A food ripeness determination method and apparatus, a steaming and roasting device, and an electronic device

Abstract

The application provides a food maturity determination method and device, a steaming and baking equipment and an electronic equipment. The method comprises the following steps: obtaining an initial image collected by an image collection device periodically in a cooking process; preprocessing the initial image to obtain a target image containing a target food; extracting a highlight feature of a surface of the target food in the target image; determining a highlight dynamic change characteristic according to the highlight features extracted in multiple continuous periods, and determining the maturity of the target food based on a correlation between the highlight feature change and the food maturity. The application improves the accuracy and reliability of food maturity determination.

Description

Technical Field

[0001] This invention relates to the field of kitchen appliance technology, and more specifically, to a method, apparatus, steaming and baking equipment, and electronic equipment for determining the ripeness of food. Background Technology

[0002] Traditional cooking equipment such as steam ovens mainly rely on preset time-temperature curves to control the cooking process, lacking the ability to perceive the actual state of the food in real time, which can easily lead to overcooked or undercooked food, affecting its taste and nutrition.

[0003] In existing technologies, ripeness is typically determined by detecting color changes on the surface of food. However, this method has drawbacks in practical applications: during cooking, the steam oven cavity contains complex light sources, including heat radiation from heating elements, illumination from supplementary lighting, and multiple reflections from the metal inner wall. These factors can easily cause problems such as localized overexposure, shadow occlusion, and color temperature shifts in the image. These lighting interferences result in severely distorted color information of the collected food, making it difficult to accurately reflect the true state of the food and thus reducing the reliability and accuracy of ripeness determination. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a method, apparatus, steaming and baking equipment and electronic equipment for determining food maturity, so as to improve the accuracy of food maturity determination.

[0005] In a first aspect, a method for determining the ripeness of food is provided, applied to a steaming and baking equipment, the steaming and baking equipment including a cooking cavity, a light source and an image acquisition device installed inside the cooking cavity, the method comprising: During the cooking process, initial images are acquired periodically by an image acquisition device; The initial image is preprocessed to obtain a target image containing the target food. Extract the highlight features from the surface of the target food in the target image; highlights are bright spots formed after light source shines on the food surface and is reflected. Based on the highlight features extracted from multiple consecutive periods, the dynamic change characteristics of highlights are determined, and the maturity of the target food is determined based on the correlation between the changes in highlight features and the maturity of food.

[0006] Optionally, the initial image is preprocessed to obtain a target image containing the target food, including: The initial image is subjected to illumination correction to obtain the first processed image; The first processed image is devastated to obtain the second processed image; The ROI region in the second processed image is cropped to obtain the target image, where the ROI region is the area where the target food is located.

[0007] Optionally, extracting the highlight features of the target food surface in the target image includes: Identify the highlight areas in the target image; Extract the highlight features of the highlight region. The highlight features include at least one of the following: highlight area ratio, highlight intensity mean, and highlight distribution dispersion. The highlight area ratio is the area of ​​the highlight region relative to the corresponding area of ​​the target food. The highlight intensity mean is the average light intensity value of all pixels in the highlight region.

[0008] Optionally, determining the highlight region in the target image includes: The target image is converted to the HSV color space, and the V channel image is extracted as the luminance image; The brightness image is binarized to obtain candidate highlight regions; The candidate regions for highlights are preprocessed to obtain the highlight regions. The preprocessing includes noise removal, void filling, and separation of adhered regions.

[0009] Optionally, based on the specular features extracted from multiple consecutive periods, the dynamic variation characteristics of the specular highlights are determined, including: The rate of change of the proportion of the highlight area over time is determined based on the proportion of the highlight area extracted from multiple consecutive periods. And / or, based on the highlight intensity values ​​extracted from multiple consecutive periods, determine the rate of change of the highlight intensity value over time; And / or, based on the specular dispersion extracted from multiple consecutive periods, determine the rate of change of specular dispersion over time.

