JP6732271B1 - Meat quality discrimination program and system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To automatically and accurately determine meat quality without resorting to human labor.
SOLUTION: In a meat quality discriminating program for discriminating meat quality, an information acquisition step for acquiring image information relating to the appearance of the meat quality to be discriminated, reference image information relating to the external appearance of meat quality acquired in the past, and three or more stages of meat quality. The discriminating step of discriminating the meat quality based on the reference image information corresponding to the image information acquired in the information acquiring step is executed by the computer by utilizing the degree of association of.
[Selection diagram] Fig. 3

Description

The present invention relates to a meat quality discriminating program and system suitable for discriminating meat quality with high accuracy.

The meat quality of meat is evaluated on the basis of items such as "fat crossing", "flesh color", "meat tightness and texture", "fat color and quality", and the like. Then, the meat quality is finally represented by the grade from the comprehensive discrimination result of each of these items. In the past, the meat quality of this meat was evaluated by a panelist (consumer) as a sensory evaluation by humans for the quality and characteristics of the meat (whether hard or soft, strong or weak flavor, etc.). However, the evaluation by the panelists often causes blurring, and it is often difficult to make a unified judgment. There are also cases where the meat quality is analyzed through equipment analysis, but if the equipment analysis is performed every time meat is shipped, labor and cost will increase.

Therefore, there has been a demand for a system capable of highly accurately evaluating meat quality without relying on sensory evaluation by humans or device analysis.

Therefore, the present invention has been devised in view of the above-mentioned problems, and the purpose thereof is to automatically and accurately determine the meat quality of meat without relying on sensory evaluation or instrumental analysis by humans. The object of the present invention is to provide a meat quality determination program and system capable of performing the above.

The meat quality determination program according to the present invention is a meat quality determination program for determining the meat quality of meat, an information acquisition step of acquiring image information of the image of the meat to be determined, reference image information of the meat imaged in the past, and meat quality. And a determination step of determining the meat quality by prioritizing one having a higher degree of association based on the reference image information corresponding to the image information acquired in the information acquisition step by using the degree of association of three or more levels with Is executed by a computer.

Even if there is no particular skill or experience, anyone can easily determine the meat quality with high accuracy without relying on human sensory evaluation or device analysis.

It is a block diagram showing the whole composition of the system to which the present invention is applied. It is a figure which shows the specific structural example of a search apparatus. It is a figure for demonstrating operation|movement of this invention. It is a figure for demonstrating operation|movement of this invention. It is a figure for demonstrating operation|movement of this invention. It is a figure for demonstrating operation|movement of this invention. It is a figure for demonstrating operation|movement of this invention. It is a figure for demonstrating operation|movement of this invention. It is a figure for demonstrating operation|movement of this invention. It is a figure for demonstrating operation|movement of this invention.

Hereinafter, a meat quality determination program to which the present invention is applied will be described in detail with reference to the drawings.

FIG. 1 is a block diagram showing an overall configuration of a meat quality determination system 1 in which a meat quality determination program to which the present invention is applied is installed. The meat quality determination system 1 includes an information acquisition unit 9, a determination device 2 connected to the information acquisition unit 9, and a database 3 connected to the determination device 2.

The information acquisition unit 9 is a device for a person who uses the system to input various commands and information, and is specifically configured by a keyboard, buttons, a touch panel, a mouse, a switch, and the like. The information acquisition unit 9 is not limited to a device for inputting text information, and may be a device such as a microphone capable of detecting a voice and converting the voice into text information. In addition, the information acquisition unit 9 may be configured as an imaging device capable of capturing an image of a camera or the like. The information acquisition unit 9 may be composed of a scanner having a function of recognizing a character string from a paper document. The information acquisition unit 9 may be integrated with the determination device 2 described below. The information acquisition unit 9 outputs the detected information to the determination device 2. The information acquisition unit 9 may be configured by a unit that specifies the position information by scanning the map information. The information acquisition unit 9 may be composed of an illuminance sensor for measuring a temperature sensor, a humidity sensor, and a wind direction sensor. In addition, the information acquisition unit 9 may be configured by a communication interface that acquires weather data from the Meteorological Agency or a private weather forecast company. The information acquisition unit 9 may be composed of a body sensor that is attached to the body to detect body data. The body sensor detects, for example, body temperature, heart rate, blood pressure, number of steps, walking speed, and acceleration. It may be configured with a sensor for performing. Further, the body sensor may be one that acquires biometric data of not only humans but also animals. In addition, the information acquisition unit 9 may be configured as a device that acquires information by scanning information such as drawings or reading it from a database. The information acquisition unit 9 may be configured by an odor sensor that detects an odor or scent other than these.

The database 3 stores various information necessary for performing meat quality determination. As information necessary for performing meat quality determination, reference image information of meat imaged in the past, reference ultrasonic image information previously imaged from a living body of a livestock providing meat, free amino acid analysis from meat, fatty acid composition, Reference analysis information that analyzes one or more of oleic acid, inosinic acid, guanylic acid, and vitamin E, reference production area information about the production area of the meat imaged in the past, reference obtained from the livestock of the livestock that provided the meat in the past Biometric information for use, reference breeding environment information regarding the breeding environment of livestock that provides the imaged meat in the past, reference feed information regarding feed that was applied to the livestock that provided the imaged meat in the past, and actual judgments against these The data set with the meat quality that has been processed is stored.

That is, in the database 3, in addition to such reference image information, reference ultrasonic image information, reference analysis information, reference production area information, reference biometric information, reference breeding environment information, reference bait information. Any one or more and meat quality are linked|related and memorize|stored.

The discriminating device 2 is composed of, for example, an electronic device such as a personal computer (PC), but is embodied in any other electronic device such as a mobile phone, a smartphone, a tablet type terminal, a wearable terminal, etc. in addition to the PC. It may be a materialized product. The user can obtain a search solution by this discriminating device 2.

FIG. 2 shows a specific configuration example of the discrimination device 2. The discriminating device 2 performs wired communication or wireless communication with a control unit 24 for controlling the entire discriminating device 2 and an operation unit 25 for inputting various control commands via operation buttons, a keyboard or the like. A communication unit 26, a determination unit 27 that makes various determinations, and a storage unit 28, which is represented by a hard disk or the like and stores a program for performing a search to be executed, are connected to the internal bus 21. .. Further, the internal bus 21 is connected to a display unit 23 as a monitor that actually displays information.

