JP2021066542A - Determination device, determination method, and determination program - Google Patents

Abstract

To provide a technology that can determine normality of an object stored in a package.SOLUTION: A determination device (10) includes: an image data acquisition part which acquires image data obtained by imaging a package; a weight data acquisition part which acquires weight data related to a weight of the package which stores an object; and a determination part which refers to the image data and the weight data to determine whether or not a desired object is stored in the package.SELECTED DRAWING: Figure 1

Description

The present invention relates to a determination device, a determination method, and a determination program.

Conventionally, in physical distribution, a technique for determining a packaged product from image data of a packaging material has been known. In such a technique, for example, a display related to a product on the surface of a packaging material is imaged, a product name is specified by a computer based on the obtained image data, and product information corresponding to the product name is transmitted via a network. A technique for obtaining data from a server is known (see, for example, Patent Document 1). The technology is used to create a label that displays an identification code according to the product and attach it to the packaging material.

Japanese Unexamined Patent Publication No. 2003-104554

However, the prior art as described above may not be able to determine whether the goods actually contained in the packaging material are correct.

One aspect of the present invention is to provide a technique capable of determining the correctness of an object contained in a packaging material.

In order to solve the above problems, the determination device according to one aspect of the present invention relates to an image data acquisition unit that acquires image data obtained by imaging a packing material and the weight of the packing material that houses the object. It includes a weight data acquisition unit for acquiring weight data, and a determination unit for determining whether or not a desired object is contained in the packing material by referring to the image data and the weight data.

Further, in order to solve the above-mentioned problems, the determination method according to one aspect of the present invention includes a step of acquiring image data obtained by imaging a packing material and a weight related to the weight of the packing material containing an object. A step of acquiring data and a step of determining whether or not a desired object is contained in the packing material by referring to the image data and the weight data are included.

Further, in order to solve the above-mentioned problems, the determination program according to one aspect of the present invention is a determination program for operating a computer as the above-mentioned determination device, and is the image data acquisition unit and the weight data acquisition unit. And it is a determination program for making a computer function as the determination unit.

According to one aspect of the present invention, it is possible to provide a technique capable of determining the correctness of an object contained in a packaging material.

It is a figure which shows typically an example of the structure of the determination apparatus which concerns on Embodiment 1 of this invention. It is a block diagram which shows an example of the functional structure of the determination apparatus which concerns on Embodiment 1 of this invention. It is a figure for demonstrating an example of the weight data table which concerns on Embodiment 1 of this invention. It is a flowchart which shows an example of the processing flow in the method of determining the packaged thing which concerns on Embodiment 1 of this invention. It is a figure which shows typically an example of the image displayed on the liquid crystal panel in Embodiment 1 of this invention. It is a figure which shows typically an example of the functional structure in the determination apparatus which concerns on Embodiment 2 of this invention. It is a figure which shows typically an example of the functional structure in the determination apparatus which concerns on Embodiment 3 of this invention.

[Embodiment 1]
Hereinafter, one embodiment of the present invention will be described in detail. First, the overall configuration of the determination device according to the embodiment of the present invention will be described.

[Overall configuration of judgment device]
FIG. 1 is a diagram schematically showing an example of the configuration of the determination device according to the first embodiment of the present invention. As shown in FIG. 1, the determination device 10 includes a scale 1, a camera 2, a liquid crystal panel 3, a notification lamp 4, and a switch 5. Transfer devices 21 and 22 are arranged on both sides of the scale 1. The transport device 21 is a device for transporting the package 20 to the scale 1, and the transport device 22 is a device for carrying out the package 20 from the scale 1.

A stopper 11 is arranged on one side edge of the scale 1 that is not adjacent to the transfer devices 21 and 22. The stopper 11 is a ridge extending along the transport direction of the transport devices 21 and 22, and projects upward from the top surface of the scale 1.

The scale 1 is a digital scale for measuring the weight of the package 20. The scale 1 is arranged at a position where the top surface of the scale 1 is substantially flush with the top surfaces of the transport devices 21 and 22.

The camera 2 is arranged on the opposite side of the scale 1 via the stopper 11. When the scale 1 is viewed from the front, the camera 2 is arranged at a position where the back surface of the package 20 is photographed.

The liquid crystal panel 3 is arranged on the other side of the stopper 11 and at a sufficiently high position above the camera 2 toward the scale 1.

