JP2021149834A - Currency information generation device, currency processing device, currency information generation system, currency information generation method, and currency information generation program - Google Patents

Abstract

To provide a currency information generation device, a currency processing device, a currency information generation system, a currency information generation method, and a currency information generation program, capable of generating coin information of virtual currency corresponding to currency even in a state where a real object of the currency having desired damage cannot be obtained.SOLUTION: A currency information generation device includes a control unit that generates damage information being information relating to damage of first currency from currency information of the first currency, generates pattern information being information relating to a pattern of second currency from currency information of the second currency, and generates currency information on virtual currency obtained by fusing the damage information and the pattern information from the damage information and the pattern information.SELECTED DRAWING: Figure 1

Description

The present invention relates to a money information generation device, a money processing device, a money information generation system, a money information generation method, and a money information generation program. More specifically, the present invention relates to a money information generation device, a money processing device, a money information generation system, a money information generation method, and a money information generation program suitable for generating virtual money image information.

In a money processing device that processes money such as coins and banknotes (banknotes), the characteristics of money are acquired by using a plurality of different types of sensors mounted on the money identification device. Then, it is common practice to identify the type of money, authenticity, positive loss, etc. based on the comparison between the characteristics of the acquired money and the template information which is the reference for identification.

For example, Patent Documents 1 and 2 disclose an image collating device that collates an image of money with a plurality of template images corresponding to various currencies and determines the authenticity of the money. In this device, when determining the authenticity of a coin, an average image obtained by synthesizing a plurality of images of the same type of coin is used as a template image in order to suppress variations due to individual differences in the coin.

Patent No. 4563740 Patent No. 4563741

In the inventions described in Patent Documents 1 and 2, it is necessary to acquire a plurality of images for each denomination from coins distributed in the market in advance and generate a template image from the acquired plurality of images.

Also, when determining the correct loss rather than the authenticity of money, usually, multiple images are acquired for each denomination from the dirty money distributed in the market in advance, and template information is generated from the acquired multiple images. doing.

By the way, when a coin is recast, the coin processing device in the market quickly generates template information of the recast coin so that the coin processing device can quickly identify the recast coin. Is required to be applied to.

However, when template information is generated from real money as in the inventions described in Patent Documents 1 and 2, only unused new money (hereinafter, also referred to as new money) exists immediately after recasting. The template information corresponding to the polluted money cannot be generated. In such a situation after recasting, the contaminated money with a large degree of contamination cannot be identified.

Therefore, it is required to be able to generate monetary information (image information and template information) of the defaced money, that is, virtual monetary information of the defaced money, even if the actual defaced money is not available.

On the contrary, in a situation where only the actual dirty money is available, it may be necessary to generate template information from new money.

The present invention has been made in view of the above situation, and money information capable of generating virtual coin information of money corresponding to the money even when the actual money of the desired degree of damage is not available. It is an object of the present invention to provide a generation device, a money processing device, a money information generation system, a money information generation method, and a money information generation program.

In order to solve the above-mentioned problems and achieve the object, the present invention is a monetary information generator, and the monetary information generator relates to damage of the first money from the money information of the first money. Damage information which is information is generated, pattern information which is information about the pattern of the second currency is generated from the currency information of the second currency, and the damage information and the pattern are generated from the damage information and the pattern information. It is characterized by including a control unit that generates monetary information of virtual money in which information is fused.

Further, in the present invention, in the above invention, the control unit has a machine learning algorithm related to the generation of the damage information and a machine related to the generation of the pattern information so that the monetary information of the virtual currency becomes genuine. It is characterized in that the learning algorithm and the machine learning algorithm related to the generation of monetary information of the virtual money are machine-learned.

Further, the present invention is characterized in that, in the above invention, the first currency is a loss currency and the second currency is a new currency.

Further, the present invention is characterized in that, in the above invention, the first currency is a new currency and the second currency is a loss currency.

Further, the present invention is characterized in that, in the above invention, the first type of money is different from the second type of money.

Further, the present invention is characterized in that, in the above invention, the material of the first currency is the same as the material of the second currency.

Further, in the present invention, in the above invention, the second currency has a first region composed of the same first material as the material of the first currency and a second region composed of the second material. The control unit generates pattern information which is information about the pattern of the first region from the monetary information of the first region, and the damage information and the pattern of the first region. It is characterized in that the damage information and the pattern information of the first region are fused to generate virtual monetary information of the first region from the information.

