OPERATING A HOUSEHOLD GARDEN APPLIANCE WITH AT LEAST ONE CAMERA

Description

[0001] The invention relates to a method for operating a household cooking appliance having a cooking chamber and at least one camera configured to capture pixel-based images from the cooking chamber, in which method at least one image from the cooking chamber is captured by the at least one camera, and the image is evaluated. The invention also relates to a household cooking appliance having a cooking chamber and at least one camera for capturing pixel-based images, wherein the household cooking appliance is configured to carry out the method. The invention is particularly advantageously applicable to ovens, microwave ovens, steam treatment appliances, or any combination thereof.

[0002] DE 10 2016 215 550 A1 discloses a method for determining the degree of browning of food in a cooking chamber of a household cooking appliance. The household cooking appliance comprises a camera directed into the cooking chamber and a light source for illuminating the cooking chamber. A reference image is recorded by means of the camera, a first measurement image is recorded at a first brightness of the light source, a second measurement image is recorded at a second brightness of the light source, a difference image is generated from the first measurement image and the second measurement image, and the difference image is compared with the reference image. A household cooking appliance comprises a camera directed into a cooking chamber, a light source for illuminating the cooking chamber, and a control device coupled to the camera and the light source. The household cooking appliance is configured to carry out the method.

[0003] DE 10 2005 014 713 A1 discloses a sensor device with a data processing unit for determining the degree of browning of a food item arranged in a cooking chamber and with at least one sensor for detecting a radiation intensity reflected by the food item. In order to provide a sensor device for cooking appliances by means of which the degree of browning of a food item can be determined safely, reliably, and in particular independently of the size and shape of the food item, it is proposed that the data processing unit be provided for determining a relevance parameter for a characteristic of the detected radiation intensity depending on the temporal profile of the detected radiation intensity.

[0004] WO 2014 / 053002 A2 provides a device for characterizing a chromatic property of food. The device comprises a light source arranged to emit light having at least two wavelengths or wavelength ranges. The light source is further arranged to direct the light onto a surface of at least the food. The device also comprises a detector positioned to detect at least a portion of the reflected light and arranged to generate an output indicative of an intensity of the detected reflected light. The device is arranged to generate corresponding indications for the at least two wavelengths or wavelength ranges.A relationship between the information for one of the at least two wavelengths or wavelength ranges and the information for the other or another of the at least two wavelengths or wavelength ranges indicates the chromatic property of the surface of the food.

[0005] DE 10 2017 206 056 A1 discloses a method for operating a cooking appliance, in which a cooking chamber is irradiated with light of different wavelength ranges and light originating from the cooking chamber is measured, wherein measurement results are spectroscopically evaluated and operation of the cooking appliance is modified depending on a result of the spectroscopic evaluation. A cooking appliance is configured to carry out the method and comprises: a cooking chamber, at least one light source for emitting light into the cooking chamber, and at least one light sensor for measuring light reflected in the cooking chamber, wherein the cooking appliance further comprises: an evaluation device for spectroscopically evaluating the measurement results determined by the at least one light sensor, and a control device for controlling a cooking process depending on a result of the evaluation.

[0006] EP 0 682 243 A1 discloses a device and a method for measuring the degree of browning of a product to be cooked, in particular a baked product, with at least one radiation source which generates a measuring radiation and a reference radiation of different wavelength ranges, the reflection and backscattering of which are influenced differently by the degree of browning of the product to be cooked, both of which are radiated onto the product to be cooked via an optics, with a measuring sensor for detecting the radiation emitted by the product to be cooked, with a reference sensor for detecting the intensities of the measuring radiation and the reference radiation, and with a device for determining the degree of browning from the intensity of the measuring radiation detected by the measuring sensor, from the intensity of the reference radiation detected by the measuring sensor, from the intensity of the measuring radiation detected by the reference sensor and from the intensity of the reference radiation detected by the reference sensor.

