阅读说明：本技术 加热烹调器 (Heating cooker ) 是由 谷口直哉 今井博久 松井严徹 岩垂真哉 于 2019-12-11 设计创作，主要内容包括：本公开的加热烹调器具备：加热室,其容纳加热对象物；拍摄部,其对所述加热室内进行拍摄；以及曝光控制部,其执行曝光控制。所述曝光控制部根据从由所述拍摄部拍摄到的图像得到的灰度信息进行曝光控制。由此,能够准确地检测加热室内的照度,在进行了曝光控制的基础上取得识别用的图像。(The disclosed heating cooker is provided with: a heating chamber for accommodating a heating object; an imaging unit that images the inside of the heating chamber; and an exposure control unit that performs exposure control. The exposure control unit performs exposure control based on gradation information obtained from the image captured by the imaging unit. Thus, the illuminance in the heating chamber can be accurately detected, and an image for recognition can be acquired after exposure control is performed.)

1. A heating cooker is provided with:

a heating chamber for accommodating a heating object;

an imaging unit that images the inside of the heating chamber; and

an exposure control section for performing exposure control,

the exposure control unit performs the exposure control based on gradation information obtained from the image captured by the imaging unit.

2. The heating cooker according to claim 1,

the heating cooker further includes a light measurement object detection unit that extracts a light measurement object from the image captured by the imaging unit,

the subject detection unit passes the gradation information of a subject portion in the image,

the exposure control unit performs the exposure control based on the gradation information.

3. The heating cooker according to claim 2,

the light measurement object detection unit passes only a high gradation value of a predetermined ratio in the image.

4. The heating cooker according to claim 2,

the light measurement object detection unit passes only pixels having a gradation value different from a gradation value of pixels in a predetermined pixel region of the light measurement object.

5. The heating cooker according to claim 2,

the light measurement object detection unit passes only the gradation value of a pixel within a predetermined chromaticity range.

6. The heating cooker according to any one of claims 2 to 5,

the light measurement object detection unit notifies a user that the recognition object is not detected when the number of pixels detected as the light measurement object is less than a predetermined number.

Technical Field

The present disclosure relates to a heating cooker that heats food and a method for controlling the heating cooker.

Background

A microwave oven, which is an example of a heating cooker, can heat food in a state of being placed in a container without using a pan or a frying pan. Therefore, in a sales store such as a convenience store, food such as lunch and dishes may be served by heating the food with a microwave oven.

In general, a heating time suitable for heating in a microwave oven is displayed for lunch and dishes. Generally, a clerk of the sales shop observes the display and sets the heating time in the microwave oven.

Specifically, the clerk can set the heating time by operating the numeric keys disposed on the operation unit of the microwave oven. Alternatively, in the case of using a microwave oven including a plurality of cooking buttons corresponding to heating time and wattage, a store clerk can heat a food suitable for heating by operating a button corresponding to the food to be heated.

However, setting the heating time using the numeric keys has a problem of troublesome operation. In a microwave oven in which heating times of different food items are assigned to a plurality of operation buttons, a store clerk needs to memorize the correspondence between the plurality of buttons and the food items. This causes a problem that as the types of products increase, the burden of the store clerk to memorize the correspondence increases.

In order to solve such problems, it is proposed to provide a microwave oven: when a clerk reads information attached to a barcode of a commodity, the commodity is heated with heating control contents corresponding to the barcode.

Alternatively, a microwave oven has been proposed in which a camera for taking an image of the inside of a heating chamber is provided on the top surface of the microwave oven. In the conventional microwave oven, a barcode portion is extracted from an image of a commodity put into a room, and the barcode is read to retrieve heating control contents corresponding to the commodity from code information, thereby performing appropriate heating (for example, patent document 1).

In addition, there have been disclosed examples of the following microwave ovens: an image of the food is obtained by a camera provided so as to be able to photograph the inside of the heating chamber, and an image recognition process is performed to perform cooking according to the recognition result.

Documents of the prior art

Patent document

Patent document 1: japanese patent laid-open No. 2001 and 349546

Disclosure of Invention

In a conventional microwave oven, a heating chamber is irradiated with light of an LED or the like at an appropriate illuminance, and an image suitable for image recognition processing is acquired by a camera. In this case, depending on the environment in which the microwave oven is installed, external light such as sunlight may enter the heating chamber through the opening of the door, and the illuminance in the heating chamber may not be maintained to a level suitable for image processing. In an image captured in a state where external light is incident, a target portion to be subjected to recognition processing may be whitened, and the recognition rate may be significantly reduced.

