JP7182927B2 - Bean pod inspection method and pod food manufacturing method - Google Patents

Description

TECHNICAL FIELD The present invention relates to a method for inspecting pods and a method for producing pod food, and more particularly to a method for inspecting the inside of pods and a production method equipped with the inspection method.

Soybeans, broad beans, and other pods, which consist of pods and beans covered with pods, are in demand as fresh foods. In particular, green soybeans harvested from soybeans that are immature and still green are widely used as a frozen food that has been frozen after being cooked. As a method for inspecting pods, a destructive test is known in which a part of the pods is sampled from among many pods and inspected.

Patent Literature 1 discloses an inspection method in which transmitted light is turned on from below a workbench to transmit the light, and the presence or absence of foreign matter contamination is visually determined by changes in the amount of light and changes in color tone of the transmitted light.

In Non-Patent Document 1, food is irradiated with near-infrared light, which has a higher transmittance of food than visible light, and the transmitted light is imaged with a special camera and image-processed. It is disclosed that detection of such as is possible.

Japanese Patent Application Laid-Open No. 2006-162438

Toyohashi University of Technology Press Release April 24, 2014

However, with the conventional method of inspecting samples by destroying them, it is impossible to inspect all food items, such as green soybeans, whose marketability is lowered by destruction, so inspection omissions inevitably occur. , there is a problem that the accuracy of inspection decreases.

Since the inspection method of Patent Document 1 is a visual inspection method using visible light, there is no need to destroy the food. There is

In the inspection method of Non-Patent Document 1, even near-infrared light does not reach the inside of the food, and there is a concern that the purpose of the inspection cannot be achieved. For example, when the pod of a bean pod is thick, the near-infrared light that strikes the pod is diffused and does not reach the inside, making it difficult to inspect the condition inside the pod.

Therefore, an object of the present invention is to provide a method for inspecting beans and a method for producing a food product of beans, which can inspect the state of the inside of beans with high accuracy without destroying the beans.

The method for inspecting beans and the method for producing a food product according to the present invention includes a step of inspecting by irradiating X-rays to beans that have not been wet-heated, and the tube voltage of the X-rays is set to V (kV) A method that satisfies the following formulas (1) and (2), where S (m/min) is the speed of the pods passing through the X-ray irradiation area.
10≦S≦60 (1)
25≦V≦S+40 (2)

The method for inspecting pods according to the present invention includes the steps of irradiating X-rays on pods that have not been wet-heated to obtain X-ray image information, , a gray value of the pod area of the pod, a gray value of the bean outer edge of the pod, and a gray value of the bean area of the pod.

According to the present invention, the boundary between the pod and the bean is clear and the bean region can be specified more reliably by irradiating the bean pod before wet heating with X-rays. Therefore, the internal state of the pod can be inspected with high accuracy without destroying the pod.

It is a block diagram which shows the structure of the inspection apparatus which concerns on this embodiment. 3 is a perspective view schematically showing the configuration of an X-ray imaging unit; FIG. It is a flow chart which shows the manufacturing method of the bean pod foodstuffs concerning this embodiment. 4 is an X-ray image of pods captured by the inspection method according to the present embodiment. FIG. 5A is an X-ray image of the pods after wet heating, FIG. 5A after boiling and FIG. 5B after steaming. 6A is an X-ray image of a pod, FIG. 6B is a graph showing X-ray transmission intensity, and FIG. 6C is a binary data image. 7A is an X-ray image of a pod, FIG. 7B is a graph showing X-ray transmission intensity, and FIG. 7C is a binary data image. FIG. It is a schematic diagram with which it uses for description of a non-defective product model. Fig. 9A is a model of a good product, and Fig. 9B is an X-ray image of the good product. Fig. 10A is a model of the defective product (1), and Fig. 10B is an X-ray image of the defective product. Fig. 11A is a model of the defective product, and Fig. 11B is an X-ray image of the defective product. 12A is a defective product (dent) model, FIG. 12B is an X-ray image of the defective product (dent), and FIG. 12C is a defective product (discoloration) model. 12D is an X-ray image of a defective product (discoloration). Fig. 13A is a diagram for explaining the pods of the defective product (4), Fig. 13A is a model of the defective product, and Fig. 13B is an X-ray image of the defective product. It is a list which put together the X-ray image of a non-defective product. It is the table|surface which put together the X-ray image of the defective article. FIG. 2 is a schematic diagram of a bean pod for explaining the measurement points of the gradation value. It is a graph which shows the relationship between tube voltage and belt speed. It is an X-ray image of pods after being heated with dry heat, which is imaged by the inspection method according to the present embodiment.

