for protecting the cardboard layer from the surrounding environment. When producing a package, the packaging material PM is provided by unwinding the reel 102, thereby providing a roll 104. The roll 104 may be sterilized or subjected to any other treatment to remove microorganisms. In Figure 1 In the example shown, a sterilization device 106 is provided on top of the filling machine 100. The sterilization device 106 may be a LVEB device configured to kill microorganisms by using a low voltage electron beam. Another possibility is to use a hydrogen peroxide bath to kill microorganisms.

[0068] After the web 104 is treated to remove microorganisms, the web 104 may be formed into a tube. Once formed into the tube, the food FP may be filled into the tube from above through a filling tube 108. To ensure that the tube is sealed together longitudinally, a longitudinal sealing device 110 may be provided.

[0069] After the longitudinal seal, the tube is fed in the feed direction FD into a transverse sealing device 112 where transverse seals are made. Two transverse seals are usually made simultaneously so that the upper seal of one package and the lower seal of the other package are formed simultaneously. Once the two seals are completed, a cut is made between the two seals so that the lowermost package can be released from the tube. After providing the transverse seals, the package 114 is folded and formed into its final shape, for example a brick shape.

[0070] Although a roll-fed filling machine is shown, other types of filling machines may also be used. For example, another option is a so-called blank-fed filling machine. In this type of machine, a blank (i.e., a lay-flat sleeve of packaging material) is provided and formed into a package containing food.

[0071] Figure 2 The package 114 is shown in more detail. As shown, after the package 114 is fed from the transverse sealing device 112, a first seal 200 may be provided at one end of the package 114 and a second seal 202 may be provided at the other end. In a subsequent step, a so-called folding device ( Figure 1 In the embodiment shown in Figure 11, the package 114 can be folded into its final shape. For example, a flat top and a flat bottom can be formed, and the transverse seals can be folded down so that they are adjacent to the flat top and the flat bottom, respectively. The packaging material PM can be provided with weakening lines to facilitate folding.

[0072] In order to ensure that the transverse seal meets set quality requirements, an image dataset depicting the transverse seal may be captured and analyzed. Figure 3 A method for such an analysis is shown. As shown, in a first step, seal image data can be recorded, i.e. an image data set can be captured. This step can be performed in various ways. One of these ways is to take samples in the produced packaging and analyze these samples in detail. The number of samples may vary from filling machine to filling machine and the sampling frequency may depend on, for example, the packaging material PM used. For carton packaging comprising multiple layers, where one of these layers is made of cardboard, it has proven to be beneficial to dissolve the packaging to remove the cardboard layer. Once the cardboard layers are removed, the plastic layers that adhere to each other and thus form the transverse seal can be more easily analyzed. In addition, since the plastic layers are usually transparent, dissolving the packaging to remove the cardboard layer also has the advantage that light can be emitted through the remaining layers of the packaging material PM.

[0073] In the image analysis step, the image data set captured in the seal image recording step may be analyzed to find different deviations. For example, if the width of the transverse seal is found to be below a preset threshold, a notification may be sent to an operator.

[0074] In addition to identifying deviations that may indicate quality issues, the features extracted in the image analysis step can also be fed into the seal quality characterization step. In this step, the different features extracted from the image analysis step can be further analyzed.

[0075] Data from the seal quality characterization step can be input to the statistical evaluation step. In the statistical evaluation step, data from multiple packages can be used to look for deviations over time, for example. As shown in the figure, the statistical evaluation step can be configured to interact directly with the seal image recording step. The benefit of this is that the settings used can be adjusted to pinpoint certain features of the seal that require additional data. For example, from the statistical evaluation step, input can be provided regarding the frequency used to irradiate the sample. Capturing more image data sets using this frequency can result in being able to perform more reliable statistical analysis. The communication between the seal image recording step and the statistical evaluation step can follow a pre-programmed pattern or can be based on a machine learning / artificial intelligence approach (ML / AI), where the communication between the two steps is allowed to evolve over time. The output of the statistical evaluation step can be an updated machine setting for the filling machine including the transverse sealing device.

