Method for manufacturing food dough and method for manufacturing bakery food

Abstract

To provide a method for manufacturing food dough and a method for manufacturing bakery food that does not depend on the knowledge and experience of craftsmen during manufacturing, and prevents differences in evaluation results due to differences in the skills and individual differences of evaluators. [Solution] A method for manufacturing food dough, comprising: a kneading step of kneading dough containing cereal flours using a mixer; an image acquisition step of photographing the dough being kneaded in the mixer and acquiring a group of analysis images consisting of multiple analysis images using an image acquisition device; an analysis step of analyzing the progress of the dough kneading by analyzing the multiple analysis images; and a control step of controlling the dough manufacturing process based on the results of the analysis step.

Description

[Technical Field]

[0001] The present invention relates to a method for producing food dough and a method for producing bakery food products. [Background Art]

[0002] Dough containing wheat flour is produced, for example, by appropriately adding auxiliary materials to flours mainly composed of wheat flour, further adding water, and kneading the mixture. If this kneading step is too short or excessively performed, it greatly affects the quality of the final secondary processed product, so appropriate management is required.

[0003] The progress of kneading depends on the type of wheat flour raw material, lot differences, and other environments, so it is difficult to control it only by time. As a method for grasping the progress of kneading, for example, a method in which skilled craftsmen evaluate with their five senses based on the ever-changing properties of dough, such as the hardness and color of dough being kneaded in a mixer, is often adopted, and the evaluator needs to acquire craftsmanship that cannot be learned overnight. Particularly for bakery dough, the quality of kneading has a great impact on quality, and experience is required to grasp the progress of kneading.

[0004] Heretofore, as an example of using image analysis in food production management, a method for determining the degree of deterioration of edible oil used in deep-frying cooking for frying foods has been proposed (see, for example, Patent Document 1). [Prior Art Documents] [Patent Documents]

[0005] [Patent Document 1] International Publication No. WO2021 / 200103 [Summary of the Invention] [Problems to be Solved by the Invention]

[0006] As mentioned above, evaluating the progress of dough mixing by evaluators requires not only a great deal of time to acquire the necessary skills, but also the possibility of differences in evaluation results due to variations in the evaluators' abilities and individual differences. Therefore, there is a strong need for manufacturing methods for food dough and bakery products that do not rely on the knowledge and experience of the craftsman, and that prevent differences in evaluation results due to variations in the evaluators' abilities and individual differences.

[0007] The present invention aims to solve the aforementioned problems of the conventional approach and achieve the following objectives. Specifically, the present invention aims to provide a method for manufacturing food dough and a method for manufacturing bakery food that, during manufacturing, does not depend on the knowledge and experience of the craftsman, and prevents differences in evaluation results due to differences in the skill or individual differences of the evaluators. [Means for solving the problem]

[0008] As a result of their research to solve the above problems, the inventors have found that by photographing the dough being kneaded in a mixer, analyzing the dough's texture (including cracking; the same applies hereinafter) through image analysis, and understanding the progress of kneading, particularly the hydration status of the dough, it is possible to control the kneading process and obtain food-grade dough with excellent secondary processing properties.

[0009] The present invention is based on the inventors' knowledge, and the means for solving the above-mentioned problems are as follows: <1> A method for manufacturing food dough, The kneading process involves mixing the dough containing cereal flours using a mixer, The process includes an image acquisition step of photographing the dough being kneaded in the mixer and acquiring a group of analysis images consisting of multiple analysis images using an image acquisition device, The analysis process involves analyzing the progress of the dough mixing by analyzing the aforementioned multiple analysis images, A method for producing food dough, characterized by including a control step that controls the dough manufacturing process based on the results of the analysis step. <2> The above food dough uses grain flours mainly consisting of wheat flour as an ingredient. <1> This is a method for manufacturing food dough as described above. <3> The food dough is bakery dough. <1> or <2> This is a method for manufacturing food dough as described above. <4> The food dough is bread dough. <1> ~ <3> This is a method for producing food dough as described in any of the following. <5> The aforementioned kneading process is a process in which kneading is performed at a low speed. <1> ~ <4> This is a method for producing food dough as described in any of the following. <6> The aforementioned analysis step involves referring to the analysis results of multiple analysis images already obtained to analyze the progress of the dough mixing, The control step involves referring to the analysis results of the progress of dough mixing obtained and controlling the dough manufacturing process. <1> ~ <5> This is a method for producing food dough as described in any of the following. <7> The control step includes determining the endpoint of the mixing step from the results of the analysis step. <1> ~ <6> This is a method for producing food dough as described in any of the following. <8> The aforementioned <1> ~ <7> This is a method for producing bakery food products, characterized by including a step of heating food dough produced by a food dough production method described in any of the above. [Effects of the Invention]

[0010] According to the present invention, it is possible to solve the aforementioned problems in the conventional method, achieve the aforementioned objectives, and provide a method for manufacturing food dough and a method for manufacturing bakery food that does not depend on the knowledge and experience of craftsmen during manufacturing, and prevents differences in evaluation results due to differences in the skill or individual differences of evaluators. [Brief explanation of the drawing]

[0011] [Figure 1] Figure 1 is a block diagram showing the system configuration of an image acquisition device according to a first embodiment, which is an example of the image acquisition process. [Figure 2]FIG. 2 is a diagram for explaining an imaging region in which an imaging apparatus according to a first embodiment, which is an example of an image acquisition step, captures a moving image. [Figure 3] FIG. 3 is a schematic diagram for explaining frame images constituting a moving image according to the first embodiment, which is an example of an image acquisition step, and the time when the moving image is captured. [Figure 4] FIG. 4 is a diagram for explaining pixels constituting an image according to the first embodiment, which is an example of an image acquisition step. [Figure 5] FIG. 5 is a flowchart for explaining an image acquisition step according to the first embodiment, which is an example of an image acquisition step. [Figure 6] FIG. 6 is a block diagram showing the system configuration of an analysis apparatus according to the first embodiment, which is an example of an analysis step. [Figure 7] FIG. 7 is a schematic diagram for explaining analysis images constituting a moving image group according to the first embodiment, which is an example of an analysis step. [Figure 8] FIG. 8 is a flowchart for explaining an analysis step according to the first embodiment, which is an example of an analysis step. [Figure 9] FIG. 9 is a block diagram showing the system configuration of an analysis apparatus according to a second embodiment, which is an example of an analysis step. [Figure 10] FIG. 10 is a flowchart for explaining an analysis step according to the second embodiment, which is an example of an analysis step. [Figure 11] FIG. 11 is a block diagram showing the system configuration of an analysis apparatus according to a third embodiment, which is an example of an analysis step. [Figure 12] FIG. 12 is a flowchart for explaining an analysis method according to the third embodiment, which is an example of an analysis step. [Figure 13] FIG. 13 is a block diagram showing the system configuration of an analysis apparatus according to a fourth embodiment, which is an example of an analysis step. [Figure 14]FIG. 14 is a flowchart for describing an analysis method according to a fourth embodiment, which is an example of an analysis step. [Figure 15] FIG. 15 is a graph showing the change over time in the average number of target pixels in Test Example 1. Description of Embodiments

[0012] (Method for Producing Food Dough) The method for producing food dough of the present invention includes at least a kneading step, an image acquisition step, an analysis step, and a control step, and further includes other steps as necessary.

[0013] <Kneading Step> The kneading step is a step of kneading dough containing cereal flours using a mixer.

[0014] The type of the mixer is not particularly limited and may be appropriately selected according to the purpose, and examples thereof include vertical mixers and horizontal mixers.

[0015] The food dough targeted by the present invention is dough containing cereal flours. The food dough is preferably dough-shaped.

[0016] The food dough is preferably dough to which water is added in an amount of 40 to 100 parts by mass relative to 100 parts by mass of cereal flours.

[0017] The raw material for the food dough is not particularly limited as long as it contains cereal flours, and materials used as known raw materials for food dough can be appropriately selected; however, it is preferable to use cereal flours mainly composed of wheat flour.

[0018] The cereal flours are not particularly limited and may be appropriately selected, and examples thereof include wheat flour, rye flour, barley flour, glutinous barley flour, oat flour, corn flour, rice flour, buckwheat flour, soybean flour, and bran flour. These cereal flours may be used alone, or two or more thereof may be used in combination.

[0019] There are no particular restrictions on the wheat flour mentioned above, and it can be appropriately selected according to the purpose. Examples include strong flour, semi-strong flour, medium flour, weak flour, durum flour, and whole wheat flour. The wheat flour may be used alone or in combination of two or more types.

