Automatic charge settling device for eating and drinking

Description: TECHNICAL FIELD [Detailed description of the invention]

【0001】

[Technical field to which the invention belongs]

The present invention relates to an automatic settlement device for food and drink charges in a dining room and the like, and particularly relates to an automatic settlement device for food and drink charges suitable for a cafeteria-type dining room.

【0002】

[Conventional technology]

In the cafeteria-style dining room, the user can freely select and serve cooked foods such as delicatessen prepared in various types, and therefore, depending on the type of food selected by the user. Since the prices (charges) are different, it is difficult to automate the payment settlement.

【0003】

Therefore, various automatic settlement devices have been proposed so as to tackle this proposition and automatically settle the price, but all of these conventional techniques are tableware to be used according to the type of food. The price was set automatically by deciding the type of food, setting the price, and distinguishing the tableware.

【0004】

For example, in Japanese Patent Application Laid-Open No. 55-47558, the material of the tray (basin) for separating tableware is transparent or translucent, and the tableware placed on this tray is imaged from below by a TV camera, and the bottom surface of the tableware is taken. We propose a method to identify tableware by detecting the size of (threading) and settle the price at a preset price for each tableware.

【0005】

However, relying only on the size of the bottom surface in this way limits the types of tableware that can be identified. Therefore, Japanese Patent Publication No. 5-7745 proposes a device in which an identifiable sign is added to the threading of the tableware to be used so that the types of identifiable tableware can be increased.

【0006】

On the other hand, in Japanese Patent Application Laid-Open No. 4-304597, the tableware placed on the tray is imaged from above by a TV camera, the tableware is identified by the flat shape of the tableware, and the price set in advance for each tableware is used. We are proposing a device to settle the price.

【0007】

[Problems to be Solved by the Invention]

The conventional technique does not give consideration to increasing the types of tableware that can be identified, and has a problem that it is difficult to apply to automatic payment for a dining room with many menus (types of delicatessen). That is, in the conventional technology, since the identification is performed by focusing only on the two-dimensional shape of the tableware, there is a limit to the types of tableware that can be identified, which makes it difficult to cope with the diversification of the types of tableware. It becomes.

【0008】

On the other hand, in the method of adding a sign to tableware, it is necessary to process the tableware for that purpose, and as a result, there are the following problems. That is, it costs extra to add a sign to the tableware, and especially in a restaurant with a large number of users, the number of tableware used is large, so a large cost is required. Further, this method has a problem that the sign may disappear due to washing of the tableware, the number of times the tableware can be repeatedly used is limited, and the cost is further increased.

【0009】

An object of the present invention is to provide a dining room price automatic settlement device capable of sufficiently increasing the types of tableware that can be discriminated without requiring special processing of the tableware.

【0010】

[Means for solving problems]

The above object is achieved by using three-dimensional shape information, that is, three-dimensional information for identifying tableware. In other words, by incorporating not only the flat shape of the tableware but also its height as information, it is possible to identify tableware with the same two-dimensional shape but different heights, such as tableware for ramen and large flat plates. Therefore, the types of tableware that can be identified can be sufficiently increased.

【0011】

At this time, in the present invention, in order to capture the height of the tableware as information, a detection means using the principle of triangular survey is used. FIG. 2 is an example of an optical system used in the present invention to capture the height of tableware as information. The pattern illuminating device 3 generates flat-plate light so that slit-shaped illumination can be obtained on the irradiated surface. By doing so, the tableware 8a and 8b such as bowls and plates placed on the tray 6 are irradiated with the slit light 9a and 9b, and the irradiated portion is imaged by the TV camera 2 to obtain an image signal. It has become.

【0012】

At this time, as shown in the figure, the imaging optical axis X of the television camera 2 and the irradiation optical axis Y of the pattern irradiation device 3 have a constant angle θ.₀And take an image in this state. Then, the image becomes as shown in FIG. 3, and the light radiated to the high part of the tableware deviates from the light on the surface of the tray 6, and is observed on the right side, for example, as shown in the figure.

【0013】

Then, the height of the position where the light is irradiated, that is, the height of the tableware can be calculated from the irradiation angle of the slit light and the degree of the deviation of the light at this time. In the example of FIG. 3, since the light shift of the tableware 8a such as a bowl is larger than that of the tableware 8b such as a plate, it can be determined that the height of the tableware 8a is higher.

