Image processing method and device, electronic equipment and storage medium

Abstract

The invention discloses an image processing method and device, electronic equipment and a storage medium. According to the embodiment of the invention, a first image of the interior of cooking equipment at a first environment temperature is acquired; the first image comprises at least one target food material; determining first color data corresponding to the first image; comparing the first color data with second color data of at least one target food material in a second temperature environment, and determining an initial color difference value corresponding to each target food material; determining a target color difference value according to the initial color difference value of the at least one target food material and the coefficient corresponding to each target food material; and performing color correction on the first image based on the target color difference value to obtain the target image, thereby improving the image processing efficiency while optimizing the quality of the recorded cooking video.

Description

Technical Field

[0001] The present application belongs to the field of image processing technology, and specifically relates to an image processing method, device, electronic device and storage medium. Background Art

[0002] Currently, when shooting the cooking process, the camera is often exposed to a high temperature environment for a long time, which not only tests the camera's heat resistance, but also causes the captured image to be filled with dense noise caused by high temperature.

[0003] Although existing noise reduction algorithms perform well in normal environments, their processing time window in the time domain is extremely short, so when faced with noise reduction tasks in high-temperature environments, the effect is often unsatisfactory. The reason is that in high-temperature environments, the signal is already mixed with a large number of high-frequency components that are difficult to remove, which seriously damages the image quality, thus seriously affecting the final effect and clarity of image processing. Overall, the application of current noise reduction algorithms in high-temperature environments still has great limitations, which reduces the effect of image processing. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide an image processing method, device, electronic device and storage medium, which can solve the problem of poor image processing effect in the process of image processing in related technologies.

[0005] In a first aspect, an embodiment of the present application provides an image processing method, the method comprising:

[0006] Acquire a first image of the interior of a cooking device at a first ambient temperature; the first image includes at least one target food;

[0007] Determining first color data corresponding to the first image;

[0008] Comparing the first color data with the second color data of the at least one target food in the second temperature environment to determine an initial color difference corresponding to each target food;

[0009] Determining a target color difference value according to an initial color difference value of at least one target ingredient and a coefficient corresponding to each target ingredient;

[0010] The first image is color corrected based on the target color difference to obtain a target image. In a second aspect, an embodiment of the present application provides an image processing device, the device comprising:

[0011] A first acquisition module is used to acquire a first image of the interior of the cooking device at a first ambient temperature; the first image includes at least one target food;

[0012] a first determination module, configured to determine first color data corresponding to the first image; compare the first color data with second color data of the at least one target food in a second temperature environment to determine an initial color difference corresponding to each target food; and determine a target color difference according to the initial color difference of the at least one target food and a coefficient corresponding to each target food;

[0013] The obtaining module is used to perform color correction on the first image based on the target color difference to obtain a target image.

[0014] In a third aspect, an embodiment of the present application provides an image processing system, which includes a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus; the memory is used to store executable instructions, and the executable instructions enable the processor to execute the image processing method as described in any one of the above items.

[0015] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, an image processing method as described in any one of the above items is implemented.

[0016] In an embodiment of the present application, an image processing method is provided, which obtains a first image of the interior of a cooking device at a first ambient temperature; the first image includes at least one target ingredient; first color data corresponding to the first image is determined; the first color data is compared with second color data of at least one target ingredient in a second temperature environment to determine an initial color difference corresponding to each target ingredient; a target color difference is determined based on the initial color difference of at least one target ingredient and a coefficient corresponding to each target ingredient; color correction is performed on the first image based on the target color difference to obtain a target image, and in the process of image processing, the color difference between the first color data corresponding to the target ingredient at the first ambient temperature and the second color data corresponding to the target ingredient at the second ambient temperature can be used as the initial color difference, and the initial color difference is adjusted to obtain the target color difference, thereby realizing noise reduction processing on the first image, and further, color correction is performed on the first image based on the target color difference to obtain the target image, thereby realizing color correction processing on the first image, optimizing the quality of the recorded cooking video, and thereby improving the efficiency of image processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a step flow of an image processing method provided in an embodiment of the present application. Figure 1 ;

[0018] Figure 2This is a step flow of an image processing method provided in an embodiment of the present application. Figure 2 ;

[0019] Figure 3 This is a step flow of an image processing method provided in an embodiment of the present application. Figure 3 ;

[0020] Figure 4 is a logic block diagram of an image processing device provided in an embodiment of the present application;

[0021] Figure 5 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0023] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0024] Method Embodiment

[0025] The image processing method provided in the embodiment of the present application is described in detail below through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0026] Reference Figure 1 , showing the steps of an image processing method provided by an embodiment of the present application Figure 1 ,like Figure 1 As shown, the method specifically includes steps 101 to 106:

[0027] Step 101: Acquire a first image of the interior of a cooking device at a first ambient temperature; the first image includes at least one target food.

[0028] In an embodiment of the present application, during the image processing process, the image processing system may first acquire a first image under a first temperature environment; the first image includes a plurality of target ingredients.

[0029] Exemplarily, the first image may include a variety of vegetables, or a plurality of meat ingredients, such as tomatoes, broccoli, chicken breast, beef, etc., which are not limited in the embodiments of the present application.

[0030] In this step, the first ambient temperature may be a high temperature environment, for example, an environment with a temperature greater than or equal to 60 degrees Celsius, or an environment with a temperature greater than or equal to 70 degrees Celsius, etc., which is not limited in the embodiments of the present application.

[0031] In this step, the first image may be an image of any frame in a cooking video acquired using a camera, and the first image may include multiple target ingredients and a background area excluding the target ingredients, etc., which is not limited in the embodiments of the present application.

[0032] In this step, at least one target ingredient may include multiple different ingredients. During the cooking process, multiple target ingredients can be pre-determined according to the recipe. For example, when the recipe is scrambled eggs with tomatoes, the target ingredients may include eggs, tomatoes, shallots, garlic, etc., which are not limited in the embodiments of the present application.

