Description

The present invention is in the field of determining a measure for a degree of degradation. In particular, it relates to a computer-implemented method for determining a measure for a degree of degradation associated with a sample, use of a measure for a degree of degradation of a sample for determining a measure for a time of degradation of a sample, use of a measure for a degree of degradation as an indication for degradability of a material, a computer program product comprising instructions which, when the computer program is executed, cause a computer to carry out the steps of the method as described herein, a product comprising a material related to a sample and an indication of a degree of degradation, a system for determining a degree of degradation.

Background

Pollution due to non-degradable materials such as plastics is a worldwide problem. Depending on the material and the object formed with the material, it takes hundreds of years for plastics to degrade. Until the material is completely degraded, it stays in the environment and is potentially harmful. Hence, biodegradable materials are desired. Identifying those materials relies on intensive testing using different tests; one of which is disintegration testing. Here materials are incubated in a specific habitat and the disintegrated pieces are collected to follow the extent to which the material disintegrates through microbial activity. So far, sieves are used to identify that a material has decomposed to a sufficiently small size. This requires sieving the complete content of a sample box thereby disturbing the whole testing environment. Another option is visual verification lacking objectivity and reproducibility. Hence, determining disintegration still relies on interpretation or a significant physical intervention into the system to be analyzed.

It was hence the object of the present invention to overcome these shortcomings. In particular, a method for determining a degree of degradation is desired. This method should be easy, reliable, objective, reproducible and avoid physical intervention.

Summary

These objects were achieved by the present disclosure. In one aspect it relates to a computer-implemented method for determining a measure for a degree of degradation associated with a sample comprising: receiving an image data set associated with an image of the sample, determining a measure for an area associated with the sample and/or associated with a non-sample object based on the image data set, determining a measure for the degree of degradation based on the measure for the area associated with the sample and/or associated with a non-sample object , providing the measure for the degree of degradation.

In another aspect, it relates to a use of a measure for a degree of degradation of a sample as obtained by the method as described herein for determining a measure for a time of degradation of a sample. In another aspect, it relates to a use of a measure for a degree of degradation of a sample as obtained by the method as described herein as an indication for degradability of a material associated with the sample.

In another aspect, it relates to a computer program product comprising instructions which, when the computer program is executed, cause a computer to carry out the steps of the method as described herein.

In another aspect, it relates to a product comprising a material related to a sample and an indication of a measure for a degree of degradation associated with the sample as determined by the method as described herein.

In another aspect, it relates to a system for determining a degree of degradation for a sample comprising: an input for receiving an image data set associated with an image of the sample, a processor for executing the steps of any of the method as described herein, an output for providing the degree of degradation.

In another aspect, it relates to a non-transitory computer-readable data medium storing a computer program including instructions for executing steps of the method as described herein.

Currently, methods known in the art do not provide the possibility to easily follow a temporal evolution of material degradation. Especially, an early quantification is desired since degradation tests are oriented on verifying final degradation, but without intermediate meaningful results. Sieving is a coarse method and thus, not applicable for quantification. Further, sieving can destroy the sample due to mechanical interaction. Visual verification can be inaccurate and not reproducible due to strong subjectiveness and potential errors. These needs are met by the present disclosure. In particular, the present disclosure provides means for an easy, reliable, objective, reproducible method for determining a measure for a degree of degradation that avoids strong mechanical intervention with the sample and the sample environment. Using human experience for determining a degree of degradation as done in the field, opens up errors due to inaccuracy and results may not be reproducible due to subjective interpretation. Furthermore, the results may not be comparable. In contrast, the invention does not rely on human help and equipment for building a system as described herein and means for facilitating the method are all-purpose, readily available and low-cost hardware. The invention provides a non-human and hence automatic verification and thus, it contributes to the automation of degradability testing. Additionally, determining a degree for degradation and a time for degradation by means of data processing equipment such as a computer is time-efficient, can lower costs since human interaction is not needed and provides precise, accurate and reliable results. Furthermore, by generating an image of the sample and determining a degree of degradation based on the image, a visual representation of the sample and the overall degradation process can be generated. This comes with the benefits of keeping a local relationship within the sample without disturbing sample or sample environment. Hence, further insights into degradation can be obtained. Not disturbing the sample or sample environment comes with the benefit that the spatial relationship between parts of the sample are kept and information relating to the location where degradation occurred can be obtained.

Embodiments

Any disclosure and embodiments described herein relate to the methods, the system, the uses, the product, the computer program element, the non-transitory computer-readable data medium, the computer-readable data medium lined out above and vice versa. Advantageously, the benefits provided by any of the embodiments and examples equally apply to all other embodiments and examples and vice versa. The system may be suitable for carrying out the steps of the methods.