[0020] Other ingredients besides cereal flours in the aforementioned food dough are not particularly limited and can be appropriately selected according to the purpose. Examples include starches (unprocessed or modified starch), sugars; yeast and sourdough starter; yeast food; leavening agents such as baking soda and baking powder; egg products such as whole egg powder, egg yolk powder, and egg white powder; proteins such as gluten and soy flour; dairy products; oils and fats; additives such as emulsifiers, thickeners, sweeteners, flavorings, colorings, and ascorbic acid; inorganic salts such as sodium chloride; and enzymes. These may be used individually or in combination of two or more.

[0021] Examples of food doughs include bakery dough and noodle dough. The present invention is useful for the production of bakery dough, which requires training to determine the appropriate mixing time, and is particularly useful for the production of bread dough.

[0022] There are no particular restrictions on the types of bakery foods that use the aforementioned bakery dough; they can be appropriately selected according to the purpose, and examples include bread and pizza.

[0023] There are no particular restrictions on the types of bread mentioned above, and they can be selected appropriately depending on the purpose. Examples include sliced ​​bread (e.g., rolls, white bread, dark bread, French bread, hardtack, hot dog buns, croissants, etc.), savory breads, sweet breads, and steamed buns.

[0024] There are no particular restrictions on the manufacturing method of the aforementioned bread products; conventional methods can be used, including the sponge and dough method, the straight dough method, the quick method, and the liquid dough method.

[0025] There are no particular restrictions on the types of noodles that use the aforementioned noodle dough, and they can be appropriately selected according to the purpose. Examples include Chinese noodles, udon, soba, pasta, hiyamugi, and somen.

[0026] -Kneading- There are no particular restrictions on the mixing conditions; they can be selected as appropriate depending on the purpose.

[0027] In bakery dough, including bread dough, the mixing process is divided into two stages: low-speed mixing, which is performed at a relatively slow speed, and high-speed mixing, which is performed at a faster speed. Low-speed mixing is performed for the purpose of dispersing the raw materials and hydrating the flours. High-speed mixing is performed for the purpose of incorporating air and forming gluten. This invention is particularly useful for managing low-speed mixing, which is performed at a low speed.

[0028] <Image acquisition process> The image acquisition step involves photographing the dough being kneaded in the mixer and acquiring a group of analysis images consisting of multiple analysis images using an image acquisition device.

[0029] There are no particular restrictions on the method of the image acquisition process, and it can be appropriately selected according to the purpose. For example, one method is to use all images of the dough as analysis images, or to use images that exclude kneading components such as hooks in the mixer from the captured images as analysis images.

[0030] There are no particular restrictions on when the aforementioned dough is photographed; it can be selected as appropriate depending on the purpose, and it may be photographed during part of the kneading process or during the entire process.

[0031] An example of the image acquisition process is described below.

[0032] [First embodiment of the image acquisition process] As a first embodiment of the image acquisition process, the following describes a method that includes an acquisition step in which the acquisition unit of the image acquisition device acquires a plurality of images of the dough being kneaded in a mixer, and a determination step in which the determination unit of the image acquisition device analyzes the plurality of images and determines whether or not the images can be selected as the analysis images based on the results of the analysis.

[0033] The first embodiment of the image acquisition process includes the following: The determination step involves determining from a plurality of images that an image can be selected as the analysis image in which the kneading member of the mixer is included in a predetermined area or less within the region where the kneading member of the mixer kneads the dough and which is used for analyzing the properties. - To determine whether the image can be selected as the analysis image based on whether the R (red), G (green), and B (blue) values ​​of each pixel in the image are within a predetermined range. The aforementioned images are multiple frame images that constitute a moving image.

[0034] Figure 1 is a block diagram illustrating the system configuration of an image acquisition device that implements a first embodiment of the image acquisition process. As shown in Figure 1, the image acquisition device 2 includes a control unit 4 that comprehensively controls each part of the image acquisition device 2. The control unit 4 is connected to an acquisition unit 6, an image processing unit 8, a discrimination unit 10, a storage unit 12, a elimination unit 14, and a transmission unit 15.

[0035] The acquisition unit 6 acquires a video image M (see Figure 3) captured by a shooting device such as a digital camera (not shown). The video image M captures the dough being placed in the bowl 222 of a vertical mixer as shown in Figure 2 and being kneaded by the hook (kneading member) 224 of the vertical mixer.

[0036] The image processing unit 8 extracts multiple frame images F1 to Fn (n; n is a natural number) necessary for analyzing the roughness of the dough from all frame images F (see Figure 3) of the moving image M acquired by the acquisition unit 6. In this embodiment, the progress of dough mixing is evaluated by analyzing the roughness of the dough during a predetermined time period T1 within the time T from when water is added to the flour until it becomes dough in the kneading process. Therefore, the image processing unit 8 extracts n frame images F1 to Fn that constitute the moving image M1 captured during the predetermined time period T1. Furthermore, the image processing unit 8 performs a trimming process to cut out a partial region A (see Figure 2) from the frame images F1 to Fn that show the entire inside of the bowl 222, which is within the area where the kneading member, the hook 224, kneads the dough and is used for analyzing the roughness of the dough.

[0037] The discrimination unit 10 determines whether an image can be selected as an analysis image from n images S1 to Sn that have been trimmed by the image processing unit 8, in which the hook 224 is contained in a portion region A below a predetermined area. Specifically, the discrimination unit 10 analyzes the values ​​of R (red: integer from 0 to 255), G (green: integer from 0 to 255), and B (blue: integer from 0 to 255) for each pixel in each of the images S1 to Sn.

[0038] The discrimination unit 10 determines whether the analysis results, i.e., the values ​​of R, G, and B (R, G, B), are within a predetermined range. The predetermined range is at least one range of R, G, and B that indicates the color of the hook 224 being photographed (R1~R2, G1~G2, B1~B2) (R1, G1, and B1 are integers from 0 to 254, and R2, G2, and B2 are integers from 1 to 255), which is set in advance and stored in the storage unit 12.

[0039] For example, in the image S1 shown in Figure 4, the discrimination unit 10 determines the (R, G, B) values ​​of all pixels P11 to Pxy, and marks pixel P11 only if it determines that the (R, G, B) values ​​of pixel P11 are within a predetermined range (R1 to R2, G1 to G2, B1 to B2). Similarly, the discrimination unit 10 marks pixels P12 to Pxy only if it determines that the (R, G, B) values ​​of pixels P12 to Pxy are within a predetermined range (R1 to R2, G1 to G2, B1 to B2).

[0040] Furthermore, the discrimination unit 10 determines whether pixels that have been determined to be within a predetermined range, i.e., marked pixels, form a region of a predetermined number or more. For example, in a region formed by adjacent pixels being marked consecutively, such as region A1 shown in Figure 4, the discrimination unit 10 maintains the marking of the pixels forming the region if the number of pixels forming this region is greater than or equal to the predetermined number. On the other hand, the discrimination unit 10 erases the marking of pixels where adjacent pixels are not marked, such as pixel P14 shown in Figure 4. Also, in a region A2 shown in Figure 4, where adjacent pixels are marked consecutively, but the number of pixels forming this region is less than the predetermined number, the discrimination unit 10 erases the marking of the pixels forming this region as well. The predetermined number is set in advance and stored in the storage unit 12.

[0041] Furthermore, the discrimination unit 10 calculates the total number of marked pixels in image S1 and determines whether the calculated total number is greater than or equal to a threshold. If it is determined that the total number of marked pixels is greater than or equal to the threshold, the discrimination unit 10 determines that image S1 cannot be selected as an analysis image. On the other hand, if it is determined that the total number of marked pixels is less than the threshold, the discrimination unit 10 determines that image S1 can be selected as an analysis image. The threshold is set in advance and stored in the storage unit 12.

[0042] The discrimination unit 10, similar to image S1, determines the (R, G, B) values ​​of all pixels in each of images S2 to Sn. Furthermore, similar to image S1, the discrimination unit 10 marks pixels in each of images S2 to Sn that it determines have (R, G, B) values ​​within a predetermined range, and erases the markings of pixels that do not form a predetermined number of consecutive regions. Similar to image S1, the discrimination unit 10 also determines whether each of images S2 to Sn can be selected as an analysis image based on the total number of marked pixels.

[0043] As described above, the storage unit 12 stores a predetermined range used for analyzing images S1 to Sn, a predetermined number and threshold used for discrimination by the discrimination unit 10, etc. The exclusion unit 14 excludes images that the discrimination unit 10 has determined not to be selectable as analysis images. The transmission unit 15 transmits a group of images, i.e., a group of analysis images, that the discrimination unit 10 has determined to be selectable as analysis images, to the analysis device 1.

[0044] Next, the image acquisition process will be described using the image acquisition device 2 according to this first embodiment. Figure 5 is a flowchart illustrating the process performed by the control unit 4 to acquire the analysis image group.