The invention aims to provide a heating cooker, which can accurately detect the illumination in a heating chamber according to an image shot by a camera even if external light such as sunlight enters from an opening part of a door, and can acquire an image for recognition after exposure control is performed. This can improve the recognition accuracy of the image to be recognized.

In order to solve the above conventional problems, a heating cooker according to the present disclosure includes: a heating chamber for accommodating a heating object; an imaging unit that images the inside of the heating chamber; and an exposure control unit that performs exposure control. The exposure control unit performs exposure control based on gray level information obtained from the image captured by the imaging unit.

The disclosed heating cooker can accurately detect the illuminance in the heating chamber from the image captured by the camera even when external light such as sunlight enters from the opening of the door, and can acquire an image for recognition after exposure control is performed. Therefore, the recognition accuracy of the image to be recognized can be improved.

Drawings

Fig. 1 is a perspective view showing an external appearance of a heating cooker according to embodiment 1 of the present invention.

Fig. 2 is a schematic configuration diagram of a heating cooker according to embodiment 1 of the present disclosure.

Fig. 3 is a diagram showing a label of product information including heating control information displayed on a product heated by the heating cooker of embodiment 1 of the present disclosure.

Fig. 4 is a diagram showing an indoor image of the heating cooker according to embodiment 1 of the present disclosure in an empty state.

Fig. 5A is a diagram showing an example of an indoor image of a heating cooker according to embodiment 1 of the present disclosure in a state in which food is placed.

Fig. 5B is a diagram showing an example of an indoor image of a heating cooker according to embodiment 1 of the present disclosure in a state in which food is placed.

Fig. 6A is a graph showing a histogram of gradation values of an indoor image of a heating cooker according to embodiment 1 of the present disclosure in a state in which food is put.

Fig. 6B is a graph showing a histogram of gradation values of an indoor image in a state where food is put in the heating cooker according to embodiment 1 of the present disclosure.

Fig. 7A is a diagram showing an example of a region passing through a filter when a high-gradation pass filter process is applied to an indoor image by the light metering object detection unit according to embodiment 1 of the present disclosure.

Fig. 7B is a diagram showing an example of a region passing through a filter when the light metering object detection unit according to embodiment 1 of the present disclosure performs high-gradation pass filter processing on an indoor image.

Fig. 8A is a diagram showing an example of a histogram of the gradation values of an indoor image obtained by applying a filtering process to an indoor image at a high gradation level by the light metering object detection unit according to embodiment 1 of the present disclosure.

Fig. 8B is a diagram showing an example of a histogram of the gradation values of an indoor image obtained by applying a filtering process to an indoor image at a high gradation level by the light metering object detection unit according to embodiment 1 of the present disclosure.

Fig. 9A is a diagram showing an example of a region that passes through a filter when a contrast filter process is applied to an indoor image by the light metering object detection unit according to embodiment 1 of the present disclosure.

Fig. 9B is a diagram showing an example of a region that passes through a filter when the light metering object detection unit according to embodiment 1 of the present disclosure performs contrast filtering processing on an indoor image.

Fig. 10A is a diagram showing an indoor image when the light metering object detecting unit according to embodiment 1 of the present disclosure performs chroma filtering processing on the indoor image.

Fig. 10B is a diagram showing an example of an area that passes through a filter when the photometry target detection unit according to embodiment 1 of the present disclosure performs chroma filtering processing on an indoor image.

Fig. 11 is a diagram showing an example of a filter range on the xy chromaticity diagram when the photometric object detection unit according to embodiment 1 of the present disclosure performs chromaticity filter processing on an indoor image.

Fig. 12 is a flowchart showing a flow of an operation of the heating cooker according to embodiment 1 of the present disclosure.

Detailed Description

A heating cooker according to a first aspect includes: a heating chamber for accommodating a heating object; an imaging unit that images the inside of the heating chamber; and an exposure control unit that performs exposure control based on gradation information obtained from the image captured by the imaging unit.

Thus, even when external light such as sunlight enters from the opening of the door, the illuminance in the heating chamber can be accurately detected from the image captured by the camera, and an image for recognition can be acquired after exposure control is performed. Therefore, the recognition accuracy of the image to be recognized can be improved.

