Game token counting system

Abstract

To provide a recognition system of a chip having a setup capable of recognizing color of a chip according to an image and measuring the number of chips under a different illumination environment.SOLUTION: In a chip recognition system 10, a chip W is configured to at least partially have a specific color 121 for showing value of the chip W. The chip recognition system 10 includes: a recording device 11 for recording a state of the chip W as an image by using a camera 212; an image analysis device 14 for recognizing at least two colors of the specific color 121, and a reference color R differing from the specific color 121 existing in the recorded image by analyzing the image; and a recognition device 12 at least including an artificial intelligence device 12a for identifying the specific color 121 of the chip W by using an image analysis result by the image analysis device 14. Plural images of the chip W irradiated with light having different illuminance and the reference color 121 are taught to an artificial intelligence device 12a of the chip recognition device 12 as teacher data.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a system for recognizing the large number of chips used in an arcade by type using images and counting the number of chips of each type. [Background technology]

[0002] Conventionally, gaming facilities such as casinos use gaming tokens (hereinafter referred to as "chips"), and game bets and payouts are made with the chips. In order to accurately identify the chips stacked on the table, a method is used in which a camera is used to recognize the chips as an image. Patent Document 1 discloses an example of a system that uses a camera to recognize the movement of chips during a game. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2015 / 107902 Summary of the Invention [Problem to be solved by the invention]

[0004] When recognizing chips using an image with a camera, it is necessary to recognize not only the outline of the chips but also the differences in the chip colors and to grasp the number of stacked chips by chip type. However, even if the chips are the same, the colors of the chips recognized by the camera are captured or recognized as different colors depending on the lighting environment in which the chips are placed, and they are not recognized as the same color. For this reason, it was previously not possible to count the number of each type from an image.

[0005] The present invention has been made in consideration of such problems, and provides a chip recognition system having a mechanism for recognizing the color of chips from an image and for counting the number of chips even under different lighting environments. [Means for solving the problem]

[0006] A chip recognition system according to one aspect of the present invention comprises: A chip recognition system for recognizing chips used on a gaming table in a gaming facility, The chip has at least a specific color that indicates the value of the chip, a recording device that records the state of the chip as an image using a camera; an image analysis device that performs image analysis on the recorded image to recognize at least two colors, the specific color and a reference color that is different from the specific color and exists in the image; and a recognition device including at least an artificial intelligence device that identifies a specific color of the chip using the image analysis result by the image analysis device, The artificial intelligence device of the chip recognition device is an artificial intelligence device that is taught as training data a plurality of images of the chip and a reference color illuminated with different illuminances.

[0007] Furthermore, the chip has at least a specific color in a predetermined position or shape that indicates the value of the chip.

[0008] Furthermore, the recognition device may specify the number of chips by specifying the specific color of the chip. Also, the recognition device may specify the number of chips of each specific color by specifying the specific color of the chips for each chip.

[0009] Furthermore, the artificial intelligence device of the recognition device may be taught a plurality of images of the reference color and the chip illuminated under different lighting conditions as training data, and may determine the specific color of the chip based on a relative relationship with the reference color.

[0010] The recognition device may be configured to determine the specific color of the stacked chips, and may be configured to be able to determine the specific color or number of chips even when some of them are hidden by the camera's blind spot.

[0011] A recognition system for recognizing an object according to one aspect of the present invention includes: The article has a specific color that can identify the article or the package at least in part, A recording device that records the state of the item as an image using a camera; an image analysis device that performs image analysis on the recorded image to recognize at least two colors, the specific color and a reference color that is different from the specific color and exists in the image; A recognition device including at least an artificial intelligence device that identifies a specific color of the item itself or its packaging using the image analysis result by the image analysis device, The artificial intelligence device of the item recognition device is an artificial intelligence device that is taught using a plurality of images of the reference color and a specific color of the item itself or its packaging illuminated with different illuminance as training data.

[0012] Furthermore, the article itself or its packaging at least partially has a specific color at a predetermined position or in a predetermined shape that allows the article or packaging to be identified.

[0013] Furthermore, the recognition device may specify the number of the articles by specifying a specific color of the article itself or a package thereof, or may specify the number of articles of each specific color by specifying a specific color of the articles themselves or packages thereof for each article.

[0014] Furthermore, the artificial intelligence device of the recognition device is taught a plurality of images of the reference color and the specific color of the article itself or the package illuminated under different lighting conditions as training data. Also, the specific color of the article itself or the package may be determined based on a relative relationship with the reference color.