[0033] In an embodiment of the present application, during the image processing process, the image processing system may first acquire a first image in a low temperature environment.

[0034] Step 102: Determine first color data corresponding to the first image.

[0035] The image processing method provided in the embodiment of the present application obtains a first image of the interior of a cooking device at a first ambient temperature; after the first image includes at least one target ingredient, the image processing system can determine first color data corresponding to the first image.

[0036] In this step, the first color data corresponding to the first image may include first color data of a plurality of target ingredients in the first image, and the first color data is acquired in a high temperature environment.

[0037] In this step, during the image processing, the image processing system may first determine the first color data in a high temperature environment based on the cooking video.

[0038] Step 103: Compare the first color data with the second color data of at least one target food in the second temperature environment to determine an initial color difference corresponding to each target food.

[0039] In the image processing method provided in the embodiment of the present application, after determining the first color data corresponding to the first image, the image processing system can compare the first color data with the second color data of at least one target food in the second temperature environment to determine the initial color difference corresponding to each target food.

[0040] In this step, the second temperature environment may be a low temperature environment, for example, an environment with a temperature less than 60 degrees Celsius, or an environment with a temperature less than 50 degrees Celsius, etc., which is not limited in the embodiments of the present application.

[0041] In this step, the second color data of at least one target food in the second temperature environment may include second color data of a plurality of target food, and the second color data is obtained in a low temperature environment.

[0042] Exemplarily, in an embodiment of the present application, the second color data may be RGB data in a normal temperature environment, and the second color data will not be affected by high temperature noise.

[0043] Exemplarily, in this step, the initial color difference corresponding to each target ingredient may include: determined according to the first color data under the high temperature environment and the second color data under the low temperature environment, the initial color difference of each ingredient includes the difference of three colors corresponding to RGB, for example: when the target ingredient is tomato, the color data of the R channel under the high temperature environment is 240, the color data of the G channel under the high temperature environment is 40, the color data of the B channel under the high temperature environment is 30, the color data of the R channel under the low temperature environment is 245, the color data of the G channel is 30, and the color data of the B channel is 35, then the color difference corresponding to the RGB channels can be obtained, which is not limited in the embodiments of the present application.

[0044] In this step, the image processing system can compare the first color data of the target ingredient with the second color data to determine the initial color difference corresponding to the target ingredient; the initial color difference of other target ingredients in the first image is also determined after comparing the first color data under the high temperature environment and the second color data under the low temperature environment.

[0045] Furthermore, when comparing the first color data with the second color data of at least one target ingredient in the second temperature environment to determine the initial color difference corresponding to each target ingredient, the image processing system can determine, for at least one target ingredient, a first initial color difference of a first color channel corresponding to the target ingredient, a second initial color difference of a second color channel corresponding to the target ingredient, and a third initial color difference of a third color channel corresponding to the target ingredient based on the first color data and the second color data of the target ingredient; and determine the initial color difference corresponding to the target ingredient based on the first initial color difference, the second initial color difference, and the third initial color difference.

[0046] Exemplarily, the second color data of the target food may be color data of any target food in a low-temperature environment, for example, it may be data corresponding to RGB of sweet potatoes in a low-temperature environment, which is not limited in the embodiments of the present application.

[0047] In this step, the first initial color difference of the first color channel corresponding to the target ingredient can be an initial color difference determined on the R channel of any target ingredient. For example, the initial color difference on the R channel can be a value such as 5 or 10, which is not limited in the embodiments of the present application.

[0048] In this step, the second initial color difference of the second color channel corresponding to the target ingredient can be an initial color difference determined by any target ingredient on the G channel. For example, the initial color difference on the G channel can be a value such as 5 or 10, which is not limited in the embodiments of the present application.

[0049] In this step, the third initial color difference of the third color channel corresponding to the target ingredient can be an initial color difference determined by any target ingredient on the B channel. For example, the initial color difference on the B channel can be a value such as 5 or 10, which is not limited in the embodiments of the present application.

[0050] In this step, the initial color difference value corresponding to the target food may be determined by subtracting the first color data from the second color data.

[0051] Furthermore, when comparing the first color data with the second color data of at least one target ingredient in the second temperature environment to determine the initial color difference corresponding to each target ingredient, the image processing system can mark each target ingredient in the first image according to the first color data to determine the marked area corresponding to the target ingredient; downsample the marked area to determine the color area of ​​the target ingredient; compare the color information corresponding to the color area with the second color data of at least one target ingredient in the second temperature environment to determine the initial color difference corresponding to the target ingredient.

[0052] Exemplarily, in this step, the color data of the first target food material may be the color data of tomatoes extracted, or the color data of potatoes, etc., which is not limited in the embodiments of the present application.

[0053] Exemplarily, in this step, the marking process may be a process of adding markings to the color data of tomatoes, or a process of adding markings to the color data of broccoli, etc., which is not limited in the embodiments of the present application.

[0054] In this step, the marked area may be an area obtained after marking the color data, and the area may be irregular, which is not limited in the embodiments of the present application.

[0055] Exemplarily, in this step, downsampling, also known as subsampling or downsampling, is a multi-rate digital signal processing technique in the field of digital signal processing, or refers to a process used to reduce the sampling rate of a signal.

[0056] In this step, the color region of the first target ingredient may be the color region of tomatoes, or the color region of any other target ingredient, which is not limited in the embodiments of the present application.

[0057] In this step, during the image processing process, each target ingredient in the first image can be marked separately according to the first color data to determine the marked area corresponding to the target ingredient; the marked area is downsampled to determine the color area of ​​the target ingredient; the color information corresponding to the color area is compared with the second color data of at least one target ingredient in the second temperature environment to determine the initial color difference corresponding to the target ingredient.

[0058] In this step, in the process of determining the initial color difference corresponding to the target food, it can be obtained after comparing the first color data and the second color data of the target food.

[0059] Step 104: Determine a target color difference value according to an initial color difference value of at least one target ingredient and a coefficient corresponding to each target ingredient.

