JP3552872B2 - Food and beverage automatic payment device - Google Patents

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an automatic payment device for a food and drink in a cafeteria or the like, and more particularly to a food and beverage automatic payment device suitable for a cafeteria type dining room.
[0002]
[Prior art]
In a cafeteria-style cafeteria where users can freely select and sort out various kinds of greed items such as prepared dishes and cooked rice prepared in a pre-arranged container, automatic payment devices for various types of food and drinks are used. However, in these methods, a price is set in advance for tableware to be used, and an automatic payment of a food and drink price corresponding to a type of each food is performed by discriminating the tableware.
[0003]
For example, in JP-A-55-47558, a specially transparent or translucent tray is used as a tray for sorting dishes, and the dishes placed on the tray are imaged from below by a television camera. Then, an apparatus for discriminating tableware by detecting the size of the bottom surface (twisting) and adjusting the price based on a price set in advance for each tableware is proposed. Since the types of tableware that can be distinguished are limited only by the size of the bottom of the tableware, we propose a device that can handle a wide variety of foods by adding identifiable information to the thread of the tableware. ing.
[0004]
On the other hand, in Japanese Patent Application Laid-Open No. Hei 4-304597, tableware placed on a tray is imaged from above by a television camera, the tableware is identified based on the planar shape of the tableware, and a fee is set based on a price preset for each tableware. Has been proposed for a device to settle accounts.
[0005]
[Problems to be solved by the invention]
In the above prior art, no special consideration is given to the timing of capturing image data for tableware identification, and at the time of image data capture, an image of an object such as a user's arm, which is an obstacle to tableware identification, is captured. There is a problem that it becomes difficult to identify a suitable tableware.
[0006]
That is, it is ideal that the image data for identifying the tableware be taken in a state where the user places the tray on a predetermined table and then retracts the arm holding the tray from the surface of the table. However, in the prior art, the above-described problem occurs because the image data is fetched without giving consideration to checking whether or not such a state has occurred.
[0007]
SUMMARY OF THE INVENTION An object of the present invention is to provide a dining room food and beverage automatic payment device that can clearly detect the timing required for taking in image data for tableware identification and always obtain accurate tableware identification.
[0008]
[Means for Solving the Problems]
The above object is to place a tray for tableware at a predetermined position on a predetermined table, and determine the type and number of tableware placed on the tray based on image data taken from above. In a food and beverage automatic payment device of a system for automatically adjusting the food and beverage price, the processing required for the tableware discrimination is started after confirming that there is no object other than the tray on the table. Is achieved in this way.
[0009]
Tableware recognition processing can be performed in a state where there is no other object that may become an obstacle, so that there is a possibility that an error may occur in the settlement of the food and drink price, and the accurate food and drink price is always accurate. You can get an automatic payment.
[0010]
BEST MODE FOR CARRYING OUT THE INVENTION
Hereinafter, a food and beverage automatic payment apparatus according to the present invention will be described in detail with reference to the illustrated embodiments.
FIG. 3 shows an embodiment of the present invention. In the figure, reference numeral 1 denotes a recognition device, which has a hardware configuration described later, and performs control and calculations necessary for recognition of tableware and settlement of fees.
[0011]
Reference numeral 2 denotes a television camera, and reference numeral 3 denotes a pattern irradiating device. In this embodiment, as the pattern illuminating device 3, slit light is generated, the irradiation position is changed regularly, and the object is scanned and illuminated. The three-dimensional information of the subject can be detected from the image data of the subject captured by the television camera 2.
[0012]
Reference numeral 4 denotes a card reader, which comprises, for example, a non-contact reading type card reader, and functions to read an ID card inserted by a cafeteria user.
Reference numeral 5 denotes a display panel, which functions to display a recognized result, a total amount of payment, and the like.
Reference numeral 6 denotes a tray (bon tray), 7 denotes a table on which the tray 6 is placed, and 8 denotes a tableware. In the example of this figure, the tableware 8 shows a state in which two tablewares 8a and 8b are separated by the tray 6. It is.