[0015] The recognition device is configured to determine the specific color of the stacked multiple items themselves or packaging, and is capable of determining the specific color even if some of the items are hidden by the blind spot of the camera. Also, the recognition device is configured to determine the specific color of the stacked multiple items themselves or packaging, and is capable of determining the total number of the items or the number of items of each specific color, even if some of the items are hidden by the blind spot of the camera.

[0016] A chip recognition system according to one aspect of the present invention A chip recognition system for recognizing chips used on a gaming table in an amusement facility, The chip has at least a specific color that indicates the value of the chip, a recording device that records the state of the chip as an image using a camera; an image analysis device that performs image analysis on the recorded image to recognize at least two colors, the specific color and a reference color that is different from the specific color and exists in the image; and a recognition device including at least an artificial intelligence device that identifies a specific color of the chip using the image analysis result by the image analysis device, The artificial intelligence device of the recognition device is configured to extract a center line from an image of the chip, and perform image analysis of a predetermined range of surrounding images centered on the center line to recognize at least two colors, the specific color in the surrounding image and a reference color different from the specific color, and is an artificial intelligence device taught using multiple surrounding images of the chip and the reference color illuminated at different illuminances as training data.

[0017] A recognition system for recognizing an object according to one aspect of the present invention includes: A recognition system that recognizes objects, The article has a specific color that can identify the article or the package at least in part, A recording device that records the state of the item as an image using a camera; an image analysis device that performs image analysis on the recorded image to recognize at least two colors, the specific color and a reference color that is different from the specific color and exists in the image; A recognition device including at least an artificial intelligence device that identifies a specific color of the item itself or its packaging using the image analysis result by the image analysis device, The artificial intelligence device of the recognition device is configured to recognize a specific color from an image of the item itself or its packaging, extract an image portion of the specific color, and recognize at least two colors, the specific color and the reference color, in the peripheral image by image analysis of the peripheral image of the specific color, and is an artificial intelligence device that has been taught multiple peripheral images of the specific color and the reference color of the item itself or its packaging illuminated at different illuminances as training data. Effect of the Invention

[0018] According to the present invention, chips used on a gaming table can be recognized by type from an image and the number of chips can be counted. [Brief description of the drawings]

[0019] [Figure 1] FIG. 1 is a diagram showing a schematic diagram of a chip recognition system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a side view of the chip in the embodiment of the present invention. [Diagram 3] FIG. 3 is a block diagram showing a schematic configuration of a chip recognition system in an embodiment of the present invention. [Figure 4] FIG. 4 is a diagram illustrating an article recognition system according to another embodiment of the present invention. [Diagram 5] FIG. 5 is an explanatory diagram of another embodiment for determining the color of a chip. [Figure 6] FIG. 6 shows a side view of the chip and an enlarged view thereof. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0020] Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings. In each drawing, components having equivalent functions are denoted by the same reference numerals, and detailed description of the components having the same reference numerals will not be repeated.

[0021] Fig. 1 is a diagram showing a chip recognition system 10 according to an embodiment of the present invention. As shown in Fig. 1, in this embodiment, a camera 212 for capturing an image of the state of chips W stacked on a gaming table 4 is provided outside the gaming table 4. The chip W has a configuration in which, as shown in FIG. 2, at least a part of the chip W has a specific color 121 that indicates the value of the chip W, A recording device 11 that records the state of the chip W as an image using a camera 212; an image analysis device 14 that performs image analysis on the recorded image to recognize at least two colors, the specific color 121 and a reference color R that is different from the specific color 121 and exists in the image; and a recognition device 12 including at least an artificial intelligence device 12a for identifying a specific color 121 of the chip W using the image analysis result by the image analysis device 14, The artificial intelligence device 12a of the chip recognition device 12 is an artificial intelligence device that is taught using a plurality of images of the chip W and a reference color 121 illuminated with different illuminance as training data. The chip recognition system 10 according to this embodiment is communicatively connected to the camera 212 .

[0022] FIG. 3 is a block diagram showing a schematic configuration of a chip recognition system 10 according to this embodiment. 3, the chip recognition system 10 includes a recording device 11, a recognition device 12, a learning machine 13, and an image analysis device 14. At least a part of the chip recognition system 10 is realized by a computer.