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

(overall structure)
The inspection apparatus 10 shown in FIG. 1 includes an X-ray imaging section 12 , a storage section 14 , an input section 16 , an output section 18 and a processing section 20 , which are connected via a bus 22 . The processing unit 20 reads application programs such as a basic program and an image processing program stored in advance, and controls the entire inspection apparatus 10 according to these various programs. The processing unit 20 can execute a plurality of programs (application programs, etc.) in parallel.

The storage unit 14 includes, for example, at least one of a semiconductor storage device, a magnetic tape device, a magnetic disk device, or an optical disk device. The storage unit 14 stores an operating system program, a driver program, an application program, data, etc. used for processing in the processing unit 20 . For example, the storage unit 14 stores, as an application program, an inspection program or the like for causing the processing unit 20 to perform an inspection process for inspecting the inside of the pod. The inspection program may be installed in the storage unit 14 from a computer-readable portable recording medium such as CD-ROM, DVD-ROM, etc. using a known setup program or the like.

The storage unit 14 also stores non-defective product data of non-defective pods and X-ray images, which will be described later. The non-defective product data is information on beans and pods that should be possessed by non-defective bean pods, for example, information in which the size (area) and shape are quantified. Furthermore, the storage unit 14 may temporarily store temporary data related to predetermined processing.

The input unit 16 may be any device that can input data, such as a touch panel and a keyboard. The operator can use the input unit 16 to input characters, numbers, symbols, and the like. The input unit 16 generates a signal corresponding to the operation when operated by the operator. The generated signal is then supplied to the processing unit 20 as an operator's instruction.

The output unit 18 may be any device as long as it can display video, images, etc., for example, a liquid crystal display or an organic EL (Electro-Luminescence) display. The output unit 18 displays an image or the like according to the image data input from the processing unit 20 . Also, the output unit 18 may be a device that prints images or characters on a display medium such as paper.

As shown in FIG. 2, the X-ray imaging unit 12 acquires X-ray image information by irradiating the pod 28 with X-rays 29 and receiving the X-rays transmitted through the pod 28 . The X-ray imaging unit 12 includes an X-ray irradiator 23, an X-ray image receiver 24, and a belt conveyor 26 as a transport unit. The X-ray irradiator 23 and the X-ray image receiver 24 are arranged so as to vertically face each other with the belt conveyor 26 interposed therebetween. A belt conveyor 26 conveys a plurality of pods 28 in one direction. A plurality of pods 28 on the belt conveyor 26 are arranged in such a manner that the pods 28 do not overlap each other.

The X-ray irradiator 23 irradiates X-rays 29 from above the belt conveyor 26 . The X-ray irradiator 23 irradiates X-rays 29 across the belt conveyor 26 in the width direction to form a planar irradiation area AR. The pods 28 pass through the X-ray irradiation area AR at the running speed of the belt conveyor 26 .

The X-ray image receiver 24 is a line sensor whose longitudinal length is substantially the same as the width direction of the belt conveyor 26 . The X-ray image receiver 24 receives the X-rays transmitted through the pod 28 and outputs the obtained X-ray image information to the processing unit 20 via a LAN (Local Area Network) (not shown) and the bus 22 . .

When the tube voltage of the X-ray irradiator 23 is V (kV) and the running speed of the belt conveyor 26 is S (m/min), the tube voltage V and the speed S are given by the following formulas (1) and (2). Fulfill.
10≦S≦60 (1)
25≦V≦S+40 (2)

By satisfying the above formulas (1) and (2), the boundary between the pod and the bean is clear, and the outline of the bean pod 28, the outline of the bean, and the shade of the bean area can be identified without reducing productivity. An X-ray image can be obtained. As the tube voltage V increases, the X-ray penetrating power increases, resulting in a brighter X-ray image. On the other hand, when the tube voltage V is small, the X-ray transmission power becomes small, so the X-ray image becomes dark. Further, when the speed S is lowered, the amount of X-rays passing through the pod increases, so the X-ray image becomes brighter. On the other hand, increasing the speed S reduces the amount of X-rays that pass through the pod, resulting in a darker X-ray image. Therefore, when the speed S is increased to increase productivity, the amount of X-rays decreases, but by increasing the tube voltage V and increasing the amount of X-rays, a clearer X-ray image can be obtained. .