Further, in the present invention, in the above invention, the second material is different from the material of the first money and is the same material as the material of the other third money, and the control unit is the third material. The damage information which is the information about the damage of the third money is generated from the money information of the money of the above, and the pattern information which is the information about the pattern of the second area is generated from the money information of the second area. A virtual second region in which the damage information of the third currency and the pattern information of the second region are fused from the damage information of the third currency and the pattern information of the second region. It is characterized by generating monetary information of.

Further, in the present invention, the second currency is different from the first region composed of the same first material as the material of the first currency and the material of the first currency. It also has a second region made of the same second material as the material of the other third money, and the money information generator has a third region made of the first material and a third region. The correspondence between the feature amount of the third region and the feature amount of the fourth region generated from the monetary information of the fourth currency including the fourth region composed of the second material. The control unit further includes a stored storage unit, and the control unit is characterized in that it generates monetary information of the virtual money based on the correspondence relationship.

Further, in the above invention, in the above invention, the control unit generates a plurality of damage information related to the first currency from the currency information of a plurality of first coins having the same material and different degrees of damage. However, a plurality of damage information relating to the third currency is generated from the currency information of the plurality of third coins having the same material but different degrees of damage, and the plurality of damage information relating to the first currency is generated. And from the pattern information, monetary information of a plurality of first virtual coins in which each of the plurality of damage information related to the first currency and the pattern information are fused is generated, and the currency information relating to the third currency is generated. From the plurality of damage information and the pattern information, monetary information of a plurality of second virtual currencies in which each of the plurality of damage information related to the third currency and the pattern information are fused is generated, and the plurality of monetary information is generated. The first feature quantity of the region corresponding to the first region is calculated from the monetary information of the first virtual currency, and the monetary information of the plurality of second virtual coins is transferred to the second region. The second feature amount of the corresponding region is calculated, and the optimum first feature amount and the optimum first feature amount from the plurality of the first feature amount and the plurality of the second feature amount are calculated based on the correspondence relationship. The combination of the second feature amount is determined, and the monetary information of the first virtual currency and the currency of the second virtual currency corresponding to the optimum first feature amount and the second feature amount, respectively, are determined. From the information, a second including the monetary information of the first virtual money in the area corresponding to the first area and the monetary information of the second virtual money in the area corresponding to the second area. It is characterized by generating monetary information of 3 virtual currencies.

Further, the present invention is characterized in that, in the above invention, the damage information is information regarding damage to the base of the first currency.

Further, in the present invention, in the above invention, the type of the first currency is the same as the type of the second currency, and the control unit is based on the currency information on the first surface of the first currency. A pattern that generates damage information that is information about damage to the first surface and is information about a pattern of the second surface from the monetary information of the second surface that is different from the first surface of the second currency. Information is generated, and the damage information of the first surface and the pattern information of the second surface are fused with the damage information of the first surface and the pattern information of the second surface. It is characterized in that the monetary information of the second surface is generated.

Further, the present invention is characterized in that, in the above invention, the monetary information is image information.

Further, the present invention is a money processing system, wherein the money processing system includes a money information generating device and a money processing device having a storage unit for storing template information based on the money information of the virtual money. It is characterized by having.

Further, the present invention is a money processing device, wherein the money processing device includes the money information generating device and a storage unit that stores template information based on the money information of the virtual money. It is a feature.

Further, the present invention is a monetary information generation system, and the monetary information generation system is a damage information generation unit that generates damage information which is information on damage of the first money from the money information of the first money. And the pattern information generation unit that generates pattern information that is information about the pattern of the second currency from the currency information of the second currency, and the damage information and the pattern information from the damage information and the pattern information. It is characterized by including a virtual money information generation unit that generates money information of fused virtual money.

Further, the present invention is a method for generating money information, wherein the method for generating money information includes a step of generating damage information which is information on damage of the first money from the money information of the first money, and a first step. A virtual currency in which the damage information and the pattern information are fused from the step of generating the pattern information which is the information about the pattern of the second currency from the currency information of the second currency and the damage information and the pattern information. It is characterized by comprising a step of generating monetary information of.