[0007] JP 61265429 A discloses a method in which a surface of a food to be heated is irradiated with two types of light, each with a different wavelength, and the reflected light is detected by a photometer. The food is heated by a heater and irradiated with light sources with different emission wavelengths, in order to detect the rays reflected from the food using the photometer with sensitivities for these two emission wavelengths. The emission intensity of the first light source has its maximum at a wavelength of 300 W, 600 nm, while the emission intensity of the second light source has its maximum at a wavelength of 700 W, 1200 nm. The surface condition of the food can be determined from the light rays.Accordingly, cooking that shows a good final state at all times can be achieved by presetting the detection level of reflected rays suitable for a cooking menu.

[0008] It is the Task The present invention aims to at least partially overcome the disadvantages of the prior art and, in particular, to provide an improved possibility for operating a household cooking appliance based on an image evaluation of a cooking chamber content.

[0009] This object is achieved according to the features of the independent claims. Advantageous embodiments are the subject of the dependent claims, the description, and the drawings.

[0010] The object is achieved by a method for operating a household cooking appliance with a cooking chamber and at least one camera which is set up to record pixel-based images from the cooking chamber, in which (a) at least one image from the cooking chamber is recorded by means of the at least one camera and (b) the image is evaluated excluding the brightness values ​​of its associated pixels.

[0011] This method offers the advantage that image data recorded from the cooking chamber can be evaluated largely independently of a brightness distribution in the cooking chamber generated, for example, by cooking chamber lighting and / or ambient light. In other words, the method solves the problem of the typically inhomogeneous brightness distribution in the cooking chamber for image evaluation. In particular, the evaluation is advantageously independent of the shelf level and food height. It also achieves the advantage of greater robustness against light source-induced changes in brightness, which arise, for example, due to operating temperature, age of the light source and / or changing light incidence through a cooking chamber door.The method is also advantageously largely independent of structural changes to the lighting arrangement, such as the number and / or arrangement of light sources for illuminating the cooking chamber. Furthermore, it has the advantage that image analysis can be carried out more simply and quickly, particularly by reducing the amount of data to be evaluated.

[0012] The household cooking appliance can, in particular, be an oven, a microwave oven, a steam treatment appliance, or any combination thereof, e.g., an oven with additional microwave and / or steam treatment functions. The cooking chamber can also be referred to as a muffle or oven. The household cooking appliance can have one or more cooking chambers, e.g., in the form of a double-decker oven with two cooking chambers arranged one above the other.

[0013] A further development is that the cooking chamber has several shelf levels for positioning food supports such as wire racks, baking trays, etc. The cooking chamber typically has a loading opening located at the front, which can be closed by means of a cooking chamber door.

[0014] The at least one camera captures pixel-based images, with each pixel being assigned multiple color space coordinates or their associated values. This can also be expressed as an image having multiple color space channels (hereinafter also referred to simply as "channels"), which indicate the possible color space coordinates.

[0015] It's a further development that the camera is a color camera. The pixels of a captured color image are assigned multiple colors or color space channels, e.g., red, green, and blue in the case of an RGB image.

[0016] A further development is that the camera is a black-and-white camera that captures a series of multiple (single-channel) images at the shortest possible intervals. Different light colors are used to illuminate each image, e.g., red, green, and blue. The individual (single-channel) images in the series can be concatenated and then viewed as a single color image.

[0017] If there is food in the cooking chamber, the at least one captured image typically shows the food (e.g., one or more dishes arranged in a distributed manner) and often also areas of the cooking chamber, such as a cooking chamber wall. For evaluation purposes, the image area that does not show any food can be disregarded in a further development. For this purpose, object recognition can be performed on the food, for example. The identification of image areas that contain food and image areas that do not show any food but, for example, a cooking chamber wall, is generally known and will therefore not be discussed in more detail here.

[0018] In a further development, the at least one cooking chamber camera is arranged in an upper half of the cooking chamber in order to be able to record the food being cooked particularly over its entire surface. In particular, the at least one cooking chamber camera can be arranged in the area of ​​a ceiling, a left side wall, a right side wall, a rear wall, and / or the cooking chamber door. For example, one cooking chamber camera can be arranged in the area of ​​the ceiling of the cooking chamber and another cooking chamber camera can be arranged in the upper third or quarter of the left side wall or the right side wall.