The control unit 24 is a so-called central control unit for controlling each component installed in the discrimination device 2 by transmitting a control signal via the internal bus 21. The control unit 24 also transmits various control commands via the internal bus 21 in response to an operation via the operation unit 25.

The operation unit 25 is embodied by a keyboard or a touch panel, and an execution command for executing a program is input by the user. When the user inputs the execution command, the operation unit 25 notifies the control unit 24 of the input. The control unit 24, which has received this notification, executes the desired processing operation in cooperation with each component including the determination unit 27. The operation unit 25 may be embodied as the information acquisition unit 9 described above.

The determination unit 27 determines the search solution. The discriminating unit 27 reads various information stored in the storage unit 28 and various information stored in the database 3 as necessary information when executing the discriminating operation. The discrimination unit 27 may be controlled by artificial intelligence. This artificial intelligence may be based on any known artificial intelligence technology.

The display unit 23 is configured by a graphic controller that creates a display image under the control of the control unit 24. The display unit 23 is realized by, for example, a liquid crystal display (LCD) or the like.

When the storage unit 28 is configured by a hard disk, under the control of the control unit 24, predetermined information is written to each address and is read out as needed. The storage unit 28 also stores a program for executing the present invention. This program is read and executed by the control unit 24.

The operation of the meat quality determination system 1 having the above configuration will be described.

In the meat quality determination system 1, for example, as shown in FIG. 3, it is premised that three or more levels of association between the reference image information and the meat quality are preset. The reference image information is obtained from the image information obtained by capturing an image of the appearance of meat, and can be obtained by analyzing the image information. This image may be a moving image as well as a still image. This reference image information may specify the meat quality by analyzing the imaged image of the meat. The reference image information is assumed to be composed of image data obtained by imaging meat that has been disassembled for meat, that is, at the time of slaughter, but it is composed of image data from the living body j of the livestock that provides meat. May be.

The meat quality referred to here may be expressed by, for example, “marbling”, that is, the degree of marbling, or may be evaluated based on the BMS (Beef Marbling Standard) criteria. In addition, the meat quality may be expressed by "the color of the meat". This "flesh color and color" is the color and gloss of the meat, and like "Marbling", the color of the meat was evaluated based on the BCS (Beef Color Standard) criteria. Good. The meat quality also includes luster. Meat quality includes "meat tightness and texture", which may be visually evaluated. This meat quality may be evaluated by the texture of meat, and when these are fine, a soft texture can be obtained. The meat quality includes "fat color and quality", and the color is judged on the basis of white or cream color and evaluated in consideration of gloss and quality.

The meat quality may be expressed through the grade of the meat, or the meat quality may be expressed by a ranking evaluated by the system side or the user side in five or ten levels. good. Or it could simply be a very tasty, delicious, ok, ordinary expression.

These meat qualities may be discriminated based on the previously learned characteristic amount. At this time, using artificial intelligence, the image data of meat and the meat quality are learned in advance, and when actually acquiring the reference image information, the meat quality is determined by comparing with these learned image data. You may do so.

Further, as an alternative to meat quality, any one or more of marbling, meat color tone, meat tightness, and fat color tone and quality may be output. In such a case, one or more of meat image data, marbling, meat color tone, meat tightness, fat color tone and quality are learned, and reference image information is actually acquired. At the time of performing the determination, the determination may be performed by comparing with the learned image data.

The meat quality may be judged as good or bad on the basis of previous experience by the evaluator, or may be actually tasted to judge the taste. In such a case, multiple inspectors tasting the meat quality evaluate the taste in terms of texture, sourness, fragrance, chewyness, bitterness, etc. in multiple stages, and statistically analyze them for quality. It may be an evaluation value. Further, the meat quality may be determined by a taste sensor capable of detecting the taste, or may be determined by analyzing various devices.

In the example of FIG. 3, the input data is, for example, reference image information P01 to P03. The reference image information P01 to P03 as such input data is linked to the meat quality as output. In this output, the meat quality as the output solution is displayed.

The reference image information is associated with each other with respect to the meat qualities A to D as the output solutions through three or more levels of association. The reference image information is arranged on the left side through this degree of association, and each meat quality is arranged on the right side through the degree of association. The degree of association indicates the degree to which the meat quality is highly related to the reference image information arranged on the left side. In other words, this degree of association is an index that indicates what kind of meat quality each reference image information is likely to be associated with, and the accuracy in selecting the most probable meat quality from the reference image information. Is shown. In the example of FIG. 3, w13 to w19 are shown as the degree of association. These w13 to w19 are shown in 10 levels as shown in Table 1 below, and the closer to 10 points, the higher the degree of association between each combination as an intermediate node and the meat quality as an output. On the contrary, the closer to 1 point, the lower the degree of association between each combination as an intermediate node and the price as an output.

The discriminating device 2 acquires in advance the association degrees w13 to w19 of three or more stages shown in FIG. That is, the discriminating device 2 accumulates past data sets to determine which of the reference image information and the meat quality in that case was adopted and evaluated in discriminating the actual search solution, and analyzes these. The degree of association shown in FIG. 3 is created by analysis.

For example, it is assumed that the meat quality A is evaluated as a large amount as the meat quality for the reference image information obtained by imaging the meat in the past. By collecting and analyzing such data sets, the degree of association with the reference image information becomes stronger.

This analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference image information P01, analysis is performed from various data obtained as a result of past evaluation of meat quality. In the case of reference image information P01, if there are many cases of meat quality A, the degree of association leading to this evaluation of meat quality is set higher, and if there are many cases of meat quality B, this evaluation of meat quality results. Set a higher degree of association. For example, in the example of the reference image information P01, the meat quality A and the meat quality C are linked, but from the previous case, the degree of association of w13 connected to the meat quality A is set to 7 and the degree of association of w14 connected to the meat quality C is set to 2. It is set to a point.

Further, the degree of association shown in FIG. 3 may be composed of nodes of a neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, it is not limited to the neural network, and may be composed of any decision-making factor that constitutes artificial intelligence.