[0076] Figure 3 The concept shown in can be implemented in different ways. For example, Figure 4 Generally shown for evaluation Figure 1 The device 400 for producing transverse seals 200 , 202 of packages 114 produced by the filling machine 100 shown in FIG.

[0077] The package 114 may be placed on a work station 402 so that an image data set depicting the seals 200, 202 may be obtained. Figure 4 , the second sealing part 202 is being analyzed by example. The workbench 402 may be provided with an opening so that the light L emitted from the light source 404 (e.g., LED) can fall on the sealing parts 202, 202 without being blocked by the workbench 402. The workbench 402 may include a movable member 406 so that the sealing parts 202, 202 can be moved relative to the light source 404 and the camera 408. As shown, the light source 404 may be placed at the lower part of the workbench 402 so that the light L can fall on the sealing parts 200, 202 from below, or placed towards the second side S-2 of the sealing part in a different manner. The camera 408 may be placed above the sealing parts 200, 202, i.e., facing the first side S-1 of the sealing part, so that the light L emitted from the light source 404 can pass through the sealing parts 200, 202, and then be captured by the camera 408 and converted into an image data set.

[0078] The image data set may be transmitted from the camera 408 to a control unit 410. This may include a processor 412 and a memory 414 configured to process the image data set such that adhered segments in the image data set are identified by using a first data subset associated with a first color channel, and non-adhered segments in the image data set are identified by using a second data subset associated with a second color channel, as will be further explained below.

[0079] The communication between the camera 408 and the control unit 410 can be wireless, as shown. Although not shown, in order to provide such communication, the camera 408 can be equipped with a data communication module, and in the same way the control unit 410 can include such a module. Alternatively, although not shown, the camera 408 and the control unit 410 can be components of the same unit. Another option (also not shown) is that the control unit 410 communicates with the back-end server, so that some of the data processing can be performed in the control unit 410 that can be placed on site, and some of the data processing can be performed in the back-end server (i.e., a remote data processing device). It is also possible to let the control unit 410 act as a gateway to transmit the image data set to the back-end server so that all data processing is performed in the back-end server.

[0080] Figure 5 An example of an image dataset 500 depicting a seal 202 is shown. As shown, in order to be able to convert the lengths identified in the image dataset 500 into absolute measurements, such as distances in millimeters, a reference object 502, such as a ruler, may be provided. The reference object 502 may be formed Figure 4 A portion of the movable member 406 is shown in FIG.

[0081] Figure 5The image data set 500 shown in the figure may include multiple data subsets. For example, as shown in the figure, the image data set 500 may include a first subset 600, a second subset 602 and a third subset 604. Each of these subsets may correspond to a color channel. For example, three subsets may correspond to the color channels red, green and blue. In other words, the image data set 500 may include a subset associated with a specific light frequency range.

[0082] The benefit of analyzing different subsets separately is that different features may be reflected in different frequency ranges in different ways. Therefore, by analyzing different subsets separately and then combining them, features can be identified more reliably than analyzing the image dataset 500 separately.

[0083] The different frequency ranges of the first to third data subsets may be adjusted relative to the frequency range of the light L emitted from the light source. By adjusting the light L in this manner, and also taking advantage of the fact that the wavelength of the light is known when analyzing the first to third data subsets 600, 602, 604, features of the seal, such as adhered sections and non-adhered sections, may be more reliably identified. The frequency of the light L emitted from the light source may be set by changing the settings of the light source. Another option (although not shown) is to place a filter between the light source and the seal so that only light with one or a few specific frequencies is allowed to pass.

[0084] Evaluating ultrasonic sealing by analyzing a subset as described above has proven to be particularly advantageous. One reason for this is that the seal pattern formed by an ultrasonic sealing device is different from the seal pattern formed by an induction heat sealing device because, in some cases, the contact between the ultrasonic sealing device and the packaging material is less than that between the induction heat sealing device and the packaging material, i.e., the ultrasonic sealing device applies less pressure to the packaging material.