Sample may refer to, without limitation, an object or a part of an object. An indication a degree of degradation may be determined for an object. Sample may comprise a material, preferably a solid material. Material may comprise at least one chemical substance. Chemical substance may be one of but not limited to chemical compound, alloy, polymers, pure chemical element and/or the like. Chemical compounds may comprise atoms from more than one element held together by a chemical bond. Chemical compounds may for example include molecules composed of atoms from more than one element, ionic compounds, intermetallic compounds, complexes or the like.

Material may undergo degradation, preferably biodegradation and/or disintegration. In some embodiments, sample may be at least a part of an object for which degradation may be determined. “Degradation” as used herein, is a broad term and is to be given its ordinary and customary meaning to a person skilled in the art and is not to be limited to a special or customized meaning. Degradation may be a process during which the total number of atoms and/or mass of an object decreases. Object may be a product and/or a thing. Product and/or thing may be physical items. Object may be a contiguous object made of a number of atoms. Number of atoms and/or mass of contiguous object may decrease while degrading. Object may be solid and/or solidified melting.

Degradation may be an irreversible process leading to a change in the structure of a material. Degradation may be accompanied with a change of properties of the material, for example integrity, mechanical strength, change of molecular weight and/or structure. Degradation may comprise at least one of biodegradation, disintegration, chemical degradation, photodegradation, thermal degradation or the like. Disintegration may be caused by mechanical influences. Disintegration may be a physical breakdown of a material into small fragments. Small fragments may be objects smaller than the original object size, preferably 10% of the object size and/or smaller than one centimeter. Biodegradation may be caused by microorganisms. Biodegradation may be a breakdown of a material by microorganisms, preferably into carbon dioxide, water, mineral salts of any other elements present and/or biomass. Chemical degradation may refer to a change in the chemical structure of a material, in particular caused by chemical agents including catalysts. Photodegradation may comprise degradation caused by absorption of light, in particular visible and/or UV light. Thermal degradation may comprise degradation that may be caused by heat, in particular resulting in a physical and/or chemical structural change of a material. Image data set is associated with an image of the sample. Image data set may comprise data associated with a sample and/or data associated with a non-sample object. More than one non-sample object may be associated with the image data set. Image data set may be suitable for obtaining and/or representing an image of the sample and/or non-sample object. Image data set may include data points suitable for obtaining and/or representing an image of the sample and/or non-sample object. Image data set may comprise numerical values, in particular numerical values suitable for representing a monochromatic image and/or a RGB image. For example, the monochromatic image may be represented by a number of pixels, preferably at least one, with corresponding pixel values indicating the brightness of the pixel. Pixel may be suitable for representing at least a part of an image. Pixel may be a subunit of an image. A RGB image may be represented by three values for each pixel, wherein the three values indicate the brightness of the red, blue and green part of the pixel. An image may be a visual representation of an object such as a sample.

A measure for an area associated with the sample and/or associated with a non-sample object may be a quantity suitable for determining an area associated with the sample and/or associated with a non-sample object. A value may be associated with the measure for an area associated with the sample and/or associated with a non-sample object. Value associated with the measure for an area associated with the sample and/or associated with a non-sample object may comprise a numerical value. Measure for an area associated with the sample and/or associated with a non-sample object may comprise for example a number of datapoints, in particular pixels and/or other subunits of an image, associated with the sample and/or associated with a non-sample object, an area associated with the sample and/or associated with a non-sample object or the like. A measure for an area associated with the sample and/or associated with a non-sample object may be determined with a model. A measure for an area associated with the sample and/or associated with a non-sample object may be given as numerical value. For example, a measure for an area associated with the sample and/or associated with a non-sample object may comprise an area associated with the sample, an area associated with a non-sample object, an area associated with the sample at another point in time, preferably an earlier point in time, and/or an area associated with the sample and the object other that the sample. Area associated with the sample at another point in time, preferably an earlier point in time, may comprise another value, preferably a larger value. Due to degradation area associated with the sample may decrease while area associated with a non-sample object may increase. Determining a measure for a degree of degradation may further be based on a measure for an area of the non-degraded sample. Measure for an area associated with the sample and/or measure for an area associated with the non-sample object may include a measure for an area of the nondegraded sample. Non-degraded sample may be a sample which has not been observed to degrade, preferably not observed with a degree of degradation larger than 0%.