The notification lamp 4 is arranged at a sufficiently high position along with the liquid crystal panel 3. The notification lamp 4 is a device for indicating information on the progress of the determination work of the package 20, and is composed of, for example, red, yellow, and green lamps in order from the top.

The switch 5 is a switch for the worker to operate the determination of the package 20. The switch 5 is arranged at a position that can be operated by the worker during the determination operation, for example, below the notification lamp 4 and at a position lateral to the camera 2. The switch 5 has, for example, two buttons, an A button and a B button. The A button is a button for the worker to confirm the normal determination process. The B button is a button for the worker to confirm an abnormality in the determination process.

The transport devices 21 and 22 are devices for transporting the package 20 in one direction in the plane direction, and are, for example, a belt conveyor or a roller conveyor. The direction in which the package 20 is transported from the transfer device 21 to the scale 1 and the direction in which the package 20 is carried out from the scale 1 by the transfer device 22 are both in the same straight line.

The package 20 is composed of a package material and an object to be accommodated therein. In the present embodiment, the packing material is a corrugated cardboard box, the object is a valve, and the packing material 20 is a corrugated cardboard box containing and sealed a predetermined valve. The cardboard box is sealed and the contained valves are not visible from the outside.

A label is formed on the back surface of the package 20. The label is at least the part on which the product name of the object (valve) is printed, for example, information on the brand name of the valve, the product name of the valve, and the number of valves to be contained in the package 20. It is a printing unit including (see FIG. 5).

[Functional configuration of judgment device]
FIG. 2 is a block diagram showing an example of the functional configuration of the determination device according to the present embodiment. As shown in FIG. 2, the determination device 10 includes a control unit 100 and a storage unit 104 as a functional configuration. The control unit 100 is electrically connected to the camera 2, the scale 1, the input unit 105, the liquid crystal panel 3, and the reporting unit 106.

The control unit 100 includes an image data acquisition unit 101, a weight data acquisition unit 102, and a determination unit 103. The image data acquisition unit 101 acquires image data obtained by imaging the packing material of the package 20 from the camera 2. The weight data acquisition unit 102 acquires the weight data obtained by the scale 1 weighing the package 20 from the scale 1.

The determination unit 103 refers to the image data acquired by the image data acquisition unit 101 and the weight data acquired by the weight data acquisition unit 102. The determination unit 103 determines whether or not a desired valve is contained in the cardboard box, for example, based on the information or the program stored in the storage unit 104.

The storage unit 104 has information regarding the determination of the package 20. The storage unit 104 is composed of a known recording medium, for example, a ROM (Read Only Memory) or a RAM (Random Access Memory).

The information or the like stored in the storage unit 104 is, for example, a model that outputs output data corresponding to the image data when the image data is input. Further, the output data corresponding to the image data is, for example, information regarding the type of the valve. The information regarding the type of the valve is, for example, the information printed on the label described above, and in the present embodiment, it is the brand name of the valve and the product name of the valve.

The model for outputting the output data may be able to output output data corresponding to the above-mentioned image data from the image data of the package 20. Examples of such models include neural networks and support vector machines. Examples of neural networks include convolutional neural networks (CNNs), recurrent neural networks (RNNs) and fully coupled neural networks.

When a neural network is used, the input data may be processed in advance for input to the neural network. For such processing, in addition to one-dimensional arrangement or multidimensional arrangement of data, for example, a method such as data augmentation can be used.

In addition to neural networks and support vector machines, models include clustering, inductive logic programming (ILP), genetic programming (GP), or Bayesian networks (BN: Bayesian). Network), may be used.

The model may be a trained model trained using teacher data. The teacher data includes image data captured by the camera 2 and output data corresponding to the image data. The output data included in the teacher data may be data that can be used to determine the package 20, and in addition to the valve brand name and valve product name described above, the number of valves to be contained in the package 20. , May be included.

The trained model is formed by training a neural network with a sufficient number of teacher data and determining the weight of the path according to the image data described above. Examples of algorithms for training the model include backpropagation and ID3.

The technique for recognizing an image in image data is not limited to the above example. The technique may be a technique such as optical character recognition (OCR) that converts image data into a character code that can be used by a computer and identifies it as a character. Alternatively, the technique may be a technique for identifying the image information itself from the characteristics of the image data.

A collation table is stored in the storage unit 104. The collation table stores information on the brand name, product name, and number of valves housed in the packaging material. The data in the collation table may be stored in the storage unit 104 prior to the determination process.