Further, the present invention is a monetary information generation program, wherein the monetary information generation program is a means for generating a computer from monetary information of the first monetary information, which is information on damage of the first monetary currency. , A means for generating pattern information which is information about the pattern of the second currency from the monetary information of the second currency, and a virtual fusion of the damage information and the pattern information from the damage information and the pattern information. It is characterized by functioning as a means for generating monetary information of various currencies.

Further, the present invention is a monetary information generator, and the monetary information generator generates counterfeit information, which is information related to counterfeiting of the first currency, from the currency information of the first currency, and the second Pattern information, which is information related to the second monetary pattern, is generated from the monetary information of money, and from the counterfeit information and the pattern information, the monetary information of virtual money in which the counterfeit information and the pattern information are fused is obtained. It is characterized by including a control unit to be generated.

Further, the present invention is a money processing system, wherein the money processing system includes a money information generating device and a money processing device having a storage unit for storing template information based on the money information of the virtual money. It is characterized by having.

Further, the present invention is a money processing device, wherein the money processing device includes the money information generating device and a storage unit that stores template information based on the money information of the virtual money. It is a feature.

Further, the present invention is a monetary information generation system, and the monetary information generation system is a counterfeit information generation unit that generates counterfeit information, which is information related to counterfeiting of the first currency, from the currency information of the first currency. A pattern information generation unit that generates pattern information that is information about the pattern of the second currency from the currency information of the second currency, and the counterfeit information and the pattern information from the counterfeit information and the pattern information. It is characterized by including a virtual money information generation unit that generates money information of fused virtual money.

Further, the present invention is a method for generating money information, wherein the method for generating money information includes a step of generating counterfeit information, which is information related to counterfeiting of the first currency, from the currency information of the first currency. A virtual currency in which the counterfeit information and the pattern information are fused from the step of generating pattern information which is information about the pattern of the second currency from the currency information of the second currency and the counterfeit information and the pattern information. It is characterized by comprising a step of generating monetary information of.

Further, the present invention is a monetary information generation program, wherein the monetary information generation program is a means for generating a computer from the monetary information of the first monetary money, which is information related to the forgery of the first monetary currency. , A means for generating pattern information which is information about the pattern of the second currency from the monetary information of the second currency, and a virtual fusion of the counterfeit information and the pattern information from the counterfeit information and the pattern information. It is characterized by functioning as a means for generating monetary information of various currencies.

According to the money information generation device, the money processing device, the money information generation system, the money information generation method, and the money information generation program of the present invention, even if the actual money of the desired degree of damage is not available, the money can be used. It is possible to generate coin information of the corresponding virtual currency.

It is a schematic diagram for demonstrating the outline of the method of generating monetary information in Embodiment 1. It is a block diagram explaining the structure of the money information generation apparatus which concerns on Embodiment 1, and shows the structure at the time of machine learning. It is a block diagram explaining the structure of the money information generation apparatus which concerns on Embodiment 1, and shows the structure after machine learning. It is a flowchart which shows an example of the procedure of the process performed by the money information generation apparatus which concerns on Embodiment 1 at the time of machine learning. It is a flowchart which shows an example of the procedure of the process performed by the money information generation apparatus which concerns on Embodiment 1 after machine learning. It is a block diagram explaining an example of the whole structure of the money processing system including the money information generation apparatus which concerns on Embodiment 1. FIG. It is a block diagram explaining another example of the whole structure of the money processing system including the money information generation apparatus which concerns on Embodiment 1. FIG. It is a block diagram explaining the whole structure of the money processing apparatus including the currency information generation apparatus which concerns on Embodiment 1. FIG. It is a block diagram explaining the structure of the money information generation apparatus which concerns on Embodiment 2, and shows the structure after machine learning. It is a schematic diagram for demonstrating an example of the specific processing by the money information generation apparatus which concerns on Embodiment 2. It is a flowchart which shows an example of the procedure of the process performed by the money information generation apparatus which concerns on Embodiment 1 after machine learning. It is a block diagram explaining the structure of the money information generation device which concerns on a modification form, and shows the structure at the time of machine learning. It is a block diagram explaining the structure of the money information generation device which concerns on a modified form, and shows the structure after machine learning.

Hereinafter, preferred embodiments of the money information generation device, the money information generation system, the money information generation method, and the money information generation program according to the present invention will be described with reference to the drawings.

In addition, in this specification, "money" means a thing including coins and paper leaves such as banknotes. Further, as the paper leaves to be the subject of the present invention, various paper leaves such as banknotes (banknotes), checks, gift certificates, bills, forms, securities, card-like media and the like can be applied.

