Footwear authentication system using pressure distribution image analysis

Abstract

To provide systems and methods for authenticating footwear based on pressure distribution image analysis.SOLUTION: A method for authenticating footwear using pressure distribution image analysis includes: receiving a request to authenticate footwear; and accessing a pressure distribution image for the footwear. The pressure distribution image comprises a pressure distribution represented by colors that is generated based on a preset force applied to the footwear. The method includes: executing analysis on the pressure distribution image including comparing the pressure distribution image to a pressure distribution image of an authentic version of the footwear; determining whether the pressure distribution image is within an authenticity threshold of the pressure distribution image of the authentic version; and presenting, based on the pressure distribution image being within the authenticity threshold, an index of authenticity of the footwear.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The subject matter disclosed herein generally relates to authenticating footwear. In particular, the present disclosure addresses systems and methods for authenticating footwear using pressure distribution image analysis. [Background technology]

[0002] Sellers are typically hesitant to sell high-end or luxury items if they are not confident that they will receive the same item in the event of a return and that the item is not counterfeit. Similarly, buyers are hesitant to purchase high-end or luxury items if they are not confident that the item is genuine. This level of trust is crucial for categories such as designer shoes or brand-name sneakers and athletic shoes (collectively referred to as "footwear"). These types of items are often counterfeited to a level where only an expert can determine their authenticity. [Brief description of the drawings]

[0003] [Figure 1] FIG. 1 is a diagram illustrating an exemplary network environment suitable for determining the authenticity of footwear based on pressure distribution image analysis, according to an exemplary embodiment. [Diagram 2] FIG. 2 is a diagram illustrating several components of an authenticity determining system for determining footwear authenticity based on pressure distribution image analysis, according to an exemplary embodiment. [Figure 3A] FIG. 3A is an example image of pressure distribution heat maps for both the right and left shoes. [Figure 3B] FIG. 3B is an example image of a pedobarographic measurement image of both the right shoe and the left shoe. [Figure 4] FIG. 4 is a flow chart illustrating operations of a method for authenticating footwear using pressure distribution image analysis, according to an exemplary embodiment. [Diagram 5]FIG. 5 is a flowchart illustrating operations of a method for performing statistical pressure distribution image analysis, according to an exemplary embodiment. [Figure 6] FIG. 6 is a flowchart illustrating operations of a method for performing machine learning pressure distribution image analysis, according to an example embodiment. [Figure 7] FIG. 7 is a block diagram illustrating components of a machine capable of reading instructions from a machine storage medium and performing any one or more of the methods described herein, according to some examples. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0004] In the following description, systems, methods, techniques, instruction sequences, and computing machine program products illustrating examples of the present subject matter are described. In the following description, numerous specific details are described for the purpose of explanation in order to provide an understanding of various examples of the present subject matter. However, it will be apparent to those skilled in the art that various examples of the present subject matter can be implemented without some or other of these specific details. The examples are merely representative of possible variations. Unless otherwise specified, structures (e.g., structural components) may be arbitrarily combined or subdivided, and operations (e.g., in a procedure, algorithm, or other function) may be sequence-changed or combined or subdivided.

[0005] Exemplary embodiments address the technical problem of authenticating footwear in a computationally efficient manner based on pressure distribution image analysis. When producing counterfeit designer or branded footwear, counterfeiters attempt to make the counterfeit footwear have the appearance of genuine footwear. However, the materials typically used are not the same, especially when the materials are on the inside of the footwear, e.g., within the sole.

[0006] Additionally, many designer and brand name footwear have patented technologies related to their soles. In particular, these technologies are directed to distributing the weight of the individual wearing the footwear in a manner that attempts to maximize comfort. Thus, exemplary embodiments test the pressure distribution on a shoe (e.g., the sole of the shoe) to identify whether the shoe is genuine or fake. For purposes of explanation, the terms "footwear" and "shoe" are used interchangeably.

[0007] To test the shoe, a pressure distribution image of the shoe is analyzed. In some cases, the pressure distribution image is generated using a pressure measurement machine with an artificial foot (or similar device) having sensors on the artificial foot (or similar device). The artificial foot applies a preset force to the shoe. The preset force is the same force that is applied to a real shoe. The sensors can detect the pressure generated by the sole in response, and the pressure measurements can be recorded in the form of an image. The image can be a pressure distribution heat map or a pedobarographic measurement image. In further embodiments, the pressure can be recorded in the form of a table, matrix, or other form of pressure distribution data without a graphical representation.

[0008] The image analysis authenticity determination system then analyzes the pressure distribution image by comparing it with the pressure distribution image of a genuine shoe. In further embodiments, the authenticity determination system can analyze a pressure distribution table or matrix instead of an image in a similar manner. In exemplary embodiments, the analysis can be performed using either a statistical model or a machine learning model. In some cases, the statistical model is a statistical color model configured to detect specific colors (and their locations) in the pressure distribution image. The specific color / location dataset can then be compared with the dataset of the genuine shoe being tested, and a determination can be made whether or not the comparison is within an authenticity threshold.

[0009] In the case of a machine learning model, the pressure distribution image may be applied to a machine learning model trained with training data derived from pressure distribution images of genuine footwear and pressure distribution images of counterfeit footwear. A probability that the test footwear is genuine is output from the machine learning model and compared to a probability (authenticity) threshold. If the authenticity (probability) threshold is met, the test footwear is labeled as genuine. In some cases, the machine learning model comprises one or more neural networks (e.g., convolution neural networks (CNNs)) trained to determine a similarity (e.g., a plurality of similarity scores) between the pressure distribution image of the test shoe and the pressure distribution image of the genuine shoe. The plurality of similarity scores are compared to an authenticity threshold.

[0010] 1 illustrates an exemplary network environment 100 suitable for authenticating footwear based on pressure distribution image analysis, according to an exemplary embodiment. A network system 102 provides server-side functionality to a client device 106 via a communication network 104 (e.g., the Internet, a wireless network, a cellular network, or a Wide Area Network (WAN)). The network system 102 is configured to authenticate the footwear using either a statistical model or a machine learning model to analyze a plurality of pressure distribution images, as described in more detail below.

[0011] In various cases, the client device 106 is a device associated with a user account of a user of the network system 102 who wishes to verify that footwear they own / will own is authentic. For example, the user may be a merchant who wishes to verify that returned shoes are the same authentic shoes as the shoes that were sold. In other cases, the client device 106 is a device associated with a user account of a purchaser of the network system 102 who wishes to ensure that purchased shoes are authentic. Additionally, the client device 106 may be a device of an operator associated with an intermediary that authenticates footwear on behalf of the merchant or purchaser. In some cases, the intermediary may be part of the same entity that controls the network system 102.

[0012] The client device 106 includes one or more client applications 108 that communicate with the network system 102 for additional functionality. For example, the client application 108 may be a local version of an application or component of the network system 102. Alternatively, the client application 108 exchanges data with one or more corresponding components / applications in the network system 102. The client application 108 may be provided by the network system 102 and / or downloaded to the client device 106. A footwear authenticity determination request may be sent via the client application 108. In response, the client application 108 receives an indication of whether the shoes are authentic after evaluation.