In addition, work schedule data is stored in the storage unit 104. The work schedule data includes information on the product name and the number of valves in the package 20 to be subjected to the determination process by the determination device 10. As for the work schedule data, for example, the worker may have the camera 2 take a picture of the information corresponding to the work schedule data and read it into the control unit 100. Alternatively, the work schedule data may be directly transmitted to the control unit 100 by the administrator of the determination device 10 by wireless communication or the like.

Further, the weight data table is stored in the storage unit 104, and FIG. 3 is a diagram for explaining an example of the weight data table. As shown in FIG. 3, the weight data table includes, for example, the product name of the valve, the number of valves to be contained in the package 20, and the weight at the time of packaging (product of the weight of a single valve and the number of valves). Information is stored.

The input unit 105 is configured to input a signal to the determination device 10, and is, for example, the switch 5 described above. The input unit 105 may further include a device capable of inputting the operator's operation, for example, a keyboard or a touch panel. The reporting unit 106 has a configuration for reporting information related to the determination process, and is, for example, the above-mentioned notification lamp 4. The reporting unit 106 may further include a device capable of reporting information regarding the determination process to the outside, for example, a wireless device for reporting to the administrator or a speaker for generating a voice such as an alarm.

[Example of judgment of packaged items]
The transport device 21 transports the package 20 to the scale 1. The package 20 is placed on the scale 1 from the transport device 21. As described above, the package 20 is a corrugated cardboard box containing a valve. The package 20 is placed on the scale 1 with the label facing the camera 2. Further, the package 20 is placed on the scale 1 at a position where one bottom edge portion of the side wall portion on which the label is printed abuts on the stopper 11. The transportation of the package 20 and the installation on the scale 1 may be performed by a worker or a robot.

The camera 2 is preliminarily adjusted so that the label of the package 20 can be captured as an image having sufficient resolution. The camera 2 captures the above-mentioned label on the package 20 whose distance is defined by the stopper 11. Further, the scale 1 measures the weight of the package 20 placed at a position where it comes into contact with the stopper 11.

FIG. 4 is a flowchart showing an example of a processing flow in the method for determining a package according to the present embodiment. In step S11, the image data acquisition unit 101 acquires the image data of the package 20 obtained by taking a picture of the camera 2, that is, the image of the label.
Further, the image data acquisition unit 101 transmits the acquired image data to the liquid crystal panel 3, and the liquid crystal panel 3 displays the received image data (see FIG. 5).

In step S12, the weight data acquisition unit 102 acquires the weight data of the package 20 from the scale 1. Further, the weight data acquisition unit 102 transmits the acquired weight data to the liquid crystal panel 3, and the liquid crystal panel 3 displays the received weight data (see FIG. 5).

In the present embodiment, the order of step S11 and step S12 is not limited, and the order of step S11 and step S12 may be the order, or vice versa.

The control unit 100 transmits a signal corresponding to the start of the determination process to the reporting unit 106 in response to the acquisition of the image data by the image data acquisition unit 101 or the acquisition of the weight data by the weight data acquisition unit 102. The notification unit 106 lights the yellow lamp in the notification lamp 4 in response to the signal from the control unit 100 to notify the surroundings that the determination process is in progress.

In step S13, the determination unit 103 refers to the image data acquired by the image data acquisition unit 101 and the weight data acquired by the weight data acquisition unit 102. Then, it is determined whether or not the desired valve is housed in the image cardboard box.

The determination unit 103 makes a determination with reference to the output data output by the model into which the image data is input. For example, the determination unit 103 inputs the image data of the label into a predetermined model such as the trained model described above. The model outputs information on the brand name, product name, and number of valves according to the input image data. As described above, the output data includes the product name of the valve, which is information on the type of the valve.

The determination unit 103 determines whether or not the output data based on the image data and the information corresponding to the work schedule data among the information on the valves in the collation table stored in the storage unit 104 match. When the output data and the information in the collation table match, the determination unit 103 outputs a positive (OK) determination as a determination result based on the image data. If the output data does not match the information in the collation table, the determination unit 103 outputs a rejection (NG) determination as a determination result based on the image data.

Further, the determination unit 103 determines whether or not the weight data acquired by the weight data acquisition unit 102 and the information regarding the weight in the weight data table stored in the storage unit 104 match. When the above weight data and the above information regarding the weight match, the determination unit 103 outputs a positive (OK) determination as a determination result based on the weight data. When the above weight data and the above information regarding the weight do not match, the determination unit 103 outputs a determination of no (NG) as a determination result based on the weight data.