[0085] Once features are extracted from subsets 600, 602, 604, these features can be superimposed on image data set 500, thereby forming image data set 700 with features. As shown, the edge between adhesion section 702, 702b and non-adhesion section 704 can be emphasized by superimposed lines. In the example shown, non-adhesion section 704 is a section where an incision can be provided to separate two packages from each other. In order to provide relevant information to the operator, the superimposed features are not limited to emphasizing particularly relevant lines or regions, and can also include additional information in the form of text or numbers. For example, the first width of the non-adhesion section can be marked and a measurement value can be associated with it, and text "Z1" is provided here. In a similar manner, the second width of the non-adhesion section can be marked and text "Z2" can be provided.

[0086] Figure 8is a flow chart illustrating a method 800 for evaluating a seal 200, 202. In a first step 802, an image dataset 500 may be captured. In a second step 804, adhered segments 702a, 702b may be identified. In a third step 806, a non-adhered segment 704 may be identified.

[0087] Optionally, in a fourth step 808, a sealing section may be identified by using the first and second subsets, the sealing section may correspond to a top fin, a bottom fin and / or a longitudinal seal.

[0088] Optionally, in a fifth step 810 , the sealing section may be illuminated by using the light source 404 so that light L emitted from the light source may pass through the sealing portions 200 , 202 of the package 114 into the camera 408 .

[0089] Optionally, in a sixth step 812, a reference object 502 may be provided next to the seal 200, 202, wherein the reference object has a reference length and / or a reference width. In a seventh step 814, the reference object depicted in the image data may be identified. In an eighth step 816, the absolute length and / or absolute width of the adhered segments 702a, 702b and / or the non-adhered segment 704 may be determined by using the reference length and / or the reference width.

[0090] Optionally, a substance such as ink may be applied to the seal before capturing the image data set in a ninth step 818. By applying the substance, the light L emitted from the light source may be affected in different ways in different color channels, resulting in, for example, the adhered and / or non-adhered sections being more secure and / or more reliable.

[0091] Optionally, in a tenth step 820, the segments affected by the substance may be identified using the third data subset 604. By linking the segments affected by the substance to one of the data subsets, which may be achieved by selecting a substance associated with a third color channel associated with the third data subset, the identification of the sealed segments may be made more reliable.

[0092] Optionally, prior to the first step 802 of capturing an image data set, in an eleventh step 822, the food product held in the packaging may subsequently be removed in a twelfth step 824, the packaging may be unfolded to expose the seal, and then, in a thirteenth step 826, the packaging may be dissolved to remove the cardboard layer of the packaging material.

[0093] Although different steps are mentioned in a certain order, these steps can be performed not only in the above order but also in other orders. In addition, some steps can be performed in parallel for time efficiency reasons.

[0094] From the above it can be seen that, although various embodiments of the invention have been described and shown, the invention is not restricted thereto but may also be embodied in other ways within the scope of the subject matter defined in the following claims.

Claims

1. A method (800) for evaluating a seal (200, 202) of a carton package (114) arranged to contain a food product (FP), wherein the seal (200, 202) is produced by using an ultrasonic sealing technique, the method comprising: capturing (802) an image data set (500) depicting the seal (200, 202), wherein the image data set (500) includes a first data subset (600) associated with a first color channel and a second data subset (602) associated with a second color channel, identifying (804) adhesion segments (702a, 702b) by using the first data subset (600), and The non-adherent segments (704) are identified (806) using the second data subset (602).

2. The method according to claim 1, further comprising: identifying (808) a seal segment using the first data subset (600) and the second data subset (602), wherein the seal segment corresponds to a top fin, a bottom fin, or a longitudinal seal segment of the carton package (114), The adhesive section (702a, 702b) and the non-adhesive section (704) are both contained within the sealing section.

3. A method according to any one of the preceding claims, wherein: By capturing the image data set (500) using a camera (408) positioned on a first side (S-1) of the seal (200, 202) of the package (114), the method further comprises: The sealing portion (200, 202) is illuminated (810) using a light source (404) provided on a second side (S-2) of the sealing portion (200, 202), wherein the second side of the sealing portion (200, 202) is opposite to the first side (S-1) of the sealing portion, so that light (L) emitted from the light source (404) passes through the sealing portion (200, 202) of the package (114) and enters the camera (408).