Further, the "money information" means predetermined information about money, and preferred specific examples include an image (image data) of the money and template information obtained from the coin. In the following embodiment, an example will be described in which a coin is targeted as money and image information of money (hereinafter, also simply referred to as an image) is used as money information.

The types of money that are damaged or the factors that are considered to be money that is damaged include the following.
-For coins: "dirt", "corrosion (deterioration)", "mechanical damage (scratches, holes, wear, etc.)", "deformation", "defects (defects in the manufacturing process, marking errors, molding defects, etc.)" Etc. ・ For banknotes: "Dirt", "Graffiti", "Defective (missing corners, holes, other partial missing, etc.)", "Tear / tear", "Break", "Fatigue", "Tape is attached" What was done "etc.

In the present specification, the term "damage" is a general term for the change of money from the normal state, as mentioned in the above types or factors, and is referred to as "damage". In addition, undamaged currency and damaged currency are also referred to as normal currency and damaged currency, or genuine currency and loss currency, respectively, and in the case of coins, they are also referred to as genuine currency and loss currency, or Fit coin and UnFit coin, and banknotes. In the case of, it is also referred to as a regular ticket and a loss ticket, or a Fit banknote or UnFit banknote.

In addition, it is possible to identify (or discriminate) whether or not the money is damaged, whether or not the money meets the standard, and / or whether or not the money is suitable for distribution. Good).

(Embodiment 1)
<Outline of this embodiment>
First, an outline of the method for generating monetary information in the first embodiment will be described. As shown in FIG. 1, in the present embodiment, first, a style input image as an image of the first coin and a conversion source image as an image of the second coin are prepared.

The style input image (image of the first coin) is an image of the first coin having a desired degree of damage that the desired degree of damage is desired, and has an arbitrary pattern (pattern, engraving). .. The style input image is usually an image of a coin in circulation (preferably a loss coin) with some damage, but may be an image of a undamaged coin (eg, a new coin).

The conversion source image (image of the second coin) is an image of the second coin that is desired to have the damage condition of the style input image, and has an arbitrary damage condition. The conversion source image (the image of the second coin) is usually an image of an undamaged coin (for example, a new coin), but an image of a circulating coin (preferably a loss coin) that has some damage. There may be.

Next, the damage information which is the information about the damage of the first coin is generated (extracted) from the input image for style, and the pattern information which is the information about the pattern of the second coin is generated (extracted) from the conversion source image. )do.

Then, from the damage information and the pattern information, an image of a virtual coin in which the damage information and the pattern information are fused is generated. As a result, it is possible to generate an image of a coin (however, a virtual one that does not exist) that has the same degree of damage as the first coin and has the pattern of the second coin. That is, even if the second coin having the same degree of damage as the first coin does not actually exist, the template for the second coin is based on the image of the virtual coin generated as described above. Information can be generated.

The "damage information (information on damage)" may be information on the presence of damage or information on the absence of damage. In the former case, it may be information for deteriorating the stamp on the coin or the base.

Further, the "damage condition" is a term indicating the degree of damage, and includes not only the case where there is damage but also the case where there is no damage.

That is, in the present embodiment, the first coin is a damaged coin, the second coin is a undamaged or less damaged coin, and the second coin is used as a virtual coin. The coin may be damaged to the same extent as the coin (the degree of damage may be increased), the first coin is a coin that is undamaged or less damaged, and the second coin is a damaged coin. Yes, as a virtual coin, the second coin does not have to be damaged to the same extent as the first coin (the degree of damage may be reduced).

Further, the "pattern information (information about the pattern)" may be information about the stamping of the coin (for example, 3D information) with respect to the coin. Here, the "engraving" may be one that changes due to damage to the coin, or may be one that does not change even if the coin is damaged. More specifically, as the pattern information, for example, information on a part where the way of shining light changes depending on the degree of damage, information on a part where edge information changes depending on the degree of damage, and information on a part where the material changes due to damage. And so on.

Further, in the present embodiment, the above-mentioned machine learning algorithm related to the generation of damage information, the machine learning algorithm related to the generation of pattern information, and the virtual money are used so that the image of the virtual coin looks like the real thing. Machine learning (preferably deep learning) with a machine learning algorithm related to the generation of monetary information. This makes it possible to obtain a more realistic virtual coin image. That is, the image of the generated virtual coin can be made closer to the actual image of the second coin with the desired degree of damage.