[0060] The image processing method provided in the embodiment of the present application compares the first color data with the second color data of at least one target food in the second temperature environment to determine the initial color difference corresponding to each target food. The image processing system can also determine the target color difference based on the initial color difference of at least one target food and the coefficient corresponding to each target food.

[0061] In this step, the coefficient corresponding to each target ingredient may be a weight coefficient corresponding to the RGB parameters of the target ingredient. For example, the weight coefficient of the R channel of tomatoes is higher than the weight coefficients of the G channel and the B channel.

[0062] For example, in the embodiments of the present application, the weight coefficient of the R channel of the tomato may be 0.8, the weight coefficient of the G channel may be 0.1, the weight coefficient of the B channel may be 0.1, and so on, which are not limited in the embodiments of the present application.

[0063] In this step, the target color difference may be determined based on an initial color difference of at least one target ingredient and a coefficient corresponding to each target ingredient.

[0064] Exemplarily, in this step, the target color difference corresponding to the R channel is determined based on the initial color difference value of at least one target ingredient in the R channel and the coefficient corresponding to each target ingredient, which is not limited in the embodiments of the present application.

[0065] In this step, the image processing system may determine the target color difference value corresponding to the target ingredient according to the initial color difference value of at least one target ingredient and the coefficient corresponding to each target ingredient.

[0066] Furthermore, when determining the target color difference based on the initial color difference of at least one target ingredient and the coefficient corresponding to each target ingredient, the image processing system can obtain first color deviation data corresponding to the first target ingredient within a preset time range based on the first color data and the second color data of the first target ingredient; wherein the first target ingredient is an ingredient whose color belongs to the first color channel among the at least one target ingredient; at least one second color deviation data corresponding to the first color channel is determined based on the color data of at least one second target ingredient in the first temperature environment and the color data in the second temperature environment corresponding to the first color channel; the second target ingredient is other ingredients whose color belongs to the first color channel among the at least one target ingredient except the first target ingredient; the color offset corresponding to the first color channel is determined based on the first color deviation data and the at least one second color deviation data; the initial color difference is corrected based on the color offset to obtain the target color difference.

[0067] In this step, the first color deviation data corresponding to the first target food within the preset time range can be obtained by the difference in the change rate of the color data of the R channel under the high temperature environment and the low temperature environment, or the difference in the change rate of the color data of the G channel under the high temperature environment and the low temperature environment, or the difference in the change rate of the color data of the B channel under the high temperature environment and the low temperature environment, which is not limited in the embodiments of the present application.

[0068] In this step, the at least one target ingredient whose color belongs to the first color channel may be an ingredient belonging to any channel in RGB, for example, tomatoes and red peppers both belong to the R channel, which is not limited in the embodiments of the present application.

[0069] In this step, when the first color channel is the G channel, the color data of the second target food in the first temperature environment may be the color data of the cucumber in the high temperature environment.

[0070] In this step, the color data in the second temperature environment may be color data in a low temperature environment, for example, obtaining color data of potatoes in a low temperature environment, etc., which is not limited in the embodiments of the present application.

[0071] For example, in the present application, when the first color shift data is the color shift data under the red channel, at least one second color shift data corresponding to the first color channel may include the color shift data of sweet potato, or the color shift data of red radish, etc., which is not limited in the embodiments of the present application.

[0072] It should be noted that the second target ingredient may be an ingredient belonging to the same color channel, for example, an ingredient belonging to a red channel, or an ingredient belonging to a green channel, or an ingredient belonging to a blue channel, which is not limited in the embodiments of the present application.

[0073] Exemplarily, when the first color channel is a red channel, other ingredients of the first color channel may include: tomatoes, beets, etc., which are not limited in the embodiments of the present application.

[0074] In this step, the color offset corresponding to the first color channel can be the sum of the color offsets of all ingredients in the red channel, or the sum of the color offsets of all ingredients in the green channel, or the sum of the color offsets of all ingredients in the blue channel, which is not limited in the embodiments of the present application.

[0075] In this step, the process of determining the target color difference value may include a process of correcting the initial color difference value based on the color shift.

[0076] In this step, the image processing system can correct the initial color difference according to the color shift corresponding to the RGB channels, and then obtain the target color difference.

[0077] Furthermore, when determining the target color difference based on the initial color difference of at least one target ingredient and the coefficient corresponding to each target ingredient, the image processing system can also perform multiplication processing based on the initial color difference of the target ingredient and the coefficient corresponding to the target ingredient to determine the first color difference corresponding to the target ingredient; determine the corrected first color difference based on the first color difference and color shift; and normalize the corrected first color difference corresponding to the target ingredient to obtain the target color difference corresponding to the target ingredient.

[0078] Among them, the first color difference corresponding to the target ingredient can be obtained by multiplying the initial color difference of the target ingredient and the coefficient corresponding to the target ingredient. For example: when the initial color difference under the R channel is 25, the weight coefficient of tomato in the R channel is 0.7, then the first color difference corresponding to the target ingredient can be obtained as 17.5, which is not limited in the embodiments of the present application.

[0079] It should be noted that the corrected first color difference may be determined based on the first color difference and the color offset. For example, the corrected first color difference corresponding to the R channel may be obtained after calibrating the first color difference based on the color offset.

[0080] Exemplarily, the normalization processing can be that when the target ingredient is tomato, the weight of its red channel is 0.8, while the weights of the blue channel and the green channel are less. At this time, the corrected first color difference corresponding to the tomato can be normalized to obtain the target color difference corresponding to the tomato.

[0081] In this step, in the process of determining the target color difference based on the initial color difference of at least one target ingredient and the coefficient corresponding to each target ingredient, the image processing system can determine the first color difference corresponding to the target ingredient by multiplying the initial color difference of the target ingredient and the coefficient corresponding to the target ingredient; determine the corrected first color difference based on the first color difference and color shift; and normalize the corrected first color difference corresponding to the target ingredient to obtain the target color difference corresponding to the target ingredient.