【0014】

Then, at this time, as shown by arrow A, the slit lights 9a and 9b were radiated while swinging from left to right to scan the entire tray 6, thereby including information in the height direction from the surface of the tray 6. Image data is generated, and therefore, analysis of this image data makes it possible to discriminate the type of tableware in three dimensions, and it is possible to easily cope with the diversification of menus.

【0015】

BEST MODE FOR CARRYING OUT THE INVENTION

Hereinafter, the food and drink price automatic settlement device according to the present invention will be described in detail with reference to the illustrated embodiment. FIG. 1 is an overall configuration diagram showing an embodiment of the present invention. In the figure, reference numeral 1 denotes a recognition device, which is equipped with a computer and performs predetermined processing necessary for recognizing tableware and settling the price. The TV camera 2 and the pattern irradiating device 3 irradiate the slit light and capture the image data at an angle with each other as described in FIGS. 2 and 3.

【0016】

In this embodiment, a liquid crystal projector capable of irradiating a light spot of 640 × 480 dots is used as the pattern irradiating device 3, whereby 640 slit lights, that is, 640 kinds of angles are directed in different directions. It is designed to generate slit light. Then, the angle θ between the TV camera 2 and the pattern irradiation device 3 at this time.₀Is set at about 28 °.

【0017】

Next, 4 is a card reader for reading the ID card presented by the cafeteria user. 5 is a touch panel that displays the recognized result and the settled price, and is equipped with a touch switch set on the screen, which enables data input from cafeteria users.

【0018】

6 is a tray, and as mentioned above, restaurant users select tableware 8a and 8b with food and drink such as delicatessen, put them on this tray 6, and carry them for meals. .. 7 is a table for settlement, and the cafeteria user puts the tray 6 in the middle of carrying on this table 7 and waits for the settlement.

【0019】

Next, the operation of this embodiment will be described. First, the dining room user selects various menus, takes the tableware 8a and 8b containing the selected delicatessen and other foods on the tray 6, and brings them on the table 7. After that, insert your ID card into the card reader 4. Then, when the data on the ID card is read, the tableware is recognized and the price is settled, and the result is displayed on the touch panel 5. Therefore, the cafeteria user confirms the displayed clearing contents, and if there is no mistake in the result, removes the ID card, and the clearing is completed.

【0020】

Next, the processing by the recognition device 1 will be described. First, FIG. 4 is a hardware configuration diagram of the recognition device 1, and in the figure, 10 is a data bus, and each device is connected. 11 is the CPU of the computer, which performs all the operations on this device.

【0021】

12 is a ROM, which stores the initialization program when the power is turned on. Reference numeral 13 is RAM, which stores the program executed by this device, the intermediate result of the calculation, and the image data captured from the TV camera 2.

【0022】

Reference numeral 14 is a serial I / O, and the CPU 11 exchanges information with the card reader 4 and the touch panel 5 via the serial I / O 14. Reference numeral 15 denotes a camera interface. When an imaging command is issued from the CPU 11, the camera interface 15 controls the imaging of the TV camera 2 and transfers the captured image data to the RAM 13 via the bus 10. Reference numeral 16 denotes an irradiation control unit, which controls the pattern irradiation device 3 by a command from the CPU 11 to generate slit light at various angles.

【0023】

17 is the DISK interface, 8 is the hard disk, first DISK interface 17 is for the interface of the hard disk 18, then the hard disk 18 is the teaching data necessary to determine the program to be executed by this device and the tableware, and the tableware price table. It is for storing such as. Then, the program stored in the hard disk 18 is first transferred to the RAM 13 by the program stored in the ROM 12 when the power is turned on, and then executed by the CPU 11.

【0024】

19 is a LAN interface that exchanges data with higher-level computers. In this embodiment, the settlement result is transferred to a higher-level computer, and the actual payment is settled by deduction from salary or withdrawal from a deposit such as a bank.

【0025】

Figure 5 shows the overall processing flow of the program executed by CPU 11. This process is started by turning on the power, and is first initialized in step 101. Then, in this initialization process, the program, teaching data, amount table, etc. stored in the hard disk 18 are transferred to the RAM 14, and the I / O 14, 15 and the LAN interface 19 are also initialized.

【0026】

Next, in step 102, the input from the card reader 4 and the touch panel 5 is checked, and the input is waited until there is some input. Then, when the end key is input from the touch panel 5, the process ends here. Then, when the ID card is read and input from the card reader 4, the process proceeds to step 103.

