WO2021025225A1

WO2021025225A1 - Vision counting device for verification, and vision counting system for verification, comprising same

Info

Publication number: WO2021025225A1
Application number: PCT/KR2019/012656
Authority: WO
Inventors: 이부한; 조성제; 박재훈; 이수영
Original assignee: (주)코글릭스
Priority date: 2019-08-07
Filing date: 2019-09-27
Publication date: 2021-02-11

Abstract

An embodiment relates to a vision counting device, the vision counting device comprising: a camera unit for photographing a plurality of pills arranged directly below; a display unit for displaying images corresponding to the plurality of photographed pills; and a control unit, wherein the control unit compares an image with a pre-stored pill image, generates, on the basis of a result of the comparison, pill information about the number of the plurality of arranged pills and about whether the pills are of fair quality, and displays the generated pill information on the display unit.

Description

Vision counting device for verification and vision counting system for verification including the same

Embodiments relate to a vision counting device for verification and a vision counting system for verification including the same.

There are many types of drugs manufactured by pharmaceutical companies, and they can be classified into potions, granules, capsules or pills, depending on the formulation of the drug. Various inspection methods exist for the defects of these drugs, especially softgel capsules.

As for the conventional verification coefficient, a manual method using a tray or a method of feeding tablets, capsules, softgels, etc. with vibration and mechanical feeders, and counting one by one using a sensor and vision were used. In particular, the existing verification coefficient was equipped with the same method and the same size as the existing counter, and there was no special equipment for the verification coefficient.

Embodiments provide a vision counting device for verification and a vision counting system for verification including the same.

A vision counting device according to an embodiment, comprising: a camera unit for photographing a plurality of tablets arranged directly below; A display unit that displays images corresponding to the plurality of captured tablets; And a control unit for controlling the camera unit and the display unit,

The controller compares the image with a previously stored tablet image, generates tablet information on the number and quality of the arranged plurality of tablets based on the comparison result, and displays the generated tablet information to the display unit. It is characterized by displaying.

The tablet information may include numerical information corresponding to the number of the plurality of tablets and color information for displaying different colors of good and defective products among images corresponding to the displayed plurality of tablets.

The vision counting device further includes a manipulation unit for receiving a user input,

The control unit may output a first driving signal to a motor that provides vibration to a tablet alignment unit in which the plurality of tablets are arranged according to a first manipulation signal input through the manipulation unit.

The control unit may output a second driving signal to a motor that drives a tablet alignment unit in which the plurality of tablets are arranged in a first direction according to a second manipulation signal input through the manipulation unit.

The vision counting device includes: a storage unit for storing the generated refinement information; And an output unit for printing and outputting the generated tablet information.

The control unit may perform machine learning based on the generated tablet information and the pre-stored tablet image.

In the vision counting system for verification according to another embodiment, a plurality of tablets arranged directly below are photographed, images corresponding to the photographed tablets are displayed, and the image is compared with a previously stored tablet image, A vision counting device that generates refinement information on the number and quality of the plurality of tablets arranged based on the comparison result, and displays the generated tablet information; A body portion connected by the vision counting device and a connecting member and having a wheel mounted at a lower portion thereof; A tablet alignment unit disposed above the body and directly below the vision counting device; And a funnel part disposed on the side of the body part and collecting a plurality of tablets placed when the tablet alignment part is inclined.

The vision counting system for verification further includes a vibration member for providing vibration to the tablet alignment unit, and a driving member for driving the tablet alignment unit to incline, and an operation unit provided on at least one of the vision counting device and the body unit It characterized in that the vibration member and the driving member are operated according to a user input through.

The tablet information may include numeric information corresponding to the number of the plurality of tablets and color information displaying different colors of good and defective products among images corresponding to the displayed plurality of tablets.

A method of controlling a vision counting system for verification according to another embodiment, the method comprising: photographing a plurality of tablets arranged directly below; Displaying images corresponding to the plurality of captured tablets; Comparing the image with a previously stored tablet image, and generating tablet information on the number and quality of the arranged plurality of tablets based on the comparison result; And displaying the generated purification information.

Prior to the photographing step, the step of providing vibration to a tablet alignment unit in which the plurality of tablets are arranged according to a user input signal may be further included.

After the step of displaying the generated tablet information, the step of driving the tablet alignment unit in which the plurality of tablets are arranged is inclined according to a user input signal.