[0082] Step 105: Perform color correction on the first image based on the target color difference to obtain a target image.

[0083] The image processing method provided in the embodiment of the present application can, after determining the target color difference according to the initial color difference of at least one target ingredient and the coefficient corresponding to each target ingredient, perform color correction on the first image based on the target color difference to obtain the target image.

[0084] In this step, the color correction process may be a process of processing the first image according to the color difference.

[0085] In this step, the target image may be an image obtained after noise reduction and color correction are performed on the first image in a high temperature environment.

[0086] Furthermore, the image processing system can also extract a background area from the first image; perform a limited mean filtering process on the background area to obtain a denoised background area; and perform image fusion on the background area and the target image to obtain a corrected first image.

[0087] Among them, the background area can be an image area where the target ingredients do not exist. For example, the first image is a picture of tomatoes and eggs being stir-fried in a pan. Excluding the image area of ​​ingredients such as tomatoes and eggs, the remaining area in the first image is the background area.

[0088] Exemplarily, the background area is subjected to amplitude limiting mean filtering to obtain a background area after noise reduction.

[0089] In this step, the denoised background area replaces the original background area in the first image and is fused with the target image to obtain a corrected first image, that is, the corrected first image is obtained after denoising and color correction of the first image under high temperature environment.

[0090] In summary, in the process of image processing, the image processing system can first obtain a first image of the inside of the cooking device at a first ambient temperature; the first image includes at least one target ingredient; determine the first color data corresponding to the first image; compare the first color data with the second color data of at least one target ingredient in the second temperature environment to determine the initial color difference corresponding to each target ingredient; determine the target color difference based on the initial color difference of at least one target ingredient and the coefficient corresponding to each target ingredient; perform color correction on the first image based on the target color difference to obtain a target image. In the process of image processing, the color difference between the first color data corresponding to the target ingredient at the first ambient temperature and the second color data corresponding to the target ingredient at the second ambient temperature can be used as the initial color difference, and the initial color difference can be adjusted to obtain the target color difference to achieve noise reduction processing on the first image. Furthermore, it is also necessary to perform color correction on the first image based on the target color difference to obtain the target image, achieve color correction processing on the first image, optimize the quality of the recorded cooking video, and thereby improve the efficiency of image processing.

[0091] Reference Figure 2 , showing the steps of an image processing method provided by an embodiment of the present application Figure 2 ,like Figure 2 As shown, the method specifically includes steps 201 to 214:

[0092] Step 201: Acquire a first image of the interior of a cooking device at a first ambient temperature; the first image includes at least one target food.

[0093] In an embodiment of the present application, during the image processing process, the image processing system may first acquire a first image under a first temperature environment; the first image includes a plurality of target ingredients.

[0094] Step 202: Determine first color data corresponding to the first image.

[0095] The image processing method provided in the embodiment of the present application obtains a first image of the interior of a cooking device at a first ambient temperature; after the first image includes at least one target ingredient, the image processing system can determine first color data corresponding to the first image.

[0096] In this step, during the image processing, the image processing system may first determine the first color data in a high temperature environment based on the cooking video.

[0097] Step 203: For at least one target ingredient, determine, based on the first color data and the second color data of the target ingredient, a first initial color difference value of a first color channel corresponding to the target ingredient, a second initial color difference value of a second color channel corresponding to the target ingredient, and a third initial color difference value of a third color channel corresponding to the target ingredient.

[0098] The image processing method provided in the embodiment of the present application can, after determining the first color data corresponding to the first image, determine, for at least one target ingredient, a first initial color difference value of the first color channel corresponding to the target ingredient, a second initial color difference value of the second color channel corresponding to the target ingredient, and a third initial color difference value of the third color channel corresponding to the target ingredient based on the first color data and the second color data of the target ingredient.

[0099] In this step, the initial color difference value corresponding to the target food may be determined by subtracting the first color data from the second color data.

[0100] In this step, in the process of determining the initial color difference corresponding to the target food, it can be obtained after comparing the first color data and the second color data of the target food.

[0101] Exemplarily, the initial color difference values ​​corresponding to the RGB channels may be determined respectively.

[0102] Step 204: Determine the initial color difference corresponding to the target food based on the first initial color difference, the second initial color difference, and the third initial color difference.

[0103] The image processing method provided in the embodiment of the present application, after determining, for at least one target food, a first initial color difference value of a first color channel corresponding to the target food, a second initial color difference value of a second color channel corresponding to the target food, and a third initial color difference value of a third color channel corresponding to the target food based on first color data and second color data of the target food, the image processing system can determine the initial color difference value corresponding to the target food based on the first initial color difference value, the second initial color difference value, and the third initial color difference value.

[0104] Exemplarily, the image processing system may determine an initial color difference value corresponding to the target food based on the first initial color difference value, the second initial color difference value, and the third initial color difference value.

[0105] Step 205: Obtain first color deviation data corresponding to the first target ingredient within a preset time range according to the first color data and the second color data of the first target ingredient; wherein the first target ingredient is an ingredient whose color belongs to the first color channel among at least one target ingredient.

[0106] The image processing method provided in the embodiment of the present application, after determining the initial color difference corresponding to the target ingredient based on the first initial color difference, the second initial color difference, and the third initial color difference, the image processing system can obtain the first color deviation data corresponding to the first target ingredient within a preset time range according to the first color data and the second color data of the first target ingredient; wherein the first target ingredient is an ingredient whose color belongs to the first color channel among at least one target ingredient.

[0107] In this step, the first color deviation data corresponding to the first target food within the preset time range can be obtained by the difference in the change rate of the color data of the R channel under the high temperature environment and the low temperature environment, or the difference in the change rate of the color data of the G channel under the high temperature environment and the low temperature environment, or the difference in the change rate of the color data of the B channel under the high temperature environment and the low temperature environment, which is not limited in the embodiments of the present application.

