Cooking level determination

Abstract

In an embodiment, a cooking method (100) is described. The method includes receiving (102) image data corresponding to a view of a food product during a cooking process performed by a cooking device. The method also includes identifying (104) a region of interest in the view. The region of interest includes an indication of liquid leached from the food product as a result of the cooking process. The method further includes determining (106) a cooking level of the food product based on the distribution of liquid on the surface in the view and a parameter value indicative of a cooking level 5 of the food product. The parameter value is derived from a portion of the image data corresponding to the region of interest.

Description

Technical Field

[0001] The present invention relates to a cooking method, a non-transitory machine-readable medium, and a cooking device for determining a cooking level of food. Background Art

[0002] Foods such as meat are usually cooked according to certain safety standards (e.g., killing harmful bacteria) and taste purposes (e.g., making foods such as meat tender and juicy). In order to meet such standards, food can be cooked so that the core temperature and weight loss of the food indicate a specific cooking level or degree of doneness of the food. The cooking level may refer to whether the food is raw, undercooked, cooked (where the food has a desired tenderness, juiciness and / or color (e.g., brown) level) or overcooked (where the food is hard, dry and / or too brown / burnt). It is possible to determine the cooking level of the food based on the core temperature and / or the weight loss of the food as a result of the cooking process. In the case of meat, during the cooking process, the core temperature of the meat increases, while the weight of the meat decreases (due to liquid leaching). In order to be safe to eat, meat usually needs to be cooked to reach a specific core temperature. By way of example, chicken may need to be cooked so that its core temperature is in the range of 73.8°C to 93.2°C, while salmon or whole fish may need to be cooked so that its core temperature is in the range of 65°C to 85°C. However, some meats such as steak may be cooked to a lower core temperature than other meats and be relatively safer. The steak may need to be cooked so that its core temperature is in the range of 68° C. to 80° C. By way of example, the weight loss associated with cooking meat may be in the range of 15% to 25%.

[0003] Thus, measurements of core temperature and / or weight loss during the cooking process can be used to determine the level of cooking of the food. For example, during the cooking process, a temperature probe can be inserted into the core of the food to measure the core temperature. In another example, a scale can be used to measure the weight of the food during the cooking process.

[0004] Temperature probes are relatively simple to use and allow the user to determine whether food is sufficiently cooked to be safe to eat. However, temperature probes cannot indicate other parameters of interest, such as juiciness, tenderness, etc.

[0005] The use of a scale is not simple, because the weight variation of food such as meat is mainly due to the leaching of water, fat and other liquid components from the meat onto the cooking surface. A separation mechanism is required to prevent the leached liquid from affecting the measured weight of the meat. The use of such a separation mechanism adds complexity, and sometimes the leached liquid is desired by the user because it adds a flavor element to the food.

[0006] Cooking devices such as ovens, air fryers, etc. may provide preset recipes as a reference for recommended cooking times and heating temperatures for food. However, various factors may affect the accuracy of the recipes, such as room temperature, accuracy of cooking temperature, initial food temperature, food thickness, food quantity, etc. Therefore, users may not be able to create consistent results by following preset recipes. Summary of the invention

[0007] Certain aspects or embodiments described herein relate to determining the cooking level of a food product. Certain aspects or embodiments may reduce or eliminate certain problems as described herein.

[0008] In a first aspect, a cooking method is described. The cooking method includes receiving image data corresponding to a view of a food product during a cooking process performed by a cooking device. The method also includes identifying a region of interest in the view. The region of interest includes an indication of liquid leached from the food product as a result of the cooking process. The method also includes determining a cooking level of the food product based on: a distribution of liquid on a surface in the view; and a parameter value indicative of the cooking level of the food product. The parameter value is derived from a portion of the image data corresponding to the region of interest.

[0009] Some embodiments related to the first aspect and other aspects are now described.

[0010] In some embodiments, the distribution of liquid on the surface indicates the volume of liquid that has leached from the food as a result of the cooking process. The volume of leached liquid indicates the cooking level of the food.

[0011] In some embodiments, the distribution of the liquid is indicated by an area of ​​the liquid on the surface.The region of interest comprises at least a portion of the area.

[0012] In some embodiments, the distribution is indicated by a flow path of the liquid on the surface.The region of interest includes locations along the flow path.

[0013] In some embodiments, the location of the region of interest is selected based on the prediction of the flow path.The selected location is indicative of the cooking level of the food product.

[0014] In some embodiments, the method further comprises determining a distribution of the liquid on the surface by: identifying a portion of the image data indicative of the presence of the liquid; and determining the distribution based on a geometric measurement derived from the portion of the image data.

[0015] In some embodiments, the cooking level of the food product is determined based on a model that indicates a cooking level based on a profile.

[0016] In some embodiments, the method further comprises predicting an expected distribution of the liquid based on knowledge of the surface and / or historical data of previously observed distributions of the liquid on the surface. The method may also comprise designing a model to account for the expected distribution of the liquid on the surface such that the model indicates a cooking level of the food in response to a determined distribution that follows the expected distribution.

[0017] In some embodiments, the parameter value indicative of the cooking level of the food product is derived from the pixel intensity data used to create the image data.

[0018] In some embodiments, the parameter value comprises a color value derived from the pixel intensity data of the region of interest and / or an intensity value derived from the pixel intensity data of the region of interest.

[0019] In some embodiments, the method further comprises comparing the image data to previously acquired image data to determine a parameter value.

[0020] In some embodiments, a comparison of the image data with previously acquired image data indicates a change in intensity and / or color of a portion of the image data corresponding to the region of interest. A parameter value is determined based on the change.

[0021] In some embodiments, the method further includes determining a cooking level of the food by comparing the parameter value to a threshold value indicative of the cooking level.

[0022] In a second aspect, a non-transitory machine-readable medium is described. The non-transitory machine-readable medium stores instructions that can be read and executed by a processor to implement the cooking method of any one of the first aspect or related embodiments.

[0023] In a third aspect, a cooking device is described. The cooking device is used to implement a cooking process. The cooking device includes a cooking chamber for receiving food. The cooking device also includes a housing defining the cooking chamber. The cooking device also includes an air circulation system for circulating an air flow inside the cooking chamber. The cooking device also includes a camera for capturing images during the cooking process. The cooking device also includes a controller. The controller is configured to implement the cooking method of the first aspect or a related embodiment.

[0024] Certain aspects or embodiments described herein may provide various technical benefits as follows. Certain embodiments may allow the cooking level of a food to be determined in a contactless manner (i.e., based on analysis of image data). Certain embodiments may reduce the complexity of determining the cooking level of a food (e.g., the cooking level may be determined using reduced computing resources and / or the model used to determine the cooking level may not rely on complex methods, such as artificial intelligence-based models). Certain embodiments may facilitate analysis of the cooking level on a consumer device (e.g., a cooking device) that has computing resource constraints in terms of memory and / or processing resources (e.g., because the method implemented by the consumer device is relatively simple). Certain embodiments may reduce user intervention during the cooking process (e.g., because the user may not need to do anything during the cooking process), facilitating an automatic cooking process that adapts to changes in user skills, recipes used, environment, cooking devices used, etc. Certain embodiments may provide indications of cooking level parameters that are difficult to assess, such as juiciness or tenderness.