[0023] The recording device 11 includes a fixed data storage such as a hard disk. The recording device 11 records the state of the chips W stacked on the gaming table 4 as an image captured by the camera 212. The image may be a moving image or a series of still images. The recording device 11 may provide an index or time stamp to the images acquired from the camera 212 so that the captured images can be later analyzed by a recognition device, which will be described later.

[0024] The image analyzer 14 performs image analysis on the image recorded by the recorder 11 to recognize at least two colors, namely, a specific color 121 that is at least partially applied to the chip W, and a reference color R that is different from the specific color 121 and that is present in the image. The specific color 121 is applied at least partially to the chip W at a predetermined position or in a predetermined shape. For example, it may be applied in the circumferential direction on the side of the chip W, or it may be applied as a predetermined mark on the surface of the chip W. Furthermore, the reference color R may be, for example, the color of a specific area of ​​the gaming table 4, or may be a color applied to a place in the chip W different from the specific color 121.

[0025] The recognition device 12 includes an artificial intelligence device 12a that identifies a specific color by, for example, deep learning technology using the image analysis result by the image analysis device 14, and determines the number and type of chips W placed on the gaming table 4. The recognition device 12 may further determine the position of the chips W on the gaming table 4. 3, the recognition device 12 outputs the determination result to the output device 15. The output device 15 may output the determination result of the recognition device 12 to a monitor on the gaming table 4 or the like as character information.

[0026] In this embodiment, the learning machine 13 acquires, through the image analysis device 14, a plurality of images of the chip W and the reference color R illuminated with different illuminance recorded by the recording device 11, and learns by manual instruction of the acquired images and the correct colors of the specific color 121 of the chip W and the reference color R in each image as teacher data, thereby creating a learning model 13a (recognition program). Note that, since the images of the chip W and the reference color R illuminated under the same illuminance conditions are illuminated with the same illuminance as the specific color 121 and the reference color R, the relative relationship between the specific color 121 and the reference color R can be acquired. For example, this relative relationship may be used to recognize the specific color 121.

[0027] By repeatedly performing the teaching operation of inputting the teaching data to the learning machine 13 and having it learn, the accuracy of identifying the specific color 121 of the chip W by the learning model 13a of the learning machine 13 can be improved. Even if multiple chips W placed on the gaming table 4 are partially hidden by the blind spot of the camera 212, the learning machine 13 can create a learning model 13a that can determine the specific color 121 of the chip W on the gaming table 4 by repeatedly learning such images.

[0028] The created learning model 13a can be input to the artificial intelligence device 12a via an external medium such as a USB memory or a HDD, or via a communication network.

[0029] As shown in FIG. 3, images of the chip W and the reference color R and the judgment results of the image recognition device 12 may be input to a learning machine 13 as teacher data.

[0030] It should be noted that various modifications can be made based on the above-described embodiment. An example of the modification will be described below with reference to the drawings. In the following description and the drawings used in the following description, parts that can be configured similarly to the above-described embodiment will be designated by the same reference numerals as those used for the corresponding parts in the above-described embodiment, and duplicated descriptions will be omitted.

[0031] Fig. 4 is a diagram showing a model of an article recognition system 20 according to another embodiment of the present invention. As shown in Fig. 4, in this embodiment, a camera 212 for capturing an image of an article B arranged on an article display shelf 5 is provided outside the article display shelf 5. The article B has a specific color 121 that can identify the article or the package at least partially on the article itself or on the package, A recording device 11 that records the state of the item B as an image using a camera 212; an image analysis device 14 that performs image analysis on the recorded image to recognize at least two colors, the specific color 121 and a reference color R that is different from the specific color 121 and exists in the image; and a recognition device 12a including at least an artificial intelligence device 12a for identifying a specific color 121 of the item B using the image analysis result by the image analysis device 14, The artificial intelligence device 12a of the item recognition device 12 is an artificial intelligence device that is taught using a plurality of images of the reference color R and a specific color 121 of the item B itself or its packaging illuminated with different illuminance as training data. The article recognition system 20 according to this embodiment is communicatively connected to the camera 212 .

[0032] The article recognition system 20 includes a recording device 11, a recognition device 12, a teacher device 13, and an image analysis device 14. At least a part of the article recognition system 10 is realized by a computer. The recording device 11 includes a fixed data storage such as a hard disk. The recording device 11 records the state of the item B placed on the item display stand 5 as an image captured by the camera 212. The image may be a moving image or a series of still images. The recording device 11 may provide an index or time stamp to the images acquired from the camera 212 so that the captured images can be later analyzed by a recognition device, which will be described later.