[0108] Step 206: Determine at least one second color cast data corresponding to the first color channel based on the color data of at least one second target ingredient corresponding to the first color channel in the first temperature environment and the color data in the second temperature environment; the second target ingredient is other ingredients of the at least one target ingredient whose color belongs to the first color channel except the first target ingredient.

[0109] The image processing method provided in the embodiment of the present application obtains first color deviation data corresponding to the first target ingredient within a preset time range based on the first color data and the second color data of the first target ingredient; wherein, after the first target ingredient is an ingredient whose color belongs to the first color channel among at least one target ingredient, the image processing system can determine at least one second color deviation data corresponding to the first color channel based on the color data of at least one second target ingredient corresponding to the first color channel in the first temperature environment and the color data in the second temperature environment.

[0110] For example, in the present application, when the first color shift data is the color shift data under the red channel, at least one second color shift data corresponding to the first color channel may include the color shift data of sweet potato, or the color shift data of red radish, etc., which is not limited in the embodiments of the present application.

[0111] Step 207: Determine a color shift corresponding to the first color channel according to the first color shift data and at least one second color shift data.

[0112] The image processing method provided in the embodiment of the present application, after determining at least one second color deviation data corresponding to the first color channel based on the color data of at least one second target food material corresponding to the first color channel in the first temperature environment and the color data in the second temperature environment, the image processing system can determine the color deviation corresponding to the first color channel based on the first color deviation data and the at least one second color deviation data.

[0113] In this step, the color offset corresponding to the first color channel can be the sum of the color offsets of all ingredients in the red channel, or the sum of the color offsets of all ingredients in the green channel, or the sum of the color offsets of all ingredients in the blue channel, which is not limited in the embodiments of the present application.

[0114] Step 208: Determine a first color difference corresponding to the target ingredient by performing a multiplication process based on the initial color difference of the target ingredient and the coefficient corresponding to the target ingredient.

[0115] The image processing method provided in the embodiment of the present application, after determining the color offset corresponding to the first color channel according to the first color deviation data and at least one second color deviation data, the image processing system can determine the first color difference corresponding to the target ingredient by multiplying the initial color difference of the target ingredient and the coefficient corresponding to the target ingredient.

[0116] Among them, the first color difference corresponding to the target ingredient can be obtained by multiplying the initial color difference of the target ingredient and the coefficient corresponding to the target ingredient. For example: when the initial color difference under the R channel is 25, the weight coefficient of tomato in the R channel is 0.7, then the first color difference corresponding to the target ingredient can be obtained as 17.5, which is not limited in the embodiments of the present application.

[0117] Step 209: Determine a corrected first color difference based on the first color difference and the color shift.

[0118] The image processing method provided in the embodiment of the present application, after performing multiplication processing based on the initial color difference of the target ingredient and the coefficient corresponding to the target ingredient to determine the first color difference corresponding to the target ingredient, the image processing system can determine the corrected first color difference based on the first color difference and color shift.

[0119] It should be noted that the corrected first color difference may be determined based on the first color difference and the color offset. For example, the corrected first color difference corresponding to the R channel may be obtained after calibrating the first color difference based on the color offset.

[0120] Step 210: normalize the corrected first color difference value corresponding to the target food to obtain a target color difference value corresponding to the target food.

[0121] In the image processing method provided in the embodiment of the present application, after determining the corrected first color difference based on the first color difference and the color shift, the image processing system can normalize the corrected first color difference corresponding to the target ingredient to obtain the target color difference corresponding to the target ingredient.

[0122] In this step, in the process of determining the target color difference based on the initial color difference of at least one target ingredient and the coefficient corresponding to each target ingredient, the image processing system can determine the first color difference corresponding to the target ingredient by multiplying the initial color difference of the target ingredient and the coefficient corresponding to the target ingredient; determine the corrected first color difference based on the first color difference and color shift; and normalize the corrected first color difference corresponding to the target ingredient to obtain the target color difference corresponding to the target ingredient.

[0123] Step 211: Perform color correction on the first image based on the target color difference to obtain a target image.

[0124] The image processing method provided in the embodiment of the present application, after normalizing the corrected first color difference corresponding to the target food to obtain the target color difference corresponding to the target food, the image processing system can perform color correction on the first image based on the target color difference to obtain the target image.

[0125] In this step, the color correction process may be a process of processing the first image according to the color difference.

[0126] In this step, the target image may be an image obtained after noise reduction and color correction are performed on the first image in a high temperature environment.

[0127] Step 212: extract the background area from the first image.

[0128] In the image processing method provided in the embodiment of the present application, after color correction is performed on the first image based on the target color difference to obtain the target image, the image processing system can extract the background area from the first image.

[0129] Among them, the background area can be an image area where the target ingredients do not exist. For example, the first image is a picture of tomatoes and eggs being stir-fried in a pan. Excluding the image area of ​​ingredients such as tomatoes and eggs, the remaining area in the first image is the background area.

[0130] Step 213: Perform amplitude limiting mean filtering on the background area to obtain a background area after noise reduction.

[0131] In the image processing method provided in the embodiment of the present application, after extracting the background area from the first image, the image processing system can perform a limited mean filtering process on the background area to obtain a background area after noise reduction.

[0132] Exemplarily, the background area is subjected to amplitude limiting mean filtering to obtain a background area after noise reduction.

[0133] Step 214: perform image fusion on the background area and the target image to obtain a corrected first image.

[0134] In the image processing method provided in the embodiment of the present application, after performing limited mean filtering on the background area to obtain the background area after noise reduction, the image processing system can perform image fusion on the background area and the target image to obtain a corrected first image.

[0135] In this step, the denoised background area replaces the original background area in the first image and is fused with the target image to obtain a corrected first image, that is, the corrected first image is obtained after denoising and color correction of the first image under high temperature environment.

[0136] It should be noted that, in the embodiments of the present application, the execution order of steps 212 to 214 and the execution order of steps 201 to 211 are not limited.