Model may be suitable for determining an output based on an input. Model can be a deterministic and/or data-driven model and/or a hybrid model. A deterministic model may implement requirements for a measure for an area associated with the sample and/or associated with a non-sample object . Data-driven model may be a classification model. The classification model may comprise at least one machine-learning architecture and model parameters. For example, the machine-learning architecture may be or may comprise one or more of: linear regression, logistic regression, random forest, piecewise linear, nonlinear classifiers, support vector machines, naive Bayes classifications, nearest neighbors, neural networks, convolutional neural networks, generative adversarial networks, support vector machines, or gradient boosting algorithms or the like. In the case of a neural network, the model can be a multi-scale neural network or a recurrent neural network (RNN) such as, but not limited to, a gated recurrent unit (GRU) recurrent neural network or a long short-term memory (LSTM) recurrent neural network.

The data-driven model may be trained based on training data. The term “training”, also denoted learning, as used herein, is a broad term and is to be given its ordinary and customary meaning to a person skilled in the art and is not to be limited to a special or customized meaning. Training may also include parametrizing. The term specifically may refer, without limitation, to a process of building the classification model, in particular determining and/or updating parameters of the classification model. Updating parameters of the classification model may also be referred to as retraining. Retraining may be included when referring to training herein. The data-driven model may be trained based on training data. Training the data-driven model may comprise providing training data to the model. The training data may comprise at least one training dataset. A training data set may comprise at least one input and at least one desired output. During the training the data-driven model may adjust to achieve best fit with the training data, e.g. relating the at least on input value with best fit to the at least one desired output value. For example, if the neural network is a feedforward neural network such as a CNN, a backpropagation-algorithm may be applied for training the neural network. In case of a RNN, a gradient descent algorithm or a backpropagation-through-time algorithm may be employed for training purposes.

Hybrid model may be a model comprising at least one data-driven part, in particular a machine-learning architecture, with deterministic and/or statistical adaptations and model parameters. Statistical and/or deterministic adaptations may be introduced to improve the quality of the model-based reference values since those provide a systematic relation between empiricism and theory. Statistical or deterministic adaptations may comprise limitations of any intermediate or final results determined by the classification model and/or additional input for training the classification model. A hybrid model may be more accurate than a purely data-driven model since, especially with small data sets, purely data-driven models may tend to overfitting. This can be circumvented by introducing requirements in the form of deterministic adaptations.

A measure for a degree of degradation may be a quantity suitable for determining a degree of degradation. A value may be associated with a measure for a degree of degradation. Value associated with the measure for a degree of degradation may comprise a numerical value. A degree of degradation may indicate the relation between an area associated with the sample and/or associated with a non-sample object and/or an initial area associated with the sample and/or associated with a non-sample object. A measure for a degree of degradation may be determined by performing mathematical operations on the measure for an area associated with the sample and/or associated with a non-sample object. In certain embodiments, performing other mathematical operations may include dividing, multiplying, summing, subtracting and/or other mathematical operations. For example, a measure for a degree of degradation may relate the area associated with the sample and the area associated with a non-sample object. Degree of degradation may be determined with a model. A measure for a degree of degradation may be given as a numerical value, preferably a percentage.

“Input” comprises of one or more of serial or parallel interfaces or ports, USB, Centronics Port, FireWire, HDMI, Ethernet, Bluetooth, RFID, Wi-Fi, USART, or SPI, or analogue interfaces or ports such as one or more of ADCs or DACs, or standardized interfaces or ports to further devices.

“Processor” is a local processor comprising a central processing unit (CPU) and/or a graphics processing units (GPU) and/or an application specific integrated circuit (ASIC) and/or a tensor processing unit (TPU) and/or a field-programmable gate array (FPGA). The processor may also be an interface to a remote computer system such as a cloud service. The processor may include or may be a secure enclave processor (SEP). An SEP may be a secure circuit configured for processing the spectra. A "secure circuit" is a circuit that protects an isolated, internal resource from being directly accessed by an external circuit. The processor may be an image signal processor (ISP) and may include circuitry suitable for processing images, in particular.

“Output” is one or more of serial or parallel interfaces or ports, USB, Centronics Port, FireWire, HDMI, Ethernet, Bluetooth, RFID, Wi-Fi, USART, or SPI, or analogue interfaces or ports such as one or more of ADCs or DACs, or standardized interfaces or ports to further devices. In some embodiments, the output may be configured to output a signal indicating the condition-based action.

“Computer-readable data medium” refers to any suitable data storage device or computer readable memory on which is stored one or more sets of instructions (for example software) embodying any one or more of the methodologies or functions described herein. The instructions may also reside, completely or at least partially, within the main memory and/or within the processor during execution thereof by the computer, main memory, and processing device, which may constitute computer-readable storage media. The instructions may further be transmitted or received over a network via a network interface device. Computer-readable data medium include hard drives, for example on a server, USB storage device, CD, DVD or Blue-ray discs. The computer program may contain all functionalities and data required for execution of the method according to the present invention or it may provide interfaces to have parts of the method processed on remote systems, for example on a cloud system. The term “non-transitory” has the meaning that the purpose of the data storage medium is to store the computer program permanently, in particular without requiring permanent power supply.