Further, in the present embodiment, by using an image (image information) as the currency information, it is possible to generate an image of virtual currency corresponding to the second currency (actual) with a desired degree of damage, and the result of the image. Can be visually confirmed.

<Configuration of monetary information generator>
Next, the configuration of the monetary information generator 10A according to the present embodiment will be described with reference to FIGS. 2 and 3. The monetary information generator 10A has a function equivalent to that of a general personal computer, and includes a control unit (arithmetic processing unit) 20 and a storage unit (not shown in FIGS. 2 and 3) as shown in FIGS. 2 and 3. ing.

As shown in FIG. 2, the control unit 20 has functions of a damage information generation unit 21, a pattern information generation unit 22, a virtual currency information generation unit 23, and a learning unit 24 during machine learning. After machine learning (for example, during actual operation), it has functions of a damage information generation unit 21, a pattern information generation unit 22, a virtual currency information generation unit 23, and a template generation unit 25.

The control unit 20 is composed of, for example, a software program for realizing various processes, a CPU (Central Processing Unit) that executes the software program, various hardware controlled by the CPU, and the like. Software programs and data necessary for the operation of the control unit 20 are stored in the storage unit.

Each of the units shown in FIGS. 2 and 3 of the control unit 20 is realized by executing the monetary information generation program according to the present embodiment on the CPU of the control unit 20. The monetary information generation program according to the present embodiment may be introduced in advance in the monetary information generation device 10A, or may be recorded on a computer-readable recording medium as an application program that can operate on a general-purpose OS, or may be recorded on a network. It may be provided to the user via.

The storage unit is composed of a storage device such as a hard disk device or a non-volatile memory, and includes a trained model that executes the above-mentioned processing related to the generation of damage information, a trained model that executes the processing related to the generation of pattern information, and a trained model. It stores a trained model that executes processing related to the generation of monetary information of virtual monetary information.

The damage information generation unit 21 generates (extracts) damage information, which is information on damage to the first coin, from the image of the first coin (input image for style) input to the money information generation device 10A.

The pattern information generation unit 22 generates pattern information (pattern features) which is information about the pattern of the second coin from the image (conversion source image) of the second coin input to the money information generation device 10A (the pattern information generation unit 22). Extract.

The damage information generated by the damage information generation unit 21 may be information regarding damage to the base of the first coin. That is, the damage information generation unit 21 may generate (extract) information on damage to the base of the first coin from the image of the first coin (input image for style).

Here, the "base" usually refers to a portion of a coin excluding the stamp of the coin. That is, a coin is usually composed of a base and an engraving.

The virtual currency information generation unit 23 fuses (synthesizes) the damage information and the pattern information generated from the damage information generated by the damage information generation unit 21 and the pattern information generated by the pattern information generation unit 22. Generate a virtual coin image (image information). As a result, it is possible to generate an image of a coin (however, a virtual one that does not exist) that has the same degree of damage as the first coin and has the pattern of the second coin.

The damage information generation unit 21, the pattern information generation unit 22, and the virtual currency information generation unit 23 are each constructed from a trained model, and preferably by a trained model using a convolutional neural network (CNN). Has been built. The CNN of the virtual currency information generation unit 23 is combined with each CNN of the damage information generation unit 21 and the pattern information generation unit 22.

The learning unit 24 includes a machine learning algorithm related to damage information generation by the damage information generation unit 21 and a pattern information generation unit 22 so that the virtual coin image generated by the virtual money information generation unit 23 looks like a real one. The machine learning algorithm related to the generation of pattern information by the above and the machine learning algorithm related to the generation of virtual money money information by the virtual money information generation unit 23 are machine-learned. As a result of this learning, trained models of the damage information generation unit 21, the pattern information generation unit 22, and the virtual currency information generation unit 23 are created, respectively. It is preferable that each machine learning algorithm utilizes CNN as in the trained model described above.

The learning unit 24 also includes a machine learning algorithm (preferably one using CNN), and an image (output image) of a virtual coin generated by the virtual money information generation unit 23 and an image of a real coin. Machine learning based on (training data). That is, whether the image of the virtual coin generated by the virtual money information generation unit 23 using the image of the virtual coin and the image of the real coin is virtual or real (whether it is real). ) Will be learned so that it can be discriminated more accurately. Then, the learning unit 24 relates to the learning unit 24, the damage information generation unit 21, the pattern information generation unit 22, and the virtual currency information generation unit 23 using the error between the output by the learning unit 24 and the desired output (correct answer) as a teacher signal. By giving it to the machine learning algorithm, the coupling coefficient of each CNN is gradually changed so that the correct output is finally obtained.