[0013] In certain embodiments, the client application 108 includes an authenticity determination component that exchanges data with the network system 102. In some cases, the client application 108 works with or triggers a pressure measurement machine that includes an artificial foot (or similar device) with multiple sensors that applies a predetermined force to a shoe to be authenticated (also referred to herein as a "test shoe" or "test footwear") to generate pressure distribution data or images and transmits the pressure distribution data or images to the network system 102 for analysis. In certain embodiments, the pressure measurement machine may be part of the client device 106. In other embodiments, the pressure measurement device is a standalone device that may be communicatively coupled to the client device 106 and the network system 102 (e.g., via the network 104). In these cases, the pressure measurement device may be associated with (e.g., owned by) the same entity that controls the network system 102.

[0014] The client device 106 interfaces with the network system 102 through a connection with the network 104. Depending on the form of the client device 106, any of various types of connections and networks 104 can be used. For example, the connection can be a Code Division Multiple Access (CDMA) connection, a Global System for Mobile communications (GSM) connection, or another type of cellular connection. Such a connection can implement any of various types of data transfer technologies, such as single carrier radio transmission technology (1xRTT), Evolution-Data Optimized (EVDO) technology, General Packet Radio Service (GPRS) technology, Enhanced Data rates for GSM Evolution (EDGE) technology, or other data transfer technologies (e.g., fourth generation wireless, 4G networks, 5G networks). When such technologies are used, the network 104 includes a cellular network having multiple cell sites of overlapping geographic coverage interconnected by a cellular telephone exchange. These cellular telephone switches are connected to a network backbone (eg, the public switched telephone network (PSTN), a packet-switched data network, or other type of network).

[0015] In another example, the connection to the network 104 is a Wireless Fidelity (Wi-Fi, IEEE 802.11x type) connection, a Worldwide Interoperability for Microwave Access (WiMAX) connection, or another type of wireless data connection. In such an example, the network 104 includes one or more wireless access points connected to a local area network (LAN), a wide area network (WAN), the Internet, or another packet-switched data network. In yet another example, the connection to the network 104 is a wired connection (e.g., an Ethernet link) and the network 104 is a LAN, a WAN, the Internet, or another packet-switched data network. Thus, a variety of different configurations are expressly contemplated.

[0016] The client devices 106 may include, but are not limited to, smartphones, tablets, laptops, multiprocessor systems, microprocessor-based or programmable consumer electronics, game consoles, set-top boxes, servers, or any other communication devices capable of accessing the network system 102. The client devices 106 may include a display component (not shown) for displaying information (e.g., in the form of a user interface) including an indication of whether the footwear is authentic. The client devices 106 may be executed by a human user and / or a machine user.

[0017] With particular reference to network system 102, an application programming interface (API) server 110 and a web server 112 are coupled to one or more networking servers 114 and provide programmatic and web interfaces, respectively. The one or more networking servers 114 host various systems, including an authenticity determination system 116, which comprises multiple components and may be embodied as hardware, software, firmware, or any combination thereof. The authenticity determination system 116 is described in more detail in connection with FIG. 2.

[0018] The one or more networking servers 114 are connected to one or more database servers 118 that provide access to one or more storage repositories or data stores 120. Data stores 120 are storage devices that store, for example, user accounts including user profiles (e.g., buyers, sellers, or intermediaries) and merchandise associated with the user accounts (e.g., footwear owned, sold, or purchased by the users).

[0019] Any of the systems, servers, data storage devices, or devices (collectively "components") shown in or associated with FIG. 1 may be, include, or otherwise be implemented as a special-purpose (e.g., specialized or otherwise non-general-purpose) computer that can be modified (e.g., configured or programmed by software, such as one or more software components of an application, operating system, firmware, middleware, or other program) to perform one or more of the functions described herein for that system or machine. For example, a special-purpose computer system capable of implementing any one or more of the methods described herein is described below with respect to FIG. 7, such a special-purpose computer being a means for performing any one or more of the methods described herein. Within the technical field of such special-purpose computers, a special-purpose computer modified by the structures described herein to perform the functions described herein is technically improved as compared to other special-purpose computers that lack the structures described herein or are otherwise unable to perform the functions described herein. Thus, special purpose machines constructed in accordance with the systems and methods described herein provide an improvement over the art of similar special purpose machines.

[0020] 1 may be combined, and the functions described herein for any single component may be subdivided among the components. Functions of a particular system may be embodied in different systems in alternative examples. For example, any number of client devices 106 or data storage devices 120 may be embodied within the network environment 100. Although only a single network system 102 is shown, alternatively, two or more network systems 102 may be included (e.g., localized to a particular region).

[0021] FIG. 2 illustrates components of an authenticity determination system 116 for determining whether footwear is authentic based on a pressure distribution image analysis, according to an exemplary embodiment. The authenticity determination system 116 accesses a pressure distribution image of a test shoe, analyzes the pressure distribution image, and determines whether the pressure distribution image is within an authenticity threshold of a pressure distribution image of a real shoe. To enable these operations, the authenticity determination system 116 includes a communication component 202, an image analysis component 204, an image data storage device 206, and an image analysis system, all configured to communicate with each other (e.g., via a bus, shared memory, or switch). The image analysis systems include a statistics system 208 and a machine learning system 210. In some embodiments, the authenticity determination system 116 may include the statistics system 208 and not the machine learning system 210, or may include the machine learning system 210 and not the statistics system 208.

[0022] The communication component 202 is configured to exchange data with other components of the network environment 100. Thus, the communication component 202 receives a request to authenticate a footwear from a client application 108 running on the client device 106. In some cases, the request includes a pressure distribution image of the footwear to be authenticated. In other cases, the request indicates a pressure distribution image to retrieve (e.g., previously uploaded to the image data storage 206) for analysis. The request may also include details of the footwear, including the year of manufacture or purchase, brand, model name, and / or serial number. After analysis by the authenticity determination system 116, the communication component 202 may transmit a response to the query that includes an indication of the authenticity of the footwear.

[0023] In embodiments where the pressure distribution images of the test footwear have been previously uploaded or are uploaded by another entity (e.g., an intermediary testing the product), the image analysis component 204 retrieves the pressure distribution images of the test footwear from the image data storage device 206. In exemplary cases, the image data store 206 may also comprise a database of pressure distribution images for different brands and models of real footwear. These pressure distribution images for different brands and models of real footwear may be used for comparison and for training the machine learning model, as described in more detail below. Periodically, new pressure distribution images are received (e.g., with new product releases) and the machine learning model is retrained.

[0024] In some cases, the pressure distribution image may include a heat map of foot pressure measured by a pressure measurement machine at different locations on the sole. FIG. 3A shows an example of a pressure distribution heat map for both a right shoe and a left shoe. In some cases, the pressure distribution image includes a pedobarographic measurement image as shown in FIG. 3B. Different colors correspond to different pressure measurements. In FIG. 3A and FIG. 3B, "R" indicates red, "G" indicates medium green, and "B" indicates dark blue. For example, red can indicate greater than 195 kilopascals (kPA), medium green can indicate 100 kPA, and dark blue can indicate 10 kPA.