If the running speed S of the belt conveyor 26 is less than 10 (m/min), the amount of pods 28 that can be inspected per unit time is limited, resulting in a decrease in productivity. If the running speed S of the belt conveyor 26 exceeds 60 (m/min), the X-ray image information obtained from the pods 28 may exceed the amount of calculation that can be processed by the processing unit 20 . The upper limit of the running speed S of the belt conveyor 26 can be changed according to the processing capability of the processing section 20 . When the tube voltage of the X-ray irradiator 23 is less than 25 kV, the X-ray image is too dark and the shade inside the pod becomes unclear. When the X-ray tube voltage V exceeds S+40 (kV), the X-ray image becomes too bright, the color difference between the beans and the pods is small, and it becomes difficult to identify the outer shape of the beans. Incidentally, the tube current is appropriately changed by setting the tube voltage, and is in the range of 0.2 mA to 10 mA, for example.

Further, the tube voltage V and the speed S preferably satisfy the following formula (3) within the range of 50≦S≦60. When the speed S is in the range of 50≦S≦60, the tube voltage V satisfies the following formula (3), so that it is possible to more reliably identify defects such as dents and discoloration on the bean surface.
1.5S-50≤V≤S+40 (3)

Further, the tube voltage V and speed S of the X-ray irradiator 23 preferably satisfy the following formula (4) within the range of 30≦S≦60.
25≦V≦70 (4)

(Method for producing pod food)
Next, a manufacturing method for manufacturing a bean pod food from the pod 28 harvested in the field will be described with reference to FIG. First, after harvesting the pods 28 in step SP1, they are briefly washed (step SP2). The washed pods 28 are transported from the field (step SP3) and stored in the factory (step SP4). Washing is repeated multiple times at the factory (step SP5). An internal inspection (step SP6) is performed on the pods 28 after washing.

In the internal inspection (step SP6), the X-ray imaging unit 12 acquires X-ray image information of the pods 28 being transported. The processing unit 20 reads X-ray image information. The processing unit 20 extracts features of the pods 28 from the X-ray image information to obtain feature information. The processing unit 20 determines whether the beans 28 are good or bad based on the characteristic information.

FIG. 4 shows an X-ray image of the pod 28 generated from the X-ray image information obtained by the above procedure. The X-ray image shows the bean 32 inside the pod 30 . The processing unit 20 identifies the region of the beans 32 from, for example, the X-ray image information. In the X-ray image, the bean region appears blacker than the region of the pod 30 because it is difficult for X-rays to pass therethrough. The processing unit 20 identifies certain areas displayed in black as bean areas.

Also, although not shown in the figure, the processing unit 20 identifies a region outside the bean region, which has a different density than the bean region and the pod region, and has a certain unity outside the bean region, as a foreign substance other than the bean 32, such as an insect. Furthermore, the processing unit 20 identifies that the surface of the bean 32 has an external shape abnormality (deformation, discoloration, worm-eaten) when there is a partially bright or dark portion in the bean region. As described above, the processing unit 20 obtains characteristic information of the pods 28 .

Next, the processing unit 20 determines whether the beans 28 are good or bad based on the characteristic information obtained as described above. For example, the processing unit 20 compares the bean area with non-defective product data. As a result of the comparison, the processing unit 20 determines that the product is a non-defective product when the difference between the beans region and the non-defective product data is equal to or less than a certain value. On the other hand, the processing unit 20 determines that the product is defective when the difference between the beans region and the non-defective product data exceeds a certain value.

For example, the processing unit 20 reads the image data of the non-defective pods 28 from the storage unit 14 as the non-defective data and compares it with the bean region. The processing unit 20 calculates the non-matching rate of the bean area with respect to the non-defective product data. A non-matching rate threshold for separating non-defective products from non-defective products is determined in advance from the non-defective pods 28 . When the mismatch rate is equal to or less than a predetermined threshold, the pod 28 is determined as a non-defective product, and when it exceeds the threshold, the pod 28 is determined as a defective product. The processing unit 20 can determine whether the size of the bean 32 is good or not and whether there is an abnormality in the external shape by comparing the bean region with the non-defective product data. When the processing unit 20 detects an insect in the pod 28, the processing unit 20 determines the pod 28 as a defective product.

Next, the pods 28 determined to be defective are removed from the belt conveyor 26 (step SP7). Subsequently, the pods 28 determined as non-defective are wet-heated (step SP8). Here, wet heating refers to a cooking operation in which water is used as a heat medium for heating, and specifically refers to steaming, boiling, or applying hot water (for example, water of 80° C. or higher).

The wet-heated pods 28 are frozen (step SP9), temporarily packaged (step SP10), and stored for a certain period of time (step SP11). Finally, the surface is inspected (step SP12), subdivided and packaged (step SP13), and then shipped as a pod food.