[0010] Optionally, determining the ripeness of a target food based on the correlation between changes in highlight features and food ripeness also includes: Obtain the recipe for the target food; In a pre-built database, a target mapping table matching the recipe is invoked; the target mapping table includes the mapping relationship between changes in highlight features and food ripeness. Match the maturity level in the target mapping table to the highlight dynamics of the target food.

[0011] Optionally, determining the ripeness of a target food based on the correlation between changes in highlight features and food ripeness also includes: Obtain sample data on the changes in highlight features; Based on the correlation between changes in highlight features and food maturity, maturity labels for sample data were determined; A maturity assessment model is trained based on sample data and corresponding maturity labels; The highlight dynamic characteristics of the target food are input into the trained maturity determination model, which outputs the maturity of the target food.

[0012] Secondly, a food ripeness determination device is provided, applied to a steaming and baking equipment. The steaming and baking equipment includes a cooking cavity, and a light source and an image acquisition device are installed inside the cooking cavity. The device includes: The acquisition unit is used to acquire initial images periodically captured by the image acquisition device during the cooking process; The preprocessing unit is used to preprocess the initial image to obtain a target image containing the target food. The extraction unit is used to extract the highlight features of the target food surface in the target image; the highlight is the bright spot formed after the light source shines on the food surface and is reflected. The determination unit is used to determine the dynamic change characteristics of highlights based on the highlights extracted from multiple consecutive periods, and to determine the maturity of the target food based on the correlation between the changes in highlights and the maturity of the food.

[0013] Thirdly, a steam-grilling device is provided, including a steam-grilling device body and a controller. The steam-grilling device body includes a cooking cavity, in which a light source and an image acquisition device are installed. The controller performs any of the methods in the first aspect.

[0014] Fourthly, an electronic device is provided, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; The memory is used to store computer programs; When the processor executes a program stored in the memory, it implements any of the methods described in the first aspect.

[0015] This invention provides a method, apparatus, steaming / baking equipment, and electronic device for determining food maturity. During the cooking process, initial images are periodically acquired by an image acquisition device. These initial images are preprocessed to obtain a target image containing the target food. Highlight features of the target food surface are extracted from the target image. Based on the highlight features extracted over multiple consecutive periods, the dynamic changes in highlight characteristics are determined. The maturity of the target food is then determined based on the correlation between these changes and the food's maturity. This invention utilizes a built-in light source within the steaming / baking equipment to actively illuminate and generate highlights, avoiding random interference from natural light or stray light within the cavity. The highlight features exhibit regular changes as the food surface condition evolves, making light no longer a distracting factor but rather a medium for perceiving food maturity, thereby improving the accuracy and reliability of food maturity determination.

[0016] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart of a method for determining food maturity provided by an embodiment of the present invention is shown; Figure 2 This diagram illustrates the structure of a food ripeness determination device provided in an embodiment of the present invention. Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present invention is shown. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0020] Current technologies typically identify food ripeness by detecting color changes on the food's surface. However, this method has drawbacks in practical applications: during cooking, the steam oven cavity contains complex light sources, including heat radiation from heating elements, illumination from supplemental lighting, and multiple reflections from the metal inner wall. These factors easily lead to problems such as localized overexposure, shadow occlusion, and color temperature shifts in the images. These lighting interferences cause severe distortion of the collected food color information, making it difficult to accurately reflect the food's true state, thus reducing the reliability and accuracy of ripeness determination.

[0021] Based on this, embodiments of the present invention provide a method for determining the ripeness of food, applied to a steam-roasting equipment, including a steam-roasting equipment body and a controller; the steam-roasting equipment body includes a cooking cavity, and a light source and an image acquisition device are installed inside the cooking cavity. The steam-roasting equipment may be, for example, a split-type steam oven or a steam-roasting all-in-one machine.

[0022] In one example, the image acquisition device, such as a CMOS camera, can be mounted on top of the cooking cavity to periodically acquire image information of the food to be cooked. The light source can be a white LED supplement light, which illuminates the food surface during cooking. Some of the light is reflected from the food surface to form local bright spots, i.e., highlight areas.