[0025] The pressure measurements in both types of pressure distribution images are obtained from a pressure measurement machine that includes an artificial foot or similar device having a number of pressure sensors located at different locations. When the artificial foot applies a pre-set amount of force to the shoe, the pressure sensors obtain an amount of pressure at each location. The amount of pressure at each location can then be used to generate a pressure distribution image.

[0026] In a further embodiment, the pressure distribution image may comprise a video of the dynamic pressure distribution during a process carried out using a pressure measurement machine, in which the sole absorbs energy and then transmits it through the sole to the sensors. The sensors of the pressure measurement machine thus continuously obtain multiple pressure measurements during the process. The continuous pressure measurements (e.g., dynamic pressure measurements) are compiled into a video or data stream, whereby for each time instant t, a different heat map or pressure distribution table or matrix may be generated.

[0027] In some cases, the image analysis component 204 can pre-process the pressure distribution image of the test shoe before passing the data to either the statistics system 208 or the machine learning system 210. For example, the test shoe may be a size for which the authenticity determination system 116 does not have authenticity determination pressure distribution data. In these cases, the image analysis component 204 can "resize" the image to a size for which the authenticity determination system 116 does have authenticity determination pressure distribution data. In another embodiment, the image analysis component 204 may utilize available algorithms to scale existing authenticated pressure image data, such as nearest neighbor or bilinear interpolation algorithms.

[0028] In embodiments using statistical analysis, the pressure distribution image of the test shoe is provided to a statistical system 208. The statistical system 208 uses statistical analysis (e.g., a statistical image model) to determine whether the test shoe is authentic. Thus, the statistical system 206 includes an evaluation component 212, a pressure data storage device 214, and a threshold component 216.

[0029] The evaluation component 212 is configured to apply the pressure distribution image to a statistical model. In a particular embodiment, the statistical model is a statistical color model trained to detect specific colors (and color shades) and their locations in the pressure distribution image. The detected color / location data set can then be compared to a corresponding data set of real shoes. The corresponding data set can be retrieved from the pressure data store 214. The evaluation component 212 then compares the multiple data sets. In performing the comparison, the evaluation component 212 can determine a percentage of the multiple pressure measurements (color / location data) that are within a threshold (e.g., within 95%) of the corresponding pressure measurements from the pressure data store 214. This percentage can be an authentication score. In another embodiment, a pedobarographic Statistical Parametric Mapping (pSPM) method can be utilized to compare the multiple data sets.

[0030] In some embodiments, the comparison takes into account the age of the test shoe, which can be important because sole materials change and deform at different rates with use. In these embodiments, the pressure data store 214 contains different data sets of pressure distributions (or location / pressure / time vectors) of the same brand / model for different years.

[0031] For pressure distribution operations, an additional parameter of time is considered. Thus, the data set is composed of color and location at a particular time. In performing its comparison, the evaluation component 212 may determine the percentage of pressure measurements (color / location data) in each time frame that are within a threshold (e.g., within 95%) of the corresponding pressure measurements from the pressure data store 214. The average or median of these percentages may then be determined to derive an authenticity score.

[0032] The threshold component 216 determines whether the test shoe is authentic based on an authenticity score determined from the evaluation performed by the evaluation component 212. In exemplary embodiments, the authenticity score includes a percentage of the locations where the pressure (e.g., color) is within a corresponding value or color threshold of authenticity. For example, if the pressure measurements at 90% or more of the locations (e.g., an authenticity threshold of 90% or 0.9) are within the corresponding pressure threshold in the database, the threshold component 216 labels the test shoe as authentic. In some cases, the authenticity threshold is the same for all types of shoes of a particular brand or category. In other cases, the authenticity threshold varies based on brand, model, and / or category. In some cases, the threshold component 216 may be part of the evaluation component 212.

[0033] In embodiments using machine learning analysis, the pressure distribution image is provided to a machine learning system 210. The machine learning system 210 is configured to train one or more machine learning (ML) truth-determination models to determine the probability that the pressure distribution image of the test footwear is authentic. The machine learning system 210 also refines the ML truth-determination models by retraining with updated training data. During inference or runtime, the machine learning system 210 uses the trained ML truth-determination models to determine the probability that the test footwear is authentic.

[0034] To enable these operations, the machine learning system 210 includes a training component 218, an evaluation component 220, and a threshold component 222, all configured to communicate with each other (e.g., via a bus, shared memory, or switch). Although Figure 2 shows the training component 218 and the evaluation component 220 embodied within the machine learning system 210, alternatively, the training component 218 can be separate from the evaluation component 220 in a different system or server.

[0035] In some embodiments, the training component 218 trains the authenticity determination model using pressure distribution images of both real and fake shoes as training data. In some cases, position / color data pairs (or position / color / time vectors of video) for both real and fake shoes are extracted from the corresponding pressure distribution images and used as training data to train the authenticity determination model. Machine learning can be performed using artificial intelligence such as a neural network. For example, the neural network can be trained by providing a set of pressure distribution images (or multiple pairs of position / pressure data) for real footwear and a set of pressure distribution images for the corresponding fake footwear. The weights can then be adjusted accordingly to obtain the desired results. Training the authenticity determination model can include training on the probability that the footwear is authentic (e.g., an authenticity score). For consistency, the preset amount of force applied by the pressure measurement machine to each shoe (as well as the size and shape of the artificial foot) should be the same for the real footwear, the fake footwear, and the footwear to be authenticated.

[0036] In some cases, additional data can be included in the training data to improve accuracy. The additional data can include the year of manufacture of the authentic shoes and the location where the authentic shoes were manufactured. This can be determined from a label found inside the shoe (e.g., an image of the label). For example, the quality and characteristics of the material used in the sole can change over the years, and the material or manufacturing varies slightly between different factories / locations. Additionally, materials deteriorate based on use / aging. Thus, the training data can include pressure distribution data for different ages (e.g., years of manufacture) of the same type / model of authentic footwear.

[0037] Any number of authenticity determination models can be trained. For example, a separate model can be trained for each brand and model of authentic footwear (e.g., Gucci New Ace GG Supreme Trainer). Alternatively, authenticity determination models may be trained for specific brands (e.g., Louis Vuitton, Gucci, Prada, Nike) and / or footwear categories (e.g., high tops, high heels).

[0038] Over time, the training data may be updated to refine the authenticity model. For example, over the years, pressure measurements may become larger at some locations on the sole or may change for different authentic footwear. In addition, authentic footwear is constantly being created (e.g., the same model but with different materials, the same model and materials but manufactured in different locations, the same model but with different sole technology). The training data may be updated to reflect these changes and the corresponding ML authenticity model retrained.

[0039] During runtime or inference time, the evaluation component 220 of the machine learning system 210 is configured to determine the probability that the test footwear is authentic. Thus, the pressure distribution image is applied by the evaluation component 220 to an appropriate ML authenticity model. In some cases, the evaluation component 220 formats the pressure distribution image into one or more input vectors of multiple pairs of color and position data (e.g., extracts multiple pairs of color / position data as multiple features). That is, corresponding colors can be identified at multiple different locations of the pressure distribution image. The input vectors are then applied by the evaluation component 220 to the corresponding ML authenticity model. The ML authenticity model then provides a result that is a probability (or percentage) that the test footwear is authentic.