(action and effect)
The X-ray irradiator 23 emits X-rays 29 from above toward the belt conveyor 26 . The pods 28 pass through the X-ray irradiation area AR formed from the X-ray irradiator 23 toward the belt conveyor 26 at the running speed S of the belt conveyor 26 . The X-ray imaging unit 12 acquires X-ray image information obtained by irradiating the beans 28 being transported with X-rays 29 from above, and outputs the information to the processing unit 20 . Based on the X-ray image information input from the X-ray imaging unit 12, the processing unit 20 obtains characteristic information for each pod 28 and compares the characteristic information with non-defective product data to determine the quality of the pod 28. judge. In the actual determination, features based on the size and shape of the pod 30 from the outline of the bean pod 28, and features based on the size and shape of the bean itself from the outline of the bean 32, such as foreign matter (such as insects) in the pod outside the bean area. and get. Next, foreign matter (insects, etc.) existing in the bean area and features based on discoloration of the bean area 32 are acquired from the shading of the bean area.

For example, based on the obtained X-ray image information, the image (1) of the pod 28 is cut out from the whole, the image (2) of the bean 32 is cut out from the image (1), and the cut out image (1) And the presence or absence of defects may be detected based on the image (2). Based on the image (1) of the pod 28, it is possible to detect defects that can be detected from the outline of the pod 28, such as whether the pod 30 is broken or whether there are insects in the pod area. Based on the image ( 2 ) of the bean 32 , defects that can be detected from the outline of the bean 32 , for example, defects such as irregular shapes, small grains, and bugs adjacent to the bean 32 are detected. Further, based on the image (2) of the bean 32, defects that can be detected from the shade of the bean region, such as discoloration of the bean 32 and presence or absence of surface dents, are detected. Therefore, in the inspection method according to the present embodiment, based on one X-ray image, defects that can be detected from the contour of the pod 28, defects that can be detected from the contour of the bean 32, and defects that can be detected from the shade of the bean region can be detected at the same time. can be inspected. The inspection device 10 may input the determination result to the output unit 18 . In this case, the output unit 18 can display the output result corresponding to the determination result together with the X-ray image generated from the X-ray image information.

More specifically, based on the obtained X-ray image, the density values of the outer pod region a, the pod region b, the bean outer edge c, and the bean region in FIG. 16 are measured. The gradation value is obtained by obtaining predetermined gradation data from the obtained X-ray image and converting the image luminance of each divided coordinate point into a predetermined gradation value. By comparing the gradation values of the outer pod region a, the pod region b, the bean outer edge c, and the bean region with the gradation values of the non-defective pods, it is possible to judge whether the product is good or bad. In the inspection method of the present embodiment, the tube voltage V (kV) and the belt speed S (m/min) satisfy the above formulas (1) and (2), so that the outside pod region a, the pod region b, the beans An X-ray image can be obtained in which the outer edge c, the bean area, and the defective portion e of the bean (in the case of a bean with defects) have predetermined grayscale values. The obtained X-ray images show the difference in density between the outside of the pod region a and the pod region b, the difference in density between the pod region b and the outer edge of the bean c, the difference in density between the outer edge of the bean c and the bean region, and the difference in density between the bean region and the defective part e. are each greater than or equal to a predetermined numerical value. The outline of the bean pod 28 can be easily detected when the difference in shading between the outside of the pod region a and the pod region b is greater than or equal to a predetermined value. The outline of the bean 32 can be easily detected when the difference in shade between the pod region b and the bean outer edge c is equal to or greater than a predetermined value. When the density difference between the outer edge c of the bean and the bean area is equal to or greater than a predetermined value, it becomes easier to detect an abnormality on the surface of the bean. The ratio of the grayscale difference, which is normalized by dividing the grayscale difference between the defective portion e and the central portion d of the bean region by the grayscale difference between the outside of the pod region a and the central portion d of the bean region, is equal to or greater than a predetermined value. , it becomes easier to detect defects in the bean region.

In the case of the present embodiment, the X-ray image information of the pod 28 is obtained by irradiating the pod 28 before being wet-heated with X-rays 29. Therefore, as shown in FIG. and the bean 32 are sharp, and the bean region can be specified more reliably. On the other hand, wet heating causes water to permeate the inside of the pod 30, making it difficult to identify the bean region. Incidentally, as shown in FIG. 5A, after boiling (100 ° C., 3 minutes) as wet heating, water enters the pod 102 of the pod 100, so the boundary between the bean 104 and the pod 102 becomes unclear. . The weight of the pods 28 after boiling was 102% of that before boiling. Bean pods 106 (FIG. 5B) after steaming (100° C. for 10 minutes) as wet heating also have water entering the pods 108, so the boundary between the beans 110 and the pods 108 is unclear, and the bean region is difficult to identify. The weight of the pods 28 after steaming was 102% of that before steaming.