In such a case, as shown in FIG. 4, reference image information is input as input data, meat quality is output as output data, and at least one hidden layer is provided between the input node and the output node. You may make it learn. The above-mentioned degree of association is set in either or both of the input node and the hidden layer node, and this becomes the weighting of each node, and the output is selected based on this. Then, when the degree of association exceeds a certain threshold, the output may be selected.

Such a degree of association is the learned data in artificial intelligence. After creating such learned data through a dataset of the image of the appearance of the meat to be evaluated previously and the meat quality that was actually discriminated and evaluated, in order to actually discriminate the meat quality from the above, Meat quality will be searched using the learned data. In such a case, image information of actually picked up meat in the area to be discriminated is newly acquired. The image information to be newly acquired is input by the information acquisition unit 9 described above. The image information is acquired by capturing an image of which meat is to be discriminated. This determination method may be performed by the same method as the above-described reference image information.

The meat quality is determined based on the image information newly acquired in this way. In such a case, the pre-acquired association degree shown in FIG. 3 (Table 1) is referred to. For example, when the newly acquired image information is the same as or similar to P02, the meat quality B is associated with w15 and the meat quality C is associated with the association degree w16 via the association degree. In such a case, the meat quality B with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one having the highest degree of association as the optimal solution, and the meat quality C which has the degree of association but is recognized as the association itself may be selected as the optimal solution. In addition to this, it goes without saying that an output solution to which no arrow is connected may be selected, and any other priority may be selected as long as it is based on the degree of association.

In this way, the most suitable meat quality can be searched for from the newly acquired image information and displayed to the user. By looking at the search result, the user, that is, the meat quality producer, the seller, and the distributor can sort the meat based on the searched meat quality, can predict the taste of the meat, and further You can decide the price of.

Note that the above-mentioned image may be any one or more of a spectrum image and an ultrasonic image other than an image captured by a normal camera. In such a case, as the reference image information, it is necessary to capture at least one of a spectrum image, a visible image, and an ultrasonic image according to the acquired image information. In particular, when this ultrasonic image is used, biometric data of meat in a living body of a livestock providing meat may be imaged.

In the example of FIG. 5, it is premised that a combination of the reference image information and the reference ultrasonic image information is formed. Here, the reference image information is image data of meat taken during past slaughter. The reference image information is an image captured by a normal camera, but may be composed of a spectral image that is color-coded for each frequency band. On the other hand, the reference ultrasonic image information is ultrasonic image data of a portion of a meat imaged in advance in a living body of a domestic animal that provides meat.

In addition to such reference image information, determination is made by combining reference ultrasonic image information, whereby the meat quality can be determined with higher accuracy. Therefore, in addition to the reference image information, the reference ultrasonic image information is combined to form the above-mentioned degree of association.

In the example of FIG. 5, it is assumed that the input data is, for example, reference image information P01 to P03 and reference ultrasonic image information P14 to 17. A combination of the reference image information as the input data and the reference ultrasonic image information is the intermediate node shown in FIG. Each intermediate node is further connected to an output. In this output, the meat quality as the output solution is displayed.

Each combination (intermediate node) of the reference image information and the reference ultrasonic image information is associated with each other through the three or more levels of association with the meat quality as the output solution. The reference image information and the reference ultrasonic image information are arranged on the left side through this degree of association, and the meat quality is arranged on the right side through the degree of association. The degree of association indicates the degree to which the reference image information and the reference ultrasonic image information arranged on the left side are highly related to the meat quality. In other words, this degree of association is an index indicating which meat quality each reference image information and reference ultrasonic image information is likely to be associated with, and the reference image information and the reference ultrasonic image. It shows the accuracy in selecting the most probable meat quality from the information. Therefore, the optimum meat quality is searched for by the combination of the reference image information and the reference ultrasonic image information.

In the example of FIG. 5, w13 to w22 are shown as the degree of association. These w13 to w22 are shown in 10 levels as shown in Table 1, and the closer to 10 points, the higher the degree of association between each combination as an intermediate node and the output, and conversely to 1 point. The closer to each other, the lower the degree of association between each combination as an intermediate node and the output.

The discriminating device 2 acquires in advance the association degrees w13 to w22 of three or more stages shown in FIG. That is, the discriminating device 2 accumulates past data to determine which of the reference image information and the reference ultrasonic image information, and the meat quality in that case, is suitable for discriminating the actual search solution. By analyzing these, the association degree shown in FIG. 5 is created.

For example, it is assumed that the reference image information in the past actual cases is the image data α. The reference ultrasonic image information is image data β. In such a case, the meat quality that shows how much the meat quality was actually learned as a data set and defined in the form of the above-mentioned degree of association. Note that such reference image information and reference ultrasonic image information may be extracted from a management database managed by a producer, a seller, a distributor, or the like.

This analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference image information P01 and the reference ultrasonic image information P16, the meat quality is analyzed from past data. When there are many cases where the meat quality is A (sweetness degree 〇, sourness degree 〇, bitterness degree 〇, chewy texture etc.), the association degree leading to this meat quality A is set higher, and the case of meat quality B is set. When there are many cases of meat quality A and there are few cases of meat quality A, the degree of association with meat quality B is set high and the degree of association with meat quality A is set low. For example, in the example of the intermediate node 61a, although the outputs of the meat quality A and the quality B are linked, the association degree of w13 connected to the meat quality A is 7 points and the association degree of w14 connected to the meat quality B is 2 points from the previous example. Is set to.

Further, the degree of association shown in FIG. 5 may be configured by the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, it is not limited to the neural network, and may be composed of any decision-making factor that constitutes artificial intelligence. Other configurations related to artificial intelligence are the same as those described in FIG.

In the example of the association degree shown in FIG. 5, the node 61b is a node of a combination of the reference ultrasonic image information P14 with the reference image information P01, and the association degree of the meat quality C is w15 and the association degree of the meat quality E. Is w16. The node 61c is a node that is a combination of the reference ultrasonic image information P15 and P17 with respect to the reference image information P02, and the association degree of the meat quality B is w17 and the association degree of the meat quality D is w18.

Such a degree of association is the learned data in artificial intelligence. After making such learned data, when actually determining the meat quality, the above-mentioned learned data is used. In such a case, the image information of the meat for which the meat quality is to be actually determined and the ultrasonic image information are input or selected.