The control method of the vision counting system for verification includes storing the generated refinement information; And printing the generated refinement information.

The control method of the vision coefficient system for verification may further include performing machine learning based on the generated refinement information and the pre-stored refined image.

The vision counting system for verification according to the embodiment counts tablets in real time based on vision, and displays the quantity and status of tablets in real time on a monitor. In addition, it is possible to display other types of tablets or defective products among the purification coefficients. As for the types of drugs that can be verified, it is possible to check the quantity and defects of all kinds of drugs such as tablets, capsules, and softgels.

In addition, the vibrator and mechanically unfold the drug, not only can increase the efficiency of vision recognition, but also can be collected in a vial or case by tilting the tablet alignment unit after counting and verification and collecting it into the funnel unit.

1 is a schematic diagram of a vision counting system 10 for verification according to an exemplary embodiment.

2 is a front view, a side view, and a perspective view of the vision counting system 10 for verification shown in FIG. 1.

3 is a diagram for explaining the operation of the vision coefficient system 10 for verification shown in FIG. 1.

4 is a schematic diagram of the vision counting device 110 shown in FIG. 1.

5 to 8 are exemplary diagrams for explaining a function of a vision counting system for verification according to another exemplary embodiment.

Hereinafter, various embodiments will be described with reference to the accompanying drawings. However, this is not intended to limit the technology described in the present embodiment to a specific embodiment, and it should be understood that various modifications, equivalents, and/or alternatives of the present embodiment are included. In connection with the description of the drawings, similar reference numerals may be used for similar elements.

In the present embodiment, expressions such as "have", "may have", "include", or "may include" represent the corresponding features (eg, elements such as numbers, functions, actions, or parts). It refers to existence and does not exclude the presence of additional features.

In this embodiment, expressions such as "A or B", "at least one of A or/and B", or "one or more of A or/and B" may include all possible combinations of items listed together. have. For example, "A or B", "at least one of A and B", or "at least one of A or B" includes (1) at least one A, (2) at least one B, Or (3) it may refer to both cases including both at least one A and at least one B.

Expressions such as "first", "second", "first", or "second" used in the present embodiment may modify various elements regardless of order and/or importance, and one element It is used to distinguish it from other components and does not limit the components. For example, a first user device and a second user device may represent different user devices regardless of order or importance. For example, without departing from the scope of the rights described in the present embodiment, a first component may be referred to as a second component, and similarly, a second component may be renamed to a first component.

Some component (eg, a first component) is "(functionally or communicatively) coupled with/to)" to another component (eg, a second component) or " When referred to as "connected to", it should be understood that any of the above-described components may be directly connected to the other components described above, or may be connected through other components (eg, a third component). On the other hand, when a component (eg, a first component) is referred to as being “directly connected” or “directly connected” to another component (eg, a second component), a component different from a component It may be understood that no other component (eg, a third component) exists between the elements.

The expression "configured to" used in this embodiment is, for example, "suitable for", "having the capacity to" depending on the situation. )", "designed to", "adapted to", "made to", or "capable of" . The term "configured to (or set)" may not necessarily mean only "specifically designed to" in hardware. Instead, in some situations, the expression "a device configured to" may mean that the device "can" along with other devices or parts. For example, the phrase “a processor configured (or configured) to perform A, B, and C” means a dedicated processor (eg, an embedded processor) for performing the operation, or by executing one or more software programs stored in a memory device. , May mean a generic-purpose processor (eg, a CPU or an application processor (AP)) capable of performing corresponding operations.

The terms used in this embodiment are used only to describe a specific embodiment, and may not be intended to limit the scope of other embodiments. Singular expressions may include plural expressions unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by those of ordinary skill in the technical field described in the present embodiment. Among the terms used in this embodiment, terms defined in a general dictionary may be interpreted as having the same or similar meanings as those in the context of the related technology, and unless explicitly defined in the present embodiment, they are ideally or excessively formed. It is not interpreted in a traditional sense. In some cases, even terms defined in this embodiment cannot be interpreted to exclude embodiments of the present embodiment.