[0033] The image analysis device 14 performs image analysis on the image recorded by the recording device 11 to recognize at least two colors, a specific color 121 that is at least partially imparted to the item B, and a reference color R that is different from the specific color 121 and that is present in the image. The specific color 121 that is imparted to the item B itself or its packaging is at least partially present at a predetermined position or in a predetermined shape on the item B itself or its packaging, and may be applied to any position on the item B itself or its packaging, and may have a variety of shapes. The reference color R may be, for example, the color of a part of the frame of the item display shelf 5, or the color of the wall in the background.

[0034] The recognition device 12 includes an artificial intelligence device 12a that identifies a specific color by, for example, deep learning technology using the image analysis results by the image analysis device 14, and determines the number and type of articles B placed on the article display shelf 5. The recognition device 12 may further determine the positions of the articles B placed on the article display shelf 5.

[0035] In this embodiment, the learning machine 13 acquires, through the image analysis device 14, a plurality of images of the article B itself or its packaging and the reference color R illuminated at different illuminances recorded by the recording device 11, and learns by manually instructing the acquired images and the correct specific color affixed to the article B itself or its packaging in each image as teacher data, thereby creating a learning model 13a (recognition program). Note that, for images of the article B and the reference color R illuminated under the same illuminance conditions, the relative relationship between the specific color 121 and the reference color R can be acquired because the specific color 121 and the reference color R are illuminated at the same illuminance. For example, this relative relationship may be utilized to recognize the specific color 121.

[0036] By repeatedly performing the teaching operation of inputting the teaching data to the learning machine 13 and having it learn, it is possible to improve the accuracy of identifying the specific color of the item B itself or its packaging by the learning model 13a of the learning machine 13. Even if multiple items B placed on the item display shelf 5 are partially hidden by the blind spot of the camera 212, the learning machine 13 can create a learning model 13a that can determine the specific color of the item B on the item display shelf 5 by repeatedly learning such images.

[0037] The created learning model 13a can be input to the artificial intelligence device 12a via an external medium such as a USB memory or a HDD, or via a communication network.

[0038] As shown in FIG. 3, an image of a specific color 121 of an article B itself or its packaging and a reference color R, and the judgment results of the image recognition device 12 may be input to a learning machine 13 as training data.

[0039] 5 is a diagram showing a schematic diagram of another embodiment for determining the color of the chip. In this embodiment, the artificial intelligence device 12a of the chip recognition device 12 extracts the center line C of the chip W from the image of the chip W by using the artificial intelligence.

[0040] Specifically, as shown in FIG. 3, the learning machine 13 acquires multiple images of the center line C of the chip W illuminated with different illuminances and recorded by the recording device 11 through the image analysis device 14, and learns from the acquired images and the correct position of the center line C of the chip W in each image by human instruction as teacher data, thereby creating a learning model 13a (recognition program).

[0041] By repeatedly performing the teaching operation of inputting the teaching data into the learning machine 13 and having the learning machine 13 learn, the accuracy of identifying the center line C of the chip W by the learning model 13a of the learning machine 13 can be improved. Even if multiple chips W placed on the gaming table 4 are partially hidden by the blind spot of the camera 212, the learning machine 13 can create a learning model 13a that can determine the center line C of the chip W on the gaming table 4 by repeatedly learning such images.

[0042] The created learning model 13a is input into the artificial intelligence device 12a via an external medium such as a USB memory or HDD, or via a communication network, etc., thereby enabling the artificial intelligence device 12a to extract the center line C of the chip W from the image of the chip W using artificial intelligence.

[0043] When analyzing the center line C from the image, the image may be analyzed as is, or the image may be analyzed after undergoing image processing such as color enhancement and noise removal so as to make it easier to recognize the center line C.

[0044] Furthermore, the chip recognition device 12 may extract the center line C of the chip W by measuring image features such as shape, brightness, saturation, and color using the results of image analysis after capturing an image using the camera 212 and recording it as an image, without using artificial intelligence.

[0045] 6, the artificial intelligence device 12a further includes a configuration for analyzing a peripheral image of a predetermined range around the extracted center line C (for example, a range of 8 pixels centered on the center line and perpendicular to the center line) to recognize at least two colors, the specific color 121 in the peripheral image and the reference color R different from the specific color 121. When analyzing the peripheral image of the predetermined range around the extracted center line C, the image may be analyzed as it is, or may be analyzed after image processing such as color emphasis and noise removal so that the specific color 121 can be easily recognized.