A heating cooker according to a second aspect is the heating cooker according to the first aspect, further comprising a light measurement object detection unit that extracts a light measurement object from the image captured by the imaging unit, wherein the light measurement object detection unit passes the gradation information of the light measurement object portion in the image, and the exposure control unit performs exposure control based on the gradation information.

Thus, exposure control can be performed based on gradation information of an image obtained by performing filtering processing for passing only the feature of the light measurement object in advance on the captured image. Therefore, the accuracy of exposure control can be improved.

In the heating cooker of the third aspect, in addition to the second aspect, the light measurement object detection unit may pass only a higher gradation value of a predetermined ratio in the image.

This makes it possible to perform filtering processing with high accuracy and high speed for a photometric object whose brightness is high and whose gradation value at the time of photographing is relatively high, which is known in advance, such as a white label.

A heating cooker according to a fourth aspect is the heating cooker according to the second aspect, wherein the light measurement object detection unit passes only pixels having a gradation value different from a gradation value of pixels in a predetermined pixel region of the light measurement object.

Thus, when a portion having high contrast between black and white, such as a label having a black character or a black barcode printed on a white background, is determined as a light measurement target in advance, filter processing can be performed with high accuracy.

In a heating cooker according to a fifth aspect of the present invention, in addition to the second aspect, the light measurement object detection unit passes only gradation values of pixels within a predetermined chromaticity range.

Thus, when the color of the label to be measured is defined in advance, the filtering process can be performed with high accuracy and at high speed.

A heating cooker according to a sixth aspect is the heating cooker according to any one of the second to fifth aspects, wherein the light metering object detector notifies a user that the recognition object is not detected when the light metering object is detected with less than a predetermined number of pixels.

Thus, when the recognition target does not enter the imaging range or goes out of the field of view, etc., the user is notified that the recognition target is not detected at an early stage before the recognition processing. This can urge the user to newly insert the food, confirm the state of the tag of the identification object, and the like.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings as appropriate. However, unnecessary detailed description may be omitted. For example, detailed descriptions of already known matters and repetitive descriptions of substantially the same configuration may be omitted. This is to avoid the following description becoming unnecessarily lengthy and readily understandable to those skilled in the art.

The drawings and the following description are provided to enable those skilled in the art to fully understand the present disclosure, and are not intended to limit the subject matter recited in the claims.

(embodiment mode 1)

A heating cooker according to embodiment 1 of the present disclosure will be described below with reference to the drawings.

Fig. 1 is a diagram showing an external appearance of a heating cooker according to a first embodiment of the present disclosure.

The microwave oven 100 shown in fig. 1 includes a housing 101 and a door 102 pivotally supported by the housing 101 so as to be openable and closable. A heating chamber 201 for accommodating food such as lunch or dishes (heating object 203) as a heating object is disposed inside the casing 101.

The door 102 has a transparent glass window 103 so that a user can see the inside of the housing 101. Also, the door 102 has a handle 104 in order to allow a user to easily grip the door 102.

In the present embodiment, the side of the housing 101 having the door 102 is referred to as the front, the right side from the front to the rear is referred to as the right side, and the left side from the front to the rear is referred to as the left side.

An operation display unit 105 is disposed near the door 102. The operation display unit 105 includes a liquid crystal display 106, a time setting button group 107, a heating start button 108, a cancel button 109, and a temporary stop button 110. The user can set the heating time by using the numeric buttons and the minute and second buttons. The liquid crystal display 106 displays the set heating time and the like.

The heating start button 108 is a button for starting heating after the user confirms the heating time, wattage, and the like using the liquid crystal display 106. The cancel button 109 is a button for stopping heating after heating is started by pressing the heating start button 108, or for canceling the setting of the heating time displayed on the liquid crystal display 106.

The temporary stop button 110 is a button for temporarily stopping heating in the middle of heating. After the heating is temporarily stopped, the user can perform the remaining heating from the middle by pressing the heating start button 108 again.

Fig. 2 is a schematic configuration diagram of microwave oven 100 according to embodiment 1.

The microwave oven 100 includes 2 magnetrons 202a and 202b as heating units for outputting microwaves into a heating chamber 201.

The magnetron 202a is disposed on the ceiling side of the heating chamber 201, and outputs microwaves into the heating chamber 201 from the upper part. On the other hand, the magnetron 202b is disposed on the bottom surface side of the heating chamber 201, and outputs microwaves into the heating chamber 201 from the lower portion. Food such as lunch and dishes accommodated in the heating chamber 201, that is, the heating object 203 is heated by the radiated microwaves.