[0019] In a further development, the household cooking appliance has at least one lighting device, e.g., comprising one or more light sources, in particular spotlights, for illuminating the cooking chamber. The light sources can, in principle, be arranged anywhere in relation to the cooking chamber, e.g., in a ceiling, in an upper half of the side walls of the cooking chamber (left side wall, right side wall, rear wall), in the cooking chamber door, etc. In particular, at least one light source can be arranged near a camera.

[0020] The image analysis, e.g. to determine the browning of one or more dishes, can then be carried out by excluding the brightness values ​​of the pixels of at least one recorded image.

[0021] It is a further development that the brightness values ​​are not taken into account for the evaluation and are thus excluded, but are still present in the image data of the evaluated image. This can be advantageous, for example, if the image is also intended to be displayed to a user on a screen.

[0022] Based on the evaluation or based on the result of the evaluation, the household cooking appliance can trigger at least one action, e.g. adapt a cooking process (e.g. a cooking chamber temperature) to a detected degree of cooking, determine and, if necessary, display a remaining cooking time, cancel the cooking process, issue a message to a user and / or switch to another cooking phase (e.g. a keep-warm phase), etc.

[0023] One embodiment is that in step (b), the substeps (b1) of generating an image from the captured image (hereinafter referred to without loss of generality as a "brightness-normalized" image) in which the brightness values ​​of the corresponding pixels have been separated, and (b2) of evaluating the brightness-normalized image are performed. The brightness-normalized image therefore no longer contains any brightness information. This has the advantage of significantly reducing the amount of data and thus also the computing power required for evaluation.

[0024] In one embodiment, in step (b1), the brightness-normalized image is generated from an image whose pixels each have multiple color space coordinates, including a brightness coordinate, by separating the brightness coordinate. This enables particularly simple separation or exclusion of the brightness values ​​by simply eliminating the brightness coordinate(s). In other words, the channel representing the brightness coordinate ("brightness channel") has been eliminated in the brightness-normalized image. To implement this embodiment, the image from which the brightness-normalized image is generated, or its pixels, are described by a color space that has brightness as its own color space coordinate. The remaining color space coordinates of the brightness-normalized image are also referred to below as "color coordinates." The color coordinates then span a brightness-normalized color space.Concrete value tuples of the color coordinates can then be mapped to a color location of the brightness-normalized color space.

[0025] One embodiment involves generating the brightness-normalized image by eliminating the brightness channel from an HSX image. This offers the advantage that an HSX image uses a widely used color space representation that is also easy to evaluate. Furthermore, the amount of image data can be reduced by the amount of data in the brightness channel. An HSX image is understood, in particular, to be an image whose color space coordinates include a color value (hue), a color saturation, and a brightness value. Alternatively, the brightness-normalized image can be generated by eliminating the brightness channel, for example, from an image in YUV format, YIQ format, etc.

[0026] The color value can be represented or specified as a hue angle on the color wheel (e.g., 0° for red, 120° for green, 240° for blue). Color saturation can be represented as a percentage value (e.g., 0% = neutral gray, 50% = slightly saturated color, 100% = saturated, pure color), corresponding to an interval from zero to one. Color value and saturation form the two color coordinates that define a, for example, circular, brightness-normalized (H, S) color space.

[0027] The HSX image can be available in several variants (with X = V, L, B or I), which differ in the representation of the brightness value, for example as HSV image, in which the brightness value (also called darkness) is represented as a percentage value (0% = no brightness, 100% = full brightness), corresponding to an interval from zero to one; HSL image with relative brightness instead of the brightness value; HSB image with absolute brightness instead of the brightness value; HSI image with light intensity instead of the brightness value.

[0028] Since the brightness channel X is eliminated, all variants of an HSX image can be used in the same way.