By heating the pod to a temperature that softens the texture of the pod in an environment where there is a sufficient amount of water around the pod to penetrate the interior of the pod, the water penetrates into the interior of the pod. Here, the sufficient amount of water refers to the amount that remains liquid after permeation into the pods. Therefore, heating that does not satisfy the above conditions is not included in wet heating. For example, washing or heating with hot water below 80° C. to the extent that water does not penetrate into the inside of the pods is not included in wet heating as used herein. Heating that does not use moisture as a heat medium, such as hot air heating and microwave heating, is not included in wet heating.

In the inspection method of the present embodiment, the quality is determined based on the X-ray image information of the pods 28 obtained by irradiating the pods 28 with X-rays 29 before being wet-heated. The internal state of the pod 28 can be inspected with high precision without destroying the pod.

In the inspection method of the present embodiment, since X-ray image information of all the pods 28 conveyed on the belt conveyor 26 can be obtained, all the pods 28 can be inspected. Therefore, the method for producing a soybean food can easily produce a soybean food containing no defective products by including this inspection method.

The inspection method of the present embodiment can further classify the beans 28 determined to be non-defective by the size and shape of the beans 32 based on the X-ray image information of all the beans 28 .

The method for judging the quality of the pods from the feature information is not particularly limited, but for example, outline data, binary data, and gradation data may be obtained as the feature information. The contour data are the contour lines of the pods and beans extracted from the X-ray image information. By recognizing parts that deviate greatly from the outline of a non-defective product as defective, the processing unit detects chips and dents due to worm-eaten, insects adjacent to beans, small beans (defective bean size), broken pods, etc. and so on.

Binary data is data simplified by binarizing the vicinity of the bean region of the X-ray image information. The processing unit detects defects such as discoloration and dents from simple binary data. The grayscale data is not simply binarized data, but data having integrated grayscale information. The processing unit detects defects such as discoloration and dents based on indicators such as the magnitude of change in density and brightness.

A specific example of detecting a discoloration defect based on binary data will be described with reference to FIGS. 6 and 7. FIG. Based on the X-ray image information shown in FIG. 6A, the processing unit acquires binary data obtained by binarizing the vicinity of the bean region (FIG. 6C). The binary data is compared with non-defective product data. In the case of this figure, no discoloration is observed in the binary data of the bean region, so the mismatch rate is below the threshold. Therefore, the processing unit determines that the pods are non-defective. FIG. 6B is the X-ray transmission intensity of the linear portion in FIG. 6A. In FIG. 6B, the horizontal axis indicates distance, and the vertical axis indicates X-ray transmission intensity. It can be seen from FIG. 6B that no specific peak is observed in the bean region, and that the bean 32 has neither discoloration nor depression.

On the other hand, FIG. 7A is X-ray image information of beans with discoloration or deformation. When the vicinity of the bean region is binarized based on the X-ray image information shown in FIG. 7A, the discolored portion becomes clear (FIG. 7C). In the case of this figure, when the binary data of the bean area and the non-defective data are compared, the mismatch rate exceeds the threshold. Therefore, the processing unit determines that the beans are defective. FIG. 7B is the X-ray transmission intensity of the linear portion in FIG. 7A. In FIG. 7B, the horizontal axis indicates the distance, and the vertical axis indicates the X-ray transmission intensity. From FIG. 7B, two peaks are observed in the bean region, indicating that the bean 42 is defective such as discoloration.

Next, specific examples of non-defective and defective pods 28 that can be determined by the inspection method according to the present embodiment will be described. In the following description, the non-defective product data 34 refers to image data of non-defective pods. As shown in FIG. 8, the bean pod 28 is determined to be non-defective when the mismatch rate between the bean region 32 specified by the processing unit 20 and the non-defective product data 34 is equal to or less than a threshold.

FIGS. 9A and B to FIGS. 13A and B show an X-ray image generated based on X-ray image information obtained by irradiating edamame as the pod 28 with X-rays having a tube voltage of 30 kV and a tube current of 2 mA; This is an example of comparing feature information obtained from an image and non-defective product data. The edamame shown in FIGS. 9A and 9B is determined as a non-defective product because the mismatch rate between the non-defective product data 34 and the bean region 32 is less than the threshold.

10A and 10B are examples of defective products in which the beans 36 are small. The green soybean shown in this figure is determined to be defective because the non-matching rate between the non-defective product data 34 and the bean region 36 exceeds the threshold.