The optimum meat quality is searched based on the image information and the ultrasonic image information newly acquired in this way. In such a case, the association degree shown in FIG. 5 (Table 1) acquired in advance is referred to. For example, when the newly acquired image information is the same as or similar to P02 and the ultrasonic image information is P17, the node 61d is associated through the association degree, In this node 61d, the meat quality C is associated with w19 and the meat quality D is associated with the association degree w20. In such a case, the meat quality C with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one having the highest degree of association as the optimum solution, and the meat quality D which has the degree of association but has the association itself may be selected as the optimal solution. In addition to this, it goes without saying that an output solution to which no arrow is connected may be selected, and any other priority may be selected as long as it is based on the degree of association.

Table 2 below shows examples of the association degrees w1 to w12 extending from the input.

The intermediate node 61 may be selected based on the association degrees w1 to w12 extending from this input. That is, the greater the association degrees w1 to w12, the heavier the weighting in selecting the intermediate node 61 may be. However, the degrees of association w1 to w12 may all be the same value, and the weighting in the selection of the intermediate node 61 may be all the same.

In addition to the above-mentioned reference image information, a combination of reference spectral information instead of the above-mentioned reference ultrasonic image information and three or more levels of association with meat quality for the combination may be set. Good.

By the way, the ultrasonic image information and ultrasonic image information described above is not limited to the case of capturing ultrasonic image data at a certain point of time for livestock applied as meat, in a time series from the living body of the livestock. The ultrasonic image may be captured multiple times and the time-series change tendency thereof may be acquired. The association degree is formed as reference ultrasonic image information including such time-series changes in ultrasonic image data, and multiple times are taken in time series from the living body of the livestock that provides the meat to be determined. When the time series change tendency of the ultrasonic image is acquired, the determination is performed by inputting this as the input data.

In FIG. 6, in addition to the above-mentioned reference image information, a combination of reference analysis information instead of the above-mentioned reference ultrasonic image information, and three or more levels of association with meat quality for the combination are set. An example is shown.

This reference analysis information, which is added as an explanatory variable instead of the reference ultrasonic image information, is all information about the results of chemical and physical analysis performed on meat. The reference analytical information may include analytical information obtained by analyzing any one or more of free amino acid analysis, fatty acid composition, oleic acid, inosinic acid, guanylic acid, and vitamin E. In free amino acid analysis, the ratio of various amino acids such as glutamic acid which is an umami component is analyzed. In the analysis of fatty acid composition, the results of quantitative analysis of various fatty acids such as oleic acid contained in adipose tissue are shown as evaluation criteria for texture such as mellowness and dry mouth. Oleic acid is analyzed because it is evaluated as soft and tasty as it contains a large amount of monovalent unsaturated fatty acids. Inosinic acid is a type of organic compound, inosinic acid, which is said to be an umami component of bonito flakes, and is said to increase due to aging after dismantling treatment. Guanilic acid is analyzed because guanic acid elicits the umami component of shiitake mushrooms. In addition, Vitamin E is also analyzed because it affects umami.

Since each index included in such reference analysis information also influences the taste of meat, it is possible to improve the determination accuracy by combining with the reference image information and determining the meat quality through the degree of association.

Both the reference analysis information and the analysis information may be analysis performed on the meat at the time of slaughter, or may be analysis performed on the living body of the livestock providing the meat.

In the example of FIG. 6, it is assumed that the input data is, for example, reference image information P01 to P03 and reference analysis information P18 to 21. A combination of the reference image information as such input data and the reference analysis information is the intermediate node shown in FIG. Each intermediate node is further connected to an output. In this output, the meat quality as the output solution is displayed.

Each combination (intermediate node) of the reference image information and the reference analysis information is associated with each other through the association degree of the meat quality of three or more levels as the output solution. The reference image information and the reference analysis information are arranged on the left side through this degree of association, and the meat quality is arranged on the right side through the degree of association. The degree of association indicates the degree to which the reference image information and the reference analysis information arranged on the left side are highly related to the meat quality. In other words, this degree of association is an index that indicates what kind of meat quality each reference image information and reference analysis information is likely to be associated with, and is the most reliable from the reference image information and the reference analysis information. It shows the accuracy in selecting the proper meat quality.

The discriminator 2 acquires in advance the degree of association w13 to w22 of three or more levels shown in FIG. In other words, which of the reference image information, the reference analysis information obtained when acquiring the reference image information, and the meat quality in that case is preferable for the determination device 2 to determine the actual search solution. By accumulating past data and analyzing them, the association degree shown in FIG. 6 is created.

For example, at the time of actual meat quality evaluation in the past, for certain reference image information, the reference analysis information is that the content of oleic acid is XX and the content of inosinic acid is □□. To do. In such a case, when there are many cases in which the meat quality is determined to be A, these are learned as a data set and defined in the form of the above-mentioned degree of association.

This analysis may be performed by artificial intelligence. In such a case, for example, when the reference image information P01 is the reference analysis information P20, the meat quality is analyzed from past data. When there are many cases of meat quality A, the degree of association that this meat quality leads to A is set higher, and when there are many cases of meat quality B and when there are few cases of meat quality A, the degree of association that connects meat quality to B Is set to a higher value, and the degree of association that connects meat quality to A is set to be lower. For example, in the example of the intermediate node 61a, the outputs of the meat quality A and the meat quality B are linked, but from the previous case, the degree of association of w13 connected to the meat quality A is 7 points and the degree of association of w14 connected to the meat quality B is 2 points. Is set to.

Further, the degree of association shown in FIG. 6 may be configured by the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, it is not limited to the neural network, and may be composed of any decision-making factor that constitutes artificial intelligence. Other configurations related to artificial intelligence are the same as those described in FIG.

In the example of the degree of association shown in FIG. 6, the node 61b is a node of a combination of the reference image information P01 and the reference analysis information P18, and the degree of association of the meat quality C is w15 and the degree of association of the meat quality E is w16. Has become. The node 61c is a node that is a combination of the reference analysis information P19 and P21 with respect to the reference image information P02, and the degree of association of meat quality B is w17 and the degree of association of meat quality D is w18.