In the present disclosure, microwaves generated by a magnetron are exemplified as the heating unit, but the heating unit may be heated by microwaves generated by semiconductor oscillation, a heater, warm air, steam, or the like. In addition, the number of heating sources such as magnetrons may be 1 instead of 2.

A camera 204 (an example of an imaging unit) is disposed on the top side of the heating chamber 201. The camera 204 is composed of an imaging element such as a CCD (Charge Coupled Device) and an optical element such as a lens. The camera 204 captures an image of the inside of the heating chamber 201 to generate an image. The generated image has a luminance represented by a value in the range of 0 (dark) to 255 (light), for example, for each pixel. Further, an image may be generated in which each pixel is represented by a value of 0 to 255 for each of red, blue, and green. The value corresponding to each pixel may be expressed by a range or an expression method other than 0 to 255.

In the present embodiment, the camera 204 is provided on the top side surface of the heating chamber 201. However, the camera 204 may be provided on other surfaces such as the left and right side surfaces of the heating chamber 201. In the present disclosure, by studying exposure conditions as described later, even if the imaging unit 204 is configured by 1 camera component, the recognition accuracy of the image can be improved. Therefore, the cost reduction at the time of manufacturing and the miniaturization of the housing 101 can be achieved. The imaging unit 204 may be configured by a plurality of camera members, without being limited thereto.

An illumination 205 using an LED as a light source is disposed on a side surface of the heating chamber 201 to illuminate the inside of the heating chamber 201.

In the present embodiment, the illumination 205 is disposed so as to face the inside of the heating chamber 201 from the left side surface of the heating chamber 201. However, the illumination 205 may be disposed on any one of four sides, a top surface, a bottom surface, and the like, or may be disposed in plural.

In the present embodiment, the LED-based configuration is disclosed as the light source of the illumination 205, but other light sources such as a bulb, a fluorescent lamp, and natural light may be used as the light source.

The control unit 300 is disposed below the operation display unit 105. The control unit 300 controls the components of the microwave oven 100.

In fig. 2, the control unit 300 includes a heating control unit 301, a recognition unit 302, a light metering object detection unit 303, and an exposure control unit 304.

In the present embodiment, the control unit 300 is configured by integrating the heating control unit 301, the recognition unit 302, the light measurement object detection unit 303, and the exposure control unit 304. However, these structures may be realized by different semiconductor elements or the like. The control Unit 300 may be a microcomputer having a processor such as a CPU (Central Processing Unit).

The heating control unit 301 controls the magnetron 202a and the magnetron 202 b. The heating target 203 accommodated in the heating chamber 201 is heated by microwaves radiated from the magnetron 202a and the magnetron 202 b.

The recognition unit 302 recognizes an object such as food, a graphic code such as a barcode attached to food, or a character from the image captured by the camera 204.

The light measurement object detection unit 303 performs filtering processing for passing the gradation value of the pixel of the food label unit that is the object of recognition and light measurement on the image captured by the camera 204, and then calculates the average gradation value of the entire image. The light metering object is extracted using the calculated average gradation value as an estimated gradation value of the light metering object portion. That is, the light metering object detection unit 303 passes light metering and gradation information of the recognition object portion based on the image captured by the camera 204.

The exposure control unit 304 determines whether or not exposure adjustment is necessary based on the estimated gradation value output from the photometric object detection unit 303. Then, the exposure control unit 304 controls the camera 204 or the illumination 205 as necessary to change the exposure setting.

Fig. 3 shows an example of a label to be attached to a food.

In the heating chamber 201, commodities such as a lunch, a rice ball, and dishes are put and heated. The labels described above and showing the heating power and heating time required for cooking the product are attached to the products.

In the present embodiment, information for cooking such as the heating power and the heating time is referred to as heating control information.

Information such as a product name 402, heating control information 403, money amount information 404, expiration date information 405, a barcode 406 (which may be another graphic code) for identifying a product, nutritional information 407, and notification information 408 is displayed on the label 401. In the present embodiment, the heating control information is surrounded by a block 409 in order to easily extract the heating control information from these pieces of information.

Note that, in this label 401, a heating time in the case of heating at 500W, which is a general standard when heating with a general household microwave oven, and a heating time in the case of heating at 1500W, which is a general standard when heating at a high power for a short time, are described together. For example, the label 401 displays "500W 2 min 00 sec, 1500W0 min 40 sec" as the heating control information.