[0137] In summary, in the process of image processing, the image processing system can first obtain a first image of the inside of the cooking device at a first ambient temperature; the first image includes at least one target ingredient; determine the first color data corresponding to the first image; compare the first color data with the second color data of at least one target ingredient in the second temperature environment to determine the initial color difference corresponding to each target ingredient; determine the target color difference based on the initial color difference of at least one target ingredient and the coefficient corresponding to each target ingredient; perform color correction on the first image based on the target color difference to obtain a target image. In the process of image processing, the color difference between the first color data corresponding to the target ingredient at the first ambient temperature and the second color data corresponding to the target ingredient at the second ambient temperature can be used as the initial color difference, and the initial color difference can be adjusted to obtain the target color difference to achieve noise reduction processing on the first image. Furthermore, it is also necessary to perform color correction on the first image based on the target color difference to obtain the target image, achieve color correction processing on the first image, optimize the quality of the recorded cooking video, and thereby improve the efficiency of image processing.

[0138] Reference Figure 3 , showing the steps of an image processing method provided by an embodiment of the present application Figure 3 ,like Figure 3 As shown, the method specifically includes steps 301 to 308:

[0139] Step 301: Record a video of the cooking process and extract temperature data during the video recording.

[0140] In the process of noise reduction and color correction of the video during the cooking process, as the cooking time increases, the ambient temperature at the camera position will gradually increase. As the ambient temperature increases, the noise in the image output by the camera will gradually increase, and the image output by the camera will also have color difference. However, for the cooking process, the changes in the image in the steam oven are relatively consistent. Therefore, the image data of the time period with higher temperature can be corrected based on the image data of the time period with lower temperature.

[0141] The image processing system can obtain the real-time temperature of the camera through the temperature sensor, and use the video data when the camera temperature is low as a benchmark, analyze multiple frames of image data based on the time domain, and reduce the noise of the image in the high-temperature working range where the camera is located. The cooking target object is identified, the type of ingredient is extracted, and the color and white balance of the current image are corrected based on the color change curve of the type of ingredient.

[0142] Step 302: Divide the recorded image into a low temperature area, a temperature rise area and a high temperature area based on the temperature data when the video is recorded.

[0143] According to the acquired temperature data, the image processing system may divide the recorded picture into different temperature areas. For example, the recorded picture may be divided into a low temperature area, a temperature rise area and a high temperature area.

[0144] Step 303: Based on the image data of the low temperature area and in combination with the change value of the image data of the temperature rising area, the image of the high temperature area is processed.

[0145] When recording the video of the cooking process of the steam oven, the temperature sensor located on the camera is read to obtain the ambient temperature of the camera, and the camera working time is divided into low temperature working time, heating working time and high temperature working time. The picture data of the low temperature working time is combined with the change of the picture data of the heating working time to correct the picture working in the high temperature working time and smooth the abnormal high brightness points of the picture in the high temperature working range.

[0146] Use professional imaging equipment to collect images of different ingredients in the steam oven, obtain the real color data of the ingredients as the benchmark color data, and create a one-to-one correspondence database of characteristic ingredients-cooking time-color.

[0147] When the ingredients are put into the steam oven, they are identified and their characteristic ingredients are extracted. Through prior experiments, the color change curve of the characteristic ingredients in different cooking processes is obtained and matched with the ingredients put in. The original color of the food can be obtained. Based on the original color of the food in the above database and the color of the current picture, the deviation value of the color channel of the picture can be obtained, and the color of the overall picture can be corrected based on the deviation value.

[0148] The above is a method for reducing the noise of the picture based on the time domain. After the picture is subjected to the noise reduction processing based on the time domain, the background area needs to be processed, that is, the area where the shooting target does not exist.

[0149] Step 304: Perform amplitude limiting mean filtering on the area where no shooting target exists and the brightness is low.

[0150] The camera image is divided into the image area where the photographed object exists and the image area where the photographed object does not exist. For the image area where the photographed object does not exist and the area with darker brightness, a second limiting mean filtering is performed to deal with the abnormal white noise in the low-brightness image area.

[0151] For example, in the process of eliminating abnormal noise in the dark background, the pictures collected by the camera in a high temperature environment will have some abnormal white noise that does not match the background, which is generally caused by thermal noise of complementary metal oxide semiconductor (CMOS).

[0152] Step 305: Generate a denoised video.

[0153] After performing the above two steps, the abnormal noise generated by working in a high temperature environment can be suppressed more effectively, thereby improving the effect of the video of the recorded cooking process.

[0154] Step 306: Identify the ingredients to be cooked when starting to cook.

[0155] When cooking starts, the image processing system can identify the type of ingredients.

[0156] Exemplarily, after extracting the features of the food, the type of the food can be determined, and then the color of the food can be marked and then the food image can be downsampled to extract the approximate distribution of the color of the food.

[0157] Exemplarily, when the food is put into the steam oven, the food is identified and characteristic food is extracted. The color change curve of the characteristic food in different cooking processes is obtained through previous experiments and matched with the food put in.

[0158] Step 307: extract the characteristic ingredients and match them with the ingredients in the database to obtain their color data and the color change curve during the cooking process.

[0159] For example, a variety of ingredients are used in cooking, such as stir-fried tomatoes and broccoli, and side dishes such as onions and garlic are also extracted. The extracted ingredients are matched with the ingredient categories in the database, and it can be found that tomatoes and broccoli have corresponding color parameters in the database. Generally, the red channel and brightness channel data are used for tomatoes, and the blue channel and green channel data are used for broccoli.

[0160] Step 308: Correct the color of the cooking video based on the color data in the database.

[0161] Exemplarily, in an embodiment of the present application, in the process of correcting the color of a cooking video based on the color data in a database, for example, a tomato may have a 2% drop in the red channel every minute during the hot air grilling process; in fact, if the actual image captured has a 3% drop in the image of the tomato, the polynomial y (red color shift) = a×1 (color shift of tomato) + b×2 (color shift of other vegetables) can be determined, and then the color difference value can be corrected according to the color deviation values ​​of the three RGB channels to obtain the target color difference.