In step S14, the control unit 100 refers to the image determination information and the weight determination information by the determination unit 103 to generate a screen for displaying the determination result based on the image data and displays it on the liquid crystal panel 3 ( (See FIG. 5). FIG. 5 is a diagram schematically showing an example of an image displayed on the liquid crystal panel in the present embodiment. As shown in FIG. 5, the screen includes the product name 31, the first determination information 32, and the second determination information 33.

The product name 31 is information to be determined, and is, for example, information that can identify the package 20 or the valve housed therein. The information may be information regarding the type of valve. The product name 31 represents the product name of the valve that should be housed in the packaging material, and is, for example, "AAAA".

The first determination information 32 is information related to determination based on the image data acquired by the image data acquisition unit 101, and includes, for example, the label image 321 and the image determination result information 322. The image 321 of the label is the image data acquired by the image data acquisition unit 101, and includes, for example, information regarding the type of the valve. The information regarding the valve type may be the information of the output data output by the above-mentioned model. For example, the image 321 of the label shows the valve brand name "XXX", the valve product name "AAAA", and the number information "1". ”Is included. The image determination result information 322 is information on the determination result based on the image data, and is, for example, either "OK" or "NG".

The second determination information 33 is information related to determination based on the weight data acquired by the weight data acquisition unit 102. For example, weight data information for displaying the weight data and information on the determination result based on the weight data (weight determination). Result information) and included. The weight data information may be information displayed numerically, information displayed as a relative quantity with respect to the measurable range, or both.

For example, the second determination information 33 includes a gauge 331, a weight value 332, and a weight determination result information 333. The gauge 331 is a semicircular ring and represents the measurable range of the scale 1 over the entire semicircular arc. The weight data is displayed by rotating the needle with reference to the center of the semicircle and coloring the rotated range of the needle according to the ratio of the weight value of the weight data to the measurable range of the scale 1. Will be done. The weight value 332 is a weight value indicated by the weight data.

The weight determination result information 333 is information on the determination result based on the weight data, and is, for example, either "OK" or "NG". When the determination result is "positive", it is "OK", and when it is "no", it is "NG".

The image shown in FIG. 5 shows that both the determination result based on the image data and the determination result based on the weight data are “positive”. That is, it can be seen that the package 20 contains a desired number of valves.

When both the determination result based on the image data and the determination result based on the weight data are "positive", the control unit 100 transmits a signal corresponding to the determination result to the reporting unit 106. The notification unit 106 switches the lamp lit by the notification lamp 4 from the yellow lamp to the green lamp in response to the signal from the control unit 100. As a result, it is shown to the surroundings that the determination process is positive.

When at least one of the determination result based on the image data and the determination result based on the weight data is "No", the control unit 100 transmits a signal corresponding to the determination result to the reporting unit 106. The notification unit 106 switches the lamp lit by the notification lamp 4 from the yellow lamp to the red lamp in response to the signal from the control unit 100. As a result, it is shown to the surroundings that the determination process is negative.

The control unit 100 resets the determination result in response to the input signal from the input unit 105. The input signal is, for example, a signal when an operator presses either the A or B button on the switch 5.

When the determination result is positive, the package 20 on the scale 1 is placed on the transport device 22. The transport device 22 carries out the package 20 toward the work place in the next process. Here, when the worker presses the A button on the switch 5, the input unit 105 outputs a signal due to the pressing of the A button. In response to the signal from the input unit 105, the image data acquisition unit 101 and the weight data acquisition unit 102 each discard the acquired data. The determination unit 103 may discard the information of the previous determination result according to the signal, may store the information of the previous determination result in the storage unit 104, or may store the information of the previous determination result in the storage unit 104, or the reporting unit 106 may perform the previous determination. The result information may be notified to the administrator.

If the determination result is negative, the worker who confirmed the abnormality presses the B button on the switch 5. When the control unit 100 receives the signal caused by the input unit 105 pressing the B button and then the notification unit 106 acquires the signal, the notification unit 106 stops the red lamp from lighting. The worker removes the package 20, which is the result of the negative determination, from the scale 1. Then, when the A button is pressed, the acquired data is appropriately discarded, stored, or reported as described above.

In this way, when the preparation for the determination process of the next package 20 is completed, the transfer device 21 conveys the package 20 to be determined next to the scale 1. Then, the determination device 10 determines the next package 20 as described above.

