KR102071021B1 - Smart Washer and Method for Separating Impurities of Laundry Using the Same - Google Patents

Abstract

A smart washing machine and a laundry foreign substance separating method using the same learn image data in various shapes, such as waste paper, paper, bills, earphones, electronic cigarettes and USBs, which are difficult to be distinguished before washing by applying a deep learning technique in advance, detect an X-ray image penetrated to laundry, and compare the same to learning data learned in advance, thereby easily distinguishing the presence or absence of foreign substances in the laundry.

Description

Smart Washer and Method for Separating Impurities of Laundry Using the Same}

The present invention relates to a washing machine, and in particular, various types of image data such as tissues, paper, bills, earphones, electronic cigarettes, USB, etc., which are difficult to distinguish before washing, are pre-learned by applying a deep learning technique, and the X-rays transmitted through the laundry The present invention relates to a smart washing machine for determining whether a laundry contains a foreign substance by detecting an image and comparing the learning data with previously learned data, and a method of distinguishing a foreign substance of a laundry using the same.

When washing clothes or blankets, if a machine that does not remove wet objects such as earphones, e-cigarettes, banknotes, or clothes from the laundry is contaminated by metal products or paper sticks to the laundry, Can cause problems.

In particular, in the case of water-soaked items such as paper or tissue paper, it is decomposed during the washing process and adheres to the washing machine filter to shorten the life of the filter, and when the next washing, a part of the foreign matter comes off and sticks to the laundry.

In general households, there is no way to filter out foreign substances in advance when the washing machine is running.

Electronic products such as earphones, e-cigarettes and USB can be damaged when washing with laundry and damage during the washing process.

In the case of bills, banks are compensated according to the degree of damage caused by laundering, but most damaged bills are recycled without compensation.

Korean Patent No. 10-1292892

In order to solve such a problem, the present invention is to learn in advance by applying a deep learning technique of various types of image data, such as tissue, paper, bills, earphones, electronic cigarette, USB, etc., difficult to distinguish before washing, and transmitted to the laundry It is an object of the present invention to provide a smart washing machine for determining whether a laundry contains a foreign substance by detecting the X-ray image and comparing the previously learned learning data with a foreign object.

Smart washing machine according to the characteristics of the present invention for achieving the above object,

A washing machine body forming an appearance of the washing machine;

A tub having a cylindrical structure accommodated inside the washing machine body to receive water therein;

A drum disposed inside the tub and having a cylindrical structure in which a plurality of through holes are formed to rotate while receiving rotational force from a drum driving motor through a rotating shaft and allow water and air to pass therethrough;

An X-ray generating unit mounted on one side of the upper surface of the tub and radiating X-rays in a downward direction to be transmitted to the laundry through the through-holes;

An X-ray detector mounted on one side of a lower surface of the tub to detect an X-ray transmitted through the laundry to generate an X-ray image; And

When receiving the X-ray image detected from the X-ray detection unit, it characterized in that it comprises a control unit for determining whether the laundry contains foreign matter by comparing the received X-ray image with the training data learned by the recognition model of the neural network.

Smart washing machine according to a feature of the present invention,

A washing machine body forming an appearance of the washing machine;

A tub having a cylindrical structure accommodated inside the washing machine body to receive water therein;

A rotating tank disposed inside the tub and having a cylindrical structure in which a plurality of through-holes are formed to be rotated by receiving rotational force from a driving motor through a rotating shaft and allow water and air to pass therethrough;

A door formed on an upper surface of the washing machine body to form an inlet through which laundry is input, and to open and close the inlet;

An X-ray generator mounted on one side of the lower surface of the door and radiating X-rays in a downward direction to penetrate laundry

An X-ray detector mounted on one side of the lower surface of the tub to detect an X-ray passing through the laundry to generate an X-ray image; And

When receiving the X-ray image detected from the X-ray detection unit, it characterized in that it comprises a control unit for determining whether the laundry contains foreign matter by comparing the received X-ray image with the training data learned by the recognition model of the neural network.