[0025] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiment(s) described hereinafter. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Exemplary embodiments of the present invention will now be described, by way of example only, with reference to the following drawings, in which:

[0027] Figure 1 Relating to a cooking method according to an embodiment;

[0028] Figure 2 is a schematic diagram of a cooking ecosystem according to an embodiment;

[0029] Figure 3 is a schematic diagram of a cooking device for implementing a cooking process according to an embodiment;

[0030] Figure 4 (a) to (c) schematically depict example images of food during a cooking process according to an embodiment, and Figure 4 (d) schematically depicts the Figure 4 (c) the liquid leached from the food as depicted;

[0031] Figure 5 Relating to a cooking method according to an embodiment;

[0032] Figure 6 (a) to (b) are graphs representing experimental data collected during a cooking process implemented according to various embodiments;

[0033] Figure 7 Relating to a cooking method according to an embodiment;

[0034] Figure 8 (a) to (d) schematically depict example images of food during a cooking process according to an embodiment;

[0035] Fig. 9 relates to cooking methods according to various embodiments;

[0036] Fig.10 is a schematic diagram of a machine-readable medium for implementing various embodiments; and

[0037] Fig.11 is a schematic diagram of an apparatus for implementing various embodiments. DETAILED DESCRIPTION

[0038] As used herein, a "cooking process" refers to the application of heat to a food product to cause a change in the food product. Such application of heat may result in the food product merely being warmed, or may cause a greater change in the food product, such as may be achieved using a cooking method such as baking, grilling, frying, air frying, etc.

[0039] As used herein, "cooking device" refers to any device capable of applying heat to food to complete the above-mentioned cooking process. Heat can be applied to food by the cooking device in one or more ways, such as by conduction, convection, or radiation. Examples of cooking devices include: ovens, microwave ovens, hobs, air fryers, etc.

[0040] As used herein, "cooking level" refers to (e.g., at least one) parameter that indicates how well a food is cooked as a result of a cooking process. The parameter may include the food's core temperature, surface temperature, juiciness, tenderness, color (e.g., degree of browning), etc. Thus, any number or combination of these parameters may indicate the cooking level of a food.

[0041] The camera can be used to capture images of food during the cooking process. Therefore, consumers can watch a video of the cooking process in real time or save a video of the cooking process. During the cooking process, the food may have various visual changes, such as surface color changes, liquid leaching, meat size changes, etc. These visual changes can be detected in the images captured during the cooking process.

[0042] Normally, meat is composed of 70% to 80% water. The cooking process causes the meat muscles to shrink, causing water and other chemical components (e.g., fat, protein, etc.) to leach out of the meat. Therefore, the cooking level of the meat can be proportional to the volume of liquid that is leached out of the meat. In addition, the volume of liquid that is leached out of the meat can indicate the juiciness of the meat. For example, if too much liquid is leached out, the meat may become hard and dry. Since the collagen in the meat decomposes (e.g., melts) at about 70°C, during the cooking process, as the temperature increases, the water and other components trapped by the collagen are released from the meat at an increasingly faster rate. Since the core of the meat usually takes the longest time to reach this temperature during the cooking process, the rate of liquid leached out as a result of the cooking process can increase when the surface of the meat reaches 70°C, and this increase in the rate of leaching liquid will continue for at least a period of time after the core of the meat also reaches 70°C (during which the surface of the meat will dry and / or turn brown). Therefore, liquid leaching is a potential good indicator of the cooking level of the meat, and other foods can also leach liquid, such as certain meat substitutes and certain vegetables.

[0043] Certain embodiments described herein may provide an improved method of determining the cooking level of a food product.

[0044] Figure 1 It relates to a cooking method 100 according to an embodiment. The cooking method 100 may be computer-implemented, for example by a processor of a cooking device, as described in more detail below. Image data may be acquired by a camera during the cooking process.

[0045] The cooking method 100 includes, at block 102 , receiving image data corresponding to a view of a food product during a cooking process performed by a cooking device.

[0046] In some cases, image data may refer to (e.g., raw) imaging data acquired by a camera. In some cases, the image data may have been processed after being acquired by the camera. In either case, image data may refer to any data that may represent at least a portion of a view of a food product. Depending on any processing that occurs before receiving image data for implementing the cooking method 100, the image data may be in any suitable image format. For example, the image data may include pixel intensity data (e.g., pixel intensity values ​​for each color channel). The color channel may be based on any appropriate color model. For example, a color model may include a red-green-blue (RGB) color model, a hue-saturation-value (HSV) color model, and the like.

[0047] The cooking method 100 also includes identifying a region of interest in the view at block 104. The region of interest includes an indication of liquid leached from the food product as a result of the cooking process.

[0048] The area of ​​interest in the view may correspond to a portion of the image data (e.g., pixel intensity data) where the presence of liquid leaching is detectable (e.g., via analysis of the image data, as described below). In some cases, the area of ​​interest may include a portion of a surface on which liquid leaching may be detected. The surface may support the food during the cooking process. Thus, as a result of the liquid leaching covering the surface, any liquid leaching that flows onto the surface may be detected via a change in the appearance of the surface (e.g., a change in color, reflectivity, etc.). During the cooking process, the liquid leaching itself may change color (e.g., it may become more brown over time). Thus, certain changes in the appearance of the surface may indicate the presence of liquid leaching from the food.

[0049] In some cases, the area of ​​interest may include the entire area of ​​the leached liquid. In some cases, the area of ​​interest may include or correspond to a portion (or a small portion) of the entire area of ​​the leached liquid. Identifying the area of ​​interest may include identifying such area or portion of the area of ​​the leached liquid. Image analysis can be used to identify the area of ​​interest, for example, based on observed changes in image data acquired at different times during the cooking process. For example, pixel intensity data may change as a result of the cooking process. Pixel intensity data acquired at different times during the cooking process can be compared to identify any changes in the pixel intensity data that indicate the presence of the leached liquid. In some cases, any such identification of the area of ​​interest may include identifying a portion (e.g., relevant pixels) of the image data corresponding to (e.g., mapped to) the area of ​​interest in the view.

[0050] The cooking method 100 also includes determining a cooking level of the food based on the distribution of the liquid on the surface in the view and a parameter value indicative of the cooking level of the food at block 106. The parameter value is derived from a portion of the image data corresponding to the region of interest.

[0051] In some embodiments, the parameter value indicative of the cooking level of the food product is derived from the pixel intensity data used to create the image data.

[0052] In some embodiments, the parameter value comprises a color value (such as hue) derived from pixel intensity data of the region of interest.

[0053] In some embodiments, the parameter value comprises an intensity value derived from pixel intensity data of the region of interest.

[0054] During the cooking process, the infusion liquid may flow across a surface that is visible in view (e.g., a surface such as a baking sheet on which the food is supported during the cooking process). As the infusion liquid flows across the surface, the appearance of the surface may change. The appearance of the surface may also change as the infusion liquid itself is cooked during the cooking process (e.g., the liquid may be baked onto the surface).

