Cooking control method and system based on image recognition

Abstract

The invention relates to the technical field of image processing, in particular to a cooking control method and system based on image recognition, and the method comprises the steps: obtaining a cooking video stream of food materials in cooking equipment in a cooking operation process of the cooking equipment according to reference cooking parameters; performing image recognition on the cooking video stream to obtain image features of the food material in the current cooking time period, and determining the maturity of the food material based on the image features; determining a mature state of the food materials based on the image features, adjusting cooking parameters of the cooking equipment according to the mature state, and controlling the cooking equipment to perform cooking operation based on the adjusted cooking parameters; according to the invention, a more intelligent and personalized cooking solution can be provided for the user.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a cooking control method and system based on image recognition. Background Art

[0002] The cooking equipment in the related art lacks intelligence in cooking control. For example, the cooking time and heat of the ingredients need to be set manually based on experience or recommended by a cooking recipe manual. This often ignores the differences in the types and weights of the main ingredients, seasonings, and condiments, which leads to differences in cooking time and heat, resulting in poor color and taste of the cooked food, and even problems of burnt or undercooked food.

[0003] Therefore, it is necessary to solve the problem that in complex situations such as the diversity of cooking ingredients, the diversity of cooking methods, and the variability of ingredient weights, the cooking of ingredients can only be better completed by relying on experience or the guidance of professionals such as chefs, so as to improve the intelligence of cooking. Summary of the invention

[0004] The object of the present invention is to provide a cooking control method and system based on image recognition to solve the problems existing in the prior art.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] In one aspect, an embodiment of the present invention provides a cooking control method based on image recognition, the method comprising the following steps:

[0007] S100, when the cooking device performs a cooking operation according to reference cooking parameters, a cooking video stream of the food in the cooking device is obtained; wherein the reference cooking parameters include a plurality of cooking time periods and cooking temperatures corresponding to the plurality of cooking time periods, each of the cooking time periods includes a plurality of reference video segments divided according to a set segment duration, each of the reference video segments has a corresponding reference feature variation degree, and each of the reference feature variation degrees is arranged in sequence according to the time sequence of the corresponding segment duration;

[0008] S200, performing image recognition on the cooking video stream to obtain image features of the food in the current cooking time period, and determining the maturity of the food based on the image features; wherein the image features include glossiness, color and transparency;

[0009] S300, if it is determined that the maturity of the food does not reach the maturity threshold, determine the maturity state of the food based on the image features, adjust the cooking parameters of the cooking equipment according to the maturity state, and control the cooking equipment to perform cooking operations based on the adjusted cooking parameters; wherein the maturity state represents the difference between the current characteristic change degree of the food and the reference characteristic change degree.

[0010] Optionally, the reference cooking parameters are obtained in advance in the following manner:

[0011] S110, determining a heating area of ​​a cooking device, wherein the heating area of ​​the cooking device is provided with M heating tubes arranged at equal intervals;

[0012] S120, dividing the heating area of ​​the cooking device into M grids based on the M heating tubes, setting a target temperature of the food in each cooking time period, and the target temperatures of the M heating tubes are increased or decreased in sequence;

[0013] S130, respectively controlling the M heating tubes to heat the food in the cooking device at corresponding target temperatures, sampling to obtain a plurality of characteristic images and a plurality of temperature distribution graphs during the heating process of the M heating tubes at the corresponding target temperatures, dividing the characteristic images into grids to generate a plurality of characteristic distribution graphs, and the plurality of characteristic distribution graphs and the plurality of temperature distribution graphs. Figure 1 One to one correspondence;

[0014] S140, fitting the temperature values ​​of the M heating tubes in the temperature distribution diagram to obtain a temperature fitting curve, fitting the image features of the M grids in the feature distribution diagram to obtain an image feature fitting curve, performing linear regression processing on the M temperature fitting curves and the image feature fitting curve respectively, to obtain reference feature variation degrees for different cooking temperatures.

[0015] Optionally, in S200, performing image recognition on the cooking video stream to obtain image features of the food, and determining the maturity of the food based on the image features includes:

[0016] S210, obtaining a mature image of the food after cooking, and extracting reference features of the mature image; wherein the reference features include reference color, reference transparency, reference glossiness, and reference grayscale;

[0017] S210, obtaining a most recently captured frame of image from the cooking video stream, determining image features of the image based on the reference features, and determining the maturity of the food based on the image features and the reference features; wherein the image features include texture features and color features.