[0040] The probability (e.g., authenticity score) output by the evaluation component 220 is then compared to an authenticity threshold by the threshold component 222. In some cases, the authenticity threshold is the same for all types of footwear of a particular brand or category. In other cases, the authenticity threshold varies based on brand, model, and / or category. For example, the authenticity threshold may be 0.8 or 80% probability for designer sneakers. Thus, a probability of 0.79 output by the evaluation component 220 would result in the test footwear being labeled as fake or inauthentic, while a probability of 0.82 would result in the test footwear being labeled as authentic.

[0041] 4 is a flow chart illustrating operations of an exemplary method 400 for determining the authenticity of footwear, according to an exemplary embodiment. Operations in the method 400 may be performed by the authenticity determination system 116 using the components described above with respect to FIG. 2. Thus, the method 400 is described by way of example with reference to the authenticity determination system 116. However, it should be appreciated that at least some of the operations of the method 400 may be deployed on a variety of other hardware configurations or performed by similar components present elsewhere in the network environment 100. Thus, the method 400 is not intended to be limited to the authenticity determination system 116.

[0042] In operation 402, the authenticity determination system 116 (e.g., communication component 202) receives a request to authenticate footwear. The request can be received from a seller, a purchaser, or an intermediary authenticating the footwear on behalf of the seller or purchaser. In some cases, the request includes a pressure distribution image of the footwear to be authenticated (e.g., a request from an intermediary with a pressure measurement machine). Additionally or alternatively, the request can include one or more of a serial number associated with the footwear, a year purchased or manufactured, or a brand / model of the footwear. In some cases, the request does not include a pressure distribution image, but includes a reference to a pressure distribution image uploaded to the image data storage device 206.

[0043] In operation 404, the image analysis component 204 accesses a previously uploaded pressure distribution image of the footwear. In some cases, the pressure distribution image can be received from an entity different from the user who sent the request. For example, the footwear in question may be a return from the purchaser to the seller and delivered to an intermediary who performs the authenticity determination. In this case, the intermediary may have a pressure measurement machine that generates a pressure distribution image and uploads the pressure distribution image to the image data storage device 206. Here, the authenticity determination request may be sent by an individual associated with the seller or the intermediary. A similar scenario may be that the intermediary receives the footwear from the seller before delivering it to the purchaser and performs the authenticity determination on behalf of the purchaser (e.g., the request is from the purchaser or the intermediary). Furthermore, the seller may want to pre-authenticate the footwear before offering it for sale (e.g., the request is from the seller or the intermediary). In some embodiments where the request includes a pressure distribution image, operation 404 is skipped (e.g., operation 404 is optional or not required).

[0044] In operation 406, the image analysis component 204 pre-processes the pressure distribution image of the test footwear. For example, the test footwear may be of a size for which the authenticity determination system 116 does not have pressure distribution data for authenticity determination. In these cases, the image analysis component 204 "resizes" the image to a size for which the authenticity determination system 116 has pressure distribution data for authenticity determination. In embodiments in which resizing is not required, operation 406 is optional or not required.

[0045] In embodiments that use statistical analysis, method 400 proceeds to operation 408 where statistical image analysis is performed. Operation 408 is described in more detail in connection with FIG. 5 below. In embodiments that use machine learning analysis, method 400 proceeds to operation 410 where machine learning analysis is performed. Operation 410 is described in more detail in connection with FIG. 6 below.

[0046] At operation 412, an indication of the authenticity of the footwear is provided. In some cases, the indication may be displayed on a user interface of the client device 106 via the client application 108. In other cases, an electronic communication (e.g., email, text message) may be generated and sent to the client device 106. When the item being authenticated is (or will be) listed for sale using the network system 102, a badge indicating the authenticity of the footwear may be included graphically in a display of the listing for the footwear.

[0047] 5 is a flow chart illustrating operations (e.g., operation 408) of a method 500 for pressure distribution image analysis according to an exemplary embodiment. The operations in the method 500 may be performed by the authenticity determination system 116 using the components described above with respect to FIG. 2. Thus, the method 500 is described by way of example with reference to the authenticity determination system 116. However, it should be appreciated that at least some of the operations of the method 500 may be deployed on various other hardware configurations or may be performed by similar components present elsewhere in the network environment 100. Thus, the method 500 is not intended to be limited to the authenticity determination system 116.

[0048] In operation 502, the evaluation component 212 applies the pressure distribution image to a statistical model. In certain embodiments, the statistical model comprises a statistical image model that is trained to identify multiple colors (e.g., multiple shades of color) at different locations on the pressure distribution image. In some cases, the statistical image model can generate a color / location dataset.

[0049] In operation 504, the evaluation component 212 compares the color / location dataset from the pressure distribution image of the footwear to be authenticated to a corresponding color / location dataset accessed from the pressure data store 214. The evaluation component 212 uses the identifier / information associated with the footwear (e.g., received with the request) to access the corresponding color / location dataset of the authentic footwear. In some cases, the pressure data store 214 includes different pressure distributions for different years of the same brand / model. Thus, the information associated with the footwear may include the year of purchase or year of manufacture and / or the place of manufacture of the footwear.

[0050] The evaluation component 212 compares the color (representing the pressure measurements) at multiple locations along the sole to a dataset of corresponding colors / locations for the sole of genuine footwear. In performing its comparison, the evaluation component 212 may determine whether each of the color / location measurements is within a comparison threshold (e.g., 95%) of the corresponding color / location measurements for genuine footwear.

[0051] In operation 506, the threshold component 216 determines an authenticity score based on the comparison. The authenticity score may include a percentage of a number of locations where the pressure measurements of the test footwear are within the comparison threshold of the corresponding pressure measurements of the genuine article. For example, if 9 out of 10 locations are within the threshold of the corresponding pressure measurements of the genuine article, the authenticity score is 0.9 or 90%.

[0052] A determination is made whether the authenticity score meets (e.g., meets or exceeds) an authenticity threshold at operation 508. For example, if the pressure measurements at 90% of the locations (e.g., an authenticity threshold of 90% or 0.9) are within the corresponding pressure threshold for authentic footwear, the threshold component 216 labels the test footwear as authentic at operation 510. If the authenticity score does not meet the authenticity threshold, the footwear is labeled as a counterfeit item at operation 512.

[0053] In some cases, the authenticity threshold is the same for all types of footwear of a particular brand or category. In other cases, the authenticity threshold varies based on brand, model, and / or category. The authenticity threshold can be a default threshold, configurable by an operator of the authenticity determination system 116, or machine learned. For example, training the machine learning model can include training one or more models to determine the authenticity threshold.