[0055] In some cases, the total area of ​​leached liquid on the surface increases as the cooking process progresses. The increase in the total area of ​​leached liquid can indicate the cooking level of the food.

[0056] In some cases, the appearance (e.g., color, reflectivity, etc.) of the surface may change as the cooking process proceeds. The appearance may be represented by a parameter value. For example, the presence of an leached liquid on the surface may change a parameter value, such as the reflectivity (e.g., spectral reflectivity) of the surface. In some cases, such a change in parameter value may be measured via image data (e.g., pixel intensity data) corresponding to a portion of the image data of the surface (e.g., a region of interest). For example, during the cooking process, the pixel intensity data of a color channel (or another measure of color such as hue under the HSV color model) may change by a certain value. Thus, certain changes in the appearance of the surface visible in the view may be represented by changes in the parameter value. Such changes in the parameter value may indicate the cooking level of the food.

[0057] Thus, changes in the distribution of the leached liquid on the surface (e.g., changes in size, shape, etc.) can indicate the cooking level of the food. In addition, changes in parameter values ​​derived from a portion of the image data corresponding to the area of ​​interest can indicate the cooking level of the food. Such changes can be detected and quantified during the cooking process. Based on these changes, the cooking level can be determined. In some cases, the cooking level can be determined based on a model of the cooking level indicating a specific change, such as a change in the distribution of the leached liquid and / or a change in the parameter value derived from a portion of the image data corresponding to the area of ​​interest. In some cases, the model can specify a threshold value for the distribution of the liquid and / or a change in the parameter value indicating a certain cooking level.

[0058] The method 100 and certain other embodiments described herein may provide certain technical benefits, such as described below.

[0059] Certain embodiments may allow for the determination of the cooking level of a food product in a contactless manner (i.e., based on analysis of image data). Certain embodiments may reduce the complexity of determining the cooking level of a food product (e.g., reduced computing resources may be employed to determine the cooking level and / or the model used to determine the cooking level may not rely on complex methods such as artificial intelligence-based models). Certain embodiments may facilitate analysis of the cooking level on a consumer device (e.g., a cooking apparatus) that has computing resource constraints in terms of memory and / or processing resources (e.g., due to the relative simplicity of the method implemented by the consumer device). Certain embodiments may reduce user intervention during the cooking process (e.g., because the user may not need to do anything during the cooking process), facilitating an automatic cooking process that adapts to changes in user skills, recipes used, environment, cooking apparatus used, etc. Certain embodiments may provide an indication of cooking level parameters that are difficult to assess, such as juiciness or tenderness.

[0060] Figure 2 is a schematic diagram of a cooking ecosystem 200 according to an embodiment. Certain embodiments described herein (e.g., cooking method 100) can be implemented in certain portions of cooking ecosystem 200. Cooking ecosystem 200 depicts various devices and entities that can be deployed as part of cooking ecosystem 200. As described below, in some cases, not every device or entity depicted is required.

[0061] The cooking ecosystem 200 includes a cooking device 202 for cooking a food 204. The cooking device 202 includes a controller 206 for controlling the cooking process. For example, the controller 206 can control a heating element (not shown) of the cooking device 202 (e.g., controlling the cooking temperature of the cooking device 202). The controller 206 is communicatively coupled to a camera 208 for capturing images. The camera 208 is positioned so that an area of ​​interest associated with the food 204 is within the field of view of the camera 208. This particular configuration is an example. For example, the camera 208 may or may not be inside the cooking device 202, but even if the camera 208 is outside the cooking device 202, it can still have the food 204 within its field of view.

[0062] In some cases, the cooking ecosystem 200 includes a cloud computing service 210 that is communicatively coupled to the controller 206. The cloud computing service 210 can provide data storage and / or data processing services. The cloud computing service 210 can provide computing resources if there are not enough available computing resources in any connected device. In some cases, the cloud computing service 210 can provide updates and other services for the cooking device 202.

[0063] In some cases, the cooking ecosystem 200 includes a user device 212 that is communicatively coupled to the controller 206. The user device 212 can refer to any computing device associated with a user (e.g., a user of the cooking apparatus 202). Examples of the user device 212 include: a smartphone, a smart watch, a tablet, an Internet of Things (IoT) device, etc. In some cases, the user device 212 can be communicatively coupled to the cloud computing service 210.

[0064] Any one or combination of the controller 206, the cloud computing service 210, and the user device 212 can be used to implement the cooking method 100 and other embodiments described herein. For example, in some cases, the controller 206 can implement the cooking method 100 and related embodiments. In this regard, the controller 206 can include a processor (not shown) for implementing the cooking method 100 and related embodiments. In other cases, processing circuit devices associated with various devices and entities of the cooking ecosystem 200 can implement the cooking method 100 and related embodiments.

[0065] Figure 3 3 is a schematic diagram of a cooking device 300 for implementing a cooking process according to an embodiment. The cooking device 300 can implement the functionality of certain embodiments described herein, such as Figure 1 Certain features of the cooking device 300 may correspond to or have similar Figure 2 The cooking device 202 features similar functionality.

[0066] The cooking device 300 includes a cooking chamber 302 for receiving a food 304. The cooking device 300 also includes a housing 306 defining the cooking chamber 302. The cooking device 300 also includes an air circulation system 308 for circulating an air flow inside the cooking chamber 302. Thus, in this regard, the cooking device 300 may have a form similar to a fan oven or an air fryer. The cooking device 300 also includes a camera 310 for capturing images (views associated with the food 304) during the cooking process. The captured images may correspond to or be used to derive the first image data and the second image data.

[0067] The cooking device 300 also includes a controller 312, such as a controller corresponding to Figure 2 Controller 206. In this embodiment, controller 312 is configured to implement cooking method 100.

[0068] Thus, in this embodiment, the controller 312 is configured to: receive image data corresponding to a view of a food product during a cooking process performed by a cooking device; identify an area of ​​interest in the view, wherein the area of ​​interest includes an indication of liquid leached from the food product as a result of the cooking process; and determine a cooking level of the food product based on: the distribution of liquid on a surface in the view; and a parameter value indicating the cooking level of the food product, wherein the parameter value is derived from a portion of the image data corresponding to the area of ​​interest.

[0069] although Figure 3 The controller 312 of the cooking apparatus 300 is described as implementing the cooking method 100, but in some cases, other devices or entities (such as Figure 2 Depicted) can implement at least some of the functionality of cooking method 100 (and related embodiments).

[0070] Figure 4 (a) through (c) schematically depict example images 400 of an example food product 402 acquired successively during a cooking process, at a first, second, and third time respectively during the cooking process (ie, each image depicts a "view" of the food product 402). Figure 4 (d) depicts only the liquid leached from the food 402 for the third time (ie, the leached liquid has been separated from the food 402 and the background).

[0071] As time passes during the cooking process, the area of ​​leached liquid 404 on the surface surrounding the food 402 increases. Figure 4 In (a), no liquid is leached from the food 402. Figure 4 In (b), at a later stage in the cooking process, the leaching liquid 404 is observed to have flowed on the surface around the food 402. Figure 4 In (c), even more leached liquid 404 is observed on the surface later in the cooking process. Figure 4 (b) and Figure 4 (c) The area of ​​the leached liquid 404, it can be appreciated that Figure 4 (b) Compared with Figure 4 The food 402 in (c) is easier to cook. Figure 4 As shown in (a) to (c), the food 402 shrinks as the cooking process proceeds.