[0045] First, the control unit 4 instructs the acquisition unit 6 to acquire a moving image M (see Figure 3) which is composed of multiple frame images F taken by the camera device of the dough being kneaded in the vertical mixer (step S10).

[0046] Next, the control unit 4 instructs the image processing unit 8 to extract n frame images F1 to Fn that constitute the moving image M1 captured during a predetermined time period T1 from all frame images F (see Figure 3) that constitute the moving image M acquired in step S10, as images necessary for analyzing the roughness of the fabric (step S11).

[0047] Next, the control unit 4 instructs the image processing unit 8 to crop a portion of the frame image F1, which shows the entire inside of the bowl 222, from a portion A (see Figure 2) within the area where the hook 224 kneads the dough and which is used for analyzing the roughness of the dough (step S12), thereby generating image S1.

[0048] Next, the control unit 4 instructs the discrimination unit 10 to analyze the R, G, and B values ​​of pixel P11 (see Figure 4) that constitutes the image S1 generated in step S12 (step S13). The control unit 4 then instructs the discrimination unit 10 to determine whether the R, G, and B values ​​(R, G, B) analyzed in step S13 are within a predetermined range (step S14). If it is determined in step S14 that the (R, G, B) values ​​of pixel P11 are within the predetermined range (step S14: Yes), the control unit 4 instructs the discrimination unit 10 to mark pixel P11 (step S15). On the other hand, if it is determined in step S14 that the (R, G, B) values ​​of pixel P11 are outside the predetermined range (step S14: No), the control unit 4 proceeds to the process in step S16.

[0049] The control unit 4 determines whether the processing in steps S13 to S15 has been completed for all pixels of the image S1 (step S16). If it is determined in step S16 that the processing in steps S13 to S15 has not been completed for all pixels of the image S1 (step S16: No), the control unit 4 returns to the processing in step S13 and repeats the processing in steps S13 to S16 until the processing in steps S13 to S15 has been completed for all pixels (P12 to Pxy) of the image S1.

[0050] On the other hand, if in step S16 it is determined that the processing in steps S13 to S15 has been completed for all pixels of image S1 (up to pixel Pxy) (step S16: Yes), the control unit 4 causes the discrimination unit 10 to determine whether the pixels that were determined to be within a predetermined range in step S14 and marked in step S15 form a predetermined number or more consecutive region (step S17). If in step S17 it is determined that the marked pixels form a predetermined number or more consecutive region (for example, region A1 shown in Figure 4) (step S17: Yes), the control unit 4 maintains the marking of the pixels that form a predetermined number or more consecutive region. On the other hand, if in step S17 it is determined that the marked pixels do not form a predetermined number or more consecutive region (for example, region A2 and pixel P14 shown in Figure 4) (step S17: No), the control unit 4 causes the discrimination unit 10 to erase the marking of the pixels that do not form a predetermined number or more consecutive region (step S18).

[0051] Next, the control unit 4 instructs the discrimination unit 10 to calculate the total number of marked pixels in image S1 and to determine whether the calculated total number is greater than or equal to a threshold (step S19). If the discrimination unit 10 determines in step S19 that the total number of marked pixels is greater than or equal to the threshold (step S19: Yes), the discrimination unit 10 determines that image S1 is unsuitable as an analysis image, and the control unit 4 receives the discrimination result from the discrimination unit 10. The control unit 4 then determines that since the hook 224 is visible in region A1, etc., of image S1, image S1 is unsuitable as an analysis image for analyzing the roughness of the fabric, and instructs the exclusion unit 14 to exclude image S1 (step S20). On the other hand, if the discrimination unit 10 determines in step S19 that the total number of marked pixels is less than the threshold (step S19: No), the discrimination unit 10 determines that image S1 is suitable as an analysis image, and the control unit 4 receives the discrimination result from the discrimination unit 10. The control unit 4 then determines that the hook 224 is not visible in image S1 because there are no marked pixels or only a few marked pixels, or even if the hook 224 is visible, it is not to an extent that would hinder the analysis of the fabric's texture, and selects image S1 as the analysis image for analyzing the fabric's texture (step S21).

[0052] The control unit 4 determines whether the processing in steps S12 to S21 has been completed for all frame images (step S22). If it is determined in step S22 that the processing in steps S12 to S21 has not been completed for all frame images (step S22: No), the control unit 4 returns to the processing in step S12 and repeats the processing in steps S12 to S21 until the processing in steps S12 to S21 has been completed for all frame images (F2 to Fn).

[0053] On the other hand, if it is determined in step S22 that the processing in steps S12 to S21 has been completed for all frame images (up to frame image Fn) (step S22: Yes), the control unit 4 transmits all the images selected as analysis images in step S21 to the analysis device 1 via the transmission unit 15 (step S23).

[0054] In the first embodiment of the image acquisition process, the example given was that the exclusion unit 14 excludes images in which the hook 224 is visible in an area larger than a predetermined area. However, the configuration may also exclude a predetermined number of images in descending order of the area containing the hook 224 (in descending order of the number of marked pixels).

[0055] Alternatively, instead of excluding the image containing hook 224 (for example, image S1 in Figure 4), the region containing hook 224 (for example, region A1 in Figure 4) can be excluded from the analysis, and the region not containing hook 224 (for example, the region other than region A1 in Figure 4) can be used as the analysis image, thereby allowing the image containing hook 224 (for example, image S1 in Figure 4) to be used for analysis.

[0056] Furthermore, in the first embodiment of the image acquisition process, the case in which the image acquisition device 2 acquires moving images, etc., captured by a photographing device (not shown) was described as an example. However, the image acquisition device 2 may also be configured to include a photographing unit, and the photographing unit may be configured to photograph the dough during mixing.

[0057] Furthermore, although the first embodiment of the image acquisition process was described using the case where the image acquisition device 2 acquires moving images as an example, it is also possible to acquire multiple still images that have been continuously captured (burst shooting) and use multiple still images captured during a predetermined time period T1 instead of frame images F1 to Fn to select the analysis image.

[0058] Furthermore, the discrimination step may involve using an image recognition model trained with multiple training images of the dough being kneaded in the mixer as input values ​​and the analysis results of the training images as output values ​​to determine whether or not multiple images can be selected as the analysis images.

[0059] Furthermore, in the first embodiment of the image acquisition process, analysis images were selected after the fabric was photographed, but it is also possible to determine whether or not the fabric can be selected as an analysis image before photographing it. For example, the method may include a detection step in which the detection unit of the image acquisition device determines whether or not the mixing member of the mixer is present in a partial region used for analyzing the roughness of the fabric within the region in which the mixing member of the mixer mixes the fabric, and a shooting step in which, if it is determined in the detection step that the mixing member is not present, the shooting unit of the image acquisition device takes an image of the fabric being mixed in the mixer as the analysis image.

[0060] <Analysis process> The analysis step involves analyzing the progress of the dough mixing by analyzing the multiple analysis images.

[0061] In the analysis process described above, the degree of dough roughness (the degree of shadows in the analysis images) is quantified by analyzing the multiple analysis images, thereby allowing the progress of dough mixing to be determined.

[0062] As shown in the [Examples] section below, the degree of shading in the analysis image (e.g., the average number of target pixels) fluctuates for a while after mixing begins, but tends to decrease as mixing progresses, bottoms out at the optimal end of mixing, and then shows an increasing trend. Note that continuing mixing after bottoming out will degrade the quality of the final product.

[0063] Therefore, by analyzing the degree of roughness of the dough, it is possible to understand the progress of the dough mixing.

[0064] As for the method of the aforementioned analysis process, there are no particular restrictions as long as it is possible to analyze the degree of roughness of the dough from multiple analysis images and grasp the progress of the dough mixing; it can be appropriately selected according to the purpose.

[0065] The multiple analysis images (group of analysis images) analyzed in the aforementioned analysis step may represent a part of the mixing process or the entire process, as long as the progress of the mixing can be understood.

[0066] The aforementioned analysis process can also be carried out by referring to the analysis results of multiple previously acquired analysis images (information acquired in advance) and analyzing the progress of the dough mixing.

[0067] An example of the analysis process is described below.

[0068] [First embodiment of the analysis process] As a first embodiment of the analysis process, the method for analyzing the roughness of the dough and understanding the progress of dough mixing is described below. This method includes: a feature value acquisition step for acquiring the feature value of each pixel constituting the analysis image; an average feature value calculation step for calculating the average feature value of the analysis image from the feature value of each pixel; a standard feature value calculation step for calculating the standard feature value of the analysis image group from the average feature value of each analysis image; a selection step for calculating the difference between the feature value of each pixel and the standard feature value, and selecting the pixels whose difference exceeds a predetermined value as the target pixels; a count calculation step for calculating the number of target pixels for each analysis image; and an average count calculation step for calculating the average number of target pixels in the analysis image group from the number of target pixels in each analysis image.