[0162] Finally, the image processing system can perform color correction on the first image based on the target color difference to obtain the target image.

[0163] Exemplarily, the process of correcting according to the deviation value may include adjusting filters of three color channels when synthesizing image colors.

[0164] For example, the thermal noise common in CMOS sensors is generally characterized as an abnormal high-frequency signal in the time domain. Taking the value of a certain channel (red channel) of a pixel as an example, the appearance of noise is generally characterized by the value of the channel increasing to a very high value in a very short period of time, forming a peak. The purpose of noise reduction is to eliminate this peak.

[0165] Exemplarily, the acquired signal features may include the frequency domain signal of the image, because the signals generated by thermal noise are mainly high-frequency signals, as well as the color data of the camera and the grayscale gradient data of the image; the data of the color channel is collected by downsampling (which can be understood as the image being reduced to a 64*64 color block group), which is not limited in the embodiments of the present application.

[0166] Specifically, when the temperature of the camera is in a higher temperature range for a long time, the time window of the general time domain noise reduction algorithm is very short, and the effect of noise reduction processing in a high temperature environment is poor (because the signal already contains more high-frequency components at this time). At this time, it is necessary to use the signal features obtained in the low temperature environment to optimize the processing algorithm in the high temperature environment.

[0167] For example, the assumption is that the CMOS color shift of the image is consistent across the entire frame.

[0168] Known: the type of food in the image, and the color (original color) of the food of the corresponding type.

[0169] Obtain the color data of the target ingredient, compare the color data of the target ingredient with the data in the database, and obtain the difference of the image data. Multiply the difference by the coefficient of the ingredient and perform normalization. A cooking session may use multiple ingredients, and the above process is performed once for each ingredient.

[0170] Output: The color deviation value of the CMOS, and the filter of the composite image is adjusted based on the deviation value.

[0171] The above is a method for reducing noise on the picture based on the time domain. The camera picture is divided into the picture area where the photographed object exists and the picture area where the photographed object does not exist. For the picture area where the photographed object does not exist and the area with darker brightness, a second limited mean filtering is performed to deal with the abnormal white noise in the low-brightness picture area.

[0172] In summary, in the process of chromatic aberration repair, there will be chromatic aberration in the imaging under high temperature environment, which can be considered as the offset of CMOS imaging channel, and this offset needs to be corrected. As for the elimination of imaging noise, it can be considered that the gradient changes of most pictures in the whole cooking process are uniform, but thermal noise will produce abnormal gradient data locally, which needs to be smoothed.

[0173] In the embodiments of the present application, the recorded video is mainly divided into different intervals based on time, and the time domain noise reduction is performed on the high temperature area based on the low temperature area. In addition, the area where there is no photographed object is filtered to achieve spatial domain noise reduction.

[0174] Device Embodiment

[0175] like Figure 4 As shown, Figure 4 A logical block diagram of an image processing device provided in an embodiment of the present application is shown, the device comprising:

[0176] A first acquisition module 1001 is used to acquire a first image of the interior of a cooking device at a first ambient temperature; the first image includes at least one target food;

[0177] The first determination module 1002 is used to determine the first color data corresponding to the first image; compare the first color data with the second color data of the at least one target food in the second temperature environment to determine the initial color difference corresponding to each target food; determine the target color difference according to the initial color difference of the at least one target food and the coefficient corresponding to each target food;

[0178] The obtaining module 1003 is used to perform color correction on the first image based on the target color difference to obtain a target image.

[0179] Optionally, the first determining module includes:

[0180] A second acquisition module is used to acquire first color deviation data corresponding to the first target ingredient within a preset time range according to the first color data and the second color data of the first target ingredient; wherein the first target ingredient is an ingredient whose color belongs to the first color channel among the at least one target ingredient;

[0181] a second determination module, configured to determine at least one second color shift data corresponding to the first color channel according to color data of at least one second target food corresponding to the first color channel in the first temperature environment and color data in the second temperature environment; the second target food is other food of the at least one target food whose color belongs to the first color channel except the first target food; and determine the color shift corresponding to the first color channel according to the first color shift data and the at least one second color shift data;

[0182] The obtaining module is used to correct the initial color difference value based on the color shift to obtain a target color difference value.

[0183] Optionally, the determining module further includes:

[0184] A determination submodule is used to determine, for at least one target ingredient, a first initial color difference value of a first color channel corresponding to the target ingredient, a second initial color difference value of a second color channel corresponding to the target ingredient, and a third initial color difference value of a third color channel corresponding to the target ingredient based on the first color data and the second color data of the target ingredient; and determine the initial color difference value corresponding to the target ingredient based on the first initial color difference value, the second initial color difference value, and the third initial color difference value.

[0185] Optionally, the device further comprises:

[0186] The third determination module is used to mark the color data of the first target food in the first image to determine the marked area; downsample based on the marked area to determine the color area of ​​the first target food; and determine the target color difference based on the color area and the color shift.

[0187] Optionally, the first determining module further includes:

[0188] A first determination submodule, configured to determine a first color difference corresponding to the target ingredient by performing a product process based on an initial color difference of the target ingredient and a coefficient corresponding to the target ingredient; and determine a corrected first color difference based on the first color difference and the color shift;

[0189] The obtaining submodule is used to normalize the corrected first color difference value corresponding to the target food to obtain the target color difference value corresponding to the target food.

[0190] Optionally, the device further comprises:

[0191] An extraction submodule, used for extracting a background area from the first image;

[0192] The first obtaining submodule is used to perform a limited mean filtering process on the background area to obtain a denoised background area; and perform image fusion on the denoised background area and the target image to obtain a corrected first image.