Method for separating foreign matters of the laundry using a smart washing machine according to the characteristics of the present invention,

Opening a door of the washing machine and putting laundry into the washing machine;

Receiving a start control signal from the scan button formed at one side of the washing machine main body to scan a foreign matter included in the laundry at the controller;

The control unit controls to irradiate the X-rays from the X-ray generating unit installed on the upper inside of the washing machine, and to control the X-ray detection unit installed on the inner top of the washing machine to detect the X-ray image transmitted through the laundry;

When the control unit receives the detected X-ray image, the control unit compares the received X-ray image with training data learned by a recognition model of a neural network in cooperation with a neural network processing device to determine whether the laundry contains foreign materials; And

If the received X-ray image is determined to be a foreign matter, the controller outputs the received X-ray image to a display unit formed on one side of the washing machine, and an alarm message to remove the foreign matter of laundry through the speaker formed on one side of the washing machine. It characterized in that it comprises a step of controlling to output.

According to the above-described configuration, the present invention learns in advance various types of image data such as tissue paper, paper, bills, earphones, electronic cigarette, USB, etc., which are difficult to distinguish before washing by applying a deep learning technique, and is detected as an X-ray image. By comparing the data with the learning data, it is possible to distinguish foreign matters before washing, and thus there is an effect of easily determining whether the laundry contains foreign substances.

1 is a perspective view showing the appearance of a smart washing machine that separates the foreign matter of the laundry according to the first embodiment of the present invention.
2 is a perspective view showing the structure of the tub and the drum of the smart washing machine according to the first embodiment of the present invention.
3 is a cross-sectional view illustrating a tub and a drum of the smart washing machine according to the first embodiment of the present invention.
4 is a cross-sectional view illustrating a configuration of an X-ray generator, a drum, and an X-ray detector according to a first embodiment of the present invention.
5 is a view briefly illustrating an internal configuration of a smart washing machine according to a first embodiment of the present invention.
FIG. 6 is a diagram illustrating a method of classifying foreign matters in a laundry using a smart washing machine according to a first embodiment of the present invention.
7 is a diagram illustrating a configuration of an X-ray generator of a smart washing machine according to a second embodiment of the present invention.
8 is a cross-sectional view showing the configuration of a smart washing machine that separates the foreign matter of the laundry according to the third embodiment of the present invention.

Throughout the specification, when a part is said to "include" a certain component, it means that it can further include other components, except to exclude other components unless specifically stated otherwise.

1 is a perspective view showing the external appearance of a smart washing machine that separates the foreign matter of the laundry according to the first embodiment of the present invention, Figure 2 is a perspective view showing the structure of the tub and drum of the smart washing machine according to the first embodiment of the present invention 3 is a cross-sectional view illustrating a tub and a drum of a smart washing machine according to a first embodiment of the present invention, and FIG. 4 is a configuration of an x-ray generating unit, a drum, and an x-ray detecting unit according to the first embodiment of the present invention. 5 is a cross-sectional view illustrating an internal configuration of a smart washing machine according to a first embodiment of the present invention.

The smart washing machine 100 for separating foreign matters from laundry according to the first embodiment of the present invention includes a washing machine body 101 which is a housing forming an exterior of the washing machine, and an inside of the washing machine body 101 to accommodate water therein. Is mounted on the tub 102 having a cylindrical structure in which the wash water is stored, and disposed inside the tub 102, is rotated by receiving a rotational force from the drum drive motor 107 through a rotating shaft (not shown) The drum 103 into which the laundry is put, the heater 104 for heating the air supplied into the drum 103, and the hot air heated by the heater 104 are supplied to the drum 103. The duct 105 constituting the flow path to be supplied to the inside, and the hot air heated by the heater 104 to the blower fan 106 and the drum 103 for forcibly blowing the drum 103 to the power to transfer the drum And a drum driving motor 107 to which the 103 is rotated.

The drum driving motor 107 rotates the drum 103 so that washing and dehydration of the laundry contained in the drum 103 can be performed.

The front of the washing machine body 101 is formed with an inlet opening 108 through which the laundry having an opening formed in front thereof to accommodate the laundry, and a door 109 for opening and closing the inlet 108 around the inlet 108. ) Is mounted.

On one side of the upper surface of the washing machine body 101, a scan button 110 for generating a start control signal for scanning a foreign substance contained in the laundry, a display unit 111 for outputting a recognition result determined as a foreign substance as an image, and laundry It includes a speaker 112 for outputting an alarm message to remove the foreign matter.