The vision counting system for verification according to the embodiment counts tablets in real time based on vision, and displays the quantity and status of tablets in real time on a monitor. In addition, it is possible to display other types of tablets or defective products among the purification coefficients. As for the types of drugs that can be verified, it is possible to check the quantity and defects of all kinds of drugs such as tablets, capsules, and softgels. In addition, the vibrator and mechanically unfold the drug, not only can increase the efficiency of vision recognition, but also can be collected in a vial or case by tilting the tablet alignment unit after counting and verification and collecting it into the funnel unit. The vision unit according to the embodiment can be implemented with a computer and a photographing device, for example, a camera, and can output and store verification details.

In the examples, tablets are used to mean the form of a drug, but tablets should be understood as including all types of drugs such as capsules and soft gels.

Referring to FIG. 1, the vision counting system 10 for verification includes a vision counting device 110, a tablet alignment unit 120, and a funnel unit 130. The vision counting device 110 photographs a plurality of tablets and displays a photographed image. In addition, the vision counting device 110 may determine the number of tablets, the type of tablets, and whether the tablets are defective by comparing the captured image with the previously stored tablet images. To this end, the vision counting apparatus 100 may store images of all types of tablet shapes, and may learn captured images and pre-stored images through machine learning.

In the tablet alignment unit 120, a plurality of tablets are arranged. For example, tablets are poured on a square plate for verification counting. An operator can easily check the number of tablets, good or defective tablets through the vision counting device 110 by simply pouring a plurality of tablets on the tablet alignment unit 120. Further, the tablet alignment unit 120 may vibrate left and right or up and down by driving a motor (not shown) to unfold the aggregated tablets. Further, the tablet alignment unit 120 may be driven in one direction by driving a motor (not shown) so that the placed tablets are collected in one direction, that is, in the funnel unit 130 direction. To this end, a screen may be attached to one side of the tablet alignment unit 120 so that tablets do not spill out of the tablet alignment unit 120.

The funnel unit 130 may contain tablets by selection of an operator after counting the tablets placed on the tablet alignment unit 120. The shape of the funnel unit 130 may be implemented in the shape of a funnel, and may have a structure in which tablets can be collected in a tablet case or bottle underneath. The shape of the funnel unit 130 is exemplary and is not limited thereto.

A specific shape of the verification vision counting system will be described with reference to FIGS. 2 and 3.

2A to 2C, the vision counting device 110 includes a camera unit 111, a lighting unit 112, and a display unit 113. As shown in FIG. 2A, the camera unit 111 of the vision counting device 110 photographs a plurality of tablets arranged directly below. The plurality of tablets are arranged on the tablet alignment unit 120. The lighting unit 112 irradiates light onto a plurality of tablets directly underneath the camera unit 111 to secure proper exposure. The captured image is displayed on the display unit 113.

A wheel is provided under the body part 150 so that the vision counting system 10 for verification can be easily moved. The tablet alignment part 120 is disposed on the upper part of the body part 150, and the funnel part 130 is disposed on one side. A motor (not shown) is provided under the tablet alignment unit 120 to provide vibration to the tablet alignment unit 120 or drive one side of the tablet alignment unit 120 in one direction and in the direction of the vision counting device 110 Thus, a plurality of tablets arranged in the tablet alignment unit 120 may be poured toward the funnel unit 130. Here, vibration or one-way drive may be implemented by the same motor, or vibration or one-way drive may be implemented by different motors.

The vision counting device 110 and the body portion 150 are coupled through a connection member 140.

Although not shown, the operation unit or the user interface may be provided on the vision counting device 110 or the body unit 150. The operator may control the operation of the vision counting system 10 for verification through an operation unit or a user interface. For example, power on/off, camera photographing, lighting on/off, vibration of the tablet alignment unit 120, driving, and storage and output of tablet information may be performed.

The operation unit or user interface may be a touch panel implemented on the display unit 113, and may be an operation panel including a button or switch implemented on one side of the vision counting device 110 or the body unit 150.

Referring to FIG. 3, a plurality of tablets arranged directly under the camera unit 111 of the vision counting device 110 are photographed. Images corresponding to the plurality of captured tablets are displayed on the display unit 113. The vision counting device 110 compares the captured image with a previously stored tablet image, generates tablet information on the number and quality of the plurality of tablets arranged based on the comparison result, and displays the generated tablet information on the display unit. Mark (113).

4 is a schematic diagram of the vision counting device 110 shown in FIG. 1.