[0023] As cooking progresses, food undergoes physical and chemical changes such as water evaporation, protein denaturation, oil precipitation, caramelization, and Maillard reactions. As a result, its surface microstructure and reflective optical properties change, leading to significant changes in the area, brightness, distribution pattern, and dynamic evolution trend of the highlight area.

[0024] Based on the above principles, this application proposes to use the changes in the optical properties of the food surface highlights as a key observation indicator, analyze its dynamic change patterns to characterize the food surface state (such as oil seepage, moisture drying, surface solidification, etc.), and determine the ripeness accordingly.

[0025] The following is a detailed description through examples.

[0026] This invention provides a method for determining the ripeness of food, wherein the executing entity is the controller of the aforementioned steaming and baking equipment, such as... Figure 1 As shown, the method includes the following steps: Step S101: During the cooking process, acquire initial images periodically captured by the image acquisition device.

[0027] After cooking begins, the controller directs the image acquisition device to capture an initial image at a preset interval (e.g., every 60 seconds), forming an image sequence. For example, during the roasting of pork belly, a total of 30 images are captured from the start to the end of heating, spanning 30 minutes.

[0028] Step S102: Preprocess the initial image to obtain a target image containing the target food.

[0029] In one feasible implementation, preprocessing the initial image to obtain a target image containing the target food includes: Step S102A: Perform illumination correction on the initial image to obtain the first processed image.

[0030] In this step, the initial image can be converted from the RGB color space to the HSV space, and the V channel (luminance channel) can be extracted. The CLAHE (Contrast Limited Adaptive Histogram Equalization) algorithm is used to locally enhance the contrast of the V channel to limit the excessive stretching of the histogram and avoid noise amplification. The processed V channel is then merged with the original H and S channels and converted back to an RGB image, which is used as the first processed image.

[0031] Light correction can effectively alleviate uneven lighting, enhance details in dark areas, and provide a more uniform brightness basis for subsequent devaporization and ROI extraction.

[0032] Step S102B: Perform desteaming on the first processed image to obtain the second processed image.

[0033] In steam-bake or wet-bake modes, a large amount of water vapor often adheres to the camera lens or diffuses into the air inside the cavity, resulting in blurry images, indistinct edges, and reduced contrast. To improve image clarity, the controller performs desteaming processing on the first processed image.

[0034] In one example, an unsharpened mask technique is used to sharpen the image to make it clearer: Step 1: Apply Gaussian filtering to the first image to generate a blurred image; Step 2: Subtract the original image from the blurred image to obtain the edge enhancement component; Step 3: Superimpose this component back into the original image with a certain weight (e.g., 0.5) to highlight texture and boundaries; After processing, a second processed image with significantly improved clarity is output.

[0035] The second processed image still contains non-food areas such as the baking pan and cavity walls. If used directly for feature extraction, it would increase the computational burden and introduce interference. Therefore, the following steps are performed.

[0036] Step S102C: Cropping the ROI (Region of Interest) region in the second processed image to obtain the target image, where the ROI region is the area where the target food is located.

[0037] In this step, the background subtraction method can be used to extract the foreground: a "cavity template image" (i.e., the cavity image when there is no food) is stored in advance; the current second processed image is subtracted pixel by pixel from this template to obtain a difference map; the difference map is binarized (the threshold can be set to 30-50, based on the gray level difference) to initially separate the food area.

[0038] In another implementation, the food area can also be directly cut out.

[0039] This step only retains the image of the area containing the food, excluding interfering areas such as the baking pan and background. This reduces the amount of data required for subsequent processing and improves detection efficiency.

[0040] Step S103: Extract the highlight features of the target food surface in the target image.

[0041] In this embodiment of the invention, highlights are bright spots formed after light from a light source shines on the surface of food and is reflected. Highlight characteristics include, for example, the highlight area ratio, the average highlight intensity, and the highlight distribution dispersion. The highlight area ratio is the area of ​​the highlight region relative to the corresponding area of ​​the target food, used to characterize the size of the highlight region. The average highlight intensity is the average light intensity value of all pixels within the highlight area, used to characterize the brightness of the highlight.