[Action effect]
In the present embodiment, the stopper 11 easily keeps the distance between the package 20 (label) to be imaged and the camera 2 constant. Therefore, it is possible to accurately and easily acquire the image data of the label printed on the surface of the corrugated cardboard box.

In the present embodiment, the character information in the label is identified by analyzing the image data captured by the camera 2 and recognizing the features of the image. Therefore, if the label can be imaged with a resolution that can be identified as image data, it is possible to determine the package 20 with sufficiently high accuracy. Therefore, there are few restrictions on the camera, and there are also few restrictions on the imaging conditions. Therefore, the determination device can be configured inexpensively and easily. Further, although it depends on the above-mentioned model, it is also possible to identify the image information from the features of the image. Therefore, even an image containing an image that cannot be converted into a character code such as a logo mark can be identified.

In the present embodiment, when referring to the image data, it is also possible to identify the image data as a character after converting the image data into a character code. In this case, in order to capture image data that can be converted into a character code, the camera 2 for that purpose, the adjustment of the focal position for capturing an image with desired accuracy, and the desired imaging conditions such as the illuminance around the label. The adjustment may be carried out as appropriate.

In the present embodiment, the determination device 10 further has a notification lamp 4 for reporting to the surroundings. Therefore, the normal progress and the occurrence of an abnormality in the determination process of the package 20 are notified to the surroundings. Therefore, it is possible to smoothly proceed with the determination process of the package 20.

Further, in the present embodiment, the determination device 10 further has a switch 5 as an input unit 105. Therefore, the worker can proceed while confirming the determination process of the package 20 and can surely recover from the abnormality determination through the worker.

As is clear from the above description, the determination device 10 in the present embodiment includes an image data acquisition unit 101 that acquires image data obtained by imaging the packing material, and a packing material (packing material 20) that houses the object. The weight data acquisition unit 102 that acquires the weight data related to the weight of the above, and the determination unit 103 that determines whether or not the desired object is contained in the packing material by referring to the acquired image data and the weight data. I have.

Further, the determination method in the present embodiment includes a step (S11) of acquiring image data obtained by imaging the packaging material, and a step (S12) of acquiring weight data relating to the weight of the packaging material containing the object. It includes a step (S13) of determining whether or not a desired object is contained in the packaging material with reference to the acquired image data and weight data.

Therefore, according to the present embodiment, it is possible to determine whether or not the object contained in the packaging material is correct or not.

The determination unit may make the above determination with reference to the output data output by the model into which the image data is input. This configuration is even more effective from the viewpoint of accurately acquiring the information indicated by the image data and making an accurate determination.

The output data may include information about the type of object (such as the valve product name). This configuration is even more effective from the viewpoint of accurately acquiring the information of the packaged object from the image data and making an accurate determination.

In addition, the output data may include information regarding the number of objects. This configuration
Even when a plurality of objects are contained in the packaging material, it is even more effective from the viewpoint of making an accurate determination.

[Embodiment 2]
Other embodiments of the present invention will be described below. For convenience of explanation, the same reference numerals will be added to the members having the same functions as the members described in the above embodiment, and the description will not be repeated.

FIG. 6 is a diagram schematically showing an example of a functional configuration in the determination device of the present embodiment. As shown in FIG. 6, the determination device 20 has a control unit 200 and a storage unit 204. The control unit 200 has the same functional configuration as the control unit 100 in the first embodiment except that the control unit 200 has the determination unit 203.

The determination unit 203 further includes a reference weight specifying unit 207. The reference weight specifying unit 207 specifies the reference weight of the object by referring to the reference data and the output data output by the model described above.

The storage unit 204 further stores reference data. The reference data is data in which the type of the object and the reference weight of the object are associated with each other. As described above, the type of the object is, for example, the brand name of the valve or the product name of the valve. The reference weight of the object is, for example, the weight of the valve according to the type (product name).

When casting a valve, even a good valve tends to have some variation in weight. For example, depending on the type of valve, an error of about 10% may be included, but the variation in weight may be a peculiar variation depending on the type of valve.

In the present embodiment, the determination unit 203 executes the determination based on the image data, and then executes the determination based on the weight data.

The determination unit 203 acquires the image data of the label from the image data acquisition unit 101. Then, the image data is input to the above-mentioned model, and the data of the brand name, type and number of valves corresponding thereto are acquired as output data. Then, the determination unit 203 determines whether or not the acquired output data and the information corresponding to the work schedule data in the data of the collation table stored in the storage unit 204 match. In this way, the determination unit 203 first outputs the determination result based on the image data.