[0069] A first embodiment of the analysis process includes the following: The aforementioned feature value is luminance. The selection step involves selecting as the target pixels any pixels whose difference exceeds the predetermined value and which are connected to a predetermined number or more other pixels whose difference exceeds the predetermined value.

[0070] Figure 6 is a block diagram illustrating the system configuration of the analysis apparatus 1 that implements the first embodiment of the analysis process. As shown in Figure 6, the analysis apparatus 1 includes a control unit 20 that comprehensively controls each part of the analysis apparatus 1. The control unit 20 is connected to an image group acquisition unit 22, an analysis unit 24, and a storage unit 38.

[0071] The image group acquisition unit 22 acquires an analysis image group C from the image acquisition device 2, which consists of multiple analysis images U1 to Un taken of dough being kneaded in a mixer as shown in Figure 7. The analysis unit 24 includes a brightness acquisition unit 26, an average brightness calculation unit 28, a standard brightness calculation unit 30, a selection unit 32, a count calculation unit 34, and an average count calculation unit 36, and analyzes the multiple analysis images U1 to Un that make up the analysis image group C.

[0072] The luminance acquisition unit 26 acquires the luminance of each pixel that makes up the analysis images U1 to Un. Specifically, the luminance acquisition unit 26 acquires the R, G, and B values ​​for each of the pixels D11 to Dxy (see Figure 7) that make up the analysis image U1, and converts them to luminance using the conversion formula (luminance = 0.229R + 0.587G + 0.114B) to convert the analysis image U1 to grayscale and acquires the luminance Y11 to Yxy for each pixel D11 to Dxy. The luminance acquisition unit 26 also converts the analysis images U2 to Un to grayscale in the same way as the analysis image U1 and acquires the luminance of each pixel. By converting the R, G, and B values ​​to luminance and converting to grayscale, the degree of roughness of the dough can be reliably detected even if the color of the dough differs depending on the type of flour and the proportion ratio.

[0073] The average brightness calculation unit 28 calculates the average brightness of the analyzed images U1 to Un from the brightness of each pixel. Specifically, the average brightness calculation unit 28 calculates the average brightness Ya1 of the analyzed image U1 by dividing the sum of the brightness Y11 to Yxy of pixels D11 to Dxy of the analyzed image U1 by the number of pixels in the analyzed image U1. The average brightness calculation unit 28 also calculates the average brightness Ya2 to Yan for the analyzed images U2 to Un in the same manner as for the analyzed image U1.

[0074] The standard brightness calculation unit 30 calculates the standard brightness Ys of the analysis image group C from the average brightness Ya1 to Yan of each of the analysis images U1 to Un. Specifically, the standard brightness calculation unit 30 calculates the standard brightness Ys, which is the value obtained by dividing the sum of the average brightness Ya1 to Yan by the number of analysis images U1 to Un.

[0075] The selection unit 32 calculates the difference V11 to Vxy between the brightness Y11 to Yxy of each pixel D11 to Dxy and the standard brightness Ys, and selects (marks) as target pixels any pixels whose calculated difference exceeds a predetermined value and which are connected to a predetermined number of other pixels whose calculated difference exceeds the predetermined value. The predetermined value and predetermined number are set in advance and stored in the storage unit 38. Specifically, for example, the selection unit 32 calculates the difference V11 (=Y11-Ys) between the brightness Y11 and the standard brightness Ys of pixel D11 in the analyzed image U1. If the difference V11 does not exceed the predetermined value, pixel D11 is not marked as a target pixel. On the other hand, if the difference V11 exceeds the predetermined value, and pixel D11 is connected to a predetermined number of other pixels (D12, D21, D22) whose difference V11 exceeds the predetermined value, as shown in region A3 in Figure 7, then pixel D11 is marked as a target pixel as shown in Figure 7. In contrast, even if the difference V11 exceeds a predetermined value, the selection unit 32 will not mark pixel D11 as a target pixel if it is not connected to a predetermined number of other pixels (D12, D21, D22, etc.) whose difference V11 exceeds the predetermined value. The predetermined value and predetermined number are not particularly limited as long as they can distinguish between rough and smooth parts of the fabric and mark the rough parts of the fabric as target pixels, and can be appropriately selected according to the purpose.

[0076] The selection unit 32 calculates the difference V12 to Vxy between the brightness Y12 to Yxy and the standard brightness Ys for pixels D12 to Dxy, similar to pixel D11. It then determines whether or not to select pixels D12 to Dxy as target pixels based on whether or not the difference exceeds a predetermined value, and if so, whether or not a predetermined number of pixels are connected to other pixels that also exceed the predetermined value.

[0077] Furthermore, the selection unit 32 calculates the difference between each luminance and the standard luminance Ys for each of the analysis images U2 to Un, similar to the analysis image U1. Based on whether the calculated difference exceeds a predetermined value, and if the calculated difference exceeds a predetermined value, whether it is connected to other pixels that exceed the predetermined value in a predetermined number of consecutive pixels or more, the selection unit 32 determines whether to select each pixel constituting each of the analysis images U2 to Un as a target pixel.

[0078] The counting unit 34 calculates the number of target pixels for each of the analysis images U1 to Un. Specifically, the counting unit 34 calculates, for example, the number of pixels selected as target pixels from pixels D11 to Dxy in analysis image U1. Similarly, for analysis images U2 to Un, the counting unit 34 calculates the number of pixels selected as target pixels from the pixels that make up each of the analysis images U2 to Un.

[0079] The average count calculation unit 36 ​​calculates the average number of target pixels in the analysis image group C from the number of target pixels in each of the analysis images U1 to Un. Specifically, the average count calculation unit 36 ​​calculates the average number of target pixels in the analysis image group C, which is the value obtained by dividing the sum of the number of target pixels in each of the analysis images U1 to Un by the number of analysis images U1 to Un. The average number of target pixels can be calculated, for example, as a moving average over a predetermined period. There are no particular restrictions on the predetermined period, and it can be appropriately selected according to the purpose, for example, from 1 second to 1 minute.

[0080] The analysis unit 24 analyzes the roughness of the dough based on the calculation result by the average number calculation unit 36, that is, the average number of target pixels in the analysis image group C, and grasps the progress of kneading. Specifically, the analysis unit 24 assigns an evaluation score to assess the progress of dough kneading based on the average number of target pixels in the analysis image group C. When the average number of target pixels in the analysis image group is small, the dough is of good quality and the evaluation score is high, and when the average number of target pixels in the analysis image group is large, the dough is of poor quality and the evaluation score is low.

[0081] The storage unit 38 stores the predetermined values ​​and predetermined numbers used when selecting target pixels in the selection unit 32.

[0082] Next, the analysis process will be described using the analysis apparatus 1 according to this first embodiment. Figure 8 is a flowchart illustrating the process performed by the control unit 20 to analyze the progress of dough mixing.

[0083] First, the control unit 20 instructs the image acquisition unit 22 to acquire an analysis image group C (see Figure 7), which consists of multiple analysis images U1 to Un taken of the dough being kneaded in the mixer, from the image acquisition device 2 (step S110).

[0084] Next, the control unit 20 instructs the brightness acquisition unit 26 to acquire the brightness of pixels D11 that make up the analysis image U1 (step S111). The brightness acquisition unit 26 converts the R, G, and B values ​​of pixels D11 that make up the analysis image U1 into brightness Y11 using a conversion formula. The control unit 20 determines whether or not brightness has been acquired for all pixels D11 to Dxy of the analysis image U1 (step S112). If it has not been acquired (step S112: No), it returns to the process in step S111 and acquires the brightness Y12... of the next pixel D12.... The control unit 20 repeats the processes in steps S111 and S112 until it has finished acquiring the brightness Y11 to Yxy of all pixels D11 to Dxy of the analysis image U1 (step S112: No).

[0085] Once the brightness Y11 to Yxy of all pixels D11 to Dxy in the analysis image U1 has been acquired (step S112: Yes), the control unit 20 instructs the average brightness calculation unit 28 to calculate the average brightness Ya1 of the analysis image U1 (the sum of brightness Y11 to Yxy divided by the number of pixels D11 to Dxy) from the brightness Y11 to Yxy of each pixel D11 to Dxy (step S113). The control unit 20 determines whether or not the average brightness has been calculated for all analysis images U1 to Un (step S114). If it has not been calculated (step S114: No), it returns to the process in step S111 and acquires the average brightness Ya2 for the next analysis image U2... The control unit 20 repeats the process in steps S111 to S114 until the average brightness Ya1 to Yan of all analysis images U1 to Un has been acquired (step S114: No).