[0029] In one embodiment, the pixels of the image captured in step (a) do not have an independent brightness coordinate, and in step (b1), the captured image is converted into an image whose pixels each have multiple color space coordinates, including a brightness coordinate. Thus, the brightness values ​​or brightness information can advantageously be excluded or eliminated relatively easily even from captured images that do not have an independent brightness channel.

[0030] One embodiment involves capturing an RGB or CMYK image in step (a), and then converting the RGB or CMYK image into an HSX image in step (b1). Then, the brightness-normalized ("HS") image is generated from the HSX image by separating the brightness values. This provides the advantage that color images, often generated by a color camera in RGB or CMYK format, can be used to implement the method. The transformation into an HSX image is well known; for RGB, HSV transformation is used, for example, according to the formula theorem of Gonzalez and Woods, Foley and Van Dam, or Travis. Compared to an RGB image, using an HSX image reduces the data volume by one-third, and compared to a CMYK image, even by half.

[0031] However, the process is not limited to the use of RGB, CMYK, HSX, etc. images.

[0032] It is an embodiment that the image is evaluated to determine a degree of cooking of food depicted in the image (ie, one or more different food items) using at least one remaining color coordinate, e.g. based on an evaluation of the color value, the color saturation or a color location determined from the color value and the color saturation of a brightness-normalized HSX image or HS image.

[0033] A further development is that the degree of doneness of a food item is determined by evaluating individual pixels or groups of pixels of that food item in the brightness-normalized image. This allows for the spatial dependence or spatial distribution of the degree of doneness to be taken into account.

[0034] A further development is that the degree of doneness of a food item is determined by calculating an overall color coordinate for the food item. This can be done, for example, by averaging the values ​​of at least one color coordinate of the pixels belonging to the food item (if necessary, weighted).

[0035] A degree of doneness can generally be understood as a measurement that depicts or represents different cooking states with the endpoints "undercooked" and "cooked." In this case, a change in the degree of doneness is detected by detecting a color change on the surface of the food. The current color and / or a color change thus represent a quantifiable indication of the degree of doneness.

[0036] It is a further development that the degree of doneness is a degree of browning. In contrast to the previously used determination of the degree of browning based on the increasing darkening of the food, the degree of browning can be determined in this case, for example, from a color change, e.g. from a non-brown color such as green to brown. In an HS image, this would correspond to a change in a color location in an (H, S) plane, e.g. from green (H = 120°; S = 100%) to brown (H = 20°; S = 75%). However, other degrees of doneness can also be determined instead of a degree of browning. For example, certain foods lose their color with increasing cooking degree, or a color change other than to brown can occur with increasing cooking degree. This can be taken into account, for example, if the type of food is known in advance, e.g. due to user input or automatic determination.

[0037] The degree of doneness or the achievement of a target degree of doneness can be determined across the entire surface of a food item ("globally") or separately for different parts of the food ("locally"). Specifically, with local determination of the degree of doneness, the cooking appliance can trigger at least one action if a target degree of doneness has already been reached in one part of the food, for several parts of the food, or for all parts of the food.

[0038] One embodiment determines whether the food being considered has reached a target degree of doneness based on reaching a target color point defined by the remaining color coordinates or a range thereof (e.g., Htarget ± 2° and Starget ± 5%). This enables particularly simple determination of the finished cooking state of the food being considered. In a further development, the target degree of doneness can be set before or at the start of a cooking process. For example, if a specific dish (e.g., chicken, pizza, casserole, etc.) and a desired degree of browning (e.g., "crispy") are set within a cooking program, the target color point corresponding to the target degree of doneness, in particular the target browning, can be calculated from this or retrieved from a data memory.

[0039] One embodiment includes performing steps (a) and (b) multiple times in succession. This advantageously allows the color coordinates of the food or the food surface to be evaluated at different times, thus also taking dynamic effects into account. In particular, color coordinates of a food determined consecutively can be evaluated to determine a target degree of cooking of the food and / or a remaining cooking time.