Then, the cafeteria user places the dishes 8a and 8b on which a dish and the like are arranged on the tray 6, and then places the tray 6 on the table 7 so that the fee is settled.
[0013]
For this reason, a mark as described later is drawn on the table 7, which roughly indicates the position where the tray 6 is to be placed. In the mounted state, imaging is performed by the television camera 2 under scanning of the slit light emitted from the pattern irradiation device 3, and image data is taken in.
[0014]
Next, FIG. 4 is a hardware configuration diagram of the recognition device 1, and the following devices are stored in the recognition device 1.
First, reference numeral 10 denotes a data bus, which serves to connect the respective devices to each other so that data can be exchanged arbitrarily.
Reference numeral 11 denotes a CPU for performing all operations required by the apparatus.
A ROM 12 stores an initialization program to be executed by the CPU 11 when the power is turned on.
[0015]
Reference numeral 13 denotes a RAM, which serves to store programs executed by the CPU 11 and intermediate results of calculations, image data captured from the television camera 2, and the like.
Reference numeral 14 denotes a serial I / O, and the CPU 11 exchanges information with the non-contact card reader 4 and the display panel 5 via the serial I / O 14.
Reference numeral 15 denotes a camera interface. The camera interface 15 controls imaging of the television camera 2 in accordance with an imaging command from the CPU 11 and transfers captured image data to the RAM 13 via the bus 10.
[0016]
Reference numeral 16 denotes an irradiation control unit that controls the pattern irradiation device 3 according to a command from the CPU 11.
Reference numeral 17 denotes a DISK interface, which functions to enable an interface with the hard disk 18.
Here, the hard disk 18 stores programs to be executed by the apparatus, tableware teaching data, tableware price tables, and the like.
[0017]
A LAN interface 19 exchanges data with a host computer.
In this embodiment, the settlement result is transferred to the host computer, and the actual payment is settled by deduction from salary or by withdrawal from a deposit at a bank or the like.
[0018]
FIG. 5 is an overall processing flow of a program executed by the CPU 11.
This process is started when the power is turned on, and first, in step 101, initialization is performed. In this initialization process, the program, the teaching data, the amount table, and the like stored in the hard disk 18 are transferred to the RAM 14, and the I / Os 14, 15 and the LAN interface 19 are also initialized.
[0019]
Next, in step 102, the input from the card reader 4 and the touch panel 5 is checked, and the process waits until there is any input.
Then, when the end key is input from the touch panel 5, the process is ended here.
Then, when an ID card is read from the card reader 4, the process proceeds to step 103.
[0020]
In step 103, the type of tableware is recognized. The details of the processing will be described later.
The recognition result is output as a tableware number.
In step 104, the total price is calculated from the recognized table number by searching the table number, table name, and a table in which the amount is stored in a table format.
[0021]
In step 105, the amount of money is displayed on the touch panel 5. The displayed contents are the name of the tableware recognized as the total price and the respective price.
When the processing is completed, the process returns to step 102.
At this time, the ID card number and the total amount read by the card reader 4 are written to the hard disk 18 as settlement information, and are transferred to the host computer as requested.
[0022]
Next, the tableware recognition processing in step 103 of FIG. 5 will be described.
In this embodiment, not only the planar shape of the tableware but also the height thereof is taken in as information, so that, for example, the tableware for ramen and a large flat plate have the same two-dimensional shape, but have different heights for tableware. The type of tableware that can be identified and thus can be discriminated can be sufficiently increased.
[0023]
In order to capture the height of the tableware as information, in this embodiment, a detection unit using the principle of triangulation is used in the present embodiment, similarly to the invention already filed as Japanese Patent Application No. 8-226731. To be used.
FIG. 6 shows a configuration for taking in the height of tableware as information in the embodiment shown in FIG. 3. First, as shown in FIG. To generate plate-like light so that slit-like illumination is obtained, thereby irradiating the tableware 8a, 8b such as a bowl and a dish placed on the tray 6 with slit lights 9a, 9b, The illuminated portion is picked up by the television camera 2 to obtain an image signal.