When the user opens the door 102 to put food in, the camera 204 photographs the inside of the heating chamber 201. Then, the recognition unit 302 recognizes a portion where the heating control information is displayed from the image captured by the camera 204, and recognizes the characters and numerals of the heating control information.

Specifically, the recognition unit 302 recognizes the frame 409 from the image captured by the camera 204.

Next, the recognition unit 302 recognizes a character string surrounded by the box 409 and having an alphanumeric character "500W 2001500W 040".

Then, according to a predetermined analysis rule, the recognition unit 302 decomposes the character string into a number string up to "W", a number string of 3 bits after "W", a next number string up to "W", and a number string of 3 bits after "W", that is, "500", "200", "1500", "040". The recognition unit 302 further recognizes the second digit string and the fourth digit string as "minutes" for the first 1 bit and seconds for the next 2 bits, and the power of the first digit string corresponds to the time of the second digit string and the power of the third digit string corresponds to the time of the fourth digit string. Then, the recognition unit 302 recognizes the heating control information of 2 minutes at 500W and 40 seconds at 1500W.

In the present embodiment, such a food label portion (label 401) is not the entire indoor image but the object of recognition and photometry. Further, although details will be described later, the gradation value of the food label portion (label 401) is also a target of the gradation estimation for exposure adjustment.

Fig. 4 shows an example of an indoor image when the heating chamber 201 is empty. In the microwave oven chamber, a frame indicating a rough reference of a placement position of the food and a use notice are printed on a bottom surface. In the present embodiment, the following description is given as a case where characters such as a box and a notice are printed in black on a white background, but other designs may be used for the design including the color of the indoor floor.

Fig. 5A and 5B show another example of an image obtained by imaging the inside of the heating chamber 201. In this example, fig. 5A shows an example of an image obtained by imaging the inside of a room when "boiled rice" is present in the heating chamber 201 as an example of food with high lightness, and fig. 5B shows an example of an image obtained by imaging the inside of a room when "laver meal" is present in the heating chamber 201 as an example of food with low lightness.

Fig. 6A and 6B show a histogram of image gradation values corresponding to each captured image and an average gradation value of the entire image in the case where food, which is exemplified in fig. 5A and 5B, is present indoors. The histograms of the images of fig. 5A and 5B correspond to the histograms of fig. 6A and 6B, respectively. That is, the area amount of the bright gray scale in fig. 6A is large, and the area amount of the dark gray scale in fig. 6B is large.

Fig. 7A and 7B are examples in which, when a high-tone pass filter process is performed as the process performed by the light metering target detection unit 303, the pass target pixel region of the filter for the captured image in each of fig. 5A and 5B is expressed as a black-and-white 2-value image. In fig. 7A and 7B, white portions indicate pixel regions that have passed through the filter, and black portions indicate pixel regions that have been blocked by the filter.

Fig. 8A and 8B are examples showing a case where a higher gradation passage filter process is performed as a process performed by the light metering object detecting unit 303 on the indoor images of each of fig. 5A and 5B, that is, the histogram and the average gradation value of fig. 7A and 7B. The dotted line portion of the histogram indicates a portion of the gray scale blocked by the filter in order to easily grasp the effect of the filtering process on the higher gray scale when compared with the histograms of fig. 6A and 6B, respectively.

Fig. 9A and 9B are examples in which, when contrast filtering processing is performed as processing performed by the light metering object detection unit 303, the filter pass-target pixel region for the captured image of each of fig. 5A and 5B is expressed as a black-and-white 2-value image. Similarly to fig. 7A and 7B, white portions indicate pixel regions that have passed through the filter, and black portions indicate pixel regions that have been blocked by the filtering process.

Fig. 10A shows an indoor image in a case where a background portion of a label 401 as a photometric object uses a characteristic color (yellow close to a primary color, as an example). Fig. 10B is an example in which the light measurement object detection unit 303 represents the filter passing object pixel region in a black-and-white 2-value image when the captured image of fig. 10A is subjected to the chroma filtering process. As in fig. 7, white portions indicate pixel regions that have passed through the filter, and black portions indicate pixel regions that have been blocked by the filter. In the present embodiment, a yellow label whose background color is a near-primary color is described as an example, but the color is not particularly limited.