Such a degree of association is the learned data in artificial intelligence. After creating such learned data, the above-mentioned learned data is used when actually searching the meat quality from now on. In such a case, the image information of the meat quality discrimination target and the analysis information are actually acquired. Here, the analysis information is newly acquired when the meat quality is actually estimated, but the acquisition method is the same as the above-mentioned reference analysis information.

By the way, the reference analysis information is obtained by pre-analyzing any one or more of free amino acid analysis, fatty acid composition, oleic acid, inosinic acid, guanylic acid, and vitamin E according to this analysis information, and this is used as a reference analysis. As information, the degree of association with the combination with the reference image information is formed.

The optimum meat quality is searched based on the image information newly acquired in this way and the analysis information. In such a case, the association degree shown in FIG. 6 (Table 1) acquired in advance is referred to. For example, when the newly acquired image information is the same as or similar to P02 and the analysis information is the same as or similar to P21, the node 61d is associated via the association degree. In this node 61d, the meat quality C is associated with w19 and the meat quality D is associated with the degree of association w20. In such a case, the meat quality C with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one having the highest degree of association as the optimum solution, and the meat quality D which has the degree of association but has the association itself may be selected as the optimal solution. In addition to this, it goes without saying that an output solution to which no arrow is connected may be selected, and any other priority may be selected as long as it is based on the degree of association.

In FIG. 7, in addition to the reference image information described above, a combination of the reference ultrasonic image information described above, instead of the reference ultrasonic image information, and the meat quality for the combination is set in three or more levels. An example is shown.

This reference production area information added as an explanatory variable instead of the reference ultrasonic image information is information on the production area of the meat, for example, the country level such as the United States and Japan, the regional level such as Tohoku region and Kyushu region, Hokkaido and It may be indicated at the prefecture level such as Kagoshima Prefecture, or at the Hokkaido group or town level, or at the ranch level. Since the meat production area included in the reference production area information also affects the taste of the meat, the discrimination accuracy can be improved by combining the image with the reference image information and discriminating the meat quality based on the degree of association.

In the example of FIG. 7, it is assumed that the input data is, for example, reference image information P01 to P03 and reference production area information P18 to P21. A combination of the reference image information as the input data and the reference production area information is the intermediate node shown in FIG. 7. Each intermediate node is further connected to an output. In this output, the meat quality as the output solution is displayed.

Each combination (intermediate node) of the reference image information and the reference production area information is associated with each other through the three or more levels of association with the meat quality as the output solution. The reference image information and the reference production area information are arranged on the left side through this degree of association, and the meat quality is arranged on the right side through the degree of association. The degree of association indicates the degree to which the reference image information and the reference production area information arranged on the left side are highly related to the meat quality. In other words, this degree of association is an index that indicates what kind of meat quality each of the reference image information and the reference production area information is likely to be associated with, and is the most reliable from the reference image information and the reference production area information. It shows the accuracy in selecting the proper meat quality.

The discriminator 2 acquires in advance the association degrees w13 to w22 of three or more levels shown in FIG. In other words, which of the reference image information, the reference production area information obtained when acquiring the reference image information, and the meat quality in that case is preferable for the determination device 2 to determine the actual search solution. By accumulating past data and analyzing these, the association degree shown in FIG. 7 is created.

This analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference image information P01 and the reference production area information P20, the meat quality is analyzed from past data. When there are many cases of meat quality A, the degree of association that this meat quality leads to A is set higher, and when there are many cases of meat quality B and when there are few cases of meat quality A, the degree of association that connects meat quality to B Is set to a higher value, and the degree of association that connects meat quality to A is set to be lower. For example, in the example of the intermediate node 61a, the outputs of the meat quality A and the meat quality B are linked, but from the previous case, the degree of association of w13 connected to the meat quality A is 7 points and the degree of association of w14 connected to the meat quality B is 2 points. Is set to.

Further, the degree of association shown in FIG. 7 may be configured by the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, it is not limited to the neural network, and may be composed of any decision-making factor that constitutes artificial intelligence. Other configurations related to artificial intelligence are the same as those described in FIG.

In the example of the degree of association shown in FIG. 7, the node 61b is a node of a combination of the reference image information P01 and the reference production area information P18, and the degree of association of the meat quality C is w15 and the degree of association of the meat quality E is w16. Has become. The node 61c is a node of a combination of the reference image information P02 and the reference production area information P19 and P21, and the degree of association of the meat quality B is w17 and the degree of association of the meat quality D is w18.

Such a degree of association is the learned data in artificial intelligence. After creating such learned data, the above-mentioned learned data is used when actually searching the meat quality from now on. In such a case, the image information of the meat quality determination target and the production area information are actually acquired. Here, the production area information is newly acquired when the meat quality is actually estimated, and the acquisition method is the same as that of the reference production area information described above. The method of acquiring production area information and reference production area information is as follows: keyboard input to a device such as a PC or smartphone, or character information or a two-dimensional code written on a label on which the production area is recorded for meat and analyzed. You may acquire by doing.

The optimum meat quality is searched for based on the image information newly obtained in this way and the production area information. In such a case, the previously acquired association degree shown in FIG. 7 (Table 1) is referred to. For example, when the newly acquired image information is the same as or similar to P02 and the production area information is the same as or similar to P21, the node 61d is associated through the association degree. In this node 61d, the meat quality C is associated with w19 and the meat quality D is associated with the degree of association w20. In such a case, the meat quality C with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one having the highest degree of association as the optimum solution, and the meat quality D which has the degree of association but has the association itself may be selected as the optimal solution. In addition to this, it goes without saying that an output solution to which no arrow is connected may be selected, and any other priority may be selected as long as it is based on the degree of association.

In FIG. 8, in addition to the above-mentioned reference image information, a combination of reference biological information instead of the above-mentioned reference ultrasonic image information, and three or more levels of association with meat quality for the combination are set. An example is shown.

The reference biometric information added as an explanatory variable instead of the reference ultrasonic image information includes all biometric data measured on the living body of the livestock that supplies the meat. The types of biometric data of livestock include all biometric data such as heart rate, body temperature, electrocardiogram, blood pressure, blood test results, and weight of livestock. Since the data regarding the living body included in the reference biometric information also affects the taste of the meat, it is possible to improve the discrimination accuracy by combining with the reference image information and discriminating the meat quality based on the degree of association.