[0024]
At this time, the imaging optical axis X of the television camera 2, the irradiation optical axis Y of the pattern irradiation device 3, as shown, advance with a constant angle theta _0, imaged in this state.
Then, the image becomes as shown in FIG. 6B, and the light applied to the high portion of the tableware is shifted from the light on the surface of the tray 6, and is observed on the right side, for example, as illustrated.
[0025]
Then, the height of the position where the light is irradiated, that is, the height of the tableware can be calculated based on the irradiation angle of the slit light and the degree of the shift of the light at this time.
In the example of FIG. 6, since the deviation of light at the tableware 8a such as a bowl is larger than the tableware 8b such as a dish, it can be determined that the tableware 8a is higher.
[0026]
At this time, as shown by an arrow A, the slit light 9a, 9b is irradiated, for example, while swinging from left to right in the figure to scan the entire tray 6, thereby increasing the height direction from the surface of the tray 6. Is generated. Therefore, the analysis of the image data makes it possible to discriminate the type of tableware three-dimensionally, and can easily cope with diversification of menus.
[0027]
By the way, in this embodiment, when the process proceeds to step 103 after step 102 in FIG. 5, instead of immediately starting the process of recognizing the tableware 8a and 8b, first, the process described below is executed. It is configured to do so.
[0028]
FIG. 2A is a diagram in which the table 7 is viewed from the upper side. Here, between the position where the tray 6 is to be placed and one edge of the table 7, in this case, the upper edge of the figure. As shown by an alternate long and short dash line, an image data acquisition line 10 for object detection is set, and the recognizing device 1 obtains an image captured by the television camera 2 under irradiation of slit light by the pattern irradiation device 3. The image data of the portion along the image data acquisition line 10 is fetched from the obtained image data, and an image by an object other than the table 7 exists in the image data by the image data acquisition line 10. It is configured to execute a process of determining whether or not no object is detected, and to start the recognition process of the tableware 8a, 8b when it is determined that no object is detected.
[0029]
Therefore, the image data take-in line 10 is not actually drawn on the surface of the base 7, and the position (in the frame) of the image data in the unit of frame when processing the image data inside the recognition device 1. Address). At this time, a mark 7a is drawn on the surface of the base 7 as shown in the figure to indicate the position where the tray 6 is placed.
[0030]
Next, a method of detecting an object by image data along the image data acquisition line 10 in this embodiment will be described.
First, the height information 10A is extracted from the image data by the image data receiving line 10 when the image is taken by the television camera 2 in a state where no object is present on the table 7 in advance, and To be stored.
At this time, since there is no object on the upper surface of the table 7, this height information 10A is as shown in FIG. 2B.
[0031]
Next, the cafeteria user selects various menus, puts the tableware 8 on which the selected dishes are served on the tray 6, approaches the table 7, inserts the ID card into the card reader 4, and determines that the dish is appropriate. Then, the process proceeds to the process of step 103 in FIG. 5. Here, the television camera 2 starts imaging, the recognition device 1 repeatedly captures image data by the image data capture line 10, and each time, the height based on this image data is obtained. The information 10B is compared with the stored height information 10A.
[0032]
At this time, if there is no object in a portion corresponding to the image data receiving line 10 on the platform 7, the height information based on the detected image data becomes the same as the already stored height information 10A. Therefore, at this time, it is determined that there is no object, and the above-described tableware recognition process is started.
[0033]
However, at this time, as shown in FIG. 1A, if an object such as the user's arm 9a, 9b exists in the portion of the stand 7 where the image data acquisition line 10 is set, At this time, the height information 10B obtained from the image data by the image data receiving line 10 is as shown in FIG. 1B, and height components 11a and 11b by the user's arms 9a and 9b appear. As a result, when compared with the already stored height information 10A, a difference due to the height components 11a and 11b is detected. In this case, it is determined that there is an object.
[0034]
Then, at this time, the process does not proceed to the tableware recognition process until it is determined that there is no object. The process of fetching the height information 10B and comparing it with the height information 10A is repeated, and thereafter, when neither of the differences 11a and 11b is detected, the original tableware recognition process is started.