[0042] Highlight distribution dispersion is the standard deviation of the distance from each pixel within the highlight region to its centroid, used to characterize the spatial uniformity of highlight distribution on the food surface. This feature can reflect physical states such as whether there is localized charring or uneven oil coverage on the food surface, and is one of the important criteria for judging the doneness of food.

[0043] Step S104: Based on the highlight features extracted from multiple consecutive periods, determine the dynamic change characteristics of the highlights, and based on the correlation between the changes in highlight features and the maturity of the food, determine the maturity of the target food.

[0044] In this step, the correlation between changes in highlight features and food ripeness can be calibrated experimentally.

[0045] In a specific example, taking roasted chicken as an example, the gloss characteristics corresponding to different degrees of doneness of roasted chicken are shown in Table 1 below: Table 1

[0046] As shown in the table above, in the uncooked stage, due to the high surface moisture and the lack of oil seepage, the area of ​​the highlight area is small, the brightness is low, and the dispersion is high. Moreover, as the heating time increases, the highlight area expands rapidly.

[0047] During the semi-cooked stage, as the temperature rises, a thin oil film begins to form on the surface, which increases the area and intensity of the highlights. However, the dispersion is still relatively large at this time, indicating that the surface is not completely uniform.

[0048] At the fully cooked stage: When the chicken reaches the ideal state of cooking, the surface exhibits the best gloss, with the area and intensity of the highlights reaching a moderate level, while the dispersion also decreases, indicating a more uniform surface.

[0049] If heating continues, localized scorching may occur, which will cause the highlight area to expand further, while the intensity may weaken due to carbonization, and the dispersion will increase again.

[0050] Therefore, it can be seen that the relationship between the ripeness of roasted chicken and the changes in brightness characteristics is that as the ripeness increases, the proportion of the highlight area gradually increases, the highlight brightness first increases and then decreases; the dispersion of highlight distribution first decreases and then increases.

[0051] When changes in the dynamic characteristics of the highlights show a decrease in highlight brightness and an increase in highlight distribution dispersion, it can be determined that the roasted chicken is overcooked and there is a possibility of it being burnt.

[0052] In one example, the change in highlight features with maturity can be plotted as a curve to visually represent the mapping relationship between the two.

[0053] It should be noted that the above values ​​are for illustrative purposes only and should be adjusted according to specific food types, cooking conditions, and other factors in actual application.

[0054] This invention utilizes a built-in light source within the steam-roasting equipment to actively illuminate and create highlights, avoiding random interference from natural light or stray light within the cavity. The highlight characteristics exhibit regular changes as the food surface condition evolves, making light no longer a distracting factor but rather a medium for perceiving food ripeness, thereby improving the accuracy and reliability of food ripeness determination.

[0055] Based on the above embodiments, extracting the highlight features of the target food surface in the target image includes: Step S103A: Determine the highlight area in the target image.

[0056] In one feasible implementation, determining the highlight region in the target image includes: Step A: Convert the target image to the HSV color space and extract the V channel image as the luminance image.

[0057] Highlights are characterized by a sudden increase in brightness, while color information is easily affected by carbonization. The V channel can reflect brightness changes more purely.

[0058] In another implementation, a Y component image in the YUV space can also be used, with similar results.

[0059] Step B: Binarize the brightness image to obtain the highlight candidate region.

[0060] In a specific example, a dynamic thresholding method can be used for binarization. The specific steps are as follows: Step 1: Calculate the pixel value (i.e., brightness value) of the V channel of all pixels within the ROI region, and calculate the mean and standard deviation of the brightness based on the pixel value of each pixel and the formula for mean and standard deviation; Step 2: Determine the dynamic threshold based on the calculated mean and standard deviation of brightness; The formula for calculating the dynamic threshold is:

[0061] in, For dynamic thresholds; Mean value of unlit area; This is an empirical coefficient, typically taken as 2.5 to 3.0; This represents the standard deviation of brightness.