[0072] Figure 4 (d) shows the leached liquid 404, with the food 402 and any other background objects removed from view. Certain embodiments described herein relate to image processing methods for removing the food 402 and any other background objects from view. Such image processing methods may allow the leached liquid to be analyzed without being affected by other objects.

[0073] Figure 4 (a) to (c) depict how the distribution of the leached liquid 404 changes during the cooking process. The change in this distribution of the leached liquid 404 (e.g., by determining the size or area of ​​the liquid 404 at different times during the cooking process) can be quantified. The cooking level can be determined based on a model that indicates the cooking level of a particular distribution of the liquid 404.

[0074] In some cases, the area of ​​liquid 404 can be mapped to a set of pixels (or area / spatial region) within the image data. The number of pixels in the set / area can be mapped to the actual area of ​​liquid 404 visible in the view. Therefore, the number of pixels mapped to the liquid 404 in the view can indicate the cooking level.

[0075] In some cases, the area of ​​liquid 404 can be represented by the distance that liquid 404 flows out from food 402 (e.g., via a flow path such as a channel within a surface) and / or the depth of liquid 404 collected at a specific location on or near the surface. The distance and / or height reached by liquid 404 can be proportional to the area of ​​liquid 404 (because more liquid seeps out means that the distance and / or height reached can increase). Any pixel mapped to a portion of the view indicating the flow distance and / or depth of liquid 404 can be used to indicate the cooking level. In other words, the volume of liquid seeping out from food 402 can indicate the cooking level of the food. Therefore, by determining the distribution (e.g., area, height, or other dimensions) of the volume of liquid flowing through the surface, it is possible to determine the cooking level of the food.

[0076] For example, if liquid 404 flows to a certain location in the view, the pixel mapped to that location can record a change in the parameter value. The change in the parameter value can indicate the presence of liquid 404.

[0077] In another example, if liquid 404 collects at a certain location and reaches a certain depth, the pixels mapped to that depth may record a change in parameter value. The change in parameter value may again indicate the presence of leaching liquid 404.

[0078] Thus, in some embodiments, the distribution of liquid on a surface (eg, the surface of a baking sheet supporting a food product) indicates the volume of liquid that has leached from the food product as a result of the cooking process. The volume of leached liquid indicates the cooking level of the food product.

[0079] In some embodiments, the distribution of the liquid is indicated by an area of ​​the liquid on the surface.The region of interest comprises at least a portion of the area.

[0080] In some embodiments, the distribution is indicated by a flow path of the liquid on the surface.The region of interest includes locations along the flow path.

[0081] The cooking method 100 and other embodiments described herein can be combined with other methods for determining the cooking level of the food 402. For example, computer vision can be used to detect color changes on the surface of the food 402 itself. In another example, a temperature probe can be used to measure the core temperature of the food 402. In another example, an intelligent detection method such as computer vision can be used to detect the amount of food. More food may mean more cooking time is needed. Therefore, the cooking process can be modified to account for the amount of food. In another example, the starting temperature of the food can be known (e.g., based on the initial food storage state, such as whether the food is refrigerated, frozen, etc.). Therefore, the cooking process can be modified to account for the starting temperature. In some cases, the cooking level determination can be used to send a signal to the consumer and / or the cooking device to modify the cooking process, such as deciding how to end the cooking process (e.g., according to the user's preferences and / or the recipe of the food 402 being cooked). Deciding how to end the cooking process can include deciding actions such as turning off the cooking device and specifying the cooking temperature before turning it off.

[0082] Figure 5 The present invention relates to a cooking method 500 according to an embodiment. As described above, the cooking method 500 can be implemented by a computer, such as by a processor of a cooking device. The cooking method 500 can determine the distribution (e.g., area) of the leached liquid during the cooking process. Changes in the distribution can be quantified. Such quantification can be used to inform decisions about modifying the cooking process. The cooking method 500 can implement at least a portion of the cooking method 100, as described in more detail below. The blocks of the method 500 are now described. Some blocks may be omitted from the method 500 and / or may be executed differently. Figure 5 The depicted sequence is implemented.

[0083] At block 502 of method 500, a food item is segmented from a background in a view represented by image data. Segmentation may be performed using machine learning (ML) or non-ML techniques. ML-based segmentation is well known to those skilled in the art of ML-based computer vision techniques. Non-ML techniques may include identifying boundaries in the image data by detecting sudden changes in pixel intensity values ​​within the image data. For example, a sudden change in pixel intensity values ​​between adjacent pixels (e.g., above a predetermined threshold) may indicate a boundary (e.g., a demarcation) of a food item. Thus, some non-ML techniques for segmentation may identify boundaries within a view based on identifying pixel locations associated with sudden changes in pixel intensity (e.g., above a predetermined threshold).

[0084] At block 504 of method 500, food information is identified. The identified information may include type, quantity (e.g., weight, size, etc.), storage status (e.g., refrigerated, frozen, etc.), and / or taste preference (e.g., user preference for how well the food is cooked, such as rare, medium, or well done). The food information may be identified via a user interface (associated with the user device and / or the cooking apparatus) and / or automatically from user input. For example, where the food information is automatically identified, the image data may be processed to determine the food type based on an object identification method, for example, implemented using ML-based techniques such as object detection.

[0085] At block 506 of method 500, a threshold is identified for determining when the food is cooked according to the user's preferences. In some cases, the threshold may include an indication of mass loss associated with cooking the food. Foods such as meat may lose mass during the cooking process. Some of the lost material may be leached liquid on the surface. Therefore, by determining the distribution of the leached liquid on the surface, it is possible to determine how well the food is cooked, because more liquid on the surface indicates mass loss (and therefore the food is cooked more well). In some cases, the threshold may be a threshold area and / or number of pixels corresponding to the leached liquid on the surface in the view. In some cases, the threshold may be a threshold flow rate (e.g., speed, flow distance, etc.) of the leached liquid. At the beginning of the cooking process, the flow rate of the leached liquid may increase. However, the flow rate may decrease as the cooking process approaches the end. The threshold may be based on an indicator of the flow rate of the leached liquid (e.g., depending on the stage of the cooking process, being above or below the threshold may indicate the cooking level of the food). In other words, more than one threshold may be defined for different stages of the cooking process.

[0086] At block 508 of method 500, the leached liquid is segmented from the background. Block 508 may implement segmentation in a similar manner as described with respect to block 502. In some cases, block 508 may include block 102 of method 100. For example, the identified region of interest may correspond to an area of ​​leached liquid.

[0087] At block 510, the area of ​​the leached liquid and / or the liquid flow rate is determined. For example, the number of pixels in the image data corresponding to the area may be counted. In another example, the liquid flow rate may be determined by detecting the edge of the liquid leaching and tracking the movement of the liquid edge during the cooking process. In another example, the liquid flow rate may be determined by detecting when the edge of the liquid leaching reaches a predetermined position in the view. There may be multiple predefined positions. Thus, as the liquid flows to each successive position, the liquid flow rate may be determined.