The drum 103 is formed in a cylindrical structure and is disposed long in the front-rear direction, the front and the rear are open, and the drum body 103a rotatable by receiving rotational force from the drum driving motor 107 through the rotating shaft, and the drum Inlet 108 is formed in the center of the front surface of the body 103a so that laundry can be put into the drum 103.

The drum body 103a has a plurality of through holes 103b formed at regular intervals so that water, air, and X-rays can pass therethrough.

The X-ray generating unit 120 is formed in the shape of a smooth curved arc, and is mounted on one side of the upper surface of the tub 102 to irradiate X-rays in the lower direction.

The X-ray generator 120 generates an X-ray under the control of the controller 140 and launches the light through the plurality of X-ray tubes 121 formed at the bottom thereof. Each X-ray tube 121 is disposed in line with each through hole 103b of the drum body 103a.

On one side of the upper surface of the tub 102, an area in which the X-ray generator 120 is installed is formed of a transparent material so that the X-ray passes.

The X-ray generator 120 emits X-rays through the X-ray tube 121 and passes through the through-hole 103b of the drum body 103a to be irradiated to the laundry in the drum 103.

The X-ray detection unit 130 is formed in the shape of a smooth curved arc, mounted on one side of the lower surface of the tub 102 detects the X-ray irradiated to the laundry in the drum (103).

A region on which the X-ray detector 130 is mounted is formed at one side of the bottom surface of the tub 102 by using a transparent material to detect an X-ray transmitted through the laundry to generate an X-ray image.

When the foreign matter exists in the area where the X-ray is irradiated, the X-ray detector 130 transmits the detected X-ray image to the controller 140 because the X-ray is absorbed by the foreign material and does not pass properly.

When the controller 140 receives the detected X-ray image from the X-ray detector 130, the controller 140 transmits the received X-ray image to the deep learning learner 152, and includes the foreign material of the X-ray image from the deep learning learner 152. Receive result data indicating

If the received data is determined to be a foreign substance, the controller 140 outputs the foreign substance image data determined as the foreign substance to the display unit 111 of the washing machine main body 101, and provides a foreign substance of the laundry through the speaker 112. Controls to output alarm message to remove.

When the controller 140 receives the start control signal from the scan button 110, the controller 140 drives the power of the X-ray generator 120 to irradiate the X-rays, and drives the power of the X-ray detector 130 to transmit the X-rays to the laundry. Control to detect.

The neural network processing apparatus 150 according to the first embodiment of the present invention includes a foreign material data storage unit 151, a deep learning learner 152, a determiner 153, and a learner 154.

The neural network processing apparatus 150 learns in advance by applying a deep learning technique to various types of image data such as tissue, paper, bills, earphones, electronic cigarette, USB, etc., which are difficult to distinguish before washing, and utilizes as learning data.

Neural networks are cognitive models implemented in software or hardware that mimic the computational power of biological systems using a large number of artificial neurons connected by connecting lines.

In neural networks, artificial neurons are used to simplify the function of biological neurons, and artificial neurons may be interconnected through connection lines having a connection weight. The connection weight is a specific value of the connection line and may also be referred to as connection strength. Neural networks can perform human cognitive processes or learning processes through artificial neurons. Artificial neurons may also be referred to as nodes.

The neural network may include an input layer, a hidden layer, and an output layer. The input layer may receive an input for performing learning and deliver it to the hidden layer, and the output layer may generate an output of the neural network based on signals received from nodes of the hidden layer.

The hidden layer is located between the input layer and the output layer, and can change the learning data delivered through the input layer to a predictable value. Nodes included in the input layer and the hidden layer may be connected to each other through a connection line having a connection weight, and nodes included in the hidden layer and the output layer may be connected to each other through a connection line having a connection weight.

The input layer, the hidden layer, and the output layer may include a plurality of nodes. The neural network may include a plurality of hidden layers. A neural network including a plurality of hidden layers is called a deep neural network, and learning a deep neural network is called deep learning.

The neural network processing apparatus 150 may train the neural network through supervised learning. Supervised learning is a method of inputting training data and output data corresponding thereto into a neural network, and updating connection weights of connection lines so that output data corresponding to the training data is output.

For example, the neural network processing apparatus 150 may update connection weights between artificial neurons through a delta rule and error backpropagation learning.