4, the vision counting device 110 includes a camera unit 111, a lighting unit 112, a display unit 113, a storage unit 114, an operation unit 115, an output unit 116, and a control unit 119. ). Descriptions of the same components as those described with reference to FIGS. 2 and 3 will be omitted, and functions of the control unit 119 will be described.

The control unit 119 compares the photographed tablet image with the previously stored tablet image, and generates tablet information on the number and quality of the plurality of tablets arranged based on the comparison result. Here, the tablet information may include numeric information corresponding to the number of the plurality of tablets and color information indicating different colors of good and defective products among images corresponding to the displayed plurality of tablets. For example, the color of good products may be displayed in green, and if defective products, part of the tablets are broken or broken, or other types of tablets are mixed, they may be displayed in red.

When receiving a manipulation signal (vibration signal) through the manipulation unit 115 for receiving a user input, the control unit 119 may output a driving signal to a motor that provides vibration to the tablet alignment unit 120. Accordingly, the tablet alignment unit 120 vibrates up and down or left and right, and the arranged tablets are unfolded or dispersed to increase the accuracy of vision recognition.

In addition, when the control unit 119 receives an operation signal (one-way driving signal or a vision counting completion signal) through the operation unit 115 receiving a user input, the control unit 119 is driven by a motor that drives the tablet alignment unit 120 in one direction. You can output a signal. Accordingly, the tablet alignment unit 120 is driven in one direction, so that the arranged tablets can be collected into the funnel unit 130, so that the scattered tablets can be easily collected in a container, and the next tablets can be conveniently counted and verified. can do.

The storage unit 114 may store the generated tablet information, and the output unit 116 may print out the tablet information. Here, the storage unit 114 is a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (eg, SD or XD memory, etc.). ), RAM (RAM, Random Access Memory) SRAM (Static Random Access Memory), ROM (ROM, Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), Magnetic Memory , A magnetic disk and an optical disk, and may include at least one type of storage medium.

In addition, the controller 119 performs machine learning based on the generated tablet information and a previously stored tablet image in order to increase the accuracy of vision recognition. Here, examples of the learning algorithm include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the above examples. . The artificial intelligence model may be composed of a plurality of neural network layers. Each of the plurality of neural network layers has a plurality of weight values, and a neural network operation is performed through an operation between the operation result of a previous layer and a plurality of weights. The plurality of weights of the plurality of neural network layers can be optimized by the learning result of the artificial intelligence model. For example, a plurality of weights may be updated to reduce or minimize a loss value or a cost value acquired from an artificial intelligence model during a learning process. The artificial neural network may include a deep neural network (DNN), for example, CNN (Convolutional Neural Network), DNN (Deep Neural Network), RNN (Recurrent Neural Network), RBM (Restricted Boltzmann Machine), DBN (Deep Belief Network), BRDNN (Bidirectional Recurrent Deep Neural Network), or deep Q-Networks (Deep Q-Networks), and the like, but is not limited to the above-described example.

In the embodiment described with reference to FIG. 4, it has been described that the controller 119 or the processor is included in the vision counting device 110, but in another modified embodiment, as shown in FIG. 2, the vision counting device 110 is a camera It goes without saying that it includes only the unit 111, the lighting unit 112, and the display unit 113, and the control unit 119 and other components may be included in the body unit 150 to be implemented.

Referring to FIG. 5, a plurality of tablets 121 are spread on the tablet alignment unit 120. An image captured by photographing tablets through the vision counting device 110 is displayed on one area of the display unit 113, and the number of tablets is displayed as numeric information in the other area. Although not shown, if there is a defective tablet, for example, a broken tablet, the image of the tablet may be displayed in red or the number of defective tablets may be displayed.

Referring to FIG. 6, when the vision coefficient for verification is completed, tablets arranged in the tablet alignment unit 120 may be selected by a user or automatically poured into the funnel unit 130. To this end, one side of the shape of the tablet alignment unit may be inclined, or one side may be driven upward by a motor driving, so that the tablets may be poured toward the funnel unit 130.

Referring to FIG. 7, when tablets requiring a vision coefficient for verification are poured into a tablet alignment unit, tablets are photographed through a vision counting device, tablets are counted based on the captured image, and the counted number is displayed. Then, when counting is complete, the tablets arranged in the tablet alignment unit are poured into the funnel unit.