[0193] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0194] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0195] The image processing device in the embodiment of the present application can be an electronic device, or a component in the electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or it can be other devices other than a terminal. Exemplarily, the electronic device can be a GPU BOX, a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted electronic device, a mobile Internet device (Mobile Internet Device, MID), an augmented reality (augmented reality, AR) / virtual reality (virtual reality, VR) device, a robot, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant, PDA), etc., and can also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a television (television, TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0196] The image processing device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, a Linux operating system, a Windows operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0197] The image processing device provided in the embodiment of the present application can achieve Figure 1 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0198] Alternatively, if Figure 5 As shown, an embodiment of the present application further provides an electronic device 1100, including a processor 1101 and a memory 1102, wherein the memory 1102 stores programs or instructions that can be executed on the processor 1101, and when the program or instructions are executed by the processor 1101, the various steps of the above-mentioned image processing method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, they are not described here.

[0199] In an embodiment of the present application, the memory 1102 may be used to store software programs and various data. The memory 1102 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 1102 may include a volatile memory or a non-volatile memory, or the memory 1102 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 1102 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0200] The processor 1101 may include one or more processing units; optionally, the processor 1101 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 1101.

[0201] An embodiment of the present application also provides an image processing system, which includes a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; the memory is used to store executable instructions, and the executable instructions enable the processor to execute the various processes of the above-mentioned image processing method embodiment, and can achieve the same technical effect. To avoid repetition, they are not repeated here.

[0202] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned image processing method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0203] The processor is the processor in the image processing system described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0204] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned image processing method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0205] It should be understood that the chip involved in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0206] An embodiment of the present application provides a computer program product, which is stored in a storage medium. The program product is executed by at least one processor to implement the various processes of the above-mentioned image processing method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0207] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0208] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the relevant technology, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0209] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. An image processing method, characterized in that: Applied to an image processing system, the method comprises: Acquire a first image of the interior of the cooking device at a first ambient temperature; the first image includes at least one target food; Determining first color data corresponding to the first image; Comparing the first color data with the second color data of the at least one target food in the second temperature environment to determine an initial color difference corresponding to each target food; Determining a target color difference value according to an initial color difference value of at least one target ingredient and a coefficient corresponding to each target ingredient; Color correction is performed on the first image based on the target color difference to obtain a target image.

2. The method according to claim 1, characterized in that The step of determining a target color difference value according to an initial color difference value of at least one target food and a coefficient corresponding to each target food includes: Acquire first color deviation data corresponding to the first target ingredient within a preset time range according to the first color data and the second color data of the first target ingredient; wherein the first target ingredient is an ingredient whose color belongs to the first color channel among the at least one target ingredient; Determine at least one second color cast data corresponding to the first color channel according to the color data of at least one second target food corresponding to the first color channel in the first temperature environment and the color data in the second temperature environment; the second target food is other food of the at least one target food whose color belongs to the first color channel except the first target food; Determine a color shift corresponding to the first color channel according to the first color shift data and the at least one second color shift data; The initial color difference is corrected based on the color shift to obtain a target color difference.

3. The method according to claim 1, characterized in that The comparing the first color data with the second color data of the at least one target food in the second temperature environment to determine the initial color difference corresponding to each target food includes: For at least one target food, determining, according to the first color data and the second color data of the target food, a first initial color difference value of a first color channel corresponding to the target food, a second initial color difference value of a second color channel corresponding to the target food, and a third initial color difference value of a third color channel corresponding to the target food; Based on the first initial color difference value, the second initial color difference value, and the third initial color difference value, an initial color difference value corresponding to the target food is determined.

4. The method according to claim 2, characterized in that: The step of determining a target color difference value according to an initial color difference value of at least one target food and a coefficient corresponding to each target food includes: Determine a first color difference value corresponding to the target ingredient by performing a multiplication process based on an initial color difference value of the target ingredient and a coefficient corresponding to the target ingredient; determining a corrected first color difference based on the first color difference and the color shift; The corrected first color difference value corresponding to the target food is normalized to obtain a target color difference value corresponding to the target food.

5. The method according to claim 1, characterized in that The comparing the first color data with the second color data of the at least one target food in the second temperature environment to determine the initial color difference corresponding to each target food includes: Marking each target food in the first image according to the first color data, and determining a marked area corresponding to the target food; Downsampling the marked area to determine the color area of ​​the target food; The color information corresponding to the color area is compared with the second color data of the at least one target food in the second temperature environment to determine the initial color difference corresponding to the target food.

6. The method according to claim 1, characterized in that The method further comprises: extracting a background area from the first image; Performing a limited mean filtering process on the background area to obtain a background area after noise reduction; The denoised background area and the target image are fused to obtain a corrected first image.

7. An image processing device, characterized in that: The device comprises: A first acquisition module is used to acquire a first image of the interior of the cooking device at a first ambient temperature; the first image includes at least one target food; a first determination module, configured to determine first color data corresponding to the first image; compare the first color data with second color data of the at least one target food in a second temperature environment to determine an initial color difference corresponding to each target food; and determine a target color difference according to the initial color difference of the at least one target food and a coefficient corresponding to each target food; The obtaining module is used to perform color correction on the first image based on the target color difference to obtain a target image.

8. An image processing device, characterized in that: The device also includes: A second acquisition module is used to acquire first color deviation data corresponding to the first target ingredient within a preset time range according to the first color data and the second color data of the first target ingredient; wherein the first target ingredient is an ingredient whose color belongs to the first color channel among the at least one target ingredient; a second determination module, configured to determine at least one second color shift data corresponding to the first color channel according to color data of at least one second target food corresponding to the first color channel in the first temperature environment and color data in the second temperature environment; the second target food is other food of the at least one target food whose color belongs to the first color channel except the first target food; and determine the color shift corresponding to the first color channel according to the first color shift data and the at least one second color shift data; The obtaining module is used to correct the initial color difference value based on the color shift to obtain a target color difference value.

9. An image processing system, characterized in that: The image processing system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store executable instructions, and the executable instructions enable the processor to execute the image processing method according to any one of claims 1 to 6.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or an instruction, and when the program or the instruction is executed by a processor, the image processing method according to any one of claims 1 to 6 is implemented.

Images