[0062] Step 3: Perform binarization; The pixels within the ROI region are compared to a dynamic threshold. If a pixel's pixel value is greater than the threshold, it is classified as a highlight candidate; otherwise, it is classified as background pixels. All highlight candidate pixels form the highlight candidate region.

[0063] Step C: Preprocess the candidate highlight regions to obtain the highlight regions. The preprocessing includes noise removal, void filling, and separation of adhered regions.

[0064] This step involves, for example, using opening operations to eliminate noise points; using closing operations to fill small holes inside highlight areas; and using connected component analysis to separate adhered regions.

[0065] Step S103B: Extract the highlight features of the highlight region.

[0066] After obtaining the final highlight region, the highlight area ratio, the mean highlight intensity, and the highlight distribution dispersion are extracted respectively.

[0067] In a specific example, the highlight area ratio is determined by the ratio of the number of pixels in the highlight area to the number of pixels in the ROI area.

[0068] The highlight intensity is obtained by taking the average brightness value of all pixels in the highlight area of ​​the V channel as the highlight intensity average.

[0069] In the example, the specular dispersion is calculated using the following formula:

[0070] in, The first in the highlight area The distance of each pixel from the centroid of the highlight area; For all The average value; This represents the number of pixels within the highlight area. Indicates the dispersion of specular distribution; The larger the value, the farther it is from the center of the highlight area, and the more dispersed the distribution. The smaller the value, the closer it is to the center of the highlight area, and the more concentrated the distribution.

[0071] The centroid can be calculated using the average coordinates of all pixels within all highlight regions.

[0072] Based on the above embodiments, the dynamic change characteristics of highlights are determined according to the highlight features extracted from multiple consecutive periods, including: The rate of change of the proportion of the highlight area over time is determined based on the proportion of the highlight area extracted from multiple consecutive periods. And / or, based on the highlight intensity values ​​extracted from multiple consecutive periods, determine the rate of change of the highlight intensity value over time; And / or, based on the specular dispersion extracted from multiple consecutive periods, determine the rate of change of specular dispersion over time.

[0073] The rate of change of the above features can be calculated by calculating the difference between the feature value at the current moment and the feature value at the previous moment, and then using the ratio of this difference to the highlight feature value at the previous moment to represent it.

[0074] In this embodiment of the invention, there are two ways to determine the ripeness of the target food: one is by looking up a table, and the other is by using a pre-trained neural network model. These two methods will be described in detail below.

[0075] In one feasible implementation, determining the ripeness of a target food based on the correlation between changes in highlight features and food ripeness further includes: Step S104A1: Obtain the recipe for the target food.

[0076] Step S104A2: In the pre-built database, call the target mapping table that matches the recipe; the target mapping table includes the mapping relationship between the changes in highlight features and the ripeness of the food.

[0077] The highlight feature values ​​vary depending on the characteristics of different foods.

[0078] For meat dishes and dishes with oil coatings, such as roasted pork belly and roasted whole chicken, the proportion of highlight area and the average intensity gradually increase as oil seeps out, and tend to stabilize as the dish approaches maturity; the dispersion of highlight distribution first increases and then decreases, reflecting the uniformity of oil coverage.

[0079] For some baked goods and breads, the initial highlight characteristic value is low. As the crust solidifies and caramelizes, the area ratio and the average intensity increase rapidly and remain stable during ripening. The highlight distribution dispersion fluctuates within a reasonable range, indicating the uniformity of the crust.

[0080] Step S104A3: Match the maturity level corresponding to the highlight dynamic characteristics of the target food in the target mapping table.

[0081] In another feasible implementation, determining the ripeness of the target food based on the correlation between changes in highlight features and food ripeness further includes: Step S104B1: Obtain sample data of specular feature changes.

[0082] In this embodiment of the invention, the sample data comes from actual cooking records of multiple steam ovens of the same model under different user environments; or standard samples collected under controlled variables in a laboratory environment (such as fixed temperature, humidity, food batches, etc.).