In some embodiments, the image data set may be processed, in particular before determining a measure for an area associated with the sample and/or associated with a nonsample object. Processing the image data set may comprise changing at least one data point in the image data set. Changing at least one data point in the image data set may change the image associated with the image data set. In the art a wide variety of processing techniques are known. It may be referred to Advanced Graphics Programming Using OpenGL - A volume in The Morgan Kaufmann Series in Computer Graphics by TOM McREYNOLDS and DAVID BLYTHE (2005) ISBN 9781558606593, https://doi.org/10.1016/B978-1-55860-659- 3.50030-5 for a non-exhaustive list of processing techniques for images. Examples for image processing the image data set may comprise thresholding, orienting an image, resizing an image, converting an image into a monochromatic color scheme, adjusting the contrast, tiling and/or cropping. Image data set may not be suitable for determining a measure for an area associated with the sample and/or associated with a non-sample object and/or the suitability of the image data set may be increased by processing. For example, image data set may represent an additional part of another sample and thus, the image data set may be processed to change the image data set such that it may not represent another sample. Another example may be an image data set with a RGB color scheme. In order to determine a measure for an area associated with the sample and/or associated with a non-sample object the image data set may be converted into a monochromatic color scheme and/or thresholding may be applied. By doing so, the image data set may be used for determining a measure for an area associated with the sample and/or associated with a non-sample object more efficiently and easier.

In some embodiments, the sample may comprise a polymer, in particular a degradable polymer, most preferably a biodegradable polymer. A polymer may be given its ordinary and customary meaning to a person skilled in the art and is not to be limited to a special or customized meaning. Polymer may be a material comprising a repeating unit, preferably at least two. Repeating unit may be a structural part of a molecule being comprised a plurality of times in a molecular structure. Polymer may be a macromolecule. Polymers and their degradation are of special interest since polymers are a convenient and widely used material. Usually, polymers take a long time to degrade and hence, cause pollution of the environment. Degrading polymers in an appropriate time interval contributes to less pollution of the environment. For performing a reliable, repeatable and objective analysis of polymer degradation, the invention as described herein can be used.

In some embodiments, the image data set may be generated, in particular by a camera. In this context, “generating” also includes capturing and/or recording an image and/or an image data set. The term “camera” specifically may refer, without limitation, to a device having at least one imaging element configured for recording or recording spatially resolved onedimensional, two-dimensional or even three-dimensional optical data or information. The camera may be a digital camera. As an example, the camera may comprise at least one camera chip, such as at least one CCD chip and/or at least one CMOS chip configured for recording images. The camera may be or may comprise at least one monochromatic camera and/or an RGB camera. Furthermore, the camera, besides the at least one camera chip or imaging chip, may comprise further elements, such as one or more optical elements, e.g. one or more lenses.

In some embodiments, the image data may be provided, in particular via a user interface, most preferably a graphical user interface and/or the degree of degradation may be received, in particular via a user interface, most preferably a graphical user interface. By doing so, a user may be enabled to provide and/or select data for determining an indication for a degree of degradation. Hence, the method and systems may be easy, reliable, objective, reproducible and avoiding physical intervention with the sample and the sample environment. In addition, methods and systems may be customizable, user-friendly and provides flexibility to a user. In some embodiments, the measure for a degree of degradation and/or the time of degradation may be used to determine a classifier. Such a classifier may be a label, e.g. a label for a product. In particular, a degree of degradation higher than 0%, ideally higher than 50% may result in a classifier indicating that the material associated with the sample is degradable, preferably degradable in a specified time interval.

In some embodiments, the sample may degrade in a habitat, such as water, soil, sludge, compost, air or the like. Habitat may be present on the sample while generating the image data set. Thus, the determination of a measure for a degree of degradation may be influenced and accuracy is lowered. Hence, it is advantageous to remove parts of or residues due to the habitat in which the sample is allowed to degrade because it increases the accuracy of the method and the system used. Thus, sample may be prepared for generating the image data set, preferably prior to generating the image data set. Preparing the sample for generating the image data set may include cleaning, e.g. by brushing or drying the sample, moving or performing other actions in order to remove parts of or residues due to the habitat. Instructions for removing parts of or residues due to the habitat may be provided. Providing instructions for removing parts of or residues due to the habitat may be part of the method and/or may be a step carried out by the system or computer-readable data medium.