[0040] A further development involves evaluating the temporally successive color coordinates pixel by pixel, e.g., by comparing images. For example, to determine the target degree of doneness and / or the remaining cooking time, difference images can be generated and evaluated. Reaching a target degree of doneness can then be determined, for example, based on whether the temporal change in the color coordinates for at least 70% of the pixels is below a certain threshold and, if applicable, whether these pixels are within a certain distance of a target degree of doneness.

[0041] In one embodiment, a curve of at least one color coordinate is evaluated to determine the target degree of doneness of the food and / or the remaining cooking time. This advantageously allows cooking states of the food (e.g., a degree of doneness, especially the degree of browning) to be evaluated particularly flexibly and reliably. To evaluate the temporal progression, known methods for curve evaluation or curve analysis can be used, e.g., determining maximum and / or minimum points, saddle points, points of high gradient, etc. In the exemplary case of an HSX image, the curve can, for example, comprise a temporal change in a - standardized or non-standardized - hue angle of the color value and / or a - standardized or non-standardized - change in a saturation level.

[0042] The object is also achieved by a household cooking appliance comprising a cooking chamber and at least one camera for capturing pixel-based images, wherein the household cooking appliance is configured to carry out the method as described above. The household cooking appliance can be designed analogously to the method and has the same advantages.

[0043] The analysis can be performed inside the household cooking appliance or outside the household cooking appliance, e.g., in an external data processing device such as a network server or a cloud server. For analysis inside the household cooking appliance, the appliance has a corresponding data processing device; for external analysis, it has a communication interface with an external data processing device. The process can also, in principle, be carried out in any distributed manner between the household cooking appliance and the external data processing device.

[0044] The above-described properties, features and advantages of this invention, as well as the manner in which they are achieved, will become clearer and more clearly understood in connection with the following schematic description of an embodiment, which is explained in more detail in connection with the drawings. Fig. 1 shows a sectional side view of a sketch of a household cooking appliance with at least one camera; Fig. 2 shows a plot of an average value of the various color space coordinates of an HSV image of a white reference as a function of a shelf height; Fig. 3 shows a standard deviation for the various color coordinates of an HSV image of a white reference as a function of a shelf height; Fig. 4 shows a curve of standardized color coordinates of an HSV image of a food item over the duration of a cooking operation; and Fig. 5 shows a method sequence for preparing an evaluation of a recorded image for operating the household cooking appliance.

[0045] Fig.1shows a sectional side view of a sketch of a household cooking appliance 1 with a cooking chamber 2, the front loading opening 3 of which can be closed by means of a cooking chamber door 4. The cooking chamber 2 has several shelf levels with corresponding shelf heights EH1 to EH4, whereby the shelf height EH1 is located near a floor of the cooking chamber 2 and the shelf height EH4 is located near a ceiling of the cooking chamber 2. Here, food A, which itself has a certain height, is placed on the second shelf height EH2, e.g. on a wire rack or baking tray inserted in the corresponding shelf level (not shown).

[0046] A color camera 5 is mounted in the ceiling of the cooking chamber 2, but other cameras (not shown) may also be present. The color camera 5 is configured (i.e., designed and arranged) to capture pixel-based color images from above or obliquely above the cooking chamber 2.

[0047] The household cooking appliance 1 further comprises at least one lighting device for illuminating the cooking chamber 2, e.g. comprising a spotlight (e.g. LED spotlight) 6 in the region of the ceiling and a spotlight (e.g. LED spotlight) 7 in the region of the left and / or right side wall of the cooking chamber 2. The brightness distribution resulting from the light cones in the cooking chamber 2 when the spotlights 6, 7 are in operation is inhomogeneous in the horizontal plane and also depends on the measured height in the cooking chamber 2. Overall, the light distribution in the cooking chamber is inhomogeneous in all three spatial directions.

[0048] The color camera 5 and the radiators 6, 7 are connected to a control device 8, which can also be configured as a data evaluation device.