[0018] Optionally, in S210, acquiring a most recently captured frame of image from the cooking video stream, determining an image feature of the image based on the reference feature, and determining the maturity of the food based on the image feature and the reference feature, includes:

[0019] Each grid is divided into N pixel blocks with equal spacing, and the color feature of the i-th grid is calculated by the following formula:

[0020]

[0021] Among them, c j is the hue of the jth pixel block, c0 is the reference hue, t j is the transparency of the jth pixel block, t0 is the reference transparency, g j is the glossiness of the jth pixel block, g0 is the reference glossiness; λ1, λ2 and λ3 are weight coefficients: 0≤λ1≤1, 0≤λ2≤1, 0≤λ3≤1, λ1+λ2+λ3=1, i is the grid number, i=1,2,...,M, j is the pixel block number, j=1,2,...,N;

[0022] Each grid is divided into N pixel blocks with equal spacing, and the texture features are calculated by the following formula:

[0023]

[0024] Where p(i,j) is the grayscale of the jth pixel block in the i-th grid, s(i,j) is the reference grayscale; λ4 and λ5 are weight coefficients: 0≤λ4≤1, 0≤λ5≤1, λ4+λ5=1;

[0025] The maturity of the food is calculated using the following formula:

[0026]

[0027] Among them, Ci is the color feature of the i-th grid, and T is the texture feature of the image.

[0028] Optionally, in S300, determining the maturity state of the food based on the image feature, and adjusting the cooking parameters of the cooking device according to the maturity state includes:

[0029] S310, intercepting the cooking video stream into video segments in real time according to the segment duration, performing image recognition on the video segments, and generating real-time feature change degrees corresponding to the video segments;

[0030] S320, determining a time sequence corresponding to the video clips, determining a reference feature change degree corresponding to the real-time feature change degree based on the time sequence, and determining an image feature difference degree based on the real-time feature change degree and the corresponding reference feature change degree;

[0031] S330: Determine the maturity state of the food based on the difference in the image features, and adjust cooking parameters of the cooking device according to the maturity state.

[0032] Optionally, in S310, performing image recognition on the video segment to generate a real-time feature change degree corresponding to the video segment includes:

[0033] S311, sampling the video clip stream according to a set sampling duration to obtain a plurality of video frames, and respectively generating image features of the plurality of video frames;

[0034] S312, determining the timestamp of each of the video frames, and determining the real-time feature change degree corresponding to the video segment based on the timestamp of each of the video frames and the corresponding image features.

[0035] Optionally, in S330, determining the maturity state of the food based on the image feature difference, and adjusting the cooking parameters of the cooking device according to the maturity state includes:

[0036] S331, obtaining an average cooking temperature of the cooking device in each intercepted video segment, establishing a corresponding relationship between the real-time feature change degree of each video segment and the average cooking temperature, and generating a temperature influence coefficient corresponding to the video segment according to the corresponding relationship;

[0037] S332, determining a doneness reference curve of the food based on the correspondence between the characteristic variation degree and the cooking condition coefficient, and determining a cooking time required for the food to reach a doneness threshold based on the doneness reference curve;

[0038] S333, determining the cooking temperature and cooking time of the cooking time period based on the maturity state of the food and the temperature influence coefficient, and adjusting the cooking parameters of the cooking equipment to the cooking temperature and cooking time of the cooking time period.

[0039] On the other hand, an embodiment of the present invention provides a cooking control system based on image recognition, comprising:

[0040] at least one processor;

[0041] at least one memory for storing at least one program;

[0042] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0043] The beneficial effects of the present invention are as follows: the present invention discloses a cooking control method and system based on image recognition, wherein the present invention obtains a cooking video stream of ingredients in a cooking device during a cooking operation performed by the cooking device according to reference cooking parameters; performs image recognition on the cooking video stream to obtain image features of the ingredients in a current cooking time period, and determines the maturity of the ingredients based on the image features; determines the maturity state of the ingredients based on the image features, adjusts the cooking parameters of the cooking device according to the maturity state, and controls the cooking device to perform cooking operations based on the adjusted cooking parameters; under the control of a recipe program based on image recognition, realizes cooking heat and duration control based on ingredient images, thereby improving the intelligence of cooking; and provides users with a more intelligent and personalized cooking solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0045] Figure 1 is a flow chart of a cooking control method based on image recognition according to an embodiment of the present invention;