[0046] The artificial intelligence device 12a is an artificial intelligence device that has been taught a plurality of images of the chip W and the reference color 121 illuminated with different illuminance as teacher data. Note that the peripheral image of the center line C of the chip W illuminated with the same illuminance condition can acquire the relative relationship between the specific color 121 and the reference color R because the specific color 121 and the reference color R are illuminated with the same illuminance. For example, this relative relationship may be used to recognize the specific color 121.

[0047] Furthermore, the chip recognition device 12 may recognize a specific color 121 without using artificial intelligence by capturing an image using the camera 212, recording it as an image, and then analyzing the image to measure image features such as shape, brightness, saturation, and color tone.

[0048] In summary, the artificial intelligence device 12a of the recognition device 12 is configured to extract a center line C from an image of the chip W, and perform image analysis of the peripheral image of a predetermined range centered on the center line C, thereby recognizing at least two colors, a specific color 121 in the peripheral image and a reference color R different from the specific color 121, and is an artificial intelligence device taught as training data using multiple peripheral images of the chip W and reference color R illuminated at different illuminances.

[0049] In another embodiment for judging an article, the artificial intelligence device 12a of the article recognition device 12 extracts a specific color 121 of the article B itself or its packaging from an image of the article B itself or its packaging using artificial intelligence.

[0050] Specifically, as shown in FIG. 3, the learning machine 13 acquires multiple images of the item B itself or its packaging and the reference color R illuminated at different illuminance levels and recorded by the recording device 11 through the image analysis device 14, and learns from the acquired images and the correct position of the specific color 121 applied to the item B itself or its packaging in each image by human instruction as teacher data, thereby creating a learning model 13a (recognition program).

[0051] By repeatedly performing the teaching operation of inputting the teaching data to the learning machine 13 and having it learn, it is possible to improve the accuracy of identifying the specific color of the item B itself or its packaging by the learning model 13a of the learning machine 13. Even if multiple items B placed on the item display shelf 5 are partially hidden by the blind spot of the camera 212, the learning machine 13 can create a learning model 13a that can determine the specific color of the item B on the item display shelf 5 by repeatedly learning such images.

[0052] The created learning model 13a is input to the artificial intelligence device 12a via an external medium such as a USB memory or HDD, or via a communication network, etc., and the artificial intelligence device 12a is then able to use artificial intelligence to extract the specific color 121 portion of the item B itself or its packaging from the image of the item B.

[0053] When analyzing the specific color 121 portion of an image, the image may be analyzed as is, or the image may be analyzed after undergoing image processing such as color enhancement and noise removal so as to make the specific color 121 portion easier to recognize.

[0054] Furthermore, the item recognition device 12 may extract a specific color 121 portion of the item B itself or its packaging by a method of measuring image features such as shape, brightness, saturation, and color tone without using artificial intelligence.

[0055] The artificial intelligence device 12a further includes a configuration for analyzing a peripheral image of a predetermined range around the extracted specific color 121 portion (for example, a range of 8 pixels around the specific color portion) to recognize at least two colors, the specific color 121 in the peripheral image and the reference color R different from the specific color 121. When analyzing the peripheral image of a predetermined range around the extracted specific color 121 portion, the image may be analyzed as it is, or may be analyzed after image processing such as color emphasis and noise removal so that the specific color 121 portion can be easily recognized.

[0056] The artificial intelligence device 12a is an artificial intelligence device that has been taught a plurality of images of the specific color 121 portion of the article B itself or the packaging illuminated with different illuminance and the reference color 121 as training data. Note that the peripheral images of the specific color 121 portion of the article B itself or the packaging illuminated with the same illuminance condition can acquire the relative relationship between the specific color 121 and the reference color R because the specific color 121 and the reference color R are illuminated with the same illuminance. For example, this relative relationship may be used to recognize the specific color 121.

[0057] Furthermore, the item recognition device 12 may recognize a specific color 121 without using artificial intelligence by capturing an image using the camera 212, recording it as an image, and then analyzing the image to measure image features such as shape, brightness, saturation, and color tone.