[0088] At block 512, the area of ​​the leached liquid and / or the liquid flow rate is compared to a threshold value (e.g., a threshold area and / or a threshold flow rate). If the threshold value is not reached, the method 500 proceeds again to block 508 (where image data acquired at a later time during the cooking process is analyzed according to blocks 510 to 512. If the threshold value is reached, the method 500 continues to block 514 where a decision is made as to how to proceed with the cooking process (e.g., end the cooking process, reduce the temperature, etc.).

[0089] Grilled steak is used as an example to illustrate the cooking method 500 in which the distribution of leached liquid is determined. The steak leaches liquid during grilling. An experiment was conducted to monitor the cooking level of the steak during the cooking process of implementing the cooking method 500.

[0090] In some cases, the food type (i.e., steak) is identified at the beginning or during the cooking process. In some cases, the relevant information can be obtained through user input or computer vision technology. If through computer vision technology, food and background segmentation can be used to determine the food type.

[0091] In the experiment, a 200g frozen steak was cooked to a level considered well done. Some thresholds for the amount (i.e., area) of leached liquid observable on the surface were determined, corresponding to various cooking levels (indicated as Level 1, Level 2, and Level 3, with Level 2 being well done). As described in more detail below, the area of ​​leached liquid can be determined based on the number of pixels of the image data corresponding to the leached liquid.

[0092] In the case of a 200g steak, cooking level 1 (eg, under-done) corresponds to 40k (thousand) pixels, cooking level 2 (eg, well-done) corresponds to 80k pixels, and cooking level 3 (eg, over-done) corresponds to 100k pixels.

[0093] In the case of 200 g chicken breast, cooking level 1 (eg, undercooked) corresponds to 85k pixels, and cooking level 2 (eg, well-done) corresponds to 110k pixels.

[0094] It will be appreciated that the threshold number of pixels depends on the system settings, so these example values ​​are given to provide an easily understood indication. The thresholds for different cooking levels are observed using the indicated amounts for different meat types.

[0095] The example given above indicates a threshold number of pixels (mapped to the area of ​​leached liquid on the surface). As the cooking process progresses, the number of pixels mapped to the area of ​​leached liquid will increase. However, this rate of increase may vary. As the cooking process is completed, the rate of change in area may decrease (because less liquid is leached from the food over time). Thus, the threshold may specify the maximum change in the number of pixels over a specified time period. For example, the area of ​​leached liquid may be determined periodically (e.g., every 2 minutes), and the threshold may have a predetermined value, such as 10k pixels. Thus, when the change in area within 2 minutes is less than 10k pixels (after exceeding 10k pixels in the previous 2 minutes), this may indicate that the cooking process is complete or nearly complete.

[0096] Figure 6 (a) to (b) are graphs representing steak cooking experimental data collected during a cooking process implemented according to various embodiments. Figure 6 (a) Describes the relationship between the number of pixels in the image data corresponding to the area of ​​leached liquid and the core temperature of the steak. The core temperature was measured every 2 minutes. Initially, during the first 12 minutes, no leached liquid was detected (or the amount detected was not obvious on the y-axis scale). Starting from 14 minutes, the volume of leached liquid detected increased. The number of pixels in the image data mapped to leached liquid increased as the core temperature increased. However, as Figure 6 As depicted in (b), the rate of change of the number of pixels varies throughout the cooking process. Figure 6 (b) depicts the change in the number of pixels per 2 minutes for the core temperature. Once the leaching liquid is detected, the rate of change is large. After the core temperature reaches 68°C, the rate of change decreases due to the reduction of liquid leaching. This decrease in the rate of change can indicate that the food is being cooked or almost cooked. In some cases, this decrease in the rate of change of the number of pixels can be identified and used to determine the cooking level.

[0097] Figure 7 The invention relates to a cooking method 700 according to an embodiment. As described above, the cooking method 700 may be implemented by a computer, such as a processor of a cooking device. The cooking method 700 may determine the distribution (eg, area) of the leached liquid during the cooking process.

[0098] The previously described embodiments involve determining the distribution of the leaching liquid. Block 106 of the cooking method 100 involves determining the cooking level of the food based on such distribution. Block 106 of the method 100 also involves determining the cooking level based on a parameter value derived from a portion of the image data corresponding to an area of ​​interest. As previously described, the area of ​​interest can be the entire area of ​​the leaching liquid or a portion of the area. The cooking method 700 involves determining the distribution of the leaching liquid, as well as determining the parameter value. After determining the distribution and the parameter value, the cooking level can be determined according to block 106 of the cooking method 100.

[0099] By way of example, cooking method 700 involves grilling steaks, although the principles may be applied to cooking other food types.

[0100] At block 702 of method 700, an image (i.e., image data) of a grilled steak is obtained during a first cooking period, such as at a cooking time of 6 minutes. This first image is referred to as image F1. In this example, at block 704, it is determined that image F1 has no leached liquid. In another example, there may be some visible leached liquid in the image.

[0101] In the next part of the method 700, the meat is segmented from the background to generate a binary image F4, as described below.

[0102] At block 706 of method 700, image F1 is converted to a YUV color space (eg, if image F1 uses a different color space, such as RGB) to form image F2. Performing segmentation on an image using a YUV color space rather than an RGB color space may be easier.

[0103] At block 708 of method 700, the meat in image F2 is segmented from the background to form image F3. Segmentation can be based on ML or non-ML techniques. In this example, a non-ML technique using a threshold to identify a boundary corresponding to the boundaries of the meat is used to segment the meat from the background. The use of contrasting surface colors can aid in segmentation. For example, it can be relatively easy to segment a pink / brown object such as meat from a white surface based on a threshold.

[0104] At block 710 of method 700 , image F3 is converted to a binary (eg, black and white) image F4 .

[0105] At block 712 of method 700, image F4 is processed to form image F5 by setting pixels corresponding to meat to a pixel intensity value of 0 and the background to a value of 1. In this manner, any leached liquid in image F5 may be apparent each time a new image is analyzed (i.e., pixels having a value of 1 correspond to areas that may include leached liquid).

[0106] At block 714 of method 700, subsequent images are acquired by the camera. In some cases, acquisition of images may occur periodically, such as every 1 or 2 minutes.

[0107] At block 716 of method 700, the image is read. In this example, there is leaching liquid at 13 minutes into cooking (the resulting image is now referred to as F13).

[0108] At block 718 of method 700, image F13 is converted to a hue-saturation-value (HSV) color space (although a different color space may be used). Image F13 may show the meat as having a different hue and / or saturation than the surrounding area. In some cases, a saturation channel (denoted as F_S(13)) is extracted from image F13.

[0109] At block 720 of method 700, pixels in image F_S(13) are multiplied by corresponding pixels in image F5 (to separate the infusion liquid from the meat). Figure 4 (d) depicts that in this way the food area is filtered out and only the leachate remains.