Error backward propagation learning estimates an error with forward computation for a given learning data, then propagates the estimated error starting from the output layer and moving backwards in the direction of the hidden and input layers, and reducing the error. How to update connection weights. Neural network processing proceeds in the direction of input layer-> hidden layer-> output layer, but in error back-propagation learning, the updating direction of the connection weights can proceed in the direction of output layer-> hidden layer-> input layer.

The foreign material data storage unit 151 stores foreign material image data photographed from the photographing equipment as learning data. Here, the foreign material image data refers to learning data that is previously learned by applying a deep learning technique to various types of image data such as tissue, paper, bills, earphones, electronic cigarette, USB, etc., which are difficult to distinguish before washing. Foreign object image data that has not been learned as learning data is learned as new foreign object image data and registered as learning data.

The foreign material data storage unit 151 may store the learning data received to the outside and provide the stored learning data to the deep learning learner 152.

The deep learning learner 152 may learn through neural networks using the learning data stored in the foreign material data storage 151.

The deep learning unit 152 may detect a feature value from the training data, and adjust the connection weight applied to the neural network based on the learning result of the foreign object image data. The deep learning learner 152 may calculate an error by comparing an output value generated in the output layer of the neural network with a desired expected value for the training data, and adjust the connection weight applied to the recognition model of the neural network in a direction of reducing the error.

The deep learning learner 152 may control the neural network to repeatedly perform all the foreign object image data included in the learning data based on a preset number of repetitions.

The learned neural network can be used to recognize foreign object image data. For example, when the foreign body image data is input, the recognition model of the neural network may extract a feature value from the foreign body image data, input the extracted feature value into a classifier, and output a classification result or recognition result of the input foreign body image data. have.

The deep learning unit 152 may include an input layer, a hidden layer, and an output layer to input foreign material image data to the input layer, and train the neural network to output a classification result of the input foreign material image data to the output layer.

The deep learning unit 152 may detect a feature value from foreign object image data, which is learning data received from the foreign material data storage unit 151, and train the neural network using the feature value. In other words, the deep learning learner 152 may detect feature vectors from foreign object image data, and train the neural network using the detected feature vectors.

The determination unit 153 receives and stores the recognition model of the neural network from the deep learning learner 152, receives the foreign substance image data from the control unit 140, and receives the foreign substance image data using the recognition model of the neural network. Determine whether it is included.

The determination unit 153 quantizes the received foreign object image data, extracts feature values, and compares the extracted feature values with feature vectors of the learning data learned by the deep learning learner 152 to recognize whether the foreign material is included. It transmits to the control unit 140.

When the foreign substance image data receives the recognition result that is not the foreign substance in comparison with the learning data, the controller 140 drives the drum driving motor 107 of the washing machine 100 to perform washing of the washing machine 100.

As another embodiment, the controller 140 outputs the foreign substance image data through the display 111 when the foreign substance image data is a recognition result that is not the foreign substance in comparison with the learning data. When the controller 140 determines that the foreign material image data is not learning data but is a foreign material that is to be removed by being included in the laundry, when the controller 140 receives a selection signal of a learning button (not shown) formed on one side of the washing machine body 101, In conjunction with the learner 154, a new foreign object image data may be trained as learning data using a recognition model of a neural network.

The learner 154 may control the foreign body image data determined as not the foreign body under the control of the controller 140 to learn the new foreign body image data using the recognition model of the neural network.

When receiving the recognition result determined that the foreign substance image data is the foreign substance, the controller 140 may output the foreign substance image data determined as the foreign substance through the display 111, and may detect the foreign substance of the laundry through the speaker 112. Controls to output alarm message to remove.

The control unit 140 controls the display unit 111 to enlarge the foreign matter image data at a predetermined magnification to output the foreign matter so that the foreign matter image data can be easily seen.

FIG. 6 is a diagram illustrating a method of classifying foreign matters in a laundry using a smart washing machine according to a first embodiment of the present invention.

First, the door 109 of the smart washing machine 100 is opened, and the laundry is put into the drum 103 (S100).

When the start control signal of the scan button 110 is received, the controller 140 of the smart washing machine 100 controls the X-ray generator 120 to irradiate the X-ray, and controls the X-ray detector 130 to transmit the laundry. One X-ray image is detected (S102).

The control unit 140 transmits the detected X-ray image to the determination unit 153 of the neural network processing apparatus 150, and the determination unit 153 determines that the detected X-ray image is the learning data learned from the deep learning learner 152. By comparison, it is determined whether the laundry is foreign matter (S104).