The reference weight specifying unit 207 refers to the reference data in the storage unit 204, and specifies the information of the reference weight associated with the product name of the valve specified in the determination result based on the image data. For example, the reference weight is 4.5 to 5.1 kg in the case of the above-mentioned product name "AAAA". That is, the "AAAA" valve has a tendency error that the smaller the valve, the larger the error, and the larger the valve, the sufficiently small the error.

The determination unit 203 refers to the reference weight specified by the reference weight specifying unit 207, the information on the number of valves in the above-mentioned output data, and the weight data acquired by the weight data acquisition unit 102. Then, the determination unit 203 determines whether or not the information regarding each valve in the weight data satisfies the condition of the reference weight. In this way, the determination unit 203 outputs the determination result based on the weight data.

In the reference data, information on the number of valves may be further associated with the product name of the valve and the reference weight of the valve. In this case, the determination unit 203 refers to the weight data reflecting the information on the number of valves and the reference weight of the valve associated with the information on the number of valves. Therefore, in the determination based on the weight data, the determination result based on the weight data can be output by directly referring to and comparing the weight data and the reference weight. Therefore, the determination process can be further simplified as compared with the determination based on the weight data described above.

Further, when the reference data further includes information on the number of valves, the order of the determination based on the image data and the determination based on the weight data may be in this order or vice versa, as in the first embodiment. You may.

As is clear from the above description, in the present embodiment, the determination unit refers to the reference data in which the type of the object and the reference weight of the object are related to each other and the above-mentioned output data, and refers to the object. The reference weight is specified, and the determination is made with reference to the specified reference weight and the weight data. Therefore, even when the object to be contained in the packaging material has a peculiar variation in weight, such as a valve manufactured by casting, the correctness of the package can be determined with sufficiently high accuracy.

In the present embodiment, the determination unit determines the reference weight of the object by referring to the reference data in which the type of the object, the number of the objects, and the reference weight of the object are associated with each other and the output data described above. The determination may be made by referring to the specified and specified reference weight and the weight data. In this configuration, since the weight data and the reference weight are referred to while the information on the number of valves is reflected, even when a plurality of objects having a unique variation in weight are accommodated in the packaging material. It is even more effective from the viewpoint of easily determining the correctness of the package with sufficiently high accuracy.

[Embodiment 3]
Other embodiments of the present invention will be described below. For convenience of explanation, the same reference numerals will be added to the members having the same functions as the members described in the above embodiment, and the description will not be repeated.

FIG. 7 is a diagram schematically showing an example of a functional configuration in the determination device of the present embodiment. As shown in FIG. 7, the determination device 30 has the same functional configuration as the determination device of the first embodiment except that it has a control unit 300 and a storage unit 304.

The control unit 300 includes an image data acquisition unit 101, a weight data acquisition unit 302, a determination unit 203, a timer 310, a teacher data acquisition unit 308, and a learning unit 309. The image data acquisition unit 101 has the same function as the image data acquisition unit of the first embodiment. The determination unit 203 has the same functional configuration as the determination unit of the second embodiment. The storage unit 304 is configured to further receive the information output from the learning unit 309.

The present embodiment is different from the second embodiment in that the method of acquiring the image data and the weight data and the trained model can be generated.

In the present embodiment, the image data is acquired after the weight data is acquired. When the package 20 is placed on the scale 1 at the above-mentioned position, the scale 1 measures the weight of the package 20. Then, the weight data acquisition unit 102 acquires the weight data of the package 20 measured by the scale 1.

The weight data acquisition unit 102 transmits a signal to the effect that the weight data has been acquired to the timer 310. The timer 310 measures a predetermined time such as 5 seconds in response to the signal from the weight data acquisition unit 102. When the time measurement by the timer 310 is completed, the timer 310 outputs a signal indicating that the predetermined time has been measured to the camera 2.

The camera 2 starts photographing the label of the package 20 in response to the signal from the timer 310, and the image data acquisition unit 101 acquires the image data of the label photographed by the camera 2.

As described above, in the present embodiment, the camera 2 takes an image of the packing material after a predetermined time has elapsed after the weight data acquisition unit 102 has acquired the weight data.

Further, in the present embodiment, the control unit 300 includes a teacher data acquisition unit 308 and a learning unit 309. The teacher data acquisition unit 308 acquires teacher data from, for example, the input unit 105. The teacher data includes, for example, image data of a sufficient number of prepared labels and information on the brand name of the valve corresponding to the label, the product name of the valve, the number of valves, and the reference weight of the valve.