[0054] 6 is a flow chart illustrating operations (e.g., operation 410) of a method 600 for performing machine learning pressure distribution image analysis according to an exemplary embodiment. Operations in the method 600 may be performed by the authenticity determination system 116 using the components described above with respect to FIG. 2. Thus, the method 600 is described by way of example with reference to the authenticity determination system 116. However, it should be appreciated that at least some of the operations of the method 600 may be deployed on various other hardware configurations or may be performed by similar components present elsewhere in the network environment 100. Thus, the method 600 is not intended to be limited to the authenticity determination system 116.

[0055] In operation 602, an ML authenticity determination model corresponding to the footwear to be authenticated is identified by the evaluation component 220. In some cases, a separate machine learning model is trained for each brand and model of authentic footwear. Alternatively, a machine learning model may be trained for a particular brand (e.g., Louis Vuitton, Gucci, Prada) or category of goods (e.g., designer sneakers, designer high heels). In these cases, a corresponding machine learning model is identified. Thus, operation 602 may be optional in cases where only a single ML authenticity determination model is trained.

[0056] In operation 604, the pressure distribution image of the test footwear is applied to the corresponding machine learning model by the evaluation component 220. In some cases, the entire pressure distribution image is applied to the ML authenticity determination model. In other cases, the evaluation component 220 can extract features from the pressure distribution image. For example, the features can include colors at different locations on the pressure distribution image. The features can then be formatted into one or more input vectors that are applied to the ML authenticity determination model by the evaluation component 220. In some cases, additional information can be formatted into one or more of the input vectors. The additional information can include, for example, a year (year manufactured, year purchased, etc.) and a location (e.g., manufactured) associated with the footwear.

[0057] In operation 606, a veracity or probability score is obtained from the ML veracity model. The probability score indicates the probability that the test footwear is authentic (e.g., the pressure distribution image of the test footwear matches the corresponding pressure distribution image of the authentic).

[0058] The authenticity score is then compared to an authenticity threshold by the threshold component 222 in operation 608. In some cases, the authenticity threshold is the same for all types of footwear of a particular brand or category. In other cases, the authenticity threshold varies based on brand, model, and / or category. For example, the authenticity threshold may be 0.8 or 80% probability for designer sneakers. The authenticity threshold may be a default threshold, configurable by an operator of the authenticity determination system 116, or machine learned.

[0059] At operation 610, a determination is made by threshold component 222 as to whether the authenticity score meets (e.g., meets or exceeds) an authenticity threshold. For example, an authenticity probability of 0.79 output by evaluation component 220 does not meet an authenticity threshold of 0.8. If the authenticity score or probability meets the authenticity threshold, threshold component 222 labels the footwear as genuine at operation 612. If the authenticity score or probability does not meet the authenticity threshold, the footwear is labeled as a counterfeit item at operation 614.

[0060] Some fakes may substitute a particular fake shoe for a real shoe (e.g., the real left shoe but the fake right shoe), so analysis can be performed on both the left and right shoes in a pair before labeling the pair as real.

[0061] Although exemplary embodiments are described above using pressure distribution images, alternative embodiments can use pressure distribution data such as pressure distribution tables or matrices that do not include graphics. In these embodiments, a table or matrix of pressure measurements at different positions (and times in the case of videos) can be obtained from a pressure measurement machine. Alternatively, the pressure distribution image can be pre-processed (e.g., by the image analysis component 204) to generate a table or matrix. The table or matrix can then be sent to the statistics system 208 or machine learning system 210 for analysis. The statistics system 208 can compare the values ​​in the table or matrix to a corresponding table or matrix of real values. Alternatively, the machine learning system can apply the values ​​in the table or matrix to a corresponding ML model.

[0062] 7 illustrates components of a machine 700 capable of reading instructions from a machine storage medium (e.g., a machine storage device, a non-transitory machine storage medium, a computer storage medium, or any suitable combination thereof) and performing any one or more of the methods described herein, according to some exemplary embodiments. In particular, FIG. 7 illustrates a schematic diagram of a machine 700 in the example form of a computing device (e.g., a computer) on which instructions 724 (e.g., software, programs, applications, applets, apps, or other executable code) may be executed, in whole or in part, to cause the machine 700 to perform any one or more of the methods described herein.

[0063] For example, the instructions 724 may cause the machine 700 to perform the flow diagrams of Figures 4-6. In particular embodiments, the instructions 724 may transform the machine 700 into a specific machine (e.g., a specially configured machine) that is programmed to perform the functions described and illustrated in the manner described.

[0064] In alternative embodiments, the machine 700 may operate as a stand-alone device or may be connected (e.g., networked) to other machines. In a networked configuration, the machine 700 may operate as a server or client machine in a server-client network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. The machine 700 may be a server computer, a client computer, a personal computer (PC), a tablet computer, a laptop computer, a netbook, a set-top box (STB), a personal digital assistant (PDA), a mobile phone, a smart phone, a web appliance, a network router, a network switch, a network bridge, or any machine capable of executing (sequentially or otherwise) instructions 724 that specify operations to be performed by the machine. Additionally, although only a single machine is shown, the term "machine" should also be construed to include a collection of machines that individually or together execute instructions 724 to perform any one or more of the methods described herein.

[0065] The machine 700 includes a processor 702 (e.g., a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), an application specific integrated circuit (ASIC), a radio frequency integrated circuit (RFIC), or any suitable combination thereof), a main memory 704, and a static memory 706, which are configured to communicate with each other via a bus 708. The processor 702 may include microcircuits that are temporarily or permanently configurable by some or all of the instructions 724 such that the processor 702 is configurable, in whole or in part, to perform any one or more of the methods described herein. For example, a set of one or more microcircuits of the processor 702 may be configurable to cause one or more components described herein to execute.

[0066] The machine 700 may further include a graphics display 710 (e.g., a plasma display panel (PDP), a light emitting diode (LED) display, a liquid crystal display (LCD), a projector, or a cathode ray tube (CRT), or any other display capable of displaying graphics or moving images). The machine 700 may also include input devices 712 (e.g., a keyboard), cursor control devices 714 (e.g., a mouse, a touchpad, a trackball, a joystick, a motion sensor, or other pointing device), a storage unit 716, a signal generation device 718 (e.g., a sound card, an amplifier, a speaker, a headphone jack, or any suitable combination thereof), and a network interface device 720.

[0067] Storage unit 716 includes a machine storage medium 722 (e.g., a tangible machine storage medium) on which are stored instructions 724 (e.g., software) that embody any one or more of the methods or functions described herein. The instructions 724 may also reside, completely or at least partially, in main memory 704, in processor 702 (e.g., in a processor's cache memory), or both before or during execution of the instructions by machine 700. Thus, main memory 704 and processor 702 can be considered to be machine storage media (e.g., a tangible and non-transitory machine storage medium). The instructions 724 can be transmitted or received over a network 726 via network interface device 720.

[0068] In some demonstrative embodiments, the machine 700 may be a portable computing device and may have one or more additional input components (e.g., sensors or gauges). Examples of such input components include an image input component (e.g., one or more cameras), an audio input component (e.g., a microphone), a direction input component (e.g., a compass), a position input component (e.g., a global positioning system (GPS) receiver), an orientation component (e.g., a gyroscope), a motion detection component (e.g., one or more accelerometers), an altitude detection component (e.g., an altimeter), and a gas detection component (e.g., a gas sensor). Inputs collected by any one or more of these input components may be accessible and available for use by any of the components described herein.