Fig. 11 shows, on an xy chromaticity diagram, a chromaticity range of a filter passing through when the photometry target detection section 303 performs chromaticity filtering processing. The inside of the circle indicated by the dotted line 1101 in the figure indicates the chromaticity range passed through the filter. In addition, as for the chromaticity range passed through the filter, a rectangular or an arbitrary function may be used to specify the range in addition to a circular shape. In addition, as the chromaticity diagram, uv chromaticity diagram or u' v chromaticity diagram may be used in addition to xy chromaticity diagram, and as the color system, for example, L × u × v color system, L × a × b color system or HSV color system other than XYZ color system may be used.

Fig. 12 is a flowchart showing the operation of exposure control of microwave oven 100 in embodiment 1. The following is a detailed description with reference to the flowchart of fig. 12.

In step S1, the camera 204 captures an indoor image at the initial exposure setting, and the control unit 300 advances the process to step S2. As a result of the photographing, an indoor image as shown in fig. 5A and 5B is obtained.

In step S2, the light metering object detecting unit 303 performs light metering object detection filter processing on the indoor image. In the present embodiment, the light measurement object detection unit 303 performs at least one of a high-gradation pass filter process, a contrast filter process, and a chromaticity filter process. Hereinafter, each filtering process will be described in detail.

First, the higher gradation is explained by the filtering process. When the light measurement object detection unit 303 uses this filter process, it is assumed that the background of the food label 401 to be recognized and measured is a background with relatively high brightness such as white. Since the series of processing is described on the premise that the processing is performed not in color but in a gray image, the gray scale refers to a gray scale (black: 0 gray scale, white: 255 gray scale).

As a specific flow of the filtering process for higher gradation, first, histograms of gradation values as shown in fig. 6A and 6B are created for the indoor images as shown in fig. 5A and 5B, respectively. Fig. 5A is an indoor image in which "boiled rice" is assumed as an example of a food having a relatively high lightness, and fig. 5B is an indoor image in which "sea sedge so as" is assumed as an example of a food having a relatively low lightness. Therefore, fig. 6A shows a histogram shape biased toward a high-gradation region as a corresponding histogram. Fig. 6B is the following histogram shape: in correspondence with the "sea weed" portion having particularly low lightness among the "sea weed lunch", the food label 401 and the indoor bottom surface are white and have high lightness, and therefore, the food label also has a peak in the high gradation region.

As shown in fig. 6A and 6B, the average gradation values of the entire images of food products having different lightness, such as "cooked rice" and "seaweed meal", are significantly different from each other. In the exposure control described in this embodiment, the average gradation value of the entire image is calculated as the estimated gradation value of the food label (label 401) portion as the light measurement object at the time of recognition and exposure adjustment, which is performed in the step S3 described later.

When the filtering process is not performed, even in the same illuminance environment, the difference in brightness of the food outside the food label (label 401) region is expressed as the difference in average gradation value as shown in fig. 6A and 6B. That is, the gray scale estimation error is large, and it is difficult to use the gray scale average value as it is for exposure control. In the high tone pass filter process, only a predetermined proportion of high tone values with respect to the total number of pixels of the image are passed, and low tone values are blocked.

Fig. 7A and 7B are images of the target pixel region in the case where the high-tone pass filter processing is performed on the indoor images of fig. 5A and 5B, which are expressed by black and white 2-value images. A portion of the image including the food label (label 401) as the photometric object, which has high brightness, becomes a passing pixel region.

For example, when a filter that passes a higher 50% is considered, the lower 50% of the area of the histograms of fig. 6A and 6B is blocked and takes the shape as shown in fig. 8A and 8B. The dashed lines represent the lower 50% of the pixels blocked by the filter. When calculating the average gradation value, the blocked pixels are not the subject of calculation, and therefore, as shown in fig. 8A and 8B, the difference between the average gradation values decreases and the gradation estimation error decreases as compared with fig. 6A and 6B. When there is a precondition that the brightness of the light measurement object is high, such filter processing does not detect the label portion (label 401), and the gradation value of the light measurement object (label portion) can be estimated at high speed and with high accuracy only by simple filter processing in the preprocessing stage. Therefore, the characters of the label portion can be easily recognized.