In some embodiments, the measure for the degree of degradation may be compared to another measure for the degree of degradation. Another measure for a degree of degradation may be determined by a method independent of the disclosed method. Another measure for a degree of degradation may be obtained by determining the CO2 or O2 level. O2 level may be determined as described by DIN EN ISO 17556:2012. CO2 level may be determined as described by DIN EN ISO 14855-1 :2021 and/or EN ISO 14852:1999. Measure for a degree of degradation may be determined based on the measure for the area associated with the sample and/or associated with a non-sample object and may be compared to another measure for a degree of degradation determined independent of an image data set associated with an image of the sample. Measure for a degree of degradation may be adjusted to the other measure for a degree of degradation determined independent of an image data set associated with an image of the sample. Adjusting the measure for a degree of degradation may comprise combining the at least two measures for a degree of degradation, e.g. by calculating a median.

In some embodiments, the non-sample object may comprise a color and/or brightness different from the color and/or brightness of the sample and/or a background material. Color may refer to pixel brightness and its values in a RGB scheme. A measure for an area associated with the sample may be determined based on a color and/or brightness related to the area associated with the sample. A measure for an area associated with a non-sample object may be determined based on a color and/or brightness related to the area associated with a non-sample object. By doing so, it can be easily differentiated between area associated with the sample and area associated with a non-sample object. Hence, the invention as described herein is easy to be deployed.

In some embodiments, the area associated with a non-sample object may had been associated with the sample at another point in time, preferably at an earlier point in time. Another point in time may refer to a point in time other than the point in time where the image data set associated with an image of the sample was generated. When the material of the sample may degrade, an image may have been generated at an earlier point in time with a higher measure for an area associated with the sample. Followingly, at least a part of the image associated with the image data set generated at a later point in time may relate to a part, where area associated with the sample may have been in an image at another point in time. Verifying the, preferably prior, existence of material at another point in time proofs degradation easily and visualizes the degradation.

In some embodiments, the measure for an area associated with the sample and/or associated with a non-sample object and/or the measure for the degree of degradation may be determined with a model based on the image data set, in particular a deterministic and/or hybrid and/or data-driven model. Models, in particular data-driven or hybrid models, may be trained and thus, can learn from experience. Followingly, using such models may improve the accuracy of the method or the system.

In some embodiments, at least a second image data set associated with a second image of a sample generated at a different point in time then the first image data set and an indication of a time interval between the at least two different points in time may be received and a second measure for an area associated with the sample and/or associated with a nonsample object based on the second image data set may be determined and a second measure for the degree of degradation based on the measure for the area associated with the sample and/or associated with a non-sample object may be determined and a time of degradation may be determined based on the at least two measures for the degree of degradation and the indication of the time interval and the time of degradation may be provided. By doing so, a time of degradation may be determined, which can be used as an indication for the degradability of a material associated with the sample. The time of degradation provides additional input on deciding for e.g. packaging materials or disposable parts and helps to identify suited materials. Thus, determining a time of degradation contributes to solving waste-related problems.

In some embodiments, time of degradation may be determined. Time of degradation may comprise numerical values for indicating a time or time interval. Degradation may take preferably some weeks or months, in certain cases shorter times on a day scale or longer times on a year scale may be possible. Time of degradation may be in the range of day, weeks, months and/or years. Time of degradation may be determined based on at least two measures for degree of degradation and an indication of the time between the generation of at least two image data sets associated with the at least two measures for degree of degradation. Determining the time of degradation may include performing mathematical operations such as subtracting, dividing, multiplying, summing or the like. For example, the indication of the time interval may comprise at least two points in time. In this example, the time interval may be calculated from the difference between the at least two points in time. The interval may be used as a time of degradation. In such a scenario, image data sets may have been generated of a complete sample at one point in time and of a fully degraded sample at another point in time. Determining a time of degradation from the degree of degradation provided additional insides into the material properties. For the ultimate use of materials, the time of degradation and the corresponding conditions are important to know and to prevent unnecessary distribution of non-degradable materials by providing a evidence on material’s properties.

Further possible implementations or alternative solutions of the invention also encompass combinations - that are not explicitly mentioned herein - of features described above or below in regard to the embodiments. The person skilled in the art may also add individual or isolated aspects and features to the most basic form of the invention. It shall be understood that a preferred embodiment of the invention can also be any combination of the dependent claims or above embodiments with the respective independent claim.

Further embodiments, features and advantages of the present invention will become apparent from the subsequent description and dependent claims, taken in conjunction with the accompanying drawings.