[0086] Once the average brightness Ya1 to Yan of all analysis images U1 to Un has been obtained (step S114: Yes), the control unit 20 instructs the standard brightness calculation unit 30 to calculate the standard brightness Ys of the analysis image group C, which is the sum of the average brightness Ya1 to Yan of each analysis image U1 to Un divided by the number of analysis images U1 to Un (step S115). Next, the control unit 20 instructs the selection unit 32 to calculate the difference V11 between the brightness Y11 of pixel D11 and the standard brightness Ys (step S116). The control unit 20 determines whether or not the difference V11 to Vxy between the brightness Y11 to Yxy and the standard brightness Ys has been calculated for all pixels D11 to Dxy of the analysis image U1 (step S117). If it has not been calculated (step S117: No), it returns to the process in step S116 and obtains the difference V12 for the next pixel D12... The control unit 20 repeats the processes in steps S116 and S117 until it has finished calculating the difference V11 to Vxy for all pixels D11 to Dxy of the analyzed image U1 (step S117: No).

[0087] Once the difference V11 to Vxy has been calculated for all pixels D11 to Dxy of the analysis image U1 (Step S117: Yes), the control unit 20 instructs the selection unit 32 to determine whether the difference V11 calculated in Step S116 exceeds a predetermined value (Step S118). If the difference V11 exceeds a predetermined value (Step S118: Yes), the control unit 20 instructs the selection unit 32 to determine whether pixel D11 is connected to other pixels (D12, D21, D22, etc.) whose differences (V12, V21, V22, etc.) exceed a predetermined value in a predetermined number of steps (Step S119: Yes). If pixel D11 is connected to other pixels whose differences exceed a predetermined value in a predetermined number of steps (Step S119: Yes), the control unit 20 instructs the selection unit 32 to select (mark) pixel D11 as the target pixel (Step S120).

[0088] On the other hand, if the difference V11 does not exceed a predetermined value (step S118: No), or if pixel D11 is not connected to other pixels whose difference exceeds a predetermined value in a predetermined number of consecutive pixels (step S119: No), the control unit 20 proceeds to the process in step S121.

[0089] The control unit 20 determines whether the processing in steps S118 to S120 has been completed for all pixels D11 to Dxy of the analyzed image U1 (step S121). If it has not been completed (step S121: No), it returns to the processing in step S118 and executes the processing in steps S118 to S121 for pixel D12. The control unit 20 repeats the processing in steps S118 to S121 for pixels D11 to Dxy in order until the processing in steps S118 to S121 has been completed for all pixels D11 to Dxy of the analyzed image U1 (step S121: No).

[0090] When the processing in steps S118 to S121 is completed for all pixels D11 to Dxy of the analysis image U1 (step S121: Yes), the control unit 20 instructs the counting unit 34 to calculate the number of target pixels of the analysis image U1 that were marked in step S20 (step S22). Next, the control unit 20 determines whether or not the number of target pixels has been calculated for all analysis images U1 to Un (step S123). If it has not been calculated (step S123: No), it returns to the process in step S16 and executes the processing in steps S116 to S123 for the analysis image U2. The control unit 20 repeats the processing in steps S116 to S123 for each analysis image U1 to Un in order until the number of target pixels has been calculated for all analysis images U1 to Un (step S123: No).

[0091] Once the number of target pixels has been calculated for all analysis images U1 to Un (Step S123: Yes), the control unit 20 instructs the average number calculation unit 36 ​​to calculate the average number of target pixels in the analysis image group C (the sum of the number of target pixels in each analysis image U1 to Un divided by the number of analysis images U1 to Un) from the number of target pixels in each analysis image U1 to Un calculated in Step S122 (Step S124). Then, the control unit 20 instructs the analysis unit 24 to analyze the roughness of the dough and the progress of dough mixing based on the average number of target pixels in the analysis image group C calculated in Step S124 (Step S125).

[0092] According to the first embodiment of the analysis process, since the fabric is analyzed based on the brightness of each pixel in the analysis images U1 to Un (images in which the hook 224 is not visible), the degree of fabric roughness can be automatically and accurately analyzed even for various fabrics (fabrics with different color tones), and fabric roughness can be detected.

[0093] In the first embodiment, luminance was used as an example to explain the feature value of pixels D11 to Dxy, but other quantifiable values ​​such as brightness, saturation, or a specific color (for example, at least one of the R, G, and B values) may also be used as the feature value of pixels D11 to Dxy.

[0094] [Second embodiment of the analysis process] Next, as a second embodiment of the analysis process, a method for analyzing the roughness of the dough and understanding the progress of dough mixing will be described below, which includes: an intensity acquisition step for acquiring the edge intensity detected by the Canny edge detection unit of the analyzer for each pixel constituting the analysis image; a selection step for selecting as target pixels pixels whose edge intensity exceeds a first predetermined value, and pixels whose edge intensity is less than or equal to the first predetermined value but greater than or equal to a second predetermined value which is less than the first predetermined value and is connected to other pixels that exceed the first predetermined value; a count calculation step for calculating the number of target pixels for each analysis image; and an average count calculation step for calculating the average number of target pixels in the analysis image group from the number of target pixels in each analysis image.

[0095] Figure 9 is a block diagram illustrating the system configuration of an analytical apparatus for implementing the second embodiment of the analysis process described above. Note that, for the analytical apparatus according to this second embodiment, the same reference numerals are used for components identical to those shown in Figure 6, and their descriptions are omitted. As shown in Figure 9, the analytical apparatus 41 includes a control unit 50 that comprehensively controls each part of the analytical apparatus 41. The control unit 50 is connected to an image acquisition unit 22, an analysis unit 54, and a storage unit 58.

[0096] The analysis unit 54 includes a Canny edge detection unit 55, a selection unit 62, a count calculation unit 34, and an average count calculation unit 36, and analyzes multiple analysis images U1 to Un (see Figure 7) that constitute the analysis image group C.

[0097] The Canny edge detection unit 55 detects edge intensity using the Canny edge detection algorithm to detect edges (contours and boundaries) within the image (analysis images U1 to Un). Specifically, the Canny edge detection unit 55 converts the analysis images U1 to Un to grayscale and detects edge intensity for each pixel constituting the grayscale-converted analysis images U1 to Un (for example, edge intensity E11 to Exy for pixels D11 to Dxy (see Figure 7) constituting the analysis image U1).

[0098] The selection unit 62 selects as target pixels pixels whose edge strength exceeds a first predetermined value Lmax, and pixels whose edge strength is less than or equal to the first predetermined value Lmax but less than the first predetermined value Lmax and greater than or equal to a second predetermined value Lmin (Lmax > Lmin), and which are adjacent to other pixels whose edge strength exceeds the first predetermined value Lmax. That is, (1) if the value of the edge strength exceeds the first predetermined value Lmax, the pixel with that edge strength is selected as a target pixel. Also, (2) if the value of the edge strength is less than or equal to the first predetermined value Lmax and greater than or equal to the second predetermined value Lmin, and which are adjacent to other pixels with an edge strength exceeding the first predetermined value Lmax, then the pixel with that edge strength is selected as a target pixel. On the other hand, (3) if the value of the edge strength is less than or equal to the first predetermined value Lmax and greater than or equal to the second predetermined value Lmin, then which are not adjacent to other pixels with an edge strength exceeding the first predetermined value Lmax, then the pixel with that edge strength is not selected as a target pixel. Also, (4) if the value of the edge strength is less than the second predetermined value Lmin, then the pixel with that edge strength is not selected as a target pixel.

[0099] The analysis unit 54 analyzes the roughness of the dough based on the calculation result by the average number calculation unit 36, i.e., the average number of target pixels in the analysis image group C, and grasps the progress of mixing. The storage unit 58 stores the above-mentioned first predetermined value and second predetermined value, etc., which are used when selecting target pixels in the selection unit 62.

[0100] Next, the analysis process will be described using the analysis device 41 according to this second embodiment. Figure 10 is a flowchart illustrating the process performed by the control unit 50 to analyze the progress of dough mixing.

[0101] First, the control unit 50 instructs the image acquisition unit 22 to acquire an analysis image group C (see Figure 7), which consists of multiple analysis images U1 to Un taken of the dough being kneaded in the mixer, from the image acquisition device 2 (step S230).

[0102] Next, the control unit 50 converts the analysis images U1 to Un into grayscale and obtains the edge intensity E11 detected by the Canny edge detection unit 55 for each pixel D11 that makes up the grayscale-converted analysis image U1 (step S231). The control unit 50 determines whether or not edge intensity E11 to Exy has been obtained for all pixels D11 to Dxy of the analysis image U1 (step S232). If it has not been obtained (step S232: No), it returns to the process in step S231 and obtains the edge intensity E12 to Exy for the next pixel D12 to Exy. The control unit 50 repeats the processes in steps S231 and S232 until it has finished obtaining the edge intensity E11 to Exy for all pixels D11 to Dxy of the analysis image U1 (step S232: No).