【0027】

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 price determined for the tableware is calculated from the recognized tableware number. In this price calculation, the amount table shown in FIG. 8 is used. Then, as shown in FIG. 8, this amount table stores the tableware number, the name of the tableware, and the amount in a table format, and the total amount of the price is stored using the recognized tableware number. To calculate.

【0028】

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 amount and the amount of each. Then, when the process 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 clearing information and transferred to the host computer upon request.

【0029】

FIG. 6 is a processing flow of tableware recognition in step 103. First, the height image is generated in step 201. In this height image, the shade information in the normal shade image data is the height information of the tableware. The method of generating this height image will be described later.

【0030】

An example of the generated height image is shown in FIG. This FIG. 10 is for the images of the tray 6 and the tableware 8a and 8b of FIG. 2, and the bright part shows the raised part of the tableware. FIG. 11 shows a cross-sectional view (cross-sectional luminance) of A-A'in FIG. 10, and by extracting information on each part of the image in this way, the position and height can be determined. You can ask.

【0031】

Next, in step 202, the area separation process is performed. In this region separation process, a continuous region is detected by binarizing the portion having a height of 10 mm or more from the surface of the tray 6. In step 203, the feature quantity is calculated for the separated area of one section. This one section is an area corresponding to one tableware, and here, the average height of the edge of the area, the area of the area, and the peripheral length of the area are selected as the feature quantities, and these are calculated.

【0032】

Next, in step 204, comparison with the teaching data is performed. This teaching data is registered in advance as the table shown in FIG. 7, and as shown in the figure, the tableware number, the name of the tableware, the average height of the edge, the area, and the peripheral length are registered in this table.

【0033】

Then, the calculated feature amount is compared with each value in this table, and those whose difference is equal to or less than a predetermined threshold value are searched for and matched. Then, when a matching item is found, the tableware number is registered as the recognition result in step 205, and when there is no matching item, the process proceeds to step 206.

【0034】

In step 206, it is checked whether the processing is completed for all the separated areas, and if it is not completed, the process returns to step 203, and if it is completed, the processing ends here. By the above processing, recognition of all the tableware on the tray 6 can be obtained.

【0035】

Next, FIG. 9 is a processing flow of height image generation in step 201. First, the angle θ is set to 0 in step 301. This angle θ is the irradiation angle of the slit light by the pattern irradiation device 3, and therefore, the angle 0 is the scanning start point of the detection region, that is, in the case of FIG. 1, one end of the table 7, for example, the left end of the figure of the slit light. It corresponds to the angle at which the irradiation position comes.

【0036】

Next, in step 302, the slit light is irradiated at the irradiation angle θ, and in step 303, the image irradiated with the slit light is captured. The image captured at this time is shown in FIG. In FIG. 3, two slit lights 9a and 9b are shown for the sake of clarity, but in reality, only one slit light is irradiated and moves in sequence. ..

【0037】

Next, in step 304, the height is calculated. This height is calculated by extracting an image from the slit light and detecting the position X in the horizontal direction of the slit light for each pixel Y in the vertical direction. That is, the height H is obtained by geometric calculation from the position X in the horizontal direction and the irradiation angle θ of the slit light, the position and tilt angle of the TV camera 2, and the position and tilt angle of the pattern irradiation device 3, respectively, in the vertical direction. Calculated for pixel Y.

【0038】

In step 305, the height calculation result is written in the height image. Specifically, for one line, the calculated height H is written in the memory corresponding to each pixel position Y in the vertical direction and the position X in the horizontal direction.

【0039】

Next, in step 306, the angle θ is changed by a certain minute angle Δθ. The lateral resolution of the height image is determined by the value of this minute angle Δθ. Here, a value corresponding to a lateral resolution of about 2 mm is set as this minute angle Δθ.

【0040】

In step 307, the angle θ and the maximum angle θMax are compared. If this angle θ is larger than the maximum angle θMax, it means that the scanning of the detection region has been completed, so the process ends here. That is, this maximum angle θMax corresponds to the angle at which the irradiation position by the slit light is at the other end of the table 7, for example, the right end of the table 7 in FIG.

【0041】

On the other hand, when the angle θ is less than the maximum angle θMax, the process returns to step 302, and the process of changing the minute angle Δθ again and taking an image is repeated. Therefore, by the above processing, the operation of capturing the image by changing the irradiation angle by a minute angle Δθ is repeated, and as a result, for example, in the case of the tray 6 and the tableware 8a and 8b in FIG. 1, it is shown in FIG. A height image can be obtained.