[0049] The control device 8 can also be connected to a communication module 9 (e.g. an Ethernet module, a WLAN module, etc.) and via the communication module 9, e.g. via a network N, to a computer C external to the device. This makes it possible to outsource data processing sequences or computing capacity entirely or partially from the household cooking appliance 1, e.g. to keep them available in the so-called cloud.

[0050] Fig.2shows a plot of an average of the pixel-related values ​​for the various color space coordinates or channels H (color value), S (saturation), and V (brightness) of an HSV image of a white reference as a function of the insertion heights EH1 to EH4. The color space coordinates H, S, and V are normalized to a maximum value of "1" as follows: The color value H is normalized to 360° (a normalized color value H = 0 thus corresponds to a hue angle of 0° or 360°, a color value of 0.5 to a hue angle of 180°, etc.), while the color space coordinates S and V are normalized to 100% (a normalized value of 0.5 corresponds to a saturation of 50% or a brightness of 50%, etc.).

[0051] The HSV image can be captured directly or indirectly (e.g. via an RGB image).

[0052] The mean values ​​over the pixels or the area of ​​the white reference of the H and S channels H, S are almost constant for the insertion heights EH1 to EH4, while the V channel V changes significantly.

[0053] Fig.3 shows a standard deviation for the different color coordinates or channels H, S, V of the HSV image from Fig.2 depending on the insertion heights EH1 to EH4. The standard deviation in the V channel V is significantly larger than in the H and S channels H, S. This means that the H and S values ​​of the individual pixels are almost constant within the area of ​​the white reference at the respective insertion heights EH1 to EH4.

[0054] A browning assessment of food A taking into account the brightness is therefore very error-prone, especially if the shelf height EH1 to EH4 and the height and shape of the food are not known.

[0055] Fig.4 shows a curve that is analogous to Fig.2normalized color coordinates H and S of an HSV image of the top side of a food item A in the form of a pizza mozzarella over a duration t of oven cooking in seconds.

[0056] Starting at approximately t = 800 s, the values ​​for H (lower curve) and V (upper curve) begin to change noticeably, with H decreasing and S increasing. The curves or curve progressions then transition to a plateau state after approximately 1200 s. This change in H and S corresponds to a browning of the pizza surface, so that the browning can be reliably detected even without considering the brightness value S.

[0057] From the curves or curve progressions for H and S, the target degree of doneness and / or the remaining cooking time can be determined. For example, if the time until browning begins and / or is complete is known, the time until the target degree of doneness and / or the remaining cooking time is reached can be determined using tables or characteristic curves, for example, determined experimentally.

[0058] Fig.5 shows a method sequence for preparing an evaluation of an RGB image 10 recorded by the camera 5 in a step S1 for operating the household cooking appliance 1. For example, in order to reduce the error rate in the browning assessment, the highly erroneous brightness information is omitted or excluded from further evaluation.

[0059] For this purpose, in a step S2, the recorded RGB image 10 with its channels R (red), G (green) and B (blue) is converted or transformed into an HSV image 11 with its channels H, S and V.

[0060] In a step S3, the V-channel is separated, resulting in a brightness-normalized HS image 12 whose data volume is approximately one third smaller than that of the HSV image 11. The V-channel V is therefore not used for further evaluation in step S4, as indicated by its strikethrough.

[0061] The steps S3, S3 and / or S4 can run wholly or partly on the control device 8 and / or on the computer C.

[0062] Of course, the present invention is not limited to the embodiment shown.