[0110] At block 722 of method 700, pixel data of image F_S(13) having pixel intensity values ​​greater than a threshold value, such as 25, is considered to correspond to an leaching liquid. (Changes in) the pixel intensity values ​​are examples of parameter values ​​indicative of a cooking level of the food product. The parameter value is derived from a portion of the image data corresponding to the region of interest.

[0111] At block 724 of method 700, the number of pixels for which the resulting pixel intensity value exceeds a predetermined pixel intensity threshold is compared to a threshold number of pixels indicating the distribution of the leaching liquid. For example, if the determined number of pixels is greater than a threshold number (such as 80k pixels in the previous example), method 700 continues to block 726. At block 726, information indicating a cooking level (such as an indication that a threshold has been reached) is sent to a controller (e.g., controller 206) to implement a recommended action for cooking the meat. The control action may include advising the consumer to stop the cooking process and / or controlling the heating temperature (lowering or increasing). In some cases, an implementation of block 726 may cause a control signal to be sent to a controller of the cooking device to implement a cooking action consistent with the determined cooking level.

[0112] The cooking method 700 can be used to determine the distribution of the leached liquid and derive parameter values ​​(e.g., pixel intensity values) corresponding to the portion of the image of the leached liquid. The distribution and parameter values ​​can be used to determine the cooking level. By comparing the parameter values ​​(e.g., pixel intensity values) to a threshold parameter value (e.g., for each pixel), it is possible to determine the cooking level. In addition, by comparing the value of the distribution (e.g., the number of pixels with parameter values ​​that meet or exceed the threshold parameter value) to a threshold value (e.g., a specified number of pixels), it is possible to determine the cooking level. Therefore, if the parameter value (one or more) derived from the area is higher than the threshold parameter value, the area of ​​the leached liquid can indicate the cooking level.

[0113] Figure 8 (a) to (d) schematically depict example images 800 of a food product 802 during a cooking process according to an embodiment. Previously, the area of ​​the leached liquid 804 was determined and used to determine the cooking level. However, in this embodiment, the area of ​​the leached liquid 804 is not directly determined. Instead, the area of ​​the leached liquid 804 is indicated by the distance traveled by the leached liquid as it flows over the surface (i.e., the farther traveled, the greater the area covered). A target area 806 (e.g., Figure 8 (b) to (d)). The location of the region of interest 806 indicates the cooking level of the food 802, because the more liquid that is leached, the more cooked the food 802 is. If the path of the leached liquid 804 is known or predictable, detecting the leached liquid at certain locations can indicate the cooking level of the food 802. In this regard, Figure 8 In each of (b) to (d), the location of the region of interest 806 is different. A parameter value (such as a pixel intensity value) is derived from the region of interest 806 and used to determine the cooking level. By comparing the parameter value with a threshold parameter value (which may be predefined), the cooking level of the food may be determined.

[0114] In some cases, the surface may include a channel along which the leaching liquid flows (so that the liquid may only flow along this path). For example, the surface of a baking tray supporting food may include a channel that guides the flow of the leaching liquid. Predetermined knowledge about such channels can be used to determine any changes in the distribution of the leaching liquid. In some cases, the location of the area of ​​interest may be predetermined. The location may be selected within the channel. Knowledge about the distance between the food and the location (e.g., the length of the channel) can be used to determine the distribution. In other words, the location of the area of ​​interest can indicate the cooking level of the food based on the time when the leaching liquid reaches the location during the cooking process.

[0115] Various designs of the surface may be used to provide a predictable flow path for the leaching liquid. One example is to have a channel included in the surface that extends at least partially around the perimeter of the bakeware surface. A ramp may be incorporated into the surface to direct the leaching liquid to a portion of the channel so that the leaching liquid flows along the same path each time the bakeware is used. Another example is to incorporate chambers or pools within the bakeware to receive the leaching liquid. The locations within or around the chambers / pools may indicate the height at which the leaching liquid collects, such that detection of the leaching liquid at one of these locations may indicate the cooking level of the food product as the height increases.

[0116] As previously described, a region of interest may be identified at a location along the predicted flow path. In some cases, multiple regions of interest may be identified along the predicted flow path. When the leaching liquid reaches each successive region of interest, this may indicate the cooking level of the food, because the farther the region of interest is from the food path (i.e., the distance the leaching liquid travels), the more cooked the food is. In some cases, the parameter value derived from the region of interest is color (e.g., hue value of the HSV color space). In some cases, the parameter value derived from the region of interest is saturation (e.g., according to the HSV color space). However, other parameter values ​​may be derived from the image data of the region of interest. When the leaching liquid reaches the region of interest, the parameter value may change. If the change in the parameter value exceeds a threshold parameter value, this may indicate the cooking level of the food. By way of example, the threshold parameter value may be a pixel intensity value change, which is 10. If the detected change is 10 or greater, this may indicate the cooking level of the food. In some cases where there are multiple regions of interest, the cooking level may be determined based on the distribution (i.e., which regions of interest are detected as having the presence of leached liquid) and the change in parameter value (i.e., the change in color and / or saturation in a particular region of interest). For example, there may be 5 regions of interest, labeled 1 to 5, with 5 being the farthest from the food in terms of distance of the flow path. If the leached liquid reaches region 5 of interest, and the parameter value change is above a threshold, this may indicate that the food is overcooked. However, if the leached liquid reaches region 3 of interest, and the parameter value change is above a threshold, this may indicate that the food is cooked. Thus, for example, when the leached liquid reaches target area 3, it may be desirable to stop the cooking process. Other methods may include detecting when the leached liquid reaches all regions of interest, and monitoring the change in parameter value. If a specified proportion of the regions of interest (e.g., 3 out of 5) exhibit a parameter value change above a threshold, this may indicate that the food is cooked.

[0117] Due to the distance along the infusion liquid flow path, the change in parameter value may be different at each location (because over time the infusion liquid may become baked onto the surface, changing its color). By monitoring the change in parameter value over time at at least one of these locations, it is possible to determine the cooking level of the food product.

[0118] In some cases, the flow path of the leaching liquid can be predicted based on historical information (e.g., previous usage) and / or some other analysis of how the leaching liquid flows on the surface. Based on the user's specific settings, they may have different experiences with the flow path. For example, factors such as the tilt angle of the surface, the type of baking surface, the position of the food on the surface, etc. can affect the possible flow path of the leaching liquid. Therefore, the flow path of the leaching liquid can be predicted by performing a segmentation operation during the first use of the cooking device so as to determine the flow path of the leaching liquid when cooking food.