Next, the contrast filtering process is explained. The basic idea is the same as for higher gray levels through filtering processes. The objective is to reduce an estimation error of a gradation value used for exposure control by eliminating influences other than a food label to be recognized and measured by filter processing. When the light measurement object detection unit 303 uses contrast filter processing, it is assumed that the contrast of black and white at the identification target portion in the food label to be identified and measured is large (characters, bar codes, or the like). As a specific filtering process, the photometric object detection unit 303 performs a process of passing only pixels associated with the target pixel, which have a gray scale value having a predetermined gray scale difference from the target pixel. That is, the light measurement object detection unit 303 passes only pixels having a gradation value having a predetermined gradation difference from the gradation value of the pixels in the predetermined pixel region as the measurement object.

For example, when determining whether or not a certain pixel in an image passes through a filter, a process of confirming a 5 × 5 pixel region centered on a target pixel is performed. For example, if the gradation value of the target pixel is 200 gradations and pixels having a gradation of 100 or less, which is-100 gradations, exist in the 5 × 5 pixel region, the target pixel becomes a passing pixel, and if not, a blocking pixel. Such processing is performed for all pixels in the image. The region size of 5 × 5 pixels listed here is an example, and the shape (including the size) of the region is not limited to a rectangle. The gradation difference of-100 is also an example, and the numerical value is not limited.

Fig. 9A and 9B are images of the target pixel region in the case where the contrast filtering process is performed on the indoor images of fig. 5A and 5B, which are expressed as black and white 2-value images. A portion having a high black-white contrast including a character portion to be recognized becomes a passage target region. When recognition is made and the contrast of the object to be measured is high, the contrast filter processing can estimate the gradation value of the object to be measured at high speed and high accuracy by only simple filter processing in the preprocessing stage without detecting the label portion. Therefore, the characters of the label portion can be easily recognized.

Next, the chroma filtering process will be described. The basic idea is the same as that of the higher gradation filtering process, and the influence other than the food label to be recognized and measured can be eliminated by the chroma filtering process, thereby reducing the estimation error of the gradation value used for the exposure control. When the target-of-photometry detection unit 303 uses the chroma filtering process, it is assumed that the color of the label to be measured is a characteristic color.

Fig. 10A shows an example of an indoor image in the case where the food label is yellow, for example. Since the label portion is colored, the gray level is lower than the gray level of the white indoor floor. As a specific filtering process, a process is performed in which only the gradation values of pixels that have converged within a predetermined range on the chromaticity diagram are passed. For example, let a certain pixel in an image be R: 100 gray scale, G: 100 gray scale, B: 10 gray.

For example, if considering ITU-R bt.709 as a standard, X, Y, Z can be calculated by X-0.4124R +0.3576G +0.1805B, Y-0.2126R +0.7152G +0.0722B, Z-0.0193R +0.1192G + 0.9505B. Further, since X is X/(X + Y + Z) and Y is Y/(X + Y + Z), the chromaticities X and Y can be calculated, X being 0.4028 and Y being 0.4779, respectively. In the case where the values of x and y are included in a predetermined range 1101 on the xy chromaticity diagram of fig. 11, the photometric object detecting section 303 sets the object pixel as a passing pixel. In the case of being out of the range 1101 on the xy chromaticity diagram of fig. 11, the photometric object detection section 303 sets the object image as a blocking pixel. That is, the light measurement object detection unit 303 passes only the gradation value of the pixel in the predetermined chromaticity range. The light metering object detection unit 303 performs such processing for all pixels in the image.

In this filtering, since the color information is used, the filtering condition determination is performed using RGB gray scale, but the average gray scale is calculated using gray scale. The conversion from the RGB gray to the gray can be calculated by 0.299R +0.587G + 0.114B.

Fig. 10B is a diagram showing an image passing through the target pixel region when the contrast filtering process is performed on the indoor image of fig. 10A, using a black-and-white 2-value image. The tag portion to be identified becomes a passage target area. When there is a premise that the color to be recognized and measured is a characteristic color, such filter processing enables the gradation value of the measurement target to be estimated at high speed and with high accuracy only by simple filter processing in the preprocessing stage without detecting the label portion. Therefore, the characters of the label portion can be easily recognized.

The light metering target detection unit 303 performs any of a high-gradation pass filter process, a contrast filter process, and a chroma filter process to pass only light metering of an image captured by the camera 204 and gradation information of a recognition target portion. After that, the control unit 300 advances the process to step S3.

In step S3, the light metering object detecting unit 303 calculates an average gradation value of the entire image from the gradation values subjected to the filtering process in step S2. After that, the control unit 300 advances the process to step S4.