Brief Description of the Figures

Figure 1 illustrates a sample undergoing degradation at different points in time (100).

Figure 2 illustrates a flow diagram of an example embodiment of a computer-implemented method for determining a measure for a degree of degradation associated with a sample (200).

Figure 3 illustrates an example embodiment of a system for determining a measure for a degree of degradation associated with a sample (300).

Figure 4 illustrates a flow diagram of an example embodiment of a computer-implemented method for determining a measure for a degree of degradation associated with a sample (400).

Figure 5 illustrates an example embodiment of products comprising a material related to a sample and an indication of a measure for a degree of degradation associated with the sample.

Detailed Description of Embodiments

In Fig. 1 a sample undergoing degradation at different points in time (100) is illustrated. The sample may be an arbitrary object that may comprise of at least one material. For example, the sample may comprise of a polymer, in particular a plane polymeric object such as a foil. In Fig. 1 the sample is illustrated at four different point in time, namely to, ti , t2 and to. To may be the initial time at the start of the sample and a corresponding image data set may be generated. At the start the sample may not be degraded at all and hence, the full area of the sample may be present. The sample may be allowed to degrade. Degradation may be caused by different types of degradation, for example by biodegradation, disintegration or the like. Degradation may be dependent on the sample and its surrounding. The surrounding may be solid, liquid and/or gaseous. Phase of the surrounding may determine the grade of disintegration and/or the presence and behavior of microorganism ultimately influencing the grade of biodegradation. Material of the sample may determine the grade of disintegration and/or the presence and behavior of microorganism ultimately influencing the grade of biodegradation. In particular, some materials may not be degraded by microorganisms or some materials may be degradable by microorganisms. Thermodynamic parameters may influence the grade of disintegration and/or the presence and behavior of microorganism ultimately influencing the grade of biodegradation. In particular, temperature, pressure and the like change material properties and thus, their degradation properties. Additionally, the presence of microorganisms and their activity may depend on temperature, pressure, presence of chemical substances and the like.

As a consequence of degradation, the appearance of the sample may be changed. In Fig. 1 four different images of the sample are illustrated. The sample with an initially complete area may degrade over time. Degradation of the sample may start with small holes, which widen with time and/or new holes appear. The sample may be a degradable sample. In some embodiments, the sample may be placed in soil to test for composting. Composting may be caused for example by biodegradation due to the present microorganisms and/or fraction with soil and other object in the surrounding. A measure for the degree of degradation may be determined for at least one image data set. Measure for the degree of degradation may comprise for example a relation, e.g. in the form of a percentage, of the area of sample compared to the initial area of the sample and/or a relation, e.g. in the form of a percentage of the area not related to the sample compared to the initial area of the sample and/or a relation of the area of sample and the area not related to the sample a measure for the area associated with the sample and/or associated with a non-sample object based on the image data and/or a numerical value on a scale, e.g. a numerical value between two defined numerical values such as 0 and 1.

Further, with indication of a respective time interval between at least two image data sets associated with an image of the sample, a temporal evolution of degradation may be determined, e.g. a time of degradation.

In the concrete example, which is not to be seen as limiting, the rectangular area at to may refer to the initial full area of the sample. As time passes, holes may be generated due to degradation. Holes may be represented with black, for example due to a black background. The black area may represent an area of a non-sample object and may be used as a measure for an area of a non-sample object. The remaining white area may represent the area of the sample and/or may be used as a measure for an area of the sample. A degree of degradation may be obtained from the measure for a degree of degradation.

In Fig. 2 a flow diagram of an example embodiment of a computer-implemented method for determining a measure for a degree of degradation associated with a sample (200) is illustrated. An image data set associated with an image of the sample is received (210). The image data set may be received by data processing equipment such as a computer, a mobile device, a server, a cloud system or the like. The image data set may be provided by a user. User may desire to determine a measure for a degree of degradation associated with a sample, in particular user may be a costumer. User may provide an image data set to data processing equipment. In the case of a costumer, the data processing equipment may be hosted by another person and/or party. Image data set associated with an image of the sample may comprise data suitable for representing the sample. From the image data set an image of the sample may be obtained and/or image data set may comprise an image. For example, image data set may comprise numerical values e.g. in an array suitable for obtaining and/or representing an image of the sample. Further, image data set may be suitable for obtaining and/or representing a non-sample object, e.g. a background preferably differently colored than the sample. In some embodiments, the image data set may be processed to change and/or remove at least a part of data independent of the sample.