[0119] In some cases, certain features of the flow path that indicate the direction, change in direction, and / or size of the flow path can be identified based on the analysis of the flow path. The segmentation operation that determines the flow path can provide a profile representing the distribution of the leached liquid on the surface. This distribution / profile of the leached liquid can have certain features that can be used to predict the flow path (i.e., after the liquid flows through the feature). For example, a convex feature or a concave feature in the surface can guide the liquid along the surface in a predictable manner because the liquid can flow into the concave feature and the liquid can flow around the convex feature. In another example, the corner of the flow path can indicate a change in direction. Therefore, when the liquid reaches the corner, it is expected that the liquid will flow in a different (and predictable) direction. In another example, the feature can be the starting position or the ending position of the flow path. For example, the starting position can be adjacent to the food. The ending position can be a feature on the surface (e.g., an area at the bottom of a concave feature or a slope) where the leached liquid gathers. By identifying certain features of the flow path that indicate the direction, change in direction, and / or size of the flow path, a set of positions (e.g., coordinates or pixel identifiers) consistent with the flow path can be identified. The region of interest may include such locations. In one example, the set of locations may coincide with a centerline (e.g., the middle) of the flow path. Figure 8 As depicted in (b) to (d), each region of interest 806 is approximately in the middle of the flow path of the liquid 804. Thus, in some cases, the center of the region of interest 806 can be aligned with the centerline of the flow path. Figure 8A relatively straight flow path is shown. In some cases, there may be turning points (e.g., corners) in the flow path. In some cases, a geometric analysis of the flow path profile may indicate a position along the flow path corresponding to a centerline of the flow path. For example, the x and y coordinates (e.g., pixel positions) at the respective ends of the straight portion of the flow path may be obtained by geometric analysis. The location of the region of interest may be selected along the line between the two respective ends. Thus, an analysis of the flow path during the first use of the cooking device may be used to predict the flow path during the second use of the cooking device. Once the flow path (i.e., distribution) is predicted, the cooking level may be determined in the second use based on the distribution and parameter values ​​(e.g., according to cooking method 100).

[0120] The segmented flow paths can be saved (in a memory) so that the flow path of the leaching liquid is predictable in the second use of the cooking device. The user or controller can select the location of the area of ​​interest for the second use of the cooking device. Therefore, once the leaching liquid flow path is predicted, the cooking level of the food in the second (or subsequent) use of the cooking device can be determined based on the determined distribution and parameter values. The use of predictions based on historical information and / or other analyses can allow users to use their own utensils (e.g., baking pans) and / or explain changes in the settings / environments of the cooking device. For example, a user interface of a cooking device or another user device can allow a user to instruct the cooking device to predict the leaching liquid flow path for the user's utensils and / or devices. Therefore, the cooking level can be determined based on the distribution of the leaching liquid predicted for the user's utensils and / or devices. Therefore, the results of implementing the various methods described herein can be more personalized to the user. In some cases, for example, if there is a deviation between the actual flow path and the predicted flow path, the user can adjust the predicted leaching liquid flow path via the user interface.

[0121] Thus, in some embodiments, the location of the region of interest is selected based on the prediction of the flow path.The selected location is indicative of the cooking level of the food product.

[0122] Fig. 9 The present invention relates to a cooking method 900 according to various embodiments. As described above, the cooking method 900 can be implemented by a computer, such as a processor of a cooking device. The cooking method 900 can implement at least a portion of the cooking methods 100, 500, 700, and any other cooking methods described herein. The blocks of the method 900 are now described. Some blocks may be omitted from the method 900 and / or may be implemented differently than the method 900. Fig. 9 The depicted sequence is implemented.

[0123] In some embodiments, the distribution of liquid on a surface may be determined by: at box 902 of method 900, identifying a portion of image data indicating the presence of liquid; and at box 904 of method 900, determining the distribution based on geometric measurements derived from a portion of the image data.

[0124] In some cases, the geometric dimension may be any dimension of the leaching liquid, such as length, width, area, etc. The view leaching liquid may be mapped to certain pixels / positions in the image data. The number of pixels or number of pixels corresponding to the leaching liquid across at least one dimension may represent the geometric dimension of the leaching liquid. In other words, a portion of the image data mapped to the leaching liquid may indicate the geometric dimension of the leaching liquid. Thus, in some cases, the distribution of the leaching liquid may be determined based on the pixels / positions within the image data that are mapped to the leaching liquid within the view.

[0125] In some embodiments, the cooking level of the food is determined based on a model indicating a distribution-based cooking level. In some cases, the model can be predefined. In some cases, the model can specify a threshold number of pixels (or a corresponding size or area within the image data) that indicate the cooking level of the food (e.g., based on the type of food). In some cases, the model can specify a (e.g., at least one) location of an area of ​​interest (e.g., based on an expected flow path of an leaching liquid, such as when a user uses a designated baking tray with channels incorporated in its surface, etc.). In some cases, the model can specify a threshold parameter value (e.g., a change in hue, saturation, etc.) that indicates the cooking level of the food.

[0126] In some embodiments, method 900 includes, at block 906, predicting an expected distribution of liquid based on knowledge of the surface and / or historical data of previously observed distributions of liquid on the surface. Method 900 also includes, at block 908, designing a model to account for the expected distribution of liquid on the surface such that the model indicates a cooking level of the food in response to the determined distribution following the expected distribution.

[0127] Blocks 906 to 908 of method 900 involve predicting how the leaching liquid is expected to flow on the surface (e.g., if a new baking pan is used, the cooking device is on an inclined surface, etc.), and then designing the model accordingly. Designing can mean "creating" a new model or "modifying" an existing model.

[0128] In some embodiments, method 900 includes, at block 910, comparing the image data to previously acquired image data to determine a parameter value. For example, image data acquired at a first time during a cooking process can be compared to image data acquired at a second time during the cooking process. A change in a value such as a pixel intensity value (within an area of ​​the image data mapped to the leached liquid) can be the determined parameter value.

[0129] In some embodiments, a comparison of the image data with previously acquired image data indicates a change in intensity and / or color of a portion of the image data corresponding to the region of interest. A parameter value is determined based on the change.

[0130] In some embodiments, method 900 includes, at block 912, determining a cooking level of the food by comparing the parameter value to a threshold value indicative of the cooking level. The threshold value may be predefined based on any one or more of factors such as food type, surface color (because changes in surface color may affect observable parameter values), and the like.

[0131] In some embodiments, the determined cooking level of the food can be used to inform the cooking process. For example, once the cooking level of the food reaches a predetermined or preferred state (e.g., rare, medium, well-done, well-done, etc.), the cooking process can be modified (e.g., by stopping the cooking process or by changing the cooking temperature).

[0132] Fig.10 1 is a schematic diagram of a non-transitory machine-readable medium 1000 for implementing various embodiments described herein. As used herein, the term "non-transitory" does not encompass transient propagating signals. The machine-readable medium 1000 stores instructions 1002 that can be read and executed by a processor 1004 to implement the method of any embodiment described herein (e.g., cooking method 100, 500, 700, 900, and / or related embodiments). The machine-readable medium 1000 and / or the processor 1004 can be executed by Figure 2 or Figure 3 It can be implemented by any one of the controller 206, cloud computing service 210, user device 212 and / or controller 312.

[0133] Fig.11 1 is a schematic diagram of an apparatus 1100 for implementing various embodiments described herein. The apparatus 1100 may be Figure 2 or Figure 3 It can be implemented by any one of the controller 206, cloud computing service 210, user device 212 and / or controller 312.

[0134] The device 1100 includes a processor 1102. The processor 1102 is configured to communicate with an interface 1104. The interface 1104 may be any interface (wireless or wired) that implements a communication protocol to facilitate exchanging data (e.g., image data, cooking device control instructions, etc.) with other devices such as another part of the cooking ecosystem 200.