4. The method according to claim 3, wherein the light source (404) is one or more light emitting diodes (LEDs) that emit light having at least one specific frequency, wherein the first frequency range of the first color channel and / or the second frequency range of the second color channel are set based on the at least one specific frequency of the one or more LEDs.

5. The method according to claim 3 or 4, wherein the first frequency range of the first color channel and / or the second frequency range of the second color channel are set based on properties of the packaging material (PM).

6. A method according to any one of claims 3 to 5, wherein the image dataset (500) is captured in multiple versions, wherein the multiple versions have different light settings, wherein the light settings include one or more specific frequencies of the light emitted from the light source and / or one or more amplitudes of the light emitted from the light source.

7. A method according to any one of the preceding claims, wherein the packaging material (PM) comprises a non-metallic light-blocking layer, wherein the non-metallic light-blocking layer is a cellulose-based light-blocking layer, and the cellulose-based light-blocking layer is suitable for blocking light having a frequency that causes microbial growth and / or vitamin loss in the food (FP) contained in the carton packaging (114).

8. The method according to any one of the preceding claims, further comprising: providing (812) a reference object (502) next to the sealing portion (200, 202) of the carton package (114), wherein the reference object (502) has a reference length and / or a reference width, identifying (814) the reference object (502) depicted in the image data (500), The absolute length and / or the absolute width of the adhered section (702a, 702b) and / or the non-adhered section (704) is determined (816) by using the reference length and / or the reference width.

9. The method according to any one of the preceding claims, further comprising: Prior to capturing the image data set (500), a substance such as ink is applied (818) to the seal (200, 202).

10. The method of claim 9, wherein the image data set (500) further comprises a third data subset (604) associated with a third color channel, the method further comprising: identifying (820) a segment affected by the substance using the third data subset (604), wherein said step of identifying (808) said sealing segment is performed by using said first subset (600), said second subset (602), and said third subset (604).

11. The method according to any of the preceding claims, wherein the sealing section comprises overlapping sub-sections in which the transverse seal and the longitudinal seal overlap.

12. The method according to any of the preceding claims, further comprising, before the step of capturing (802) the image data set (500), removing (822) the food product (FP) contained in the package (114), unfolding (824) the package (114) so ​​that the seals (200, 202) are exposed, and The packaging (114) is dissolved (826) such that the paperboard layer of the packaging material is removed.

13. An apparatus (400) for evaluating a seal (200, 202) of a carton package (114) arranged to contain a food product (FP), wherein the seal (200, 202) is produced by using an ultrasonic sealing technique, the apparatus (400) comprising: a camera (408) configured to capture an image data set (500) depicting the seal (200, 202), wherein the image data set (500) includes a first data subset (600) associated with a first color channel and a second data subset (602) associated with a second color channel; and A control unit (410) comprising a processor (412) and a memory (414) configured to identify adhered segments (702a, 702b) in the image data set (500) by using the first data subset (600), and to identify non-adhered segments (704) in the image data set (500) by using the second data subset (602).

14. The apparatus according to claim 13, further comprising: a light source (404) arranged to illuminate the sealing portion (200, 202), wherein the camera (408) is placed on a first side (S-1) of the sealing portion (200, 202) of the package (114), and the light source (404) is provided on a second side (S-2) of the sealing portion (200, 202), wherein the second side of the sealing portion (200, 202) is opposite to the first side (S-1) of the sealing portion (200, 202), Thereby, light (L) emitted from the light source (404) is allowed to pass through the sealing portion (200, 202) of the package (114) and enter the camera (408).

15. An apparatus according to claim 14, wherein the light source (404) is one or more light emitting diodes (LEDs) that emit light having at least one specific frequency, wherein the first frequency range of the first color channel and / or the second frequency range of the second color channel are set based on the at least one specific frequency of the one or more LEDs.

Images