[0035]
Therefore, according to this embodiment, even when the ID card is inserted into the card reader 4 and it is determined that the ID card is appropriate, and the process proceeds to the process of step 103 in FIG. 5, the tableware recognition process is immediately started. Instead of confirming that there is no object other than the tray 6 on the table 7 and then proceeding to the tableware recognition process, the optimal timing for proceeding to the tableware recognition process Can be clearly known, the type and number of tableware 8 can always be reliably recognized, and an accurate automatic payment of food and drink can be obtained in a short time.
[0036]
Therefore, effects of this embodiment are listed as follows.
(1) When identifying tableware, it is possible to confirm that there is no other object that may interfere with recognition, so that the food and drink price can always be accurately settled, and high reliability can be obtained. it can.
{Circle around (2)} Since the cafeteria user does not need to worry about detachment of the arm or the like from the tray, operability is improved.
[0037]
{Circle around (3)} Since it is confirmed that there is no obstacle, there is no need to repeat the recognition process due to erroneous settlement, and the settlement time can be shortened as a whole.
{Circle around (4)} Since the obstacle is detected based on the three-dimensional information, there is little possibility that the obstacle is affected by the color of the sleeve of the clothes of the user or the illuminance of the surroundings, and the obstacle can be stably detected.
[0038]
In the above embodiment, the object is detected based on three-dimensional information including the height of the object. However, the object is detected based on a difference in image brightness using simple two-dimensional image data. It goes without saying that it may be configured.
[0039]
【The invention's effect】
According to the present invention, tableware is recognized in a state where there is no object other than the tray on the table, so that the risk of erroneous recognition can be sufficiently suppressed.
Therefore, according to the present invention, the food and drink price can always be automatically and accurately settled, and a highly reliable food and drink automatic payment device can be easily obtained.
[Brief description of the drawings]
FIG. 1 is an explanatory diagram of an object detection method according to an embodiment of a food and drink automatic payment device according to the present invention.
FIG. 2 is an explanatory diagram of an object detection method according to an embodiment of a food and drink automatic payment device according to the present invention.
FIG. 3 is a block diagram showing one embodiment of a food and drink automatic payment device according to the present invention.
FIG. 4 is a block diagram illustrating an internal configuration of a recognition device in an embodiment of an automatic food and drink payment apparatus according to the present invention.
FIG. 5 is a flowchart illustrating an operation of the automatic food and drink payment apparatus according to the present invention.
FIG. 6 is an explanatory diagram of a tableware recognition operation according to an embodiment of the food and drink price automatic payment apparatus according to the present invention.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 1 Recognition device 2 TV camera 3 Pattern irradiation device 4 Card reader 5 Display panel 6 Tray (bon)
8 Tableware 9 Canteen user's arm 10 Image data acquisition lines 10A, 10B Height information 11a, 11b Difference in height

Claims (3)

The tray for sorting dishes is placed at a predetermined position on a predetermined table, and based on image data taken from above, the type and number of the dishes placed on the tray are determined, and the food and drink price is determined. In the automatic food and beverage price automatic payment device,
A food and drink automatic payment device, wherein the processing required for the tableware discrimination is started after confirming that there is no object other than the tray on the table. The tray for sorting dishes is placed at a predetermined position on a predetermined table, and based on image data taken from above, the type and number of the dishes placed on the tray are determined, and the food and drink price is determined. In the automatic food and beverage price automatic payment device,
An image data capture line for object detection is set between the predetermined position and one edge of the table, and image data obtained by imaging the upper surface of the table along the image data capture line. Providing means for detecting an object present on the table,
A food and beverage automatic payment apparatus, wherein the processing required for the tableware discrimination is started when the object is no longer detected by the means. In the invention of claim 2,
The means for detecting the object detects the presence or absence of the object by comparing the image data captured and stored in a state where the object does not exist on the surface of the table in advance with the image data obtained by actually capturing the image. A food and beverage automatic payment device characterized by being configured to perform the above.

Images