In step S4, the exposure control unit 304 determines whether or not exposure adjustment is necessary using the average gradation value calculated in step S3. For example, when the average tone value is 100 or more and 150 or less, it is determined that the image has been captured with brightness suitable for recognition, and the exposure control unit 304 does not perform exposure adjustment, and the control unit 300 advances the process to step S6. When the average tone value is smaller than 100 or larger than 150, the exposure control unit 304 determines that exposure adjustment is necessary, and the control unit 300 advances the process to step S5. The threshold values of 100 gradations and 150 gradations are examples, and the numerical range is not particularly limited.

In step S5, the exposure control unit 304 performs exposure adjustment based on the average gradation value. For example, when the average tone value is less than 100, the exposure control unit 304 determines that the indoor image is too dark, and sets the camera 204 to extend the exposure time. That is, the exposure control section 304 performs exposure control based on gradation information obtained from an image captured by the camera 204.

When the average tone value is larger than 150, the exposure control unit 304 determines that the indoor image is too bright, and sets the camera 204 to shorten the exposure time. As a specific method of the exposure adjustment, a method of adjusting the exposure time is exemplified, but other methods may be used. A method of adjusting the gain setting of the camera 204 may be used, or a method of combining exposure time adjustment and gain adjustment may be used. Alternatively, a method of controlling brightness in a room by the lighting 205 may be used. After the exposure adjustment is performed, the process returns to step S1, and the processing is performed again from the shooting of the indoor image.

In step S6, the control unit 300 determines whether or not the number of pixels passed through the filtering process in S2 exceeds a predetermined number. For example, when the number of pixels passed is 10000 or more, the control unit 300 advances the process to step S7, which is an image recognition process. When the number of pixels passed is less than 10000, the control unit 300 advances the process to step S9.

In step S9, the control unit 300 determines that the food label to be recognized is not captured in the captured image or is partially captured but is outside the image as a result of step S6, and notifies the user that the recognition target is not detected, and the recognition process and heating are not performed, and the process is terminated. That is, when the number of pixels detected as the photometric object is less than the predetermined number, the control unit 300 notifies the user that the recognition object is not detected. Since the user is notified that the identification target is not detected without executing the identification process, the user can be prompted to replace the food item and confirm the state of the food item label as soon as possible.

In step S7, the recognition unit 302 performs image recognition processing on the indoor image captured by the camera 204, acquires heating control information, and advances the processing to step S8.

In step S8, based on the heating control information acquired in step S7, heating controller 301 performs heating cooking and ends the processing.

As described above, according to the present embodiment, even when there is an influence of external light incident from the opening of the door 102 of the microwave oven, the gradation of the food label portion to be recognized and photometered is estimated with high accuracy from the gradation information of the image captured by the camera 204. Further, since the exposure control unit 304 performs appropriate exposure adjustment based on the estimated gradation, it is possible to perform high-precision image recognition processing on an image captured at a brightness suitable for recognition.

(other embodiments)

The above-described embodiments can also be implemented as a heating cooking system in which a heating cooking device such as a microwave oven can be connected to a network and the heating cooking device can be controlled by a server on the network. In such a heating cooking system, the processing performed by the photometric object detection unit 303 in the microwave oven 100 according to embodiment 1 is executed on the server side. This reduces the processing load of the image filtering process in the heating cooker.

Further, the above-described embodiments are intended to exemplify the technology in the present disclosure, and various modifications, substitutions, additions, omissions, and the like can be made within the scope of the claims and their equivalents.

The cooking device of the present disclosure can perform photographing and recognition of features such as shapes, and indoor conditions such as characters by using a camera, and reflect the recognized result to cooking control. Therefore, the microwave oven can be widely used in a heating cooker such as a microwave oven for home use, an electric cooker, and an IH cooking heater, in addition to a microwave oven used in a sales shop.

Description of the reference symbols

100: a microwave oven (heating cooker); 101: a housing; 102: a door; 103: a glass window; 104: a handle; 105: an operation display unit; 106: a liquid crystal display; 107: a time setting button group; 108: a heating start button; 109: a cancel button; 110: a temporary stop button; 201: a heating chamber; 202a, 202 b: a magnetron; 203: heating an object; 204: a camera (imaging unit); 205: illuminating; 300: a control unit; 301: a heating control unit; 302: an identification unit; 303: a light measuring object detection unit; 304: an exposure control unit.