The learning unit 309 trains the model using the teacher data for each image data of the label. The model is, for example, a neural network. The learning unit 309 stores the learned model in the storage unit 304. The trained model stored in the storage unit 304 is used for determining the package 20 as a model for outputting the above-mentioned output data.

As described above, the present embodiment further includes a learning unit for learning the model using the teacher data, and the teacher data includes the image data obtained by imaging the packing material and the type associated with the image data. Contains information.

In the present embodiment, the determination device 30 acquires the image data after acquiring the weight data. In general, the determination process based on the weight data is simpler than the determination process based on the image data accompanied by the certification of the image data. When the determination result based on the weight data is "No", the determination result of the package 20 is "No" regardless of whether the determination result based on the image data is correct or not. Therefore, the determination process based on the image data can be omitted. Therefore, in the present embodiment, it is possible to further reduce the load of the processing related to the determination when the determination result of "No" is obtained in the determination process based on the weight data.

Further, the worker may perform the work of placing the package 20 from the transfer device 21 on the scale 1 and transferring the package 20 from the scale 1 to the transfer device 22. In this case, in the present embodiment, if the package 20 is placed on the scale 1 at the above-mentioned position, the weight of the package 20 is measured and the label is automatically photographed by the camera 2. Therefore, it is possible to omit the work for measuring the weight by the worker and for imaging by the camera 2.

Further, in the present embodiment, the teacher data acquisition unit 308 and the learning unit 309 are further provided. Therefore, it is possible to use the data actually acquired by the determination device 30 (for example, the image of the label captured by the camera 2) as the teacher data. Therefore, the teacher data under substantially the same conditions as the actual use can be used for learning the model, which is advantageous from the viewpoint of improving the accuracy of the determination of the package 20.

As is clear from the above description, the determination device further includes a learning unit that trains the model using the teacher data, and the teacher data is associated with the image data obtained by imaging the packing material and the image data. It may include information about the type given. This configuration is even more effective from the viewpoint of improving the accuracy of determination of the package 20.

Further, the determination device further includes an imaging unit (camera 2) that images the packing material and supplies the captured image data to the image data acquisition unit, and the imaging unit is after the weight data acquisition unit acquires the weight data. The packing material may be imaged after a lapse of a predetermined time. This configuration is even more effective from the viewpoint of reducing the load of the determination process at the time of determination of rejection and from the viewpoint of labor saving of the work related to the photographing and the weight measurement by the worker.

In the present embodiment, the teacher data may be data to which the determination result is further associated. For example, the determination device further includes the above-mentioned learning unit, and the teacher data includes image data obtained by imaging the packing material, information on the weight associated with the image data, and information on the image data and the weight. The determination result associated with and may be included. This configuration is even more effective from the viewpoint of reducing the load of the determination process because the package 20 can be determined without recognizing the characters in the image data of the label.

[Example of realization by software]
The control blocks (particularly the determination units 103 and 203) of the determination devices 10, 20 and 30 may be realized by a logic circuit (hardware) formed in an integrated circuit (IC chip) or the like, or may be realized by software. May be good.

In the latter case, the determination devices 10, 20 and 30 include a computer that executes the instructions of a program that is software that realizes each function. The computer includes, for example, one or more processors and a computer-readable recording medium that stores the program. The program is, for example, a determination program for operating a computer as determination devices 10, 20, and 30, and is a determination program for operating a computer as an image data acquisition unit, a weight data acquisition unit, and the determination unit. You can do it.

Then, in the computer, the processor reads the program from the recording medium and executes it, thereby achieving the object of the present invention. As the processor, for example, a CPU (Central Processing Unit) can be used. As the recording medium, a "non-temporary tangible medium", for example, a ROM (Read Only Memory) or the like, a tape, a disk, a card, a semiconductor memory, a programmable logic circuit, or the like can be used. Further, a RAM (Random Access Memory) for expanding the above program may be further provided.

Further, the program may be supplied to the computer via an arbitrary transmission medium (communication network, broadcast wave, etc.) capable of transmitting the program. It should be noted that one aspect of the present invention can also be realized in the form of a data signal embedded in a carrier wave, in which the above program is embodied by electronic transmission.

[Modification example]
The present invention is not limited to the above-described embodiments, and various modifications can be made within the scope of the claims, and the embodiments obtained by appropriately combining the technical means disclosed in the different embodiments. Is also included in the technical scope of the present invention.