In the example of FIG. 8, it is assumed that the input data is, for example, reference image information P01 to P03 and reference biometric information P18 to P21. A combination of the reference image information as such input data and the reference biometric information is the intermediate node shown in FIG. Each intermediate node is further connected to an output. In this output, the meat quality as the output solution is displayed.

The respective combinations (intermediate nodes) of the reference image information and the reference biometric information are associated with each other through the three or more levels of association with the meat quality as the output solution. The reference image information and the reference biometric information are arranged on the left side through this degree of association, and the meat quality is arranged on the right side through the degree of association. The degree of association indicates the degree to which the reference image information and the reference biometric information arranged on the left side are highly related to the meat quality. In other words, this degree of association is an index that indicates what kind of meat quality each reference image information and reference biometric information is likely to be associated with, and is the most probable from the reference image information and the reference biometric information. It shows the accuracy in selecting the proper meat quality.

The discriminator 2 acquires in advance the association degrees w13 to w22 of three or more levels shown in FIG. In other words, the discrimination device 2 accumulates past data on which of the reference image information, the reference biometric information, and the meat quality in that case is preferable in determining the actual search solution. Are analyzed, and the degree of association shown in FIG. 8 is created.

This analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference image information P01 and the reference biometric information P20, the meat quality is analyzed from past data. When there are many cases of meat quality A, the degree of association that this meat quality leads to A is set higher, and when there are many cases of meat quality B and when there are few cases of meat quality A, the degree of association that connects meat quality to B Is set to a higher value, and the degree of association that connects meat quality to A is set to a lower value. For example, in the example of the intermediate node 61a, the outputs of the meat quality A and the meat quality B are linked, but from the previous case, the degree of association of w13 connected to the meat quality A is 7 points and the degree of association of w14 connected to the meat quality B is 2 points. Is set to.

Further, the degree of association shown in FIG. 8 may be composed of nodes of a neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, it is not limited to the neural network, and may be composed of any decision-making factor that constitutes artificial intelligence. Other configurations related to artificial intelligence are the same as those described in FIG.

In the example of the degree of association shown in FIG. 8, the node 61b is a node of a combination of the reference image information P01 and the reference biometric information P18, and the degree of association of meat quality C is w15 and the degree of association of meat quality E is w16. Has become. The node 61c is a node which is a combination of the reference biometric information P19 and P21 with respect to the reference image information P02, and the degree of association of the meat quality B is w17 and the degree of association of the meat quality D is w18.

Such a degree of association is the learned data in artificial intelligence. After creating such learned data, the above-mentioned learned data is used when actually searching the meat quality from now on. In such a case, the image information and the biological information for which the meat quality is to be discriminated are actually acquired. Here, the biometric information is newly acquired when the meat quality is actually estimated, and the acquisition method is the same as the above-described reference biometric information.

The optimum meat quality is searched based on the image information newly acquired in this way and the biological information. In such a case, the association degree shown in FIG. 8 (Table 1) acquired in advance is referred to. For example, when the newly acquired image information is the same as or similar to P02 and the biometric information is the same as or similar to P21, the node 61d is associated via the association degree. In this node 61d, the meat quality C is associated with w19 and the meat quality D is associated with the degree of association w20. In such a case, the meat quality C with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one having the highest degree of association as the optimum solution, and the meat quality D which has the degree of association but has the association itself may be selected as the optimal solution. In addition to this, it goes without saying that an output solution to which no arrow is connected may be selected, and any other priority may be selected as long as it is based on the degree of association.

The biometric information and the reference biometric information described above may be obtained by obtaining biometric data from a living body a plurality of times in a time series at time intervals and including a time series change tendency of the biometric data. As a result, it becomes possible to judge the meat quality, including the time-series trends of the biometric data of livestock.

In FIG. 9, in addition to the above-mentioned reference image information, a combination of the above-mentioned reference ultrasonic image information with the reference breeding environment information, and the degree of association of meat quality with respect to the combination in three or more stages are set. It shows an example.

This reference breeding environment information, which is added as an explanatory variable instead of the reference ultrasonic image information, includes all data regarding the environment for breeding the livestock that supplies the meat. The types of data for this breeding environment information for reference include temperature, humidity, wind direction, day illuminance, degree of indoor lighting, degree of indoor lighting, voice data, pest control status, cleaning status, manure processing status, etc. It contains all information about the breeding environment. Since the data included in the reference breeding environment information also affects the taste of meat, by combining with the reference image information and determining the meat quality based on the degree of association, it is possible to improve the determination accuracy.

In the example of FIG. 9, it is assumed that the input data is, for example, reference image information P01 to P03 and reference breeding environment information P18 to 21. The reference image information as such input data combined with the reference breeding environment information is the intermediate node shown in FIG. Each intermediate node is further connected to an output. In this output, the meat quality as the output solution is displayed.

Each combination (intermediate node) of the reference image information and the reference breeding environment information is associated with each other through the three or more levels of association with the meat quality as the output solution. The reference image information and the reference breeding environment information are arranged on the left side through this degree of association, and the meat quality is arranged on the right side through the degree of association. The degree of association indicates the degree to which the reference image information and the reference breeding environment information arranged on the left side are highly related to the meat quality. In other words, this degree of association is an index indicating what kind of meat quality each reference image information and reference breeding environment information is likely to be associated with, and from the reference image information and the reference breeding environment information, It shows the accuracy in selecting the most probable meat quality.

The discriminator 2 acquires in advance the degree of association w13 to w22 of three or more levels shown in FIG. That is, the discrimination device 2 accumulates past data, which is preferable for the reference image information, the reference breeding environment information, and the meat quality in that case in determining the actual search solution. By analyzing these, the degree of association shown in FIG. 9 is created.

This analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference image information P01 and the reference breeding environment information P20, the meat quality is analyzed from past data. When there are many cases of meat quality A, the degree of association that this meat quality leads to A is set higher, and when there are many cases of meat quality B and when there are few cases of meat quality A, the degree of association that connects meat quality to B Is set to a higher value, and the degree of association that connects meat quality to A is set to a lower value. For example, in the example of the intermediate node 61a, the outputs of the meat quality A and the meat quality B are linked, but from the previous case, the degree of association of w13 connected to the meat quality A is 7 points and the degree of association of w14 connected to the meat quality B is 2 points. Is set to.