[0103] Once the edge intensities E11 to Exy of all pixels D11 to Dxy of the analyzed image U1 have been acquired (step S232: Yes), the control unit 50 instructs the selection unit 32 to determine whether the edge intensity E11 acquired in step S231 exceeds a first predetermined value Lmax (step S233). If the edge intensity E11 exceeds the first predetermined value Lmax (step S233: Yes), the control unit 50 instructs the selection unit 32 to perform the process in step S236, i.e., to select (mark) pixel D11 as the target pixel (step S236).

[0104] On the other hand, if the edge strength E11 does not exceed the first predetermined value Lmax (step S233: No), the control unit 50 causes the selection unit 32 to determine whether the edge strength E11 is equal to or greater than the second predetermined value Lmin (step S234). If the edge strength E11 is equal to or greater than the second predetermined value Lmin (step S234: Yes), the control unit 50 determines whether the pixel D11 is connected to another pixel that exceeds the first predetermined value Lmax (step S235). If the pixel D11 is connected to another pixel that exceeds the first predetermined value Lmax (step S235: Yes), the control unit 50 causes the selection unit 32 to perform the process in step S236, i.e., to select (mark) the pixel D11 as the target pixel (step S236).

[0105] On the other hand, if the edge intensity E11 is less than or equal to the second predetermined value Lmin (step S234: No), or if pixel D11 is not connected to any other pixels with an edge intensity exceeding the first predetermined value Lmax (step S235: No), the control unit 50 does not select pixel D11 as a target pixel. That is, (1) if the value of edge intensity E11 exceeds the first predetermined value Lmax, and (2) if the value of edge intensity E11 is less than or equal to the first predetermined value Lmax and greater than or equal to the second predetermined value Lmin, and is connected to any other pixels with an edge intensity exceeding the first predetermined value Lmax, then pixel D11 is selected as a target pixel. On the other hand, (3) if the value of edge intensity E11 is less than or equal to the first predetermined value Lmax and greater than or equal to the second predetermined value Lmin, and is not connected to any other pixels with an edge intensity exceeding the first predetermined value Lmax, and (4) if the value of edge intensity is less than the second predetermined value Lmin, then pixel D11 is not selected as a target pixel.

[0106] The control unit 50 determines whether the processing in steps S233 to S236 has been completed for all pixels D11 to Dxy of the analyzed image U1 (step S237). If it has not been completed (step S237: No), it returns to the processing in step S233 and executes the processing in steps S233 to S237 for pixel D12. The control unit 50 repeats the processing in steps S233 to S237 for pixels D11 to Dxy in order until the processing in steps S233 to S237 has been completed for all pixels D11 to Dxy of the analyzed image U1 (step S237: No).

[0107] When the processing in steps S233 to S237 is completed for all pixels D11 to Dxy of the analysis image U1 (step S237: Yes), the control unit 50 instructs the counting unit 34 to calculate the number of target pixels of the analysis image U1 that were marked in step S236 (step S238). Next, the control unit 50 determines whether or not the number of target pixels has been calculated for all analysis images U1 to Un (step S239). If it has not been calculated (step S239: No), it returns to the process in step S31 and executes the processing in steps S231 to S239 for the analysis image U2. The control unit 50 repeats the processing in steps S231 to S239 for each analysis image U1 to Un in order until the number of target pixels has been calculated for all analysis images U1 to Un (step S239: No).

[0108] Once the number of target pixels has been calculated for all analysis images U1 to Un (step S239: Yes), the control unit 50 proceeds to steps S240 and S241. Note that the processes in steps S240 and S241 are the same as the processes in steps S124 and S125 shown in Figure 8, so their explanation is omitted.

[0109] According to the second embodiment of the analysis process, since the fabric is analyzed based on the edge strength obtained by Canny edge detection in each of the analysis images U1 to Un (images in which the hook 224 is not visible), the degree of fabric roughness can be automatically and accurately analyzed, and fabric roughness can be detected.

[0110] [Third embodiment of the analysis process] Next, as a third embodiment of the analysis process, a method for analyzing the roughness of the dough and understanding the progress of dough mixing will be described below, which includes: an intensity acquisition step for acquiring the edge intensity detected by the Canny edge detection unit of the analyzer for each pixel constituting the analysis image; a selection step for selecting as target pixels pixels whose edge intensity exceeds a first predetermined value, and pixels whose edge intensity is less than or equal to the first predetermined value but greater than or equal to a second predetermined value which is smaller than the first predetermined value and which are connected to other pixels that exceed the first predetermined value; and a fractal dimension calculation step for calculating the fractal dimension for the edge image created by the target pixels for each analysis image.

[0111] Figure 11 is a block diagram illustrating the system configuration of an analytical apparatus for implementing the third embodiment of the analysis process. Note that, for the analytical apparatus according to this third embodiment, the same reference numerals are used for components identical to those shown in Figure 9, and their descriptions are omitted. As shown in Figure 11, the analytical apparatus 71 includes a control unit 80 that comprehensively controls each part of the analytical apparatus 71. The control unit 80 is connected to an image acquisition unit 22, an analysis unit 84, and a storage unit 58.

[0112] The analysis unit 84 comprises a Canny edge detection unit 55, a selection unit 62, and a fractal dimension calculation unit 86, and analyzes multiple analysis images U1 to Un (see Figure 7) that constitute the analysis image group C. The fractal dimension calculation unit 86 calculates the fractal dimension, which is a value representing the degree to which a person recognizes an edge (complexity) in an image, for each analysis image U1 to Un, for the edge image (black and white binarized image) created by the target pixel. The fractal dimension calculation unit 86 also calculates the average fractal dimension of the analysis image group C based on the fractal dimensions of each analysis image U1 to Un.

[0113] The analysis unit 84 analyzes the roughness of the dough based on the calculation results from the fractal dimension calculation unit 86 and grasps the progress of kneading. When the fractal dimension value is small, the complexity of the edges is low, the texture of the dough is good, and the evaluation score is high. When the fractal dimension value is large, the complexity of the edges is high, the texture of the dough is poor, and the evaluation score is low.

[0114] Next, the analysis process will be described using the analysis apparatus 71 according to this third embodiment. Figure 12 is a flowchart illustrating the process performed by the control unit 80 to analyze the progress of dough mixing. Note that the process from steps S350 to S357 shown in Figure 12 is the same as the process from steps S230 to S237 shown in Figure 10, so its explanation will be omitted.

[0115] When the processing in steps S353 to S357 is completed for all pixels D11 to Dxy of the analysis image U1 (step S357: Yes), the control unit 80 instructs the fractal dimension calculation unit 86 to calculate the fractal dimension for the edge image created by the target pixels in the analysis image U1 (step S358). Next, the control unit 80 determines whether or not the calculation of the fractal dimension for the edge image created by the target pixels in all analysis images U1 to Un has been completed (step S359). If it has not been completed (step S359: No), it returns to the processing in step S51 and executes the processing in steps S351 to S359 for the analysis image U2. The control unit 80 repeats the processing in steps S351 to S359 for the analysis images U1 to Un in order until the calculation of the fractal dimension for the edge image created by the target pixels in all analysis images U1 to Un has been completed (step S359: No).

[0116] Once the fractal dimension has been calculated for all analysis images U1 to Un, based on the edge images created by the target pixels (step S359: Yes), the control unit 80 instructs the fractal dimension calculation unit 86 to calculate the average fractal dimension of the analysis image group C based on the fractal dimensions of each analysis image U1 to Un (step S360). Next, the control unit 80 instructs the analysis unit 84 to analyze the roughness of the fabric based on the average fractal dimension of the analysis image group C calculated in step S360 (step S361).

[0117] According to the third embodiment, since the fabric is analyzed based on the edge strength and fractal dimension obtained by Canny edge detection in each of the analysis images U1 to Un (images in which the hook 224 is not visible), the degree of fabric roughness can be automatically and accurately analyzed, and fabric roughness can be detected.

[0118] In addition, in the second and third embodiments of the analysis process described above, a smoothing step may be further included in which the analysis image acquired in the image acquisition step is smoothed, and the analysis process may be configured to analyze the smoothed analysis image. In this case, the analysis device may further include a smoothing unit that smooths the analysis images U1 to Un acquired from the image acquisition device 2, and the analysis images U1 to Un may be smoothed before Canny edge detection. An example of a smoothing filter used for image smoothing is a Gaussian filter.

[0119] [Fourth embodiment of the analysis process] Next, as a fourth embodiment of the analysis process, a method for analyzing the analysis images will be described below, using an image recognition model that has been trained using multiple training images of the dough being kneaded in the mixer as input values ​​and the analysis results of the training images as output values.