A measure for an area associated with the sample and/or associated with a non-sample object is determined based on the image data set (220). For this purpose, any measure suitable for determining an area associated with the sample and/or associated with a non- sample object may be used. As an example, measure for an area may be an area in an image associated with the sample and/or associated with a non-sample object and/or a number of pixels associated with the sample and/or associated with a non-sample object and/or the like. Area associated with the sample and/or associated with a non-sample object may be recognized for example by color, brightness or the like. Pixel values may be used for determining a color, brightness or the like. Pixel values may indicate values from 0 to 255. In a monochromatic picture, only one value may be indicated relating to the brightness of the pixel. In a RGB scheme, three-pixel values may be indicated for red, blue and the green color. Other pixel values may be indicated such as information regarding transparency, e.g. via an alpha channel. In an example, image may be an 8-bit image, also referred to as monochromatic image. In another example image may be a 24-bit image, also referred to as RGB image. In yet another example, image may be a 16-bit image. Other bit sizes of the image are possible. Area in an image may be determined by using the pixel area and/or area of an arbitrary shape suitable for fitting into the area associated with the sample and/or associated with a non-sample object. In particular, a numerical value may be determined for the measure for an area associated with the sample and/or associated with a non-sample object. A model may be used for determining a measure for an area associated with the sample and/or associated with a non-sample object. Such a model may be trained with training data. A deterministic model may implement requirements for a measure for an area associated with the sample and/or associated with a non-sample object. A data-driven model may be trained with image data sets. Data-driven model may be trained as to determine a measure for an area associated with the sample and/or associated with a non-sample object. A measure for an area associated with the sample and/or associated with a non-sample object may comprise a measure for an area of the non-degraded sample, e.g. a sample with a degree of degradation of 0%.

Methods for processing an image such as determining a measure for an area associated with the sample and/or associated with a non-sample object based on the image data or changing and/or removing at least a part of data are known in the art, for example in Advanced Graphics Programming Using OpenGL - A volume in The Morgan Kaufmann Series in Computer Graphics by TOM McREYNOLDS and DAVID BLYTHE (2005) ISBN 9781558606593, https://doi.org/10.1016/B978-1-55860-659-3.50030-5. The reference is to be seen as general reference for processing an image.

A measure for a degree of degradation is determined based on the measure for an area associated with the sample and/or associated with a non-sample object (230). Measure for a degree of degradation may be as described in the context of Fig. 1. Measure for a degree of degradation may be determined based on the measure for an area associated with the sample and/or associated with a non-sample object by performing mathematical operations, e.g. such as summing, dividing, multiplying, subtracting or the like. In an example a measure for a degree of degradation may be a relation of a measure for an area associated with the sample and a measure for an area associated with a non-sample object. Alternatively or additionally, a measure for a degree of degradation may be a relation of a measure for an area associated with the sample and/or a measure for the initial area of the sample. Another measure for the degree of degradation may be a measure for an area associated with a non- sample object, for example the holes. Such a measure for the degree of degradation may be determined as described above. As it can be seen in Figure 1 , sample may have a predetermined area such that the area of the non-degraded sample may be known. By dividing the area associated with the degraded sample by the area associated with the nondegraded sample the degree of degradation may be determined. Another option would be to divide the difference between the area of the non-degraded sample and the area associated with a non-sample object by the area of the non-degraded sample. Another example may include dividing the area associated with the sample by the sum of the area associated with the sample and the area associated with the non-sample object, e.g. the background.

The measure for the degree of degradation is provided (240), in particular after determining the measure for the degree of degradation. Measure for the degree of degradation may be provided by data processing equipment such as a computer, a mobile device, a server, a cloud system or the like. Measure for the degree of degradation may be provided to devices such as data processing equipment such as a computer, a mobile device, a server, a cloud system or the like. Such devices may be owned by a user. Thus, the measure for the degree of degradation may be provided to and/or received by a user. User may desire to determine a measure for a degree of degradation associated with a sample, in particular user may be a costumer. User may further process the measure for the degree of degradation, for example the user may obtain a degree of degradation from the measure for the degree of degradation and/or the measure for the degree of degradation may be used for tagging a product comprising at least one material associated with the sample. In some embodiments, measure for the degree of degradation may be used for certification of a material and/or a product.

In Fig. 3 an example embodiment of a system for determining a measure for a degree of degradation associated with a sample (300) is illustrated. A measure for a degree of degradation may be determined for a sample (310). In this example, the sample (310) may comprise a polymeric material such as a part of polymeric housing and/or a cardboard. Sample may be allowed to degrade. For this purpose, the sample may be put into a sample holder (320), e.g. a closed container filled with soil and/or water and/or compost. By setting the conditions of the surrounding and the sample holder (320), the surrounding of the sample and ultimately the degradation of the sample may be influenced. Conditions of the surrounding and the sample holder may be set by controlling condition setting equipment such as a temperature controlling system, a pressure controlling system, a humidity controlling system or the like.