For example, in the above-described embodiment, the notification unit 106 may execute a voice notification regarding the progress of the determination process in addition to lighting the notification lamp 4.

Further, in the above-described embodiment, the weight data in the weight data table may be the weight data of the valve measured before the determination of the package 20. Before the determination, for example, it may be at the time of manufacturing the valve or at the time of accommodating the valve in the packing material (at the time of packing). The data of the measured value of the weight of such a valve in advance is managed for each production lot of the valve, for example. Then, the weight data of the valve corresponding to the production lot and the weight data acquired for the package 20 may be referred to, and if there is a match, a positive determination may be made as a determination result based on the weight data.

In the above-described embodiment, when the package 20 is accommodated in the additional packaging material, it may be determined whether or not the desired package 20 is contained in the additional packaging using the same determination device. .. It is effective from the viewpoint of preventing further packaging mistakes.

In the above-described embodiment, the determination device may transmit the determination result information to the manager of the determination device. A positive determination result indicates the production record of the package 20. By displaying the production schedule of the package 20 and the information of the positive determination result in association with each other, the manager can immediately and easily confirm the progress of the work in the production of the package 20. Further, when the worker records the determination result of the package 20, the work of recording the worker can be omitted. Therefore, it is effective from the viewpoint of reducing the work of workers.

In the third embodiment described above, the teacher data acquisition unit and the learning unit may be included in a device other than the determination device, and even if only the learned model is input to the determination device via, for example, the input unit. Good.

1 Scale 2 Camera 3 Liquid crystal panel 4 Notification lamp 5 Switch 10, 20, 30 Judgment device 11 Stopper 20 Package 21 Conveyor device 22 Conveyor device 31 Product name 32 First judgment information 33 Second judgment information 100, 200, 300 Control unit 101 Image data acquisition unit 102, 302 Weight data acquisition unit 103, 203, 204 Judgment unit 104, 204, 304 Storage unit 105 Input unit 106 Notification unit 207 Reference weight identification unit 308 Teacher data acquisition unit 309 Learning unit 310 Timer 321 Image 322 Image Judgment result information 331 gauge 332 weight value 333 weight judgment result information

Claims (11)

An image data acquisition unit that acquires image data obtained by imaging the packaging material,
A weight data acquisition unit that acquires weight data related to the weight of the packaging material containing the object, and a weight data acquisition unit.
With reference to the image data and the weight data, a determination unit that determines whether or not a desired object is contained in the packaging material, and a determination unit.
Judgment device including. The determination device according to claim 1, wherein the determination unit makes the determination by referring to the output data output by the model into which the image data is input. The determination device according to claim 2, wherein the output data includes information regarding the type of the object. The determination unit
By referring to the reference data in which the type of the object and the reference weight of the object are associated with each other and the output data, the reference weight of the object is specified.
The determination device according to claim 3, wherein the determination is performed with reference to the specified reference weight and the weight data. The determination device according to claim 3, wherein the output data includes information on the number of the objects. The determination unit
The reference weight of the object is specified by referring to the reference data in which the type of the object, the number of the objects, and the reference weight of the object are associated with each other and the output data.
The determination device according to claim 5, wherein the determination is performed with reference to the specified reference weight and the weight data. Further equipped with a learning unit for learning the model using teacher data,
The teacher data includes
Image data obtained by imaging the packaging material and
The determination device according to any one of claims 2 to 6, wherein information about a type associated with the image data and information about the type are included. Further equipped with a learning unit for learning the model using teacher data,
The teacher data includes
Image data obtained by imaging the packaging material and
Information about the weight associated with the image data and
Judgment result associated with the image data and the information about the weight, and
The determination device according to any one of claims 2 to 6, wherein the determination device is included. An imaging unit that images the packaging material and supplies the captured image data to the image data acquisition unit is further provided.
The packaging according to any one of claims 1 to 8, wherein the imaging unit captures an image of the packaging material after a predetermined time has elapsed after the weight data acquisition unit acquires the weight data. Object judgment device. Steps to acquire image data obtained by imaging the packaging material,
A step of acquiring weight data regarding the weight of the packaging material containing the object, and
With reference to the image data and the weight data, a step of determining whether or not a desired object is contained in the packaging material, and a step of determining whether or not the desired object is contained in the packaging material.
Judgment method including. A determination program for operating a computer as the determination device according to claim 1, wherein the determination program functions as the image data acquisition unit, the weight data acquisition unit, and the determination unit.

Images