[0058] In summary, the artificial intelligence device 12a of the recognition device 12 is configured to recognize a specific color 121 from an image of the item B itself or its packaging, extract an image portion of the specific color 121, and recognize at least two colors, the specific color 121 and the reference color R, in the peripheral image by image analysis of the peripheral image of the specific color 121, and is an artificial intelligence device that has been taught using multiple peripheral images of the specific color 121 and the reference color R of the item B itself or its packaging illuminated at different illuminances as training data.

[0059] The above-described embodiment has been described for the purpose of enabling a person having ordinary skill in the art to practice the present invention. Various modifications of the above-described embodiment are naturally possible for a person skilled in the art, and the technical idea of ​​the present invention can be applied to other embodiments. Therefore, the present invention is not limited to the described embodiment, but should be accorded the broadest scope in accordance with the technical idea defined by the claims. [Explanation of symbols]

[0060] 4 Gaming Table 5 Goods display shelf 10 Chip Recognition System 11 Recording devices 12 Recognition device 12a Artificial Intelligence Device 13 Learning Machine 13a Learning Model 14 Image analysis equipment 15 Output Devices 20. Item Recognition System 121 Specific color 212 Camera Double Chip B Goods R standard color C center line

Claims

1. A chip recognition system for recognizing chips used on a gaming table in a gaming facility, The chip has at least a specific color that indicates the value of the chip, a camera that captures an image including the specific color portion and a reference color portion; A recognition device including at least an artificial intelligence device that identifies a specific color of the chip using the image, The artificial intelligence device of the recognition device is an artificial intelligence device that is taught a plurality of images including the specific color portion and the reference color portion photographed under different lighting environments as training data, The recognition system comprises a recognition device that extracts a portion of the specific color from an image of the chip and recognizes at least two colors, the specific color and the reference color, in the peripheral image by performing image analysis on the peripheral image including the portion of the specific color.

2. 2. The recognition system of claim 1, A recognition system, wherein the chip has at least a specific color at a predetermined position or in a predetermined shape that indicates the value of the chip.

3. A recognition system according to claim 1 or 2, A recognition system, wherein the recognition device identifies the number of the chips by identifying a specific color of the chips.

4. A recognition system according to any one of claims 1 to 3, The recognition device identifies the specific color of the plurality of chips for each chip, thereby identifying the number of chips of each specific color.

5. A recognition system according to any one of claims 1 to 4, A recognition system, wherein the artificial intelligence device of the recognition device is an artificial intelligence device that determines the specific color of the chip using a relative relationship with the reference color.

6. A recognition system according to any one of claims 1 to 5, The recognition device determines the specific color of multiple stacked chips, and is configured to be able to determine the specific color or number of chips even if some of them are hidden by the camera's blind spot.

7. A recognition system that recognizes objects, The article has a specific color that can identify the article or the package at least in part, a camera that captures an image including a portion of the specific color and a portion of a reference color of the object; A recognition device including at least an artificial intelligence device that uses the image to identify a specific color of the item itself or its packaging, The artificial intelligence device of the recognition device is an artificial intelligence device that is taught a plurality of images including the reference color and the specific color of the item itself or the package photographed under different lighting conditions as training data, The recognition system comprises a recognition device that extracts a portion of the specific color from an image of the object and recognizes at least two colors, the specific color and the reference color, in the peripheral image by performing image analysis on the peripheral image including the portion of the specific color.

8. The recognition system according to claim 7, A recognition system in which the item itself or packaging at least partially has a specific color at a predetermined position or in a predetermined shape that allows the item or packaging to be identified.

9. A recognition system according to claim 7 or 8, The recognition system, wherein the recognition device identifies the number of the articles by identifying a specific color of the article itself or its packaging.

10. 10. The recognition system of claim 9, The recognition device is a recognition system that identifies the number of articles of each specific color by identifying a specific color of the articles themselves or packaging for each article.

11. A recognition system according to any one of claims 7 to 10, A recognition system, wherein the artificial intelligence device of the recognition device is an artificial intelligence device that determines a specific color of the item itself or its packaging using a relative relationship with the reference color.

12. A recognition system according to any one of claims 7 to 11, The recognition system is configured such that the recognition device determines a specific color of the stacked items themselves or their packaging, and is capable of determining the specific color even when some of the items are hidden by the camera's blind spot.

13. A recognition system according to any one of claims 7 to 12, The recognition device determines the specific color of the stacked multiple items or their packaging, and is configured to be able to determine the total number of items or the number of items of each specific color even if some of the items are hidden by the camera's blind spot.

Images