[0083] The samples cover the entire process from raw to overripe to ensure data integrity, and each sample contains a time-series highlight feature vector.

[0084] Step S104B2: Determine the maturity label of the sample data based on the correlation between changes in highlight features and food maturity.

[0085] Each sample data point is labeled with its corresponding maturity level, which serves as a supervision signal for model training.

[0086] In one example, the labels are in the form of discrete categorical labels: {unripe, semi-ripe, 70% ripe, fully ripe, overripe}; or continuous numerical labels: 0.0 ~ 1.0, representing the percentage of ripeness.

[0087] Step S104B3: Train a maturity determination model based on sample data and corresponding maturity labels.

[0088] The labeled sample data is divided into training, validation, and test sets for training and evaluating model performance.

[0089] In one example, the maturity assessment model could employ a model such as LSTM (Long Short-Term Memory), XGBoost, or Random Forest.

[0090] The training process is briefly explained below: Input: a time sequence of highlight features (e.g., the past 10 time points); Output: The maturity label at the current moment; Loss functions: Cross-entropy loss is used for classification tasks, and mean squared error is used for regression tasks.

[0091] In one feasible implementation, the model can be trained separately according to recipe type (such as "meat-high fat" or "baking-low fat") to improve accuracy in specific scenarios.

[0092] Step S104B4: Input the highlight dynamic characteristics of the target food into the trained maturity determination model and output the maturity of the target food.

[0093] To verify the effectiveness of the embodiments of the present invention, a comparative experiment was conducted using roasted meat as an example, comparing its superiority with the method of determining food ripeness based on color. The experimental results are shown in Table 2 below: Table 2

[0094] As shown in Table 2 above, high light can detect key milestones such as oil precipitation and epidermal formation in advance, providing a more accurate and earlier maturity signal than color.

[0095] Therefore, highlight features exhibit superior stability and discrimination ability in real cooking environments; highlight feature detection not only avoids the fundamental defect of color distortion, but also captures key physical changes on the food surface earlier and more accurately, greatly improving the accuracy and reliability of food ripeness determination.

[0096] Based on the same inventive concept, a food ripeness determination device is provided, applicable to a steaming and baking equipment. The steaming and baking equipment includes a cooking cavity, within which a light source and an image acquisition device are installed, such as... Figure 2 As shown, the device includes: The acquisition unit 201 is used to acquire initial images periodically captured by the image acquisition device during the cooking process; The preprocessing unit 202 is used to preprocess the initial image to obtain a target image containing the target food; Extraction unit 203 is used to extract the highlight features of the target food surface in the target image; the highlight is the bright spot formed after the light source shines on the food surface and is reflected. The determining unit 204 is used to determine the dynamic change characteristics of the highlights based on the highlights extracted from multiple consecutive periods, and to determine the maturity of the target food based on the correlation between the changes in highlights and the maturity of the food.

[0097] Based on the same technical concept, embodiments of the present invention also provide an electronic device, such as... Figure 3 As shown, it includes a processor 301, a communication interface 302, a memory 303, and a communication bus 304, wherein the processor 301, the communication interface 302, and the memory 303 communicate with each other through the communication bus 304.

[0098] Memory 303 is used to store computer programs; The processor 301 is used to execute the steps of the food maturity determination method when executing the program stored in the memory 303.

[0099] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0100] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0101] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0102] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0103] The food ripeness determination device provided in this embodiment of the invention can be specific hardware on a device or software or firmware installed on the device. The implementation principle and technical effects of the device provided in this embodiment of the invention are the same as those in the foregoing method embodiments. For the sake of brevity, any parts not mentioned in the device embodiments can be referred to the corresponding content in the foregoing method embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can all be referred to the corresponding processes in the above method embodiments, and will not be repeated here.