[0046] Figure 2 It is a structural schematic diagram of a cooking control system based on image recognition according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects disclosed in the present invention, so as to fully understand the purpose, scheme and effect disclosed in the present invention. It should be noted that the embodiments and features in the embodiments in this application can be combined with each other without conflict.

[0048] refer to Figure 1 ,like Figure 1 A cooking control method based on image recognition provided by an embodiment of the present invention is shown, and the method comprises the following steps:

[0049] S100, when the cooking device performs a cooking operation according to reference cooking parameters, a cooking video stream of the food in the cooking device is obtained; wherein the reference cooking parameters include a plurality of cooking time periods and cooking temperatures corresponding to the plurality of cooking time periods, each of the cooking time periods includes a plurality of reference video segments divided according to a set segment duration, each of the reference video segments has a corresponding reference feature variation degree, and each of the reference feature variation degrees is arranged in sequence according to the time sequence of the corresponding segment duration;

[0050] Specifically, dish information input by a user through an interactive interface of a client is obtained, and ingredients corresponding to the dish information and preference information for the ingredients are determined; the preference information includes the maturity of the ingredients; reference cooking parameters matching the ingredients are obtained from a preset cooking parameter library; a cooking device is controlled to perform cooking operations according to the reference cooking parameters; during the cooking process of the cooking device, an image inside the cooking device is captured using a high-temperature resistant camera, the maturity status of the ingredients is monitored in real time, and the cooking parameters of the cooking device are adjusted according to the maturity status.

[0051] S200, performing image recognition on the cooking video stream to obtain image features of the food in the current cooking time period, and determining the maturity of the food based on the image features; wherein the image features include glossiness, color and transparency;

[0052] It should be noted that the maturity of the same ingredient is reproducible. Taking pork as an example, the maturity of pork is not affected by size, shape, initial temperature, and temperature of the heat transfer medium, and is stable. After cooking heat treatment, pork from the same raw material source and the same maturity has no significant difference in image features such as texture and color, and has regularity and repeatability. During the cooking process, physical changes will occur when food is heated, and the physical changes can be intuitively identified by appearance. The present invention establishes a corresponding relationship between the texture, shape, color, and temperature of the food based on the identification of the heating degree of different ingredients, measures the actual heated ingredients, and analyzes whether they have reached the preset maturity threshold.

[0053] S300, if it is determined that the maturity of the food does not reach the maturity threshold, determine the maturity state of the food based on the image features, adjust the cooking parameters of the cooking equipment according to the maturity state, and control the cooking equipment to perform cooking operations based on the adjusted cooking parameters; wherein the maturity state represents the difference between the current characteristic change degree of the food and the reference characteristic change degree.

[0054] By adjusting the cooking time and temperature, the maturity of the ingredients can be controlled to prevent them from being too late or too early. Under the control of the recipe program based on image recognition, the cooking temperature and duration control based on the ingredient image is realized, which improves the intelligent level of cooking and provides users with a more intelligent and personalized cooking solution.

[0055] As an improvement of the above embodiment, the reference cooking parameters are obtained in advance in the following manner:

[0056] S110, determining a heating area of ​​a cooking device, wherein the heating area of ​​the cooking device is provided with M heating tubes arranged at equal intervals;

[0057] S120, dividing the heating area of ​​the cooking device into M grids based on the M heating tubes, setting a target temperature of the food in each cooking time period, and the target temperatures of the M heating tubes are increased or decreased in sequence;

[0058] Specifically, taking M heating tubes arranged at equal intervals as the central axis, a grid corresponding to each heating tube is divided, and a total of M grids are obtained.