[0069] Executable Instructions and Machine Storage Media Various memories (e.g., 704, 706, and / or memory of processor(s) 702) and / or storage units 716 may store one or more sets of instructions and data structures (e.g., software) 724 that embody or are utilized by any one or more of the methods or functions described herein. These instructions, when executed by the one or more processors 702, cause various operations to be performed for implementing the disclosed embodiments.

[0070] As used herein, the terms "machine storage medium," "device storage medium," and "computer storage medium" (collectively "machine storage medium 722") mean the same thing and may be used interchangeably in this disclosure. These terms refer to a single or multiple storage devices and / or media (e.g., centralized or distributed databases, and / or associated caches and servers) that store executable instructions and / or data, as well as a cloud-based storage system or storage network that includes multiple storage devices or devices. Thus, these terms shall be interpreted to include, but are not limited to, solid-state memory, including memory internal or external to a processor, as well as optical and magnetic media. Specific examples of machine storage medium, computer storage medium, and / or device storage medium 722 include, for example, non-volatile memory, including semiconductor memory devices such as erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), FPGA, and flash memory devices, magnetic disks such as internal hard disks and removable disks, magneto-optical disks, and CD-ROM and DVD-ROM disks. The terms "machine storage medium" or "computer storage medium" or "device storage medium" or "device storage medium" 722 specifically exclude carrier waves, modulated data signals, and other such media, at least some of which are covered under the term "signal media" described below. In this context, mechanical storage media are non-transitory.

[0071] signal medium The terms "signal media" or "transmission media" shall be interpreted to include any form of modulated data signal, carrier wave, etc. The term "modulated data signal" means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal.

[0072] Computer-Readable Medium The terms "machine-readable medium," "computer-readable medium," and "device-readable medium" mean the same thing and may be used interchangeably in this disclosure. These terms are defined to include both mechanical storage media and signal media. Thus, these terms include both storage devices / media and carrier waves / modulated data signals.

[0073] The instructions 724 may further be transmitted or received over a communications network 726 using a transmission medium via the network interface device 720 and utilizing any one of a number of well-known transfer protocols (e.g., HTTP). Examples of communications networks 726 include a local area network (LAN), a wide area network (WAN), the Internet, a cellular network, a plain old telephone service (POTS) network, and wireless data networks (e.g., Wi-Fi, LTE, and WiMAX networks). The term "transmission medium" shall be taken to include any intangible medium capable of storing, encoding, or carrying the instructions 724 for execution by the machine 700, including digital or analog communications signals or other intangible media for enabling communication of such software.

[0074] Throughout this specification, multiple instances may implement components, operations, or structures described as a single instance. Although individual operations of one or more methods are illustrated and described as separate operations, one or more of the individual operations may occur simultaneously, and there is no requirement that the operations occur in the order shown. Structures and functions presented as separate components in an exemplary configuration may be implemented as a combined structure or component. Similarly, structures and functions presented as a single component may be implemented as separate components. These and other variations, modifications, additions, and improvements are encompassed within the scope of the subject matter of this specification.

[0075] A "component" refers to a device, physical entity, or logic with boundaries defined, for example, by function or subroutine calls, branch points, application programming interface APIs, or other techniques that provide partitioning or modularization of particular processing or control functions. Multiple components can be combined through interfaces with other components to perform machine processing. A component is a packaged functional hardware unit designed for use with other components, and may be a part of a program that typically performs a particular function among multiple related functions. Multiple components can constitute either software components (e.g., code embodied in a machine-readable medium) or hardware components.

[0076] A "hardware component" is a tangible unit capable of performing certain operations and may be configured or arranged in a particular physical manner. In various exemplary embodiments, one or more computer systems (e.g., a stand-alone computer system, a client computer system, or a server computer system) or one or more hardware components of a computer system (e.g., a processor or group of processors) may be configured by software (e.g., an application or application portion) as a hardware component that operates to perform certain operations as described herein.

[0077] In some embodiments, a hardware component may be implemented mechanically, electronically, or any suitable combination thereof. For example, a hardware component may comprise dedicated circuitry or logic permanently configured to perform a particular operation. For example, a hardware component may be a special-purpose processor such as a field programmable gate array (FPGA) or an ASIC. A hardware component may comprise programmable logic or circuitry temporarily configured by software to perform a particular operation. For example, a hardware component may comprise software contained within a general-purpose processor or other programmable processor. Once configured by such software, a hardware component is no longer a general-purpose processor, as it becomes a specific machine (or a specific component of a machine) uniquely tailored to perform the function for which it is configured. It will be appreciated that the decision to implement a hardware component mechanically, in dedicated permanently configured circuitry, or in temporarily configured circuitry (e.g., configured by software) may be driven by cost and time considerations.

[0078] Thus, the term "hardware component" should be understood to encompass a tangible entity that is physically constructed, permanently configured (e.g., hardwired), or temporarily configured (e.g., programmed) to operate in a particular manner or to perform a particular operation described herein. Given examples in which hardware components are temporarily configured (e.g., programmed), each of the hardware components need not be configured or instantiated at any one instance. For example, if a hardware component comprises a general-purpose processor that is configured by software to be a special-purpose processor, the general-purpose processor may be configured at different times as different special-purpose processors (e.g., with different hardware components). Thus, the software may, for example, configure the processor to configure a particular hardware component at one instance of time while configuring a different hardware component at a different instance of time.

[0079] Hardware components can provide information to and receive information from other hardware components. Thus, the described hardware components can be considered to be communicatively coupled. When multiple hardware components are present contemporaneously, communication can be achieved by signal transmission between or among two or more of the multiple hardware components (e.g., via appropriate circuits and buses). In examples where multiple hardware components are configured or instantiated at different times, communication between such hardware components can be achieved, for example, through storage and retrieval of information in memory structures accessed by the multiple hardware components. For example, a hardware component can not only perform an operation but also store the output of that operation in a memory device to which it is communicatively coupled. Another hardware component can then retrieve and process the stored output by subsequently accessing the memory device. Multiple hardware components can initiate communication with input or output devices or operate on resources (e.g., collections of information).

[0080] Various operations of the example methods described herein may be performed, at least in part, by one or more processors that are temporarily (e.g., by software) or permanently configured to perform the associated operations. Whether temporarily or permanently configured, such processors may constitute processor-implemented components that operate to perform one or more operations or functions described herein. As used herein, a "processor-implemented component" refers to a hardware component that is implemented using one or more processors.

[0081] Similarly, the methods described herein may be at least partially processor-implemented, with a processor being an example of hardware. For example, at least some of the operations of the methods may be performed by one or more processors or processor-implemented components. Furthermore, one or more processors may operate to support execution of associated operations in a "cloud computing" environment or as "software as a service" (SaaS). For example, at least some of the operations may be performed by a group of computers (as an example of a machine including multiple processors), and these operations are accessible via a network (e.g., the Internet) and via one or more suitable interfaces (e.g., application program interfaces (APIs)).