The determination unit 153 quantizes the X-ray image to extract feature values, and compares the extracted feature values with feature vectors of the training data learned by the deep learning learner 152 to determine whether a foreign material is included or not. 140).

When the controller 140 receives a recognition result that is not a foreign substance from the determination unit 153, the controller 140 drives the drum driving motor 107 of the washing machine 100 to perform washing of the washing machine 100 (S110).

When the controller 140 receives the recognition result determined as the foreign matter from the determination unit 153, the controller 140 may output the foreign matter image data determined as the foreign matter through the display 111, and the laundry 112 through the speaker 112. Control to output an alarm message to remove the foreign matter (S106). Subsequently, the controller 140 generates a control signal for opening the door 109 of the washing machine and transmits the control signal to a door lock control module (not shown) of the door 109 to control the door 109 to be opened (S108).

7 is a diagram illustrating a configuration of an X-ray generator of a smart washing machine according to a second embodiment of the present invention.

The X-ray generator 120 is formed in an arc shape and is mounted on one side of the upper surface of the tub 102 to radiate X-rays in a downward direction, and the pinion gear 156 is coupled to one side of the upper surface. In addition, an arc-shaped rack gear 155 is formed in which gears of the pinion gear 156 are engaged with each other, and a driving motor 157 is provided to provide rotational driving force to the pinion gear 156.

The controller 140 transmits a drive control signal of the drive motor 157 to control the movement of the pinion gear 156, and the pinion gear 156 moves on the rack gear 155. Subsequently, the X-ray generating unit 120 is moved on the rack gear 155 to match the respective positions of the through hole 103b of the drum body 103a.

8 is a cross-sectional view showing the configuration of a smart washing machine that separates the foreign matter of the laundry according to the third embodiment of the present invention.

The smart washing machine 100 for separating foreign matters of laundry according to the third embodiment of the present invention is mounted in the washing machine main body 101 to form an exterior of the washing machine and the washing machine main body 101 to receive water therein. Tub (not shown), the tub is disposed inside the tub, rotatably installed through a rotating shaft (not shown), the rotating tub 103 of the cylindrical structure into which the laundry is put, and the washing machine body 101 Inlet 108 is formed in which the laundry having an opening formed in front thereof to accommodate the laundry on the upper surface of the inlet), and a door 109 for opening and closing the inlet 108 is mounted around the inlet 108. . The door 109 is configured to open and close in the upward direction.

On one side of the upper surface of the washing machine body 101 is formed a scan button for generating a start control signal for scanning the foreign matter contained in the laundry, the display unit for outputting the recognition result determined as the foreign matter as an image, the foreign matter of the laundry It may include a speaker that outputs an alarm message to remove.

The lower surface of the door 109 is mounted with an X-ray generating unit 120 having a plurality of X-ray tube 121 for irradiating X-rays. An X-ray detector 130 is installed at the bottom of the washing machine body 101 to detect an X-ray passing through the laundry to generate an X-ray image.

The embodiments of the present invention are not only implemented through the apparatus and / or method, but may be implemented through a program for realizing a function corresponding to the configuration of the embodiment of the present invention, a recording medium on which the program is recorded, and the like. Such implementations can be readily implemented by those skilled in the art from the description of the above-described embodiments.

Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements of those skilled in the art using the basic concepts of the present invention defined in the following claims are also provided. It belongs to the scope of rights.

100: smart washing machine 101: washing machine body
102: Tub 103: Drum
103a: drum body 103b: through hole
104: heater 105: duct
106: blowing fan 107: drum drive motor
108: inlet 109: door
110: scan button 111: display unit
112: speaker 120: X-ray generator
121: X-ray tube 130: X-ray detection unit
140: control unit 150: neural network processing apparatus
151: foreign matter data storage unit 152: deep learning unit
153: determination unit 154: learning unit
155: rack gear 156: pinion gear
157: drive motor

Claims (8)