FIGS. 11A and 11B are examples of defective products in which worms 40 are present inside pods 30 and beans 38 are missing. The edamame shown in the figure is smaller than the non-defective product data 34 because the beans 38 are missing due to worm-eaten, and the mismatch rate exceeds the threshold value, so it is determined to be defective. Furthermore, the processing unit 20 identifies the edamame 40 as the insect 40, which is a region adjacent to the bean 38 and has a uniform density different from the bean region and the pod region 30. From this point of view, the green soybean is regarded as a defective product. judge.

FIGS. 12A to 12D are examples of defective products with external shape abnormalities (deformation, discoloration) on the surface of beans 42 (FIGS. 12A and 12C). If the bean 42 has a dent on the surface, the density of the part becomes bright in the X-ray image (Fig. 12B). On the other hand, if the surface of the bean 42 is discolored, the portion becomes darker in the X-ray image (FIG. 12D). In terms of size, the processing unit 20 can determine the edamame to be a non-defective product because the mismatch rate between the bean region 42 and the non-defective product data 34 is equal to or less than the threshold. However, since the bean region 42 has a partially bright portion 44 or a dark portion 48, the mismatch rate from the viewpoint of color exceeds the threshold value, and the processing unit 20 identifies the region as having an external shape abnormality. The green soybeans are determined to be defective.

13A and 13B are an example of a defective product (FIG. 13A) in which an insect 40 is present adjacent to the bean 32. FIG. Since the mismatch rate between the bean region 32 and the non-defective product data 34 is equal to or less than the threshold value, the processing unit 20 determines that the bean itself is non-defective. However, the processing unit 20 identifies the edamame 40 as the insect 40, which is different from the bean region 32 and the region of the pod 30 and has a uniform density (FIG. 13B), and determines that the green soybean is defective from this point of view. .

Next, X-rays obtained when changing the tube voltage V (kV) of the X-ray irradiator 23 and the running speed S (m/min) of the belt conveyor 26 for good and defective pods The image results are described. One good and one defective pod was prepared and used repeatedly to obtain X-ray images while changing the tube voltage V (kV) and the running speed S (m/min) of the belt conveyor 26 . As defective products, pods with defects due to dents on the surface of the beans were used. The obtained X-ray image is an 8-bit image in which 256 levels from 0 to 255 are expressed in gradation.

When the belt speed S is 10 m/min, 20 m/min, 30 m/min, 40 m/min, 50 m/min, and 60 m/min, and the tube voltage V is 25 kV, 40 kV, 50 kV, 60 kV, and 70 kV, An X-ray image of good pods is shown in FIG. 14, and an X-ray image of defective pods is shown in FIG. From FIGS. 14 and 15, it can be confirmed that the higher the tube voltage V, the brighter the image as a whole, and the higher the belt speed S, the darker the overall image.

Rejects have a dent defect in the center of the leftmost bean in the pod, and the defect is shown as a bright spot in the X-ray image. From the X-ray image, the gradation difference between the bright point of the defective portion and the dark portion of the bean area, that is, the ease of recognizing the bright point indicating the defective portion becomes easier to recognize as the tube voltage V increases, and the belt speed It can be confirmed that the faster S is, the more difficult it is to recognize.

FIG. 16 shows an example of the positions of the outside of the pod region a, the pod region b, the bean outer edge c, the bean region, and the defective portion e where the grayscale values of the X-ray image were measured. The larger the difference in shading between the outside of the pod region a and the pod region b, the easier it is to recognize the contour of the pod 28, and the easier it is to detect defects detected from the contour of the pod 28. The larger the difference in shading between the pod region b and the outer edge c of the bean, the easier it is to recognize the outline of the bean 32 and to detect defects detected from the outline of the bean 32 . The greater the difference in shading between the outer edge c of the bean and the central portion d of the bean region, the easier it is to recognize the shading of the surface of the bean, and the easier it is to detect defects that can be detected from the shading of the bean region. The greater the difference in density between the central portion d of the bean region and the defective portion e within the bean region, the easier it is to detect defects within the bean region.