[0120] Figure 13 is a block diagram illustrating the system configuration of an analytical apparatus for implementing the fourth embodiment of the analysis process. Note that, for the analytical apparatus according to this fourth embodiment, the same reference numerals are used for components identical to those shown in Figure 6, and their descriptions are omitted. As shown in Figure 13, the analytical apparatus 91 includes a control unit 90 that comprehensively controls each part of the analytical apparatus 91. The control unit 90 is connected to an image acquisition unit 22, an analysis unit 92, and a storage unit 94.

[0121] The analysis unit 92 uses the image classification model (image recognition model) 96 stored in the memory unit 94 to analyze the analysis images U1 to Un that make up the analysis image group C acquired by the image group acquisition unit 22 from the image acquisition device 2. The image classification model 96 is a pre-trained model that uses AI (artificial intelligence) to analyze the degree of roughness of the dough shown in the analysis images U1 to Un. It is a model that has been trained using multiple training images taken of dough being kneaded with the mixer hook 224 as input values ​​and the analysis results of the training images as output values. The image classification model 96 is an image recognition model constructed using image classification within image recognition technology, and is constructed by following the procedure below. First, the model creator classifies the numerous training images taken for machine learning into five categories: (1) a group of training images with no imperfections in the fabric (1 point), (2) a group of training images with almost no imperfections in the fabric (2 points), (3) a group of training images with some imperfections in the fabric (3 points), (4) a group of training images with imperfections in the fabric (4 points), and (5) a group of training images with many imperfections in the fabric (5 points). Next, the numerous training images before classification are used as input values, and the classification result after classification, i.e., one of the scores from the above classifications (1) to (5), is used as the output value for machine learning. Finally, the system is configured to output the probability that the input analysis image falls into each of the above classifications (1) to (5) (for example, for analysis image U11, the probability of (1) being 1 point is 1.1%, (2) being 2 points is 8.9%, (3) being 3 points is 80%, (4) being 4 points is 7.8%, (5) being 5 points is 2.2%, etc.) as output values.

[0122] The analysis unit 92 analyzes whether or not roughness of the fabric is visible in each of the analysis images U1 to Un, and if so, the degree of roughness, based on the output values ​​(probabilities of each of the above classifications (1) to (5)) obtained by inputting each of the analysis images U1 to Un into the image classification model 96. Specifically, the analysis unit 92 calculates the score for the classification with the highest probability among the probabilities of each of the above classifications (1) to (5) (according to the example of the output values ​​of the above analysis image U11, the probability of (3) 3 points is the highest at 80%, so 3 points), or the sum of the values ​​of each classification (1) to (5) obtained by multiplying the score of each classification (1) to (5) by the probability of each classification (according to the example of the output values ​​of the above analysis image U11, 1 point × 1.1% + 2 points × 8.9% + 3 points × 80% + 4 points × 7.8% + 5 points × 2.2% = 3.011 points) for each of the analysis images U1 to Un.

[0123] The analysis unit 92 then determines the score for analysis image group C as the score of the analysis image group C, which is the score with the most analysis images among the calculated scores for each analysis image U1 to Un, or the average value of the sum of the values ​​for each category (1) to (5) obtained by multiplying the score for each category (1) to (5) by the probability for each category (1) to (5) (the score for each analysis image U1 to Un: 3.011 points in the example of analysis image U11 above). Based on this score for analysis image group C, the roughness of the dough is analyzed and the progress of dough mixing is determined.

[0124] The memory unit 94 stores image classification models 96 and the like, which are used in the analysis unit 92 to output the probability corresponding to each of the classifications (1) to (5) of the analyzed images U1 to Un.

[0125] Next, the analysis process will be described using the analysis apparatus 91 according to this fourth embodiment. Figure 14 is a flowchart illustrating the process performed by the control unit 90 to acquire an analysis image.

[0126] First, the control unit 90 instructs the image acquisition unit 22 to acquire an analysis image group C (see Figure 7) from the image acquisition device 2, which consists of multiple analysis images U1 to Un taken of dough being kneaded in the mixer (step S470). Next, the control unit 90 reads the image classification model 96 from the storage unit 94 and instructs the analysis unit 92 to acquire the probability that each of the analysis images U1 to Un corresponds to classification (1) to (5) using the image classification model 96 (step S471). Next, the control unit 90 instructs the analysis unit 92 to calculate the score for each of the analysis images U1 to Un based on the probability acquired in step S471 (step S472).

[0127] Specifically, as described above, the analysis unit 92 calculates for each analysis image U1 to Un the score of the classification with the highest probability from among the probabilities of each classification (1) to (5), or the sum of the values ​​(scores) of each classification (1) to (5) obtained by multiplying the score of each classification (1) to (5) by the probability of each classification (1) to (5).

[0128] The control unit 90 determines whether or not scores have been calculated for all analysis images U1 to Un (step S473). If scores have not been calculated (step S473: No), it returns to the process in step S471 and repeats the processes in steps S471 to S473 until the scores for all analysis images U1 to Un have been calculated (step S473: No).

[0129] Once the scores for all analysis images U1 to Un have been calculated (Step S473: Yes), the control unit 90 instructs the analysis unit 92 to calculate the score for analysis image group C, which is the sum of the scores for each analysis image U1 to Un calculated in Step S472 divided by the number of analysis images U1 to Un (Step S474). Next, the control unit 90 instructs the analysis unit 92 to analyze the roughness of the dough from the score of analysis image group C calculated in Step S474 and to understand the progress of dough mixing (Step S475).

[0130] According to the fourth embodiment, since the fabric is analyzed using the image classification model 96 in each of the analysis images U1 to Un (images in which the hook 224 is not visible), the degree of fabric roughness can be automatically and accurately analyzed, and fabric roughness can be detected.

[0131] In the fourth embodiment described above, an image classification model 96 is used as the image recognition model, but an object detection model or a segmentation model may also be used as the image recognition model.

[0132] The object detection model is an image recognition model constructed using object detection, a type of image recognition technology. First, the model creator annotates a large number of training images taken for machine learning by drawing rectangles around areas with rough textures. Then, using the unannotated training images as input, the model outputs images in which the rough textures in the training images are drawn with rectangles.

[0133] When an object detection model is used instead of an image classification model, the analysis unit 92 inputs, for example, the analysis image U1 into the object detection model and obtains the object detection result for the analysis image U1. If an image enclosed in a rectangle is output for the analysis image U1, the analysis unit 92 calculates the area (number of pixels) of the region enclosed by the rectangle and defines this area as the "texture roughness area." The analysis unit 92 also calculates the "texture roughness area" for analysis images U2 to Un, and defines the sum of the "texture roughness area" for each of the analysis images U1 to Un divided by the number of analysis images U1 to Un as the "average texture roughness area" for the analysis image group C. The analysis unit 92 evaluates that a large "average texture roughness area" indicates a lot of texture roughness, and a small "average texture roughness area" indicates little texture roughness.

[0134] A segmentation model is an image recognition model constructed using segmentation, a type of image recognition technology. The model creator first annotates a large number of training images taken for machine learning by filling in areas with rough texture with a specific color. Then, using the unannotated training images as input, the model outputs images in which the rough texture areas of the fabric in the training images have been filled in with the specific color as output.

[0135] When a segmentation model is used instead of an image classification model, the analysis unit 92 inputs, for example, the analysis image U1 into the segmentation model and obtains the object detection result for the analysis image U1. If an image filled with a specific color is output for the analysis image U1, the analysis unit 92 calculates the area (number of pixels) of the region filled with the specific color and defines this area as the "texture roughness area." The analysis unit 92 also calculates the "texture roughness area" for analysis images U2 to Un, and defines the sum of the "texture roughness area" for each of the analysis images U1 to Un divided by the number of analysis images U1 to Un as the "average texture roughness area" for the analysis image group C. The analysis unit 92 evaluates that a large "average texture roughness area" indicates a lot of texture roughness, and a small "average texture roughness area" indicates little texture roughness.

[0136] In the embodiments of the analysis process described above, the case in which the image group acquisition unit 22 acquires an analysis image group from the image acquisition device 2 was used as an example. However, the analysis device may also be equipped with an image acquisition device, and the analysis device may select images from images of dough being kneaded in the mixer in which the hooks 224 are included in a predetermined area or less within a partial area A (see Figure 2) used for analyzing the properties of the dough, within the area in which the hooks 224 knead the dough. These images may be defined as analysis images U1 to Un.

[0137] Furthermore, the analysis device may be equipped with an image acquisition device, and when the analysis device analyzes the analysis image, the region in which the hook 224 is included within the region in which the hook 224 kneads the dough and which is used for analyzing the dough may be excluded from the analysis target.