Referring to FIG. 8, when a plurality of tablets 121 arranged in the tablet alignment unit 120 are clustered or are arranged so that vision recognition is less efficient, the tablet alignment unit 120 vibrates through the motor driving unit 122. By providing, a plurality of tablets 121 may be spread or dispersed.

An embodiment may also be implemented in the form of a recording medium including instructions executable by a computer, such as a program module executed by a computer. Computer-readable media can be any available media that can be accessed by a computer, and includes both volatile and nonvolatile media, removable and non-removable media. Further, the computer-readable medium may include both computer storage media and communication media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Communication media typically includes computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave, or other transmission mechanism, and includes any information delivery medium.

The above description is for illustrative purposes only, and those of ordinary skill in the art to which the present invention pertains will be able to understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. Therefore, it should be understood that the embodiments described above are illustrative and non-limiting in all respects. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as being distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims to be described later rather than the detailed description, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. do.

Claims

In the vision counting device,

A camera unit for photographing a plurality of tablets arranged directly below;

A display unit that displays images corresponding to the plurality of captured tablets; And

And a control unit for controlling the camera unit and the display unit,

The control unit,

Comparing the image with a previously stored tablet image, generating tablet information on the number and quality of the arranged plurality of tablets based on the comparison result, and displaying the generated tablet information on the display unit. Vision counting device made with.
The method of claim 1,

The refining information,

And color information for differently displaying colors of good and defective products among images corresponding to the displayed plurality of tablets and numerical information corresponding to the number of the plurality of tablets.
The method of claim 1,

Further comprising a manipulation unit for receiving a user input,

The control unit,

And outputting a first driving signal to a motor that provides vibration to a tablet alignment unit in which the plurality of tablets are arranged according to a first manipulation signal input through the manipulation unit.
The method of claim 3,

The control unit,

And outputting a second driving signal to a motor driving the tablet alignment unit in which the plurality of tablets are arranged in a first direction according to a second manipulation signal input through the manipulation unit.
The method of claim 1,

A storage unit for storing the generated refinement information; And

And an output unit that prints out the generated refined information.
The method of claim 5,

The control unit,

A vision counting apparatus for performing machine learning based on the generated refinement information and the pre-stored refined image.
In the verification vision counting system,

A plurality of tablets arranged directly below are photographed, an image corresponding to the plurality of photographed tablets is displayed, the image is compared with a previously stored tablet image, and the plurality of tablets arranged are displayed based on the comparison result. A vision counting device for generating refined information on whether the number and quality are good, and displaying the generated refined information;

A body portion connected by the vision counting device and a connecting member and having a wheel mounted at a lower portion thereof;

A tablet alignment unit disposed above the body and directly below the vision counting device; And

A vision counting system for verification comprising a funnel part disposed on a side of the body part and collecting a plurality of tablets placed when the tablet alignment part is inclined.
The method of claim 7,

A vibrating member for providing vibration to the tablet alignment unit,

Further comprising a driving member for driving the tablet alignment portion to be inclined,

A vision counting system for verification, characterized in that the vibration member and the driving member are operated according to a user input through an operation unit provided in at least one of the vision counting device and the body part.
The method of claim 7,

The refining information,

And color information for differently displaying colors of good products and defective products among images corresponding to the displayed plurality of tablets and numerical information corresponding to the number of the plurality of tablets.
In the control method of the vision counting system for verification,

Photographing a plurality of tablets arranged directly underneath;

Displaying images corresponding to the plurality of captured tablets;

Comparing the image with a previously stored tablet image, and generating tablet information on the number and quality of the arranged plurality of tablets based on the comparison result; And

A control method of a vision counting system for verification comprising the step of displaying the generated refinement information.
The method of claim 10,

The refining information,

And number information corresponding to the number of the plurality of tablets and color information for differently displaying colors of good and defective products among the images corresponding to the displayed plurality of tablets.
The method of claim 10,

Before the photographing step,

And providing vibration to a tablet alignment unit in which the plurality of tablets are arranged according to a user input signal.
The method of claim 10,

After the step of displaying the generated purification information,

And driving the tablet alignment unit in which the plurality of tablets are arranged to incline according to a user input signal.
The method of claim 10,

Storing the generated refinement information; And

The control method of a vision counting system for verification, further comprising the step of printing out the generated refinement information.
The method of claim 10,

And performing machine learning on the basis of the generated refinement information and the pre-stored refined image.