[0059] S130, respectively controlling the M heating tubes to heat the food in the cooking device at corresponding target temperatures, sampling to obtain a plurality of characteristic images and a plurality of temperature distribution graphs during the heating process of the M heating tubes at the corresponding target temperatures, dividing the characteristic images into grids to generate a plurality of characteristic distribution graphs, and the plurality of characteristic distribution graphs and the plurality of temperature distribution graphs. Figure 1 One to one correspondence;

[0060] Specifically, characteristic images of the food at multiple sampling moments are obtained, and features are extracted from each grid in the characteristic image to obtain a characteristic distribution map. The characteristic distribution map is corresponded to the temperature distribution map, and each grid corresponds to a temperature value. The temperature value of each grid gradually increases. During this process, the image features of the corresponding grids will also change accordingly. Since the target temperatures of adjacent grids increase or decrease successively, there will be a certain conduction or heat exchange effect between them, which can simulate the temperature changes in the actual cooking process. The resulting characteristic distribution map is more in line with the actual situation, and the adjustment of cooking parameters is more precise.

[0061] S140, fitting the temperature values ​​of the M heating tubes in the temperature distribution diagram to obtain a temperature fitting curve, fitting the image features of the M grids in the feature distribution diagram to obtain an image feature fitting curve, performing linear regression processing on the M temperature fitting curves and the image feature fitting curve respectively, to obtain reference feature variation degrees for different cooking temperatures.

[0062] As an improvement of the above embodiment, in S200, performing image recognition on the cooking video stream to obtain image features of the food, and determining the maturity of the food based on the image features includes:

[0063] S210, obtaining a mature image of the food after cooking, and extracting reference features of the mature image; wherein the reference features include reference color, reference transparency, reference glossiness, and reference grayscale;

[0064] S210, obtaining a most recently captured frame of image from the cooking video stream, determining image features of the image based on the reference features, and determining the maturity of the food based on the image features and the reference features; wherein the image features include texture features and color features.

[0065] As an improvement of the above embodiment, the maturity of the food is calculated by the following formula:

[0066]

[0067] Among them, Ci is the color feature of the i-th grid, and T is the texture feature of the image.

[0068] As an improvement of the above embodiment, the acquiring a most recently captured frame of image from the cooking video stream and determining the image feature of the image based on the reference feature includes:

[0069] Each grid is divided into N pixel blocks with equal spacing, and the color feature of the i-th grid is calculated by the following formula:

[0070]

[0071] Among them, c j is the hue of the jth pixel block, c0 is the reference hue, t j is the transparency of the jth pixel block, t0 is the reference transparency, g j is the glossiness of the jth pixel block, g0 is the reference glossiness; λ1, λ2 and λ3 are weight coefficients: 0≤λ1≤1, 0≤λ2≤1, 0≤λ3≤1, λ1+λ2+λ3=1, i is the grid number, i=1,2,...,M, j is the pixel block number, j=1,2,...,N;

[0072] During the cooking process, the image of the food can be obtained in real time, and the maturity can be determined by the image features of the food. When the glossiness of the food is low, the color is darker, and the transparency is smaller, it means that the food is more mature. Through the processing of the exponential function, the color features are mapped to the interval [0,1].

[0073] Each grid is divided into N pixel blocks with equal spacing, and the texture features are calculated by the following formula:

[0074]

[0075] Among them, p(i,j) is the grayscale of the jth pixel block in the i-th grid, s(i,j) is the reference grayscale; λ4 and λ5 are weight coefficients: 0≤λ4≤1, 0≤λ5≤1, λ4+λ5=1.

[0076] Texture features reflect the uniformity of the grayscale value distribution of each pixel in the image and the overall grayscale difference from the mature image. During the cooking process of ingredients, the more uniform the grayscale value, the higher the maturity; the smaller the overall grayscale difference, the higher the maturity.

[0077] As an improvement of the above embodiment, in S300, determining the maturity state of the food based on the image feature and adjusting the cooking parameters of the cooking device according to the maturity state include:

[0078] S310, intercepting the cooking video stream into video segments in real time according to the segment duration, performing image recognition on the video segments, and generating real-time feature change degrees corresponding to the video segments;

[0079] S320, determining a time sequence corresponding to the video clips, determining a reference feature change degree corresponding to the real-time feature change degree based on the time sequence, and determining an image feature difference degree based on the real-time feature change degree and the corresponding reference feature change degree;

[0080] S330: Determine the maturity state of the food based on the difference in the image features, and adjust cooking parameters of the cooking device according to the maturity state.