【0042】

Therefore, according to the above embodiment, the effects listed below can be obtained. Since tableware is recognized by 3D information, there are few restrictions on the type of tableware to be used, and it is possible to set various types of menus. For example, the small rice bowl with tableware number 1 and the small flat plate with tableware number 5 in Fig. 7, and the large rice bowl with tableware number 2 and the flat plate with tableware number 4 have the same planar shape, so the area, circumference, etc. are two-dimensional. Although it cannot be discriminated only by the information, in the above-described embodiment, since the height information is used, it is possible to discriminate clearly and surely.

【0043】

In the above embodiment, the height discrimination performance is adjusted to about 10 mm. On the other hand, since the height of the tableware normally used is about 20 mm to 100 mm, the menu is set to be about 9 times in the case of the present invention as compared with the case where only the flat shape is relied on as in the conventional technique. it can.

【0044】

Since the type can be identified only by the three-dimensional shape of the tableware, there is no need to add identification information such as a sign to the tableware, and the general-purpose tableware that has been used conventionally can be used as it is.

【0045】

Since it is only necessary to take an image from the upper side of the tray, the material of the tray does not matter, and since it is not identified by simple shading image information, contrast is not required between the image of the tray and the tableware, so it is used. There are no restrictions on the relative colors of trays and tableware, and general-purpose trays that have been used in the past can be used as they are.

【0046】

Since a liquid crystal projector is used to irradiate the slit light, there are no moving parts and maintenance is easy. Since the recognition is performed by paying attention to the outer shape of the tableware, there is no influence of the dishes on the tableware, and the settlement process can be performed before or after the meal. There is no need to handle cash because it is a card-based payment method.

【0047】

Since the teaching data table and the amount table are separated, it is only necessary to set the data of the amount table when setting the menu, and it is easy to change the amount. Since the height image is used, it is possible to detect only those with a height of 10 mm or more, and as a result, items other than tableware such as chopsticks and spoons are excluded from the settlement target without any special processing or setting. Processing is obtained. Therefore, according to the above-described embodiment of the present invention, it is possible to easily automate the settlement in the cafeteria-type dining room due to the above effects.

【0048】

In the above embodiment, scanning is performed with slit light, but in order to speed up imaging, the present invention may be carried out by coding a light pattern and using a technique called a spatial coding method. For example, the settlement time can be shortened. Further, in the above embodiment, an ID card is used for user identification, but it goes without saying that by changing the card reader, it is possible to easily handle payment by a prepaid card.

【0049】

[Effect of the invention]

According to the present invention, since the three-dimensional shape information is used for the identification of the tableware, the difference in the shape of the tableware can be surely identified, and therefore, the identification of many kinds of tableware can be performed without adding a special sign to the tableware. This makes it possible, and as a result, the number of menus can be significantly increased.

【0050】

As a result, according to the present invention, it is possible to provide an automatic food and drink price settlement device that can be easily applied to a cafeteria-type dining room with a large number of users.

[Simple explanation of drawings]

[Figure 1]

It is a block diagram which shows the whole structure in one Embodiment of the food and drink price automatic settlement apparatus by this invention.

[Figure 2]

It is an optical system layout diagram which shows the operation principle of one Embodiment of this invention.

[Fig. 3]

It is explanatory drawing of the captured image by one Embodiment of this invention.

[Fig. 4]

The hardware block diagram of one Embodiment of this invention.

[Fig. 5]

It is explanatory drawing of the whole processing flow by one Embodiment of this invention.

[Fig. 6]

It is explanatory drawing of the tableware recognition processing flow in one Embodiment of this invention.

[Fig. 7]

It is explanatory drawing of the teaching data table used in one Embodiment of this invention.

[Fig. 8]

It is explanatory drawing of the amount table used in one Embodiment of this invention.

[Fig. 9]

It is explanatory drawing of the height image generation processing flow by one Embodiment of this invention.

[Fig. 10]

It is explanatory drawing which shows an example of the height image obtained by one Embodiment of this invention.

[Fig. 11]

It is sectional drawing in an example of the height image obtained by one Embodiment of this invention.

[Explanation of symbols]

1 Recognition device 2 TV camera 3 pattern irradiation device 4 Card reader 5 touch panel 6 trays 7 Settlement table 8a, 8b tableware