[0104] In the embodiments provided by this invention, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0105] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0106] In addition, the functional units in the embodiments provided by the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0107] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0108] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0109] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. All should be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for determining the ripeness of food, characterized in that, Applied to a steam-and-bake equipment, the steam-and-bake equipment including a cooking cavity, wherein a light source and an image acquisition device are installed in the cooking cavity, the method includes: During the cooking process, initial images are acquired periodically by the image acquisition device; The initial image is preprocessed to obtain a target image containing the target food; Extract the highlight features of the target food surface from the target image; the highlight is the bright spot formed after the light source shines on the food surface and is reflected. Based on the highlight features extracted from multiple consecutive periods, the dynamic change characteristics of the highlight are determined, and the maturity of the target food is determined based on the correlation between the changes in highlight features and the maturity of the food.

2. The method according to claim 1, characterized in that, The preprocessing of the initial image to obtain a target image containing the target food includes: The initial image is subjected to illumination correction to obtain a first processed image; The first processed image is devastated to obtain the second processed image; The ROI region in the second processed image is cropped to obtain the target image, where the ROI region is the area where the target food is located.

3. The method according to claim 1, characterized in that, The step of extracting the highlight features of the target food surface in the target image includes: Identify the highlight region in the target image; Extract the highlight features of the highlight region. The highlight features include at least one of the following: highlight area ratio, highlight intensity mean, and highlight distribution dispersion. The highlight area ratio is the area of ​​the highlight region relative to the area corresponding to the target food. The highlight intensity mean is the average light intensity value of all pixels in the highlight region.

4. The method according to claim 3, characterized in that, Determining the highlight region in the target image includes: The target image is converted to the HSV color space, and the V channel image is extracted as the luminance image; The brightness image is binarized to obtain the highlight candidate region; The candidate region of the highlight is preprocessed to obtain the highlight region. The preprocessing includes noise elimination, void filling and separation of the bonded region.

5. The method according to claim 3, characterized in that, The determination of the dynamic change characteristics of highlights based on the highlights extracted from multiple consecutive periods includes: The rate of change of the proportion of the highlight area over time is determined based on the proportion of the highlight area extracted from multiple consecutive periods. And / or, based on the highlight intensity values ​​extracted from multiple consecutive periods, determine the rate of change of the highlight intensity value over time; And / or, based on the specular dispersion extracted from multiple consecutive periods, determine the rate of change of specular dispersion over time.

6. The method according to claim 1, characterized in that, Determining the maturity of the target food based on the correlation between changes in specular features and food maturity further includes: Obtain the recipe for the target food; In a pre-built database, a target mapping table matching the recipe is invoked; the target mapping table includes the mapping relationship between changes in highlight features and food ripeness. Match the maturity level corresponding to the hyperglycemic dynamics of the target food in the target mapping table.

7. The method according to claim 1, characterized in that, Determining the maturity of the target food based on the correlation between changes in specular features and food maturity further includes: Obtain sample data on the changes in highlight features; Based on the correlation between changes in specular features and food maturity, the maturity label of the sample data is determined; A maturity determination model is trained based on the sample data and the corresponding maturity labels. The highlight dynamic characteristics of the target food are input into the trained maturity determination model, and the maturity of the target food is output.

8. A device for determining the ripeness of food, characterized in that, Applied to a steam-and-bake equipment, the steam-and-bake equipment includes a cooking cavity, and a light source and an image acquisition device are installed inside the cooking cavity, the device including: The acquisition unit is used to acquire initial images periodically captured by the image acquisition device during the cooking process; The preprocessing unit is used to preprocess the initial image to obtain a target image containing the target food. The extraction unit is used to extract the highlight features of the target food surface in the target image; the highlight is the bright spot formed after the light source shines on the food surface and is reflected. The determining unit is used to determine the dynamic change characteristics of the highlights based on the highlights extracted from multiple consecutive periods, and to determine the maturity of the target food based on the correlation between the changes in highlights and the maturity of the food.

9. A steam-roasting device, characterized in that, The device includes a steam oven body and a controller. The steam oven body includes a cooking cavity, in which a light source and an image acquisition device are installed. The controller performs the method described in any one of claims 1-7.

10. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; The memory is used to store computer programs; When the processor executes the program stored in the memory, it implements the method described in any one of claims 1-7.

Images