[0135] The device 1100 also includes a memory 1106 (e.g., non-transitory or otherwise) that stores instructions 1108 that can be read and executed by the processor 1102 to implement various embodiments described herein (e.g., cooking methods 100, 500, 700, 900, or any related embodiments).

[0136] Any model described herein may be implemented by a processing circuit device for implementing the cooking method described herein. Therefore, certain blocks of the cooking method may involve the use of such models in order to provide the stated functionality. The model may be machine learning (ML) based or non-ML based. However, certain embodiments described herein involve the use of non-ML based models, which may avoid the need to use a large amount of computing resources and / or implement local processing.

[0137] While the invention has been illustrated and described in detail in the drawings and foregoing description, such illustration and description are to be considered illustrative or exemplary and not restrictive; the invention is not limited to the disclosed embodiments.

[0138] One or more features described in one embodiment may be combined with or substituted for features described in another embodiment.

[0139] Embodiments of the present disclosure may be provided as a method, a system, or as a combination of machine-readable instructions and processing circuitry. Such machine-readable instructions may be included on a non-transitory machine (e.g., computer) readable storage medium (including but not limited to disk storage, CD-ROM, optical storage, flash memory, etc.), and the non-transitory machine-readable storage medium has a computer-readable program code in or on it.

[0140] The present disclosure is described with reference to the flowcharts and block diagrams of the methods, devices and systems according to the embodiments of the present disclosure. Although the above flowcharts show a specific execution order, the execution order may be different from the depicted order. The frame described in one flowchart may be combined with the frame of another flowchart. It should be understood that each frame in the flowchart and / or block diagram and the combination of frames in the flowchart and / or block diagram can be implemented by machine-readable instructions.

[0141] The machine-readable instructions may be executed, for example, by a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to implement the functions described in the specification and the drawings. Specifically, a processor or a processing circuit device or a module thereof may execute machine-readable instructions. Therefore, the functional modules of the apparatus and other devices described herein may be implemented by a processor that executes machine-readable instructions stored in a memory or a processor that operates according to instructions in an embedded logic circuit device. The term 'processor' will be broadly interpreted to include a CPU, a processing unit, an ASIC, a logic unit, or a programmable gate array, etc. These methods and functional modules may all be implemented by a single processor, or may be divided among several processors.

[0142] Such machine-readable instructions may also be stored in a computer-readable memory, which may direct a computer or other programmable data processing device to operate in a particular mode.

[0143] Such machine-readable instructions may also be loaded onto a computer or other programmable data processing device to cause the computer or other programmable data processing device to perform a series of operations to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device implement the functions specified by the box (one or more) in the flowchart and / or block diagram.

[0144] Furthermore, the teachings herein may be implemented in the form of a computer program product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device to implement the methods described in the embodiments of the present disclosure.

[0145] The elements or steps described in relation to one embodiment may be combined with or replaced by the elements or steps described in relation to another embodiment. Through the study of the drawings, the present disclosure and the appended claims, those skilled in the art may understand and implement other variations of the disclosed embodiments when practicing the claimed invention. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "one" or "an" does not exclude multiple. A single processor or other unit may implement the functions of several items listed in the claims. The fact that certain measures are cited only in mutually different dependent claims does not indicate that the combination of these measures cannot be used advantageously. The computer program may be stored or distributed on a suitable medium, such as an optical storage medium or solid-state medium supplied with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems. Any reference numerals in the claims should not be interpreted as limiting the scope.

Claims

1. A cooking method (100), comprising: receiving (102) image data corresponding to a view of a food item during a cooking process performed by a cooking device; identifying (104) an area of ​​interest in the view, wherein the area of ​​interest includes an indication of liquid leached from the food product as a result of the cooking process; and The cooking level of the food is determined (106) based on: the distribution of said liquid on a surface in said view; and A parameter value indicative of the cooking level of the food product, wherein the parameter value is derived from a portion of the image data corresponding to the region of interest.

2. The cooking method of claim 1, wherein the distribution of the liquid on the surface is indicative of the volume of liquid leached from the food as a result of the cooking process, and the volume of the liquid leached therefrom is indicative of the cooking level of the food.

3. The cooking method according to any one of claims 1 to 2, wherein the distribution of the liquid is indicated by an area of ​​the liquid on the surface, and the region of interest comprises at least a portion of the area.

4. A cooking method according to any one of claims 1 to 3, wherein the distribution is indicated by a flow path of the liquid on the surface, and wherein the area of ​​interest comprises a location along the flow path. 5 . The cooking method of claim 4 , wherein the location of the region of interest is selected based on a prediction of the flow path, wherein the selected location is indicative of the cooking level of the food product.

6. The cooking method (900) according to any one of claims 1 to 5, comprising determining the distribution of the liquid on the surface by: identifying (902) a portion of the image data indicating the presence of the liquid; and The distribution is determined (904) based on geometric measurements derived from the portion of the image data.

7. The cooking method according to any one of claims 1 to 6, wherein the cooking level of the food is determined based on a model, the model indicating the cooking level based on the distribution.

8. The cooking method (900) according to claim 7, comprising: predicting (906) an expected distribution of the liquid based on knowledge about the surface and / or historical data of previously observed distributions of the liquid on the surface; as well as The model is designed (908) to account for the expected distribution of liquid on the surface such that the model indicates the cooking level of the food product in response to the determined distribution following the expected distribution.

9. The cooking method according to any one of claims 1 to 8, wherein the parameter value indicative of the cooking level of the food product is derived from pixel intensity data used to create the image data.

10. The cooking method according to claim 9, wherein the parameter values ​​include: a color value derived from said pixel intensity data of said region of interest; and / or An intensity value is derived from the pixel intensity data of the region of interest.

11. The cooking method (900) according to any one of claims 1 to 10, comprising comparing (910) the image data with previously acquired image data to determine the parameter value.

12. The cooking method of claim 11, wherein the comparison of the image data with the previously acquired image data indicates a change in intensity and / or color in the portion of the image data corresponding to the area of ​​interest, and wherein the parameter value is determined based on the change.

13. The cooking method (900) according to any one of claims 1 to 12, comprising determining (912) the cooking level of the food product by comparing the parameter value with a threshold value indicative of the cooking level.

14. A non-transitory machine-readable medium (1000) storing instructions (1002), the instructions being readable and executable by a processor (1004) to implement the cooking method according to any one of claims 1 to 13.

15. A cooking device (300) for implementing a cooking process, comprising: a cooking chamber (302) for receiving food (304); a housing (306) defining the cooking chamber; an air circulation system (308) for circulating air flow inside the cooking chamber; a camera (310) for capturing images during the cooking process; as well as A controller (312), the controller being configured to: receiving (102) image data corresponding to a view of a food item during a cooking process performed by a cooking device; identifying (104) an area of ​​interest in the view, wherein the area of ​​interest includes an indication of liquid leached from the food product as a result of the cooking process; and The cooking level of the food is determined (106) based on: the distribution of said liquid on a surface in said view; and A parameter value indicative of the cooking level of the food product, wherein the parameter value is derived from a portion of the image data corresponding to the region of interest.

Images