[0081] As an improvement of the above embodiment, in S310, performing image recognition on the video segment to generate a real-time feature change degree corresponding to the video segment includes:

[0082] S311, sampling the video clip stream according to a set sampling duration to obtain a plurality of video frames, and respectively generating image features of the plurality of video frames;

[0083] S312, determining the timestamp of each of the video frames, and determining the real-time feature change degree corresponding to the video segment based on the timestamp of each of the video frames and the corresponding image features.

[0084] Specifically, the real-time characteristic variation degree of the food is determined based on the variation of the image characteristics of each of the video frames over time.

[0085] As an improvement of the above embodiment, in S300, determining the maturity state of the food based on the image feature difference, and adjusting the cooking parameters of the cooking device according to the maturity state includes:

[0086] Obtaining an average cooking temperature of the cooking device in each intercepted video segment, establishing a corresponding relationship between the real-time feature change degree of each video segment and the average cooking temperature, and generating a temperature influence coefficient corresponding to the video segment according to the corresponding relationship;

[0087] Determine a doneness reference curve of the food based on the correspondence between the characteristic variation degree and the cooking condition coefficient, and determine the cooking time required for the food to reach a doneness threshold based on the doneness reference curve;

[0088] The cooking temperature and cooking time of the cooking time period are determined based on the maturity state of the food and the temperature influence coefficient, and the cooking parameters of the cooking device are adjusted to the cooking temperature and cooking time of the cooking time period.

[0089] refer to Figure 2 The embodiment of the present invention further provides a cooking control system based on image recognition, comprising:

[0090] at least one processor;

[0091] at least one memory for storing at least one program;

[0092] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0093] The contents of the above method embodiments are all applicable to this embodiment. The functions specifically implemented by this embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments, which will not be repeated here.

[0094] Although the description of the present disclosure has been quite detailed and specifically describes several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but should be regarded as providing a broad possible interpretation of these claims by reference to the appended claims, taking into account the prior art, so as to effectively cover the intended scope of the present disclosure. In addition, the above description of the present disclosure is based on the embodiments foreseeable by the inventor, and its purpose is to provide a useful description, and those non-substantial changes to the present disclosure that have not yet been foreseen may still represent equivalent changes to the present disclosure.

Claims

1. A cooking control method based on image recognition, characterized in that: The method comprises the following steps: S100, when the cooking device performs a cooking operation according to reference cooking parameters, a cooking video stream of the food in the cooking device is obtained; wherein the reference cooking parameters include a plurality of cooking time periods and cooking temperatures corresponding to the plurality of cooking time periods, each of the cooking time periods includes a plurality of reference video segments divided according to a set segment duration, each of the reference video segments has a corresponding reference feature variation degree, and each of the reference feature variation degrees is arranged in sequence according to the time sequence of the corresponding segment duration; S200, performing image recognition on the cooking video stream to obtain image features of the food in the current cooking time period, and determining the maturity of the food based on the image features; wherein the image features include glossiness, color and transparency; S300, if it is determined that the maturity of the food does not reach the maturity threshold, determine the maturity state of the food based on the image features, adjust the cooking parameters of the cooking equipment according to the maturity state, and control the cooking equipment to perform cooking operations based on the adjusted cooking parameters; wherein the maturity state represents the difference between the current characteristic change degree of the food and the reference characteristic change degree.

2. The method according to claim 1, characterized in that The reference cooking parameters are obtained in advance in the following manner: S110, determining a heating area of ​​a cooking device, wherein the heating area of ​​the cooking device is provided with M heating tubes arranged at equal intervals; S120, dividing the heating area of ​​the cooking device into M grids based on the M heating tubes, setting a target temperature of the food in each cooking time period, and the target temperatures of the M heating tubes are increased or decreased in sequence; S130, respectively controlling the M heating tubes to heat the food in the cooking device at corresponding target temperatures, sampling to obtain a plurality of characteristic images and a plurality of temperature distribution graphs during the heating process of the M heating tubes at the corresponding target temperatures, dividing the characteristic images into grids to generate a plurality of characteristic distribution graphs, wherein the plurality of characteristic distribution graphs correspond to the plurality of temperature distribution graphs in one-to-one correspondence; S140, fitting the temperature values ​​of the M heating tubes in the temperature distribution diagram to obtain a temperature fitting curve, fitting the image features of the M grids in the feature distribution diagram to obtain an image feature fitting curve, performing linear regression processing on the M temperature fitting curves and the image feature fitting curve respectively, to obtain reference feature variation degrees for different cooking temperatures.