Further, the degree of association shown in FIG. 9 may be composed of nodes of a neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, it is not limited to the neural network, and may be composed of any decision-making factor that constitutes artificial intelligence. Other configurations related to artificial intelligence are the same as those described in FIG.

In the example of the degree of association shown in FIG. 9, the node 61b is a node of a combination of the reference image information P01 and the reference breeding environment information P18, and the degree of association of the meat quality C is w15 and the degree of association of the meat quality E is w16. Has become. The node 61c is a node which is a combination of the reference breeding environment information P19 and P21 with respect to the reference image information P02, and the association degree of the meat quality B is w17 and the association degree of the meat quality D is w18.

Such a degree of association is the learned data in artificial intelligence. After creating such learned data, the above-mentioned learned data is used when actually searching the meat quality from now on. In such a case, the image information of the meat quality discrimination target and the breeding environment information are actually acquired. Here, the breeding environment information is newly obtained when the meat quality is actually estimated, and the obtaining method is the same as the above-mentioned reference breeding environment information.

The optimum meat quality is searched for based on the image information newly acquired in this way and the breeding environment information. In such a case, the degree of association shown in FIG. 9 (Table 1) acquired in advance is referred to. For example, when the newly acquired image information is the same as or similar to P02 and the breeding environment information is the same as or similar to P21, the node 61d is associated through the association degree. In this node 61d, the meat quality C is associated with w19 and the meat quality D is associated with the degree of association w20. In such a case, the meat quality C with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one having the highest degree of association as the optimum solution, and the meat quality D which has the degree of association but has the association itself may be selected as the optimal solution. In addition to this, it goes without saying that an output solution to which no arrow is connected may be selected, and any other priority may be selected as long as it is based on the degree of association.

Further, the breeding environment information may be replaced with the feed information regarding the feed given to the livestock. In such a case, as a substitute for the reference breeding environment information, the reference bait information relating to the bait that has been obtained on the livestock previously acquired is formed in advance in association with the reference image information. Then, when the feed information regarding the feed of the livestock that newly provides the meat to be determined is acquired, the meat quality is determined based on the feed information.

In the above-mentioned degree of association, the degree of association is expressed by a 10-level evaluation, but the present invention is not limited to this, as long as the degree of association is expressed by 3 or more levels, and conversely 3 or more levels. For example, it may be 100 steps or 1000 steps. On the other hand, this degree of association does not include two levels, that is, whether or not they are associated with each other and expressed by either 1 or 0.

According to the present invention configured as described above, anyone can easily determine/search for meat quality without special skills or experience. Further, according to the present invention, it is possible to make the determination of the search solution with higher accuracy than human beings. Further, by configuring the above-mentioned degree of association with artificial intelligence (neural network or the like), it is possible to further improve the discrimination accuracy by learning this.

In many cases, the input data and the output data described above are not completely the same in the learning process, and thus may be information obtained by classifying the input data and the output data by type. That is, the information P01, P02,... P15, 16,... That composes the input data is classified according to the criteria classified in advance on the system side or the user side according to the content of the information, and the classified input. A data set may be created between the data and the output data and the learning may be performed.

Note that, in the degree of association described above, in addition to the reference image information, reference ultrasonic image information, reference analysis information, reference production area information, reference biometric information, reference breeding environment information, and reference bait information Although the description has been given by taking the case of the combination of the above as an example, the present invention is not limited to this. That is, the degree of association is, in addition to the reference image information, any two or more of the reference ultrasonic image information, the reference analysis information, the reference production area information, the reference biometric information, the reference breeding environment information, and the reference bait information. It may be configured by a combination of. In addition to the reference image information, the degree of association is one or more of reference ultrasound image information, reference analysis information, reference production area information, reference biometric information, reference breeding environment information, and reference bait information. In addition, other factors may be added to this combination to form the degree of association.

In any case, data matching the reference information of the degree of association is input, and the degree of association is used to determine the meat quality.

Further, according to the present invention, as shown in FIG. 10, the meat quality is determined based on the degree of association of a combination of two or more types of information, reference information U and reference information V. The reference information Y is reference image information, and the reference information V is reference ultrasonic image information, reference analysis information, reference production area information, reference biometric information, reference breeding environment information, reference bait information. It is assumed to be either.

At this time, as shown in FIG. 10, the output obtained for the reference information U may be used as the input data as it is, and may be associated with the output (meat quality) via the intermediate node 61 in combination with the reference information V. .. For example, with respect to the reference information U (reference image information), after outputting an output solution as shown in FIG. 3, this is input as it is and the degree of association with other reference information V is used, The output (meat quality) may be searched.

Further, according to the present invention, instead of determining the meat quality as the output, the breeding condition of the livestock for improving the meat quality may be used as the output solution. In such a case, the breeding conditions for livestock are included in the dataset for learning the degree of association, instead of meat quality. The conditions for raising livestock include the food to be given to the livestock, the temperature, humidity, wind direction, daylight intensity, the degree of indoor lighting, the degree of indoor lighting, voice data, the extermination status of pests, the cleaning status, and the processing status of manure, etc. for the livestock. May be used.

Further, according to the present invention, it is characterized in that an optimum solution search is performed through the association degrees set in three or more stages. The degree of association can be described by a numerical value of 0 to 100%, for example, in addition to the 10 steps described above. It may be configured.

By discriminating the most probable meat quality based on the degree of association represented by a numerical value of three or more levels, the search is performed in descending order of the degree of association in a situation in which there are multiple possible candidates for the search solution. It is also possible to display it. If it is possible to display to the user in the descending order of the degree of association as described above, it is possible to preferentially display more probable search solutions.

In addition to this, according to the present invention, it is possible to make a determination without missing the determination result of an output having an extremely low degree of association such as 1%. Remind the user that even a discrimination result with a very low degree of association is connected as a slight symptom, and may be useful as the discrimination result once every tens or hundreds of times. be able to.