[0063] In general, "a", "an", etc., can be understood as a singular or a plural, in particular in the sense of "at least one" or "one or more", etc., as long as this is not explicitly excluded, e.g. by the expression "exactly one", etc. A numerical specification can also include exactly the specified number as well as a usual tolerance range, as long as this is not explicitly excluded. List of reference symbols

[0064] 1Household cooking appliance 2Cooking chamber 3Loading opening 4Cooking chamber door 5Color camera 6Spotlight 7Spotlight 8Control unit 9Communication module 10RGB image 11HSV image 12Brightness-normalized HS image AFood BB channel CRecomputer EH1-EH4Storage height GG channel HH channel NNetwork RR channel SS channel VV channel

Claims

1. Method (S1-S4) for operating a household cooking appliance (1) with a cooking chamber (2) and with at least one camera (5) which is configured for recording pixel-based images (10) from the cooking chamber (2), in which (a) at least one image (10) from the cooking chamber (2) is recorded (S1) by means of the at least one camera (5) and (b) the image (10) is evaluated (S2-S4) with exclusion of the brightness values of the associated pixels thereof, and based on a result of the evaluation, at least one action is triggered by the household cooking appliance (1).

2. Method (S1-S4) according to claim 1, wherein step (b) comprises the sub-steps (b1) a brightness-normalised image (12) is generated from the recorded image (10), wherein the brightness values of the associated pixels have been removed (S2-S3), and (b2) the brightness-normalised image (12) is evaluated (S4).

3. Method (S1-S4) according to claim 2, wherein in step (b1) the brightness-normalised image (12) is generated from an image (11), the pixels thereof in each case having a plurality of colour space coordinates (H, S, V) including a brightness coordinate (V), by the brightness coordinate (V) being removed (S3).

4. Method (S1-S4) according to claim 3, wherein in step (b1) the brightness-normalised image (12) is generated (S3) from an HSX image (11).

5. Method (S1-S4) according to one of claims 3 to 4, wherein - the pixels of the image (12) recorded in step (a) do not have a separate brightness coordinate and - in step (b1) the recorded image (10) is converted into an image (11), the pixels thereof in each case having a plurality of colour space coordinates (H, S, V) including a brightness coordinate (V) (S2).

6. Method (S1-S4) according to claim 5, wherein in step (a) an RGB image (10) is recorded (S1) and in step (b1) initially the RGB image (10) is converted (S2) into an HSX image (11) and then the brightness-normalised image (12) is generated from the HSX image (11) by removing the brightness values (V).

7. Method (S1-S4) according to one of the preceding claims, wherein the brightness-normalised image (12) is evaluated using at least one remaining colour coordinate (H, S) for determining a degree of cooking, in particular a degree of browning, of food to be cooked (A) illustrated in the image (12).

8. Method (S1-S4) according to claim 7, wherein reaching a target degree of cooking of the food to be cooked (A) is determined by reaching a target colour point of this food to be cooked (A) defined by the remaining colour coordinates (H, S) or an environment thereof.

9. Method (S1-S4) according to one of claims 3 to 8, wherein the steps (a) and (b) are repeatedly carried out chronologically in succession and colour coordinates of a food to be cooked (A) are evaluated chronologically in succession for determining a target degree of cooking of the food to be cooked (A) and / or a remaining cooking time.

10. Method (S1-S2) according to claim 9, wherein a curve progression of at least one colour coordinate (H, S) is evaluated for determining the target degree of cooking of the food to be cooked (A) and / or the remaining cooking time.

11. Method (S1-S4) for operating a household cooking appliance (1) having a cooking chamber (2) and at least one camera (5) for recording pixel-based images (12) from the cooking chamber (2), in which - at least one image (10) from the cooking chamber (2) is recorded (S1) by means of the at least one camera (5), wherein a plurality of colour space coordinates are assigned to each pixel of the recorded image (10), - the recorded image (12) is converted into an image (11), the pixels thereof in each case having a plurality of colour space coordinates (H, S, V) including a brightness coordinate (V) (S2), - a brightness-normalised image (12) is generated from the converted image (11) in which the brightness values of the associated pixels have been removed (S3) - the at least one brightness-normalised image (12) is evaluated (S4) and - based on a result of the evaluation, at least one action is triggered by the household cooking appliance (1).

12. Household cooking appliance (1) having a cooking chamber (2) and at least one camera (5) for recording pixel-based images (12), wherein the household cooking appliance (1) is configured for carrying out the method (S1-S4) according to one of the preceding claims.