3. The method according to claim 1, characterized in that In S200, performing image recognition on the cooking video stream to obtain image features of the food, and determining the maturity of the food based on the image features includes: S210, obtaining a mature image of the food after cooking, and extracting reference features of the mature image; wherein the reference features include reference color, reference transparency, reference glossiness, and reference grayscale; S210, obtaining a most recently captured frame of image from the cooking video stream, determining image features of the image based on the reference features, and determining the maturity of the food based on the image features and the reference features; wherein the image features include texture features and color features.

4. The method according to claim 3, characterized in that In S210, acquiring a most recently captured frame of image from the cooking video stream, determining image features of the image based on the reference features, and determining the maturity of the food based on the image features and the reference features, includes: Each grid is divided into N pixel blocks with equal spacing, and the color feature of the i-th grid is calculated by the following formula: Among them, c j is the hue of the jth pixel block, c0 is the reference hue, t j is the transparency of the jth pixel block, t0 is the reference transparency, g j is the glossiness of the jth pixel block, g0 is the reference glossiness; λ1, λ2 and λ3 are weight coefficients: 0≤λ1≤1, 0≤λ2≤1, 0≤λ3≤1, λ1+λ2+λ3=1, i is the grid number, i=1,2,...,M, j is the pixel block number, j=1,2,...,N; Each grid is divided into N pixel blocks with equal spacing, and the texture features are calculated by the following formula: Where p(i,j) is the grayscale of the jth pixel block in the i-th grid, s(i,j) is the reference grayscale; λ4 and λ5 are weight coefficients: 0≤λ4≤1, 0≤λ5≤1, λ4+λ5=1; The maturity of the food is calculated using the following formula: Among them, Ci is the color feature of the i-th grid, and T is the texture feature of the image.

5. The method according to claim 3, characterized in that: In S300, determining the maturity state of the food based on the image feature and adjusting the cooking parameters of the cooking device according to the maturity state includes: S310, intercepting the cooking video stream into video segments in real time according to the segment duration, performing image recognition on the video segments, and generating real-time feature change degrees corresponding to the video segments; S320, determining a time sequence corresponding to the video clips, determining a reference feature change degree corresponding to the real-time feature change degree based on the time sequence, and determining an image feature difference degree based on the real-time feature change degree and the corresponding reference feature change degree; S330: Determine the maturity state of the food based on the difference in the image features, and adjust cooking parameters of the cooking device according to the maturity state.

6. The method according to claim 5, characterized in that In S310, performing image recognition on the video segment to generate a real-time feature change degree corresponding to the video segment includes: S311, sampling the video clip stream according to a set sampling duration to obtain a plurality of video frames, and respectively generating image features of the plurality of video frames; S312, determining the timestamp of each of the video frames, and determining the real-time feature change degree corresponding to the video segment based on the timestamp of each of the video frames and the corresponding image features.

7. The method according to claim 5, characterized in that In S330, determining the maturity state of the food based on the image feature difference, and adjusting the cooking parameters of the cooking device according to the maturity state includes: S331, obtaining an average cooking temperature of the cooking device in each intercepted video segment, establishing a corresponding relationship between the real-time feature change degree of each video segment and the average cooking temperature, and generating a temperature influence coefficient corresponding to the video segment according to the corresponding relationship; S332, determining a doneness reference curve of the food based on the correspondence between the characteristic variation degree and the cooking condition coefficient, and determining a cooking time required for the food to reach a doneness threshold based on the doneness reference curve; S333, determining the cooking temperature and cooking time of the cooking time period based on the maturity state of the food and the temperature influence coefficient, and adjusting the cooking parameters of the cooking equipment to the cooking temperature and cooking time of the cooking time period.

8. A cooking control system based on image recognition, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 7.

Images