Further, according to the present invention, there is an advantage that the search policy can be determined by the method of setting the threshold value by performing the search based on the degree of association of three or more stages. If the threshold value is set low, even if the above-mentioned degree of association is 1%, it can be picked up without omission, but there is a low possibility that a more appropriate discrimination result can be suitably detected, and a lot of noise may be picked up. is there. On the other hand, if the threshold value is set high, it is highly possible that the optimal search solution can be detected with high probability, but normally, the degree of association is low, and although it is passed through, it appears once in tens or hundreds of times. In some cases, the solution is overlooked. It is possible to decide which is to be emphasized based on the idea of the user side and the system side, but it is possible to increase the degree of freedom in selecting such a point to be emphasized.

Further, in the present invention, the above-mentioned degree of association may be updated. This update may reflect information provided via a public communication network such as the Internet. Further, when each reference information including the reference image information is acquired, and the knowledge, information, and data regarding the meat quality and the improvement measure for these are acquired, the degree of association is increased or decreased according to these.

In other words, this update is equivalent to learning in artificial intelligence. This is a learning act because new data is acquired and reflected in the learned data.

In addition to updating the association degree, the system side or the user side may update the information based on the contents of research data and papers by experts, conference presentations, newspaper articles, books, etc. It may be updated artificially or automatically. You may make it utilize artificial intelligence in these update processes.

Further, not only supervised learning but also unsupervised learning, deep learning, reinforcement learning, etc. may be used for the process of first creating a learned model and the above-mentioned update. In the case of unsupervised learning, instead of reading a data set of input data and output data for learning, information corresponding to the input data is read for learning, and the degree of association related to the output data is self-formed from there. It may be allowed to.

1 meat quality discrimination system 2 discrimination device 21 internal bus 23 display unit 24 control unit 25 operation unit 26 communication unit 27 discrimination unit 28 storage unit 61 node

Claims (12)

In the meat quality determination program that determines the meat quality of meat,
An information acquisition step of acquiring image information obtained by imaging the meat to be discriminated,
Using the reference image information of the meat imaged in the past and the degree of association of meat quality in three or more stages, the degree of association is higher based on the reference image information corresponding to the image information acquired in the information acquisition step. A meat quality determination program characterized by causing a computer to execute a determination step of determining the meat quality by giving priority to one . In the information acquisition step, as the image information, a spectral image is acquired,
The meat quality discriminating program according to claim 1, wherein in the discriminating step, the image information captured as a spectral image is used as the reference image information. The information acquisition step, the image information obtained by imaging the meat at the time of slaughter, and ultrasonic image information previously captured for the living body of the livestock that provides the meat,
In the determining step, a combination having the reference image information of the meat imaged at the time of past slaughter and the reference ultrasonic image information previously imaged for the living body of the livestock providing the meat, and the meat quality. The meat quality according to claim 1, wherein the meat quality is determined based on the reference ultrasonic image information corresponding to the ultrasonic image information acquired in the information acquisition step, by using the degree of association of three or more levels. Discrimination program. In the information acquisition step, as the ultrasonic image information, to obtain a time-series change tendency of the ultrasonic images captured a plurality of times in a time series to the living body,
The meat quality according to claim 3, wherein in the determining step, as the reference ultrasonic image information, a time-series change tendency of ultrasonic images obtained by imaging a living body a plurality of times in a time-series is acquired. Discrimination program. The information acquisition step acquires analysis information obtained by analyzing any one or more of free amino acids , fatty acid composition, oleic acid, inosinic acid, guanylic acid, and vitamin E from the meat,
In the discrimination step, the reference image information obtained by previously analyzing any one or more of the reference image information and free amino acid , fatty acid composition, oleic acid, inosinic acid, guanylic acid, or vitamin E corresponding to the analysis information is acquired. Characterized by using a combination having information and three or more levels of association with the meat quality, and further determining the meat quality based on the reference analysis information corresponding to the analysis information acquired in the information acquisition step. The meat quality determination program according to claim 1 . In the information acquisition step, the production area information regarding the production area of the meat is obtained,
In the determination step, a combination having the reference image information and the reference production area information regarding the production area of the meat imaged in the past, and three or more levels of association with the meat quality are used, and further in the information acquisition step. The meat quality determination program according to claim 1 or 2 , wherein the meat quality is determined based on the reference production area information corresponding to the acquired production area information. In the information acquisition step, the biological information acquired from the living body of the livestock that provides the meat,
In the determination step, a combination having the reference image information and the reference biometric information acquired from a living body of a livestock that provides meat in the past, and a degree of association of three or more levels with the meat quality are used, and The meat quality determination program according to claim 1 or 2 , wherein the meat quality is determined based on the reference biometric information corresponding to the biometric information acquired in the information acquisition step. In the information acquisition step, as the biometric information, a time-series change tendency of biometric data acquired multiple times in a time series from a living body is acquired,
The meat quality discriminating program according to claim 7, wherein, in the discriminating step, a time-series change tendency of biometric data obtained from a living body a plurality of times in a time series is acquired as the reference biometric information. In the information acquisition step, acquiring breeding environment information regarding the breeding environment of the livestock that provides the meat,
In the determining step, a combination having the reference image information and a reference breeding environment information relating to the breeding environment of livestock that provides the meat imaged in the past, and a degree of association of three or more levels with the meat quality are used, The meat quality discriminating program according to claim 1 or 2 , further comprising: discriminating the meat quality based on the reference breeding environment information corresponding to the breeding environment information acquired in the information acquisition step. In the information acquisition step, obtain bait information regarding bait given to the livestock providing the meat,
In the determining step, a combination having the reference image information and reference bait information related to baits provided to livestock that provides meat imaged in the past, and a degree of association of three or more levels with the meat quality are used, The meat quality determination program according to claim 1 or 2 , further comprising: determining the meat quality based on the reference bait information corresponding to the bait information acquired in the information acquisition step. The meat quality discriminating program according to any one of claims 1 to 10, wherein the discriminating step uses the degree of association corresponding to a weighting coefficient of each output of a node of a neural network in artificial intelligence . In the meat quality determination system that determines the meat quality of meat,
An information acquisition means for acquiring image information obtained by imaging the meat to be discriminated,
Based on the reference image information of the meat taken in the past and the three or more levels of association with the meat quality, based on the reference image information corresponding to the image information acquired by the information acquisition means , A meat quality discriminating system characterized by comprising a discriminating means for discriminating meat quality by giving priority to high ones .

Images