A washing machine body forming an appearance of the washing machine;
A tub having a cylindrical structure accommodated inside the washing machine body to receive water therein;
A drum disposed inside the tub and having a cylindrical structure in which a plurality of through holes are formed to rotate while receiving rotational force from a drum driving motor through a rotating shaft and allow water and air to pass therethrough;
An X-ray generating unit mounted on one side of the upper surface of the tub and radiating X-rays in a downward direction to be transmitted to the laundry through the through hole;
An X-ray detector mounted on one side of a lower surface of the tub to detect an X-ray transmitted through the laundry to generate an X-ray image; And
And receiving the X-ray image detected by the X-ray detector, and comparing the received X-ray image with learning data learned by a recognition model of a neural network. Smart washing machine to separate the foreign matter. A washing machine body forming an appearance of the washing machine;
A tub having a cylindrical structure accommodated inside the washing machine body to receive water therein;
A rotating tank disposed inside the tub and having a cylindrical structure in which a plurality of through-holes are formed to be rotated by receiving rotational force from a driving motor through a rotating shaft and allow water and air to pass therethrough;
A door formed on an upper surface of the washing machine body to form an inlet through which laundry is input, and to open and close the inlet;
An X-ray generator mounted on one side of the lower surface of the door and radiating X-rays in a downward direction to penetrate the laundry;
An X-ray detector mounted on one side of a lower surface of the tub to detect an X-ray passing through the laundry to generate an X-ray image; And
And receiving the X-ray image detected by the X-ray detector, and comparing the received X-ray image with learning data learned by a recognition model of a neural network. Smart washing machine to separate the foreign matter. The method according to claim 1 or 2,
If the received X-ray image is determined to be a foreign matter, the controller outputs the received X-ray image to a display unit formed on one side of the washing machine body, and removes the foreign matter of the laundry through a speaker formed on one side of the washing machine body. Smart washing machine to separate the foreign matter of the laundry, characterized in that the control to output an alarm message. The method according to claim 1 or 2,
A foreign matter data storage unit storing foreign matter image data photographed from the photographing equipment as learning data;
A deep learning unit configured to include an input layer, a hidden layer, and an output layer to input the foreign material image data to the input layer, and to learn a neural network to output a classification result of the input foreign material image data to the output layer; And
Receiving and storing the recognition model of the neural network from the deep learning learning unit, receiving foreign material image data from the control unit, and using the recognition model of the neural network comprising a determination unit for determining whether the received foreign material image data contains foreign matter Further comprising a neural network processing unit,
The determining unit extracts feature values by quantizing the received foreign object image data, and compares the extracted feature values with feature vectors of the learning data learned by the deep learning learner to determine whether a foreign material is included or not. Smart washing machine to separate the foreign matter of the laundry, characterized in that the transmission. The method of claim 1,
The X-ray generating unit generates an X-ray under the control of the control unit and emits through a plurality of X-ray tube formed at the bottom, each X-ray tube is disposed in a straight line in each through hole of the drum Smart washing machine to distinguish foreign matter. The method according to claim 1 or 2,
On one side of the upper surface of the washing machine body is formed a scan button for generating a start control signal to scan the foreign matter contained in the laundry,
When the control unit receives a start control signal from the scan button, the X-ray generating unit drives the power to irradiate the X-ray, and drives the power of the X-ray detecting unit to control to detect the X-rays transmitted to the laundry. Smart washing machine to separate the foreign matter of the laundry. Opening a door of the washing machine and putting laundry into the washing machine;
Receiving a start control signal from the scan button formed at one side of the washing machine main body to scan a foreign matter included in the laundry at the controller;
The control unit controls to irradiate the X-rays from the X-ray generating unit installed on the upper inside of the washing machine, and to control the X-ray detection unit installed on the inner top of the washing machine to detect the X-ray image transmitted through the laundry;
When the control unit receives the detected X-ray image, the control unit compares the received X-ray image with training data learned by a recognition model of a neural network in cooperation with a neural network processing device to determine whether the laundry contains foreign materials; And
If the received X-ray image is determined to be a foreign matter, the controller outputs the received X-ray image to a display unit formed on one side of the washing machine, and an alarm message to remove the foreign matter of laundry through the speaker formed on one side of the washing machine. The method of separating foreign matters of the laundry comprising the step of controlling to output. The method of claim 7, wherein
The neural network processing apparatus extracts feature values by quantizing the received X-ray image, compares the extracted feature values with feature vectors of training data learned by the recognition model of the neural network, and determines whether the laundry includes foreign matter. And transmitting the recognition result of whether or not to the control unit.

Images