Therefore, for each of the X-ray images of the non-defective pods shown in FIG. 14, the gradation values of the outer pod region a, the pod region b, the bean outer edge c, and the central portion d of the bean region were measured. Then, the ease of detecting the outline of the bean pod 28 in each combination of the tube voltage V and the belt speed S is evaluated based on the difference in density between the outer pod area a and the pod area b, and the outline of the bean 32 is detected. Ease of detection was evaluated based on the difference in density between the pod region b and the outer edge c of the bean, and the ease of detection of the difference in density in the bean region was evaluated based on the difference in density between the outer edge c of the bean and the central portion d of the bean region. Further, for each of the X-ray images of the defective pods shown in FIG. 15, the gradation values of the outer pod region a, the central portion d of the bean region, and the defective portion e were measured. Then, the easiness of detecting a defect in the bean region in each combination of tube voltage V and each belt speed S was evaluated based on the difference in density between the defective portion e and the center portion d of the bean region.

In Table 1, for each X-ray image of a good bean pod, the gray value of the outside pod region a, the pod region b, the bean outer edge c, the central portion d of the bean region, and the X of each of the defective bean pods Regarding the line image, the results of measuring the grayscale values of the defective portion e, the central portion d of the bean region, and the outside of the pod region a are shown. The gradation value was obtained by obtaining 256 gradation data from the obtained 8-bit X-ray image and converting the image brightness of each divided coordinate point into a predetermined gradation value. The outer edge c of the bean 32 is defined as the inner area near the outermost edge of the bean 32 .

In addition, Table 1 shows the value of the gradation difference obtained by subtracting the gradation value of the pod region b from the gradation value of the pod region outside a as an index of the ease of cutting out the pod region. As an index of the ease of cutting out the bean region, the value of the difference in gradation obtained by subtracting the gradation value of the outer edge c of the bean from the gradation value of the pod region b was shown. As an index of the easiness of finding an abnormality on the bean surface, the value of the difference in gradation obtained by subtracting the gradation value of the central portion d of the bean region from the gradation value of the outer edge c of the bean was shown. The larger the gradation difference, the clearer the pod region, the bean region, and the surface of the bean can be recognized, making it easier to compare with non-defective product data and to separate non-defective products from non-defective products.

If the difference in density between the outside of the pod region a and the pod region b is 31 or more, the outline of the pod 28 can be more reliably recognized, so 2 points. .

If the shading difference between the pod region b and the bean outer edge c is 31 or more, the contour of the bean 32 can be more reliably recognized, so 2 points. In this case, it is difficult to recognize the outline of the bean 32, so a score of 0 is given and shown in the judgment column of "Ease of cutting out the bean region" in Table 1.

If the grayscale difference between the bean outer edge c and the central portion d of the bean region is 31 or more, the grayscale of the beans 32 can be more reliably recognized, so 2 points. .

In the comprehensive judgment, the case where the total score of each judgment was 0 points was rejected, and the case where the total score was 1 point or more was judged as passed. From the results in Table 1, the combinations of the tube voltage V and the belt speed S of conditions Nos. 4, 5, and 10 failed because the total score for each judgment was 0 points.

Table 1 shows the difference in density between the defective portion e and the central portion d of the bean region as an index of the ease of detecting defects in the bean region, and the difference in density between the outside of the pod region a and the central portion d of the bean region. The grayscale ratio normalized by dividing is shown. It was determined that defects in the bean area could be recognized more reliably if the ratio of the difference in density was 50% or more. From the results in Table 1, under all conditions except for the combination of tube voltage V and belt speed S of condition No. 26, the grayscale ratio is 50% or more, and defects in the bean area can be recognized more reliably. was confirmed.

FIG. 17 shows the easiness of detecting the contour of the pod, the easiness of detecting the contour of the bean, and the difference in light and shade of the bean region, with the vertical axis being the tube voltage (kV) and the horizontal axis being the belt speed (m/min). It is the figure which showed the result of having comprehensively evaluated the ease of detection. ○ is the condition where the result of 1 point or more was obtained in the comprehensive judgment, and × is the condition where the result of 0 point was obtained in the comprehensive evaluation. By satisfying the above formulas (1) and (2) with the tube voltage V (kV) and the belt speed S (m/min), the contour of the pods 28 and the contours of the beans 32 can be obtained without reducing the productivity. , and the gradation of the bean region.

In addition, in the conditions indicated by ◯ and × in FIG. 17, the ratio of the difference in density is less than 50%, which makes it difficult to detect defects such as dents in the bean area. When the tube voltage V (kV) and the belt speed S (m/min) are in the range of 50 ≤ S ≤ 60 and the condition of the above formula (3) is satisfied, the grayscale ratio is 50% or more, It was confirmed that by satisfying the above formula (3) in the range of 50≦S≦60, defects in bean regions can be recognized more reliably.

(Modification)
The present invention is not limited to the above embodiments, and can be appropriately modified within the scope of the present invention.