Depending on the desired goal, e.g. a potential application of the material for a product under specific conditions that may be reproduced by the surrounding of the sample (310), sample holder (320), surrounding and sample, e.g. shape, material or the like, may vary. A measure for a degree of degradation may be desired to be determined for the sample (310). Hence, the exemplary system may comprise among the sample (310) and the sample holder (320) a framework (330) to which the sample (310) and/or the sample holder (320) may be mounted, a remote (340) suitable for controlling the position of the sample (310), e.g. changing the sample to a position suitable for obtaining an image data set (350), a camera (360) for generating an image data set and a data storage and or processing unit (370) for storing the image data set and/or processing the image data set. For controlling the position of the sample (310) a signal, e.g. a control signal in the form of an electrical signal may be transmitted from the remote (340) to the sample holder (320). The signal may trigger a movement of the sample (310) such as a rotation and/or translation. In some embodiments, the sample (310) may be placed in soil and thus, soil may be attached to the sample (310). To remove the soil from the sample (310), a movement causing the sample (310) to shake or vibrate may be triggered by the signal. Followingly, the signal may trigger a movement suitable for placing the sample (310) for generating an image data set. When the sample placed suitable for generating an image data set (350), the image data set may be generated, e.g. with a camera (360). The generated image data set may be transmitted to a data storage and/or data processing equipment (370). Examples may comprise a server, a cloud computing system, a local computer, a mobile device or the like. Data storage and/or data processing equipment (370) may be suitable for carrying out the steps of the methods as described in the context of Fig. 2 and/or Fig. 4.

In Fig. 4 a flow diagram of an example embodiment of a computer-implemented method for determining a measure for a degree of degradation associated with a sample (400) is illustrated. An image data set associated with an image of the sample is received (410) as described in the context of Fig. 2.

The image data set may be processed (420), in particular before determining a measure for an area associated with the sample and/or associated with a non-sample object. Processing may include changing the data in the image data set such that the associated image of the sample is changed and/or processed. The image of the sample may be changed and/or processed by means of at least one of the following techniques known in the art: orienting an image, resizing an image, converting an image to the grayscale, adjusting the contrast, tiling and/or cropping. Orienting an image may include for example rotating the image. Resizing an image may include for example stretch to, fill in, fill within or different variants of fit in. Converting an image to the grayscale may include for example determining a pixel value in the monochromatic color scheme from the three-pixel values red, blue and green, in particular by using weights for red, green and blue values. Adjusting the contrast may include for example contrast stretching, histogram equalization, adaptive equalization or the like.

A measure for an area associated with the sample and/or associated with a non-sample object based on the image data set is determined (430) as described in the context of Fig. 2. A measure for the degree of degradation based on the measure for the area associated with the sample and/or associated with a non-sample object is determined (440) as described in the context of Fig. 2. The measure for the degree of degradation is provided (450) as described in the context of Fig. 2. The method may be carried out by the system described in the context of Fig. 3. Degree of degradation may same or similar as described in the context of Fig. 1

In Fig. 5 an example embodiment of products comprising a material related to a sample and an indication of a measure for a degree of degradation associated with the sample is illustrated. Products (510-530) may be different objects, such as a container (510), a cup (520) or cutlery (530). Different indications may be used for the measure for a degree of degradation such as indicating the exact degree of degradation for example accompanied by a time of degradation, here 3 months, or a simple classifier such as “compostable”, “degradable” or “biodegradable” e.g. with a specification such as “in aqueous media”. A time of degradation may be determined for example if the starting point of degradation with 0% degradation and the end point of degradation e.g. 100% degree of degradation or a lower value depending on the use case, in some scenarios 90% degree of degradation may be sufficient for testing, or the interval between the starting point and the end point are known. The time that has passed between the starting point and the end point may be referred to as the time of degradation. In some embodiments, a material associated with the sample may be classified as degradable or similar if the degradation time may be below a threshold. Another option that may be used if there is only one image data set available or the more than one image data sets do not comprise the starting point and the end point. In this case, a model may be used to determine the degradation behavior of a sample. Such a model may be a deterministic model, e.g. based on kinetics, a data-driven model trained based on historical data such that the model can learn from experience or a hybrid model as to combine the first mentioned model approaches. Model may be suitable for predicting and/or simulating the degradation behavior of a sample. Model may be used to determine end point and/or starting point. Model may be used to determine a time of degradation based on image data sets and/or measure for a degree of degradation as described in the context of Fig. 1-4.