[0082] Certain performance of operations may reside not only within a single machine, but may be distributed among one or more processors deployed across multiple machines. In some exemplary embodiments, one or more processors or processor-implemented components may be located in a single geographic location (e.g., in a home environment, an office environment, or a server farm). In other exemplary embodiments, one or more processors or processor-implemented components may be distributed across multiple geographic locations.

[0083] Multiple Examples Example 1 is a method for authenticating footwear using pressure distribution image analysis, the method comprising: receiving a request to authenticate footwear; accessing a pressure distribution image for the footwear, the pressure distribution image including a pressure distribution represented by a plurality of colors generated based on a preset force applied to the footwear; analyzing the pressure distribution image, the analyzing including comparing the pressure distribution image with a pressure distribution image of genuine footwear; determining whether the pressure distribution image is within an authenticity threshold of the pressure distribution image of the genuine footwear based on the analyzing; and causing an indication of authenticity of the footwear to be presented based on the pressure distribution image being within the authenticity threshold.

[0084] In Example 2, the subject matter of Example 1 may optionally include that analyzing the pressure distribution image includes applying the pressure distribution image for the footwear to a machine learning model trained with training data that includes data derived from the pressure distribution image of the genuine footwear.

[0085] In Example 3, the subject matter of Example 1 or Example 2 may optionally include further comprising training the machine learning model using the training data derived from the pressure distribution images for real footwear and fake footwear.

[0086] In Example 4, the subject matter of any of Examples 1-3 may optionally include, where training the machine learning model includes training by year for each of the authentic footwear, and analyzing includes basing in part on a year of the item.

[0087] In Example 5, the subject matter of any of Examples 1-4 may optionally include, wherein the pressure distribution image includes a pressure distribution heat map or a pedobarography measurement image generated based on forces applied to the footwear.

[0088] In Example 6, the subject matter of any of Examples 1-5 may optionally include, wherein the pressure distribution image includes an animation of dynamic pressure distribution during a process performed with the footwear by a pressure measuring machine.

[0089] In Example 7, the subject matter of any of Examples 1 to 6 may optionally include the request including a brand, model, and size of the footwear to be determined to be authentic, and the method including determining whether the footwear to be determined to be authentic is the same size as the real footwear, and resizing the pressure distribution image of the footwear to correspond to the size of the real footwear based on the footwear being a different size.

[0090] In Example 8, the subject matter of any of Examples 1-7 may optionally include that accessing the pressure distribution image of the footwear includes generating the pressure distribution image for the footwear using a pressure measuring machine having a plurality of sensors and an artificial foot that applies the preset force to the footwear.

[0091] In Example 9, the subject matter of any of Examples 1-8 may optionally include where presenting the indication of authenticity includes graphically displaying an authenticity badge on the listing for the footwear.

[0092] Example 10 is a system for authenticating footwear using pressure distribution image analysis, the system comprising one or more processors and a memory storing a plurality of instructions that, when executed by the one or more processors, cause the one or more processors to perform a plurality of operations, the plurality of operations comprising: receiving a request to authenticate footwear; accessing a pressure distribution image for the footwear, the pressure distribution image including a pressure distribution represented by a plurality of colors generated based on a preset force applied to the footwear; analyzing the pressure distribution image, the analyzing including comparing the pressure distribution image with a pressure distribution image of genuine footwear; determining whether the pressure distribution image is within an authenticity threshold of the pressure distribution image of the genuine footwear based on the analyzing; and presenting an indication of authenticity of the footwear based on the pressure distribution image being within the authenticity threshold.

[0093] In Example 11, the subject matter of Example 10 may optionally include that analyzing the pressure distribution image includes applying the pressure distribution image for the footwear to a machine learning model trained with training data that includes data derived from the pressure distribution image of the genuine footwear.

[0094] In Example 12, the subject matter of Example 10 or Example 11 may optionally include, wherein the method further comprises training the machine learning model using training data derived from the pressure distribution images for real footwear and fake footwear.

[0095] In Example 13, the subject matter of any of Examples 10-12 may optionally include, where training the machine learning model includes training by year for each of the authentic footwear, and analyzing includes basing in part on the year of the item.

[0096] In Example 14, the subject matter of any of Examples 10-13 may optionally include that the pressure distribution image includes a pressure distribution heat map or a pedobarography measurement image generated based on forces applied to the footwear.

[0097] In Example 15, the subject matter of any of Examples 10-14 may optionally include, wherein the pressure distribution image includes a video of dynamic pressure distribution during a process performed with the footwear by a pressure measuring machine.

[0098] In Example 16, the subject matter of any of Examples 10 to 15 may optionally include the request including a brand, model, and size of the footwear to be determined as authentic, and the method including determining whether the footwear to be determined as authentic is the same size as the real footwear, and resizing the pressure distribution image of the footwear to correspond to the size of the real footwear based on the footwear being a different size.

[0099] In Example 17, the subject matter of any of Examples 10 to 16 may optionally include that accessing the pressure distribution image of the footwear includes generating the pressure distribution image for the footwear using a pressure measuring machine having a plurality of sensors and an artificial foot that applies the predetermined force to the footwear.

[0100] In Example 18, the subject matter of any of Examples 10-17 may optionally include where presenting the indication of authenticity includes graphically displaying a badge indicating authenticity in the listing for the footwear.

[0101] Example 19 is a computer storage medium including a plurality of instructions that, when executed by one or more processors of a machine, cause the machine to perform a plurality of operations for authenticating footwear using pressure distribution image analysis, the plurality of operations including receiving a request to authenticate footwear, accessing a pressure distribution image for the footwear, the pressure distribution image including a pressure distribution represented by a plurality of colors generated based on a preset force applied to the footwear, analyzing the pressure distribution image including comparing the pressure distribution image with a pressure distribution image of genuine footwear, determining whether the pressure distribution image is within an authenticity threshold of the pressure distribution image of the genuine footwear based on the analyzing, and presenting an indication of authenticity of the footwear based on the pressure distribution image being within the authenticity threshold.

[0102] In Example 20, the subject matter of Example 19 may optionally include that accessing the pressure distribution image of the footwear includes generating the pressure distribution image for the footwear using a pressure measuring machine having an artificial foot that applies a preset pressure to the footwear.

[0103] Some portions of this specification are presented in terms of algorithms or symbolic representations of operations on data stored as bits or binary digital signals in a machine memory (e.g., computer memory). These algorithms or symbolic representations are examples of techniques used by those skilled in the data processing arts to convey the substance of their work to others skilled in the art. As used herein, an "algorithm" is a self-consistent sequence of operations or similar processes that lead to a desired result. In this context, algorithms and operations involve physical manipulations of physical quantities. Usually, though not necessarily, such quantities take the form of electrical, magnetic, or optical signals capable of being stored, accessed, transferred, combined, compared, or otherwise operated on (manipulated) by a machine. It is sometimes convenient, primarily for reasons of common usage, to refer to such signals using words such as "data," "content," "bits," "values," "elements," "symbols," "characters," "terms," ​​"numbers," "digits," and the like. However, these terms are merely convenient labels and should be associated with the appropriate physical quantities.