[0138] <Control Process> The control step is a step of controlling the fabric manufacturing process based on the results of the analysis step. By performing the control step, it is possible to manufacture fabric of good quality.

[0139] There are no particular restrictions on the aforementioned control, and it can be appropriately selected according to the purpose. The control may involve controlling the kneading process according to the progress of the dough mixing, controlling processes other than the kneading process, or controlling both.

[0140] There are no particular limitations on the control of the kneading process, and it can be appropriately selected according to the purpose. For example, this could include determining the end point of the kneading process (adjusting the kneading process to end at a suitable time), determining whether or not water needs to be added and how much water to add, determining whether or not auxiliary ingredients need to be added and how much to add, or determining whether or not the dough temperature needs to be adjusted and what that temperature is. In the present invention, among these, it can be suitably used to determine the end point of the kneading process.

[0141] There are no particular restrictions on the control of processes other than the aforementioned kneading process, and they can be appropriately selected according to the purpose. For example, this could include determining the fermentation time (adjusting it to achieve a suitable fermentation time).

[0142] For example, as shown in the [Examples] section described later, the degree of roughness of the dough (the degree of shadows produced) fluctuates for a while, but tends to decrease as the mixing progresses, bottoms out at a suitable time for the end of mixing, and then shows an increasing trend. For example, one method is to take the derivative of the moving average value of the average number of target pixels calculated in the average number calculation step, and determine the end of the mixing step when that value approaches 0.

[0143] Furthermore, a specific value can be used as an indicator to show the degree of roughness of the dough (the extent of shadows produced). The end of the kneading process can be determined by setting this value, or by setting it a certain time after a certain period of time has elapsed. This specific indicator value can be set after a craftsman has conducted tests and manufactured the dough using the same raw materials.

[0144] The control process can also be carried out by referring to the analysis results of the progress of dough mixing (information previously obtained) and controlling the dough manufacturing process.

[0145] Furthermore, machine learning may be used to control the dough manufacturing process. For example, a model trained using machine learning, with the results of the analysis process as input values ​​and the end point of the kneading process as output values, may be used to determine the end point of the kneading process.

[0146] The control process may be carried out by connecting a fabric manufacturing process control device to the analyzer, or by providing a fabric manufacturing process control unit within the analyzer.

[0147] If a dough manufacturing process control unit is provided within the analytical device, for example, in the analytical device 1 shown in Figure 6, the dough manufacturing process control unit can be connected to the control unit 20.

[0148] The information, such as the endpoint of the mixing process, controlled (determined) by the aforementioned control process may be communicated by outputting a signal to a notification device such as a monitor or speaker. Alternatively, for example, a signal may be output to a device controlling the mixer, so that the mixer stops when the mixing process reaches its endpoint.

[0149] <Other processes> The aforementioned other steps are not particularly limited as long as they do not impair the effects of the present invention, and any known steps in the method of producing food dough can be carried out as appropriate, such as a fermentation step, a molding step, a proofing step, etc.

[0150] (Method of manufacturing bakery food products) The method for producing bakery food products of the present invention includes at least a step of heating the food dough produced by the method for producing food dough of the present invention described above (hereinafter sometimes referred to as the "heating step" or "baking step"), and may include other steps as needed.

[0151] There are no particular restrictions on the heating conditions in the aforementioned heating process, and they can be appropriately selected depending on the type of bakery food being manufactured.

[0152] The aforementioned other steps are not particularly limited as long as they do not impair the effects of the present invention, and any known steps in the manufacturing method of bakery food can be carried out as appropriate. [Examples]

[0153] The present invention will be explained below with reference to test examples, but the present invention is not limited in any way to these test examples.

[0154] (Test Example 1) Bread was produced using dough with the following formulation. For the wheat flour, either bread flour A (Test Example 1A) or B (Test Example 1B), which have different raw wheat compositions, were used. <Formulation> · Flour 100 parts by mass • Baker's yeast 3.7 parts by mass • Salt 2 parts by mass · 5 parts by mass of white sugar (• 5 parts by mass of oil and fat (to be added after low-speed mixing is complete)) · Approximately 75 parts by mass of water

[0155] <Kneading process> -Slow mixing- A vertical mixer manufactured by Shinagawa Kogyosho was used, and low-speed mixing was performed using a spiral hook.

[0156] Trained bakers performed visual inspections and checked the dough properties to determine the optimal timing for slow mixing. As a result, the optimal time to finish slow mixing was 4 minutes and 30 seconds for Test Example 1A using bread flour A, and 6 minutes for Test Example 1B using bread flour B. Furthermore, when the physical properties of the dough were checked at 2 minutes from the start of low-speed mixing, and at 1 minute 30 seconds to 3 minutes after the optimal end time for low-speed mixing, the evaluation of the dough deteriorated.

[0157] Furthermore, when bread was produced using this dough after subsequent high-speed mixing, fermentation, shaping, proofing, and baking, the quality of the bread obtained from dough where low-speed mixing was completed earlier or later than the optimal mixing time was poor.

[0158] [Image Analysis] The dough used in the low-speed mixing process described above was subjected to image analysis as follows.

[0159] -Image acquisition- In accordance with the [First Embodiment of the Image Acquisition Process] described in the [Modes for Carrying Out the Invention] section, multiple images were acquired from the video footage of the dough during slow mixing using an image acquisition device. A GoPro Hero10 (manufactured by GoPro) was used as the camera. In this test example, the number of frame images was set to 30 per second. Images showing spiral hooks were excluded from the analysis images used to analyze fabric imperfections.

[0160] -Image Analysis- Next, in accordance with the [First Embodiment of the Analysis Process] described in the [Modes for Carrying Out the Invention] section, the analysis images selected from multiple images were analyzed to analyze the fabric's condition. The average number of pixels corresponding to fabric roughness (shadows) was calculated as a moving average over a 30-second period.

[0161] Figure 15 shows the change over time in the average number of target pixels corresponding to dough roughness. In Figure 15, "●" indicates the results for Test Example 1A, and "□" indicates the results for Test Example 1B. As shown in Figure 15, the average number of target pixels in both Test Examples 1A and 1B showed a decreasing trend from the start of mixing, and was found to be at its lowest point (showing the bottom) at the time that a trained baker judged to be the optimal time to end low-speed mixing, and then increased thereafter.

[0162] Therefore, it was demonstrated that by photographing the dough during the kneading process and performing image analysis, the dough production can be controlled without relying on the knowledge and experience of the craftsman, and a high-quality dough with good secondary processing properties can be produced. [Explanation of symbols]

[0163] 1, 41, 71, 91... Analyzer 2. Image acquisition device 4. Control Unit 6... Acquisition part 8. Image Processing Unit 10... Discrimination section 12... Storage section 14... Exclusion part 15 ··· Transmitter 20, 50, 80, 90... Control Unit 22 ··· Image acquisition unit 24, 54, 84, 92... Analysis Department 26 ··· Brightness acquisition unit 28 ··· Average Brightness Calculation Unit 30 ··· Standard Brightness Calculation Unit 32, 62... Selection section 34 ··· Quantity Calculation Unit 36 ··· Average Count Calculation Unit 38, 58, 94... Storage section 55 ··· Canny edge detection unit 86 ··· Fractal Dimension Calculation Unit 96 ··· Image classification model 222... Bowl 224 ··· Hook (mixing component)

Claims

1. A method for manufacturing food dough, The kneading process involves mixing the dough containing cereal flours using a mixer, The process includes an image acquisition step of photographing the dough being kneaded in the mixer and acquiring a group of analysis images consisting of multiple analysis images using an image acquisition device, The analysis process involves analyzing the progress of the dough mixing by analyzing the aforementioned multiple analysis images, A method for producing food dough, comprising a control step that controls the dough manufacturing process based on the results of the analysis step.

2. A method for producing food dough according to claim 1, wherein wheat flour and other grain flours are used as raw materials for the food dough.

3. The method for producing food dough according to claim 1, wherein the food dough is bakery dough.

4. The method for producing food dough according to claim 1, wherein the food dough is bread dough.

5. The method for producing food dough according to claim 1, wherein the kneading step is a step in which the kneading is performed at a low speed.

6. The aforementioned analysis step involves referring to the analysis results of multiple analysis images already obtained to analyze the progress of the dough mixing, The method for manufacturing food dough according to claim 1, wherein the control step controls the dough manufacturing process by referring to the analysis results of the progress of kneading of the acquired dough.

7. The method for producing food dough according to claim 1, wherein the control step includes determining the endpoint of the kneading step from the results of the analysis step.

8. A method for producing bakery food, characterized by including a step of heating food dough produced by the method for producing food dough according to any one of claims 1 to 7.

Images