In the above embodiment, the case of inspecting the pods 28 that have not been wet-heated has been described, but in the case of heating that does not use moisture as a heat medium, inspection may be performed after the heating. FIG. 18 is an X-ray image obtained by irradiating the pod 50 heated by dry heat (160° C., 8 minutes) with X-rays at a tube voltage of 30 kV and a tube current of 2 mA. From this figure, it was found that the boundary between the pod 52 and the bean 54 was clear and the bean region 54 could be identified more reliably because water did not enter the pod 52 . The weight of the pods 50 after heating with dry heat was 61% of that before heating.

In the above embodiment, the internal inspection is performed immediately before the wet heating (step SP8), but the present invention is not limited to this. If the beans 28 are not wet-heated, the timing when the beans 28 are not heated at all, for example, after washing after harvesting (step SP2) and before transportation (step SP3), or when entering the factory The internal inspection may be performed after (step SP4) and before cleaning (step SP5).

In the above embodiment, the case where one tube voltage condition is determined and the inside of the pod is inspected has been described, but the present invention is not limited to this. For example, the inside of the pod may be inspected based on a plurality of pieces of X-ray image information acquired by X-rays irradiated under a plurality of conditions. Specifically, from among a plurality of X-ray image information with different tube voltage conditions, images with conditions suitable for inspecting the pods, the outer shape of the beans, and the surface of the beans are selected, and the non-defective and non-defective images of each pod and bean are selected. Good quality inspection may be performed.

28 pods 29 x-rays 30 pods 32 beans 40 insects

Claims (11)

Equipped with a process of inspecting by irradiating X-rays to pods that have not been wet-heated,
The inspecting step includes:
When the X-ray tube voltage is V (kV) and the speed of the pods passing through the X-ray irradiation area is S (m/min), the following formulas (1) and (2) are satisfied . ,
Defects that can be detected from the outline of the pod, defects that can be detected from the outline of the bean inside the pod of the pod, and defects that can be detected from the density of the bean area that is the area of the bean inside the pod at the same time. inspect
Method for inspecting pods.
10≦S≦60 (1)
25≦V≦S+40 (2) 2. The method for inspecting pods according to claim 1, wherein the inspecting step satisfies the following formula (3) when the speed S is in the range of 50≤S≤60.
1.5S-50≤V≤S+40 (3) 3. The method for inspecting a soybean according to claim 1, wherein the soybean is green soybean. The method for inspecting pods according to any one of claims 1 to 3, wherein the wet heating is an operation of steaming, boiling, or applying hot water. Equipped with a process of inspecting by irradiating X-rays to pods that have not been wet-heated,
The inspecting step includes:
When the X-ray tube voltage is V (kV) and the speed of the pods passing through the X-ray irradiation area is S (m/min), the following formulas (1) and (2) are satisfied. ,
Defects that can be detected from the outline of the pod, defects that can be detected from the outline of the bean inside the pod of the pod, and defects that can be detected from the density of the bean area that is the area of the bean inside the pod at the same time. inspect
A method for producing a pod food.
10≦S≦60 (1)
25≦V≦S+40 (2) 6. The method for producing a pod food product according to claim 5 , wherein the inspecting step satisfies the following formula (3) when the speed S is in the range of 50≤S≤60.
1.5S-50≤V≤S+40 (3) 7. The method for producing a soybean food product according to claim 5 or 6 , wherein the soybean is green soybean. The method for producing a pod food product according to any one of claims 5 to 7 , wherein the wet heating is steaming, boiling, or applying hot water. A step of irradiating X-rays to the pods that have not been wet-heated to obtain X-ray image information;
The gray value outside the pod region of the pod, the gray value of the pod region of the pod, the gray value of the bean outer edge of the bean inside the pod of the pod , and the above of the pod of the X-ray image information and measuring the gradation value of the bean area, which is the area of the bean inside the pod . The gradation difference between the gradation value outside the pod region and the pod region gradation value, the gradation difference between the pod region gradation value and the bean outer edge gradation value, and the bean outer rim gradation value 10. The method for inspecting pods according to claim 9 , wherein the gradation difference between the gradation value of the bean region and the gradation value of the bean region satisfies a condition that each of them is equal to or greater than a predetermined numerical value. further measuring the density value of the defective portion of the bean region;
The gradation difference obtained by dividing the gradation difference between the gradation value of the defective portion of the bean region and the gradation value of the bean region by the gradation difference between the gradation value of the outside of the pod region and the gradation value of the bean region. 11. The method for inspecting pods according to claim 9 or 10 , wherein the ratio satisfies a condition that the ratio is equal to or greater than a predetermined value.

Images