[0104] Unless otherwise specifically stated, descriptions herein using terms such as "processing," "computing," "calculating," "determining," "presenting," "displaying," and the like refer to machine (e.g., computer) operations or processes that manipulate or transform data represented as physical (e.g., electronic, magnetic, or optical) quantities in one or more memories (e.g., volatile memory, non-volatile memory, or any suitable combination thereof), registers, or other machine components that receive, store, transmit, or display information. Furthermore, unless otherwise indicated, the articles "a" or "an" are used herein to include one or more instances, as is common in patent documents. Finally, as used herein, the conjunction "or" refers to a non-exclusive "or" unless otherwise specifically stated.

[0105] Although the summary of the present subject matter has been described with reference to certain examples, various modifications and changes can be made to these examples without departing from the broader scope of the examples of the present invention. For example, the various examples or features thereof may be mixed and matched or selected by those skilled in the art. Such examples of the present subject matter may be referred to herein, individually or collectively, under the term "invention" merely for convenience, but are not intended to spontaneously limit the scope of the present application to any single invention or concept when in fact more than one is disclosed.

[0106] The examples provided herein are believed to be described in sufficient detail to enable those skilled in the art to practice the teachings disclosed. Other examples may be used and derived therefrom, such that structural and logical substitutions and changes may be made without departing from the scope of the present disclosure. Thus, the Detailed Description is not to be construed in a limiting sense, and the scope of the various examples is defined solely by the appended claims, along with the full scope of equivalents to which such claims are entitled.

[0107] Further, instances may be provided for resources, operations, or structures described herein as a single instance. In addition, boundaries between various resources, operations, modules, engines, and data stores are somewhat arbitrary, with particular operations being illustrated in the context of a particular example configuration. Other allocations of functionality are contemplated and may be included within the scope of various examples of the invention. In general, structures and functionality presented as separate resources in an example configuration may be implemented as combined structures or resources. Similarly, structures and functionality presented as a single resource may be implemented as separate resources. These and other variations, modifications, additions, and improvements are within the scope of the examples of the invention as expressed by the appended claims. The specification and drawings are therefore to be regarded in an illustrative and not a restrictive sense.

Claims

1. 1. A method comprising: Receiving a request to authenticate an item of footwear; accessing a pressure distribution image for the footwear, the pressure distribution image including a pressure distribution represented by a plurality of colors generated based on a preset force applied to the footwear; analyzing the pressure distribution image with an image analysis system, the analyzing including comparing the pressure distribution image with a pressure distribution image of a genuine piece of footwear; determining whether the pressure distribution image is within an authenticity threshold of the genuine pressure distribution image based on the analyzing; and presenting an indication of authenticity of the footwear based on the pressure distribution image being within the authenticity threshold.

2. Analyzing the pressure distribution image includes:

2. The method of claim 1 , comprising applying the pressure distribution image for the footwear to a machine learning model trained with training data that includes data derived from the pressure distribution image of the genuine footwear.

3. The method of claim 2 , further comprising training the machine learning model with the training data derived from the pressure distribution images for real and fake footwear.

4. training the machine learning model includes training on each of the authentic footwear by year; The method of claim 3 , wherein the analyzing is based in part on a year of the product.

5. The method of claim 1 , wherein the pressure distribution image comprises a pressure distribution heat map or a pedobarography measurement image generated based on forces applied to the footwear.

6. The method of claim 1 , wherein the pressure distribution image comprises an animation of a dynamic pressure distribution during a process performed with the footwear by a pressure measuring machine.

7. The request includes a brand, model, and size of the footwear to be authenticated; Determining whether the footwear to be determined as authentic is the same size as the genuine footwear; and resizing the pressure distribution image of the footwear to correspond to a size of the real footwear based on the footwear being a different size.

8. Accessing the pressure distribution image of the footwear includes:

2. The method of claim 1, comprising generating the pressure distribution image for the footwear using a pressure measuring machine having an artificial foot equipped with a plurality of sensors and applying the preset forces to the footwear.

9. Providing the indication of authenticity includes: The method of claim 1 , comprising graphically displaying an authenticity badge in the footwear listing.

10. 1. A system comprising: one or more processors; a memory storing a plurality of instructions that, when executed by the one or more processors, cause the one or more processors to perform a plurality of operations; The plurality of operations include: Receiving a request to authenticate an item of footwear; accessing a pressure distribution image for the footwear, the pressure distribution image including a pressure distribution represented by a plurality of colors generated based on a preset force applied to the footwear; analyzing the pressure distribution image, the analyzing including comparing the pressure distribution image with a pressure distribution image of a genuine piece of footwear; determining whether the pressure distribution image is within an authenticity threshold of the genuine pressure distribution image based on the analyzing; and presenting an indication of authenticity of the footwear based on the pressure distribution image being within the authenticity threshold.

11. The system of claim 10 , wherein analyzing the pressure distribution image includes applying the pressure distribution image for the footwear to a machine learning model trained with training data that includes data derived from the pressure distribution image of the genuine footwear.

12. The plurality of operations include: The system of claim 11 , further comprising training the machine learning model with the training data derived from the pressure distribution images for real and fake footwear.

13. training the machine learning model includes training on each of the authentic footwear by year; The system of claim 12 , wherein the analyzing is based in part on a year of the product.

14. The system of claim 10 , wherein the pressure distribution image comprises a pressure distribution heat map or a pedobarography measurement image generated based on forces applied to the footwear.

15. The system of claim 10 , wherein the pressure distribution image comprises an animation of dynamic pressure distribution during a process performed with the footwear by a pressure measuring machine.

16. The request includes a brand, model, and size of the footwear to be authenticated; The method comprises: Determining whether the footwear to be determined as authentic is the same size as the genuine footwear; and resizing the pressure distribution image of the footwear to correspond to a size of the real footwear based on the footwear being a different size.

17. Accessing the pressure distribution image of the footwear includes:

11. The system of claim 10, comprising generating the pressure distribution image for the footwear using a pressure measuring machine having an artificial foot equipped with a plurality of sensors and applying the preset force to the footwear.

18. Providing the indication of authenticity includes: The system of claim 10, further comprising graphically displaying an authenticity badge in the footwear listing.

19. A machine storage medium containing a plurality of instructions that, when executed by one or more processors of a machine, cause the machine to perform a plurality of operations; The plurality of operations include: Receiving a request to authenticate an item of footwear; accessing a pressure distribution image for the footwear, the pressure distribution image including a pressure distribution represented by a plurality of colors generated based on a preset force applied to the footwear; analyzing the pressure distribution image, the analyzing including comparing the pressure distribution image with a pressure distribution image of a genuine piece of footwear; determining whether the pressure distribution image is within an authenticity threshold of the genuine pressure distribution image based on the analyzing; and presenting an indication of authenticity of the footwear based on the pressure distribution image being within the authenticity threshold.

20. Accessing the pressure distribution image of the footwear includes:

20. The machine storage medium of claim 19, comprising generating the pressure distribution image for the footwear using a pressure measurement machine having an artificial foot that applies a preset pressure to the footwear.

Images