Each trained model of the damage information generation unit 21, the pattern information generation unit 22, and the virtual currency information generation unit 23 incorporates the trained parameters that are the parameters (coefficients) obtained as a result of learning using the data set. Functions as an inference program.

In addition, each trained model may be additionally trained. That is, by applying a data set different from that at the time of training to each trained model and performing further training, a new trained parameter is generated, and each trained model incorporating this new trained parameter is used. You may.

The template generation unit 25 uses the machine-learned damage information generation unit 21, the pattern information generation unit 22, and the virtual currency information generation unit 23 to generate the same pattern as the second coin, although the degree of damage is different from each other. Generate template information from images of multiple virtual coins you have.

The first coin used for the style input image and the second coin used for the conversion source image are such that the first coin (money) is a loss coin (loss money) and the second coin (a second coin). The coin) may be a new coin (new coin). In this case, even in a situation where the second coin is recast and only a new coin of the second coin exists, it is possible to generate an image of a virtual coin corresponding to the loss of the second coin.

On the other hand, the first coin (money) may be a new coin (new money) and the second coin (money) may be a loss coin (loss coin). In this case, even in a situation where only the loss of the second coin exists, it is possible to generate an image of a virtual coin corresponding to the new coin of the second coin.

Further, the type of the first coin (money), that is, the denomination may be different from the type of the second coin (money), that is, the denomination. Even in such a case, it is possible to generate an image of a virtual coin corresponding to the second coin having a desired degree of damage.

The material of the first coin (money) is preferably the same as the material of the second coin (money) (including the case where it is substantially the same). This makes the generated virtual coin image more authentic. This is because coins of the same material are damaged in a similar manner even if they are of different types. Here, the material of the first and second coins is more preferably the material of the coin on the surface of each coin.

Even in the case of banknotes, the method of damage usually differs depending on the material. For example, paper banknotes and polymer sheet banknotes (polymer banknotes) are soiled differently.

The color of the first coin (money) may be similar to the color of the second coin (money). This also makes the generated virtual coin image more authentic. This is because coins with similar colors are damaged in the same way even if they are of different types.

Further, as shown in FIG. 1, the type of the first coin (money), that is, the denomination may be the same as the type of the second coin (money), that is, the denomination. In this case, the damage information generation unit 21 generates damage information on the first surface (for example, the surface) of the first coin (for example, a 10-yen coin), and the pattern information generation unit 22 generates damage information on the first surface. , A virtual pattern information of the second surface is generated from an image of a second surface (for example, the back surface) different from the first surface of the image of the second coin (for example, a 10-yen coin different from the first coin). The monetary information generation unit 23 is based on the damage information of the first surface generated by the damage information generation unit 21 and the pattern information of the second surface generated by the pattern information generation unit 22, and these damage information and patterns. Generates a virtual image of the second surface where the information is fused. This makes it possible to generate a more authentic image of the virtual second surface. This is because coins of the same type are damaged in similar ways, even if they have different aspects.

Here, a process suitable for the case where the second coin, particularly the surface thereof, has a plurality of regions each composed of a plurality of materials will be described. Bicolor coins are suitable as such coins. Specifically, for example, a new 500-yen coin scheduled to be issued by the first half of 2021 is suitable.

A first region in which the surface of a second coin (for example, a new 500-yen coin) is made of the same first material as the material of the first coin (for example, the current 500-yen coin) (for example, nickel brass). When having (for example, a ring unit), the pattern information generation unit 22 generates pattern information of the first region from the image of the first region of the second coin, and the virtual currency information generation unit 23 generates damage information. From the damage information generated by the generation unit 21 and the pattern information of the first region generated by the pattern information generation unit 22, a virtual image of the first region in which the damage information and the pattern information are fused is generated. do. As a result, even if the second coin is a bicolor coin, it corresponds to a first region (for example, a ring portion) of a desired degree of damage made of the same first material as the material of the first coin. An image of a virtual first region can be generated.

Also, the second coin (for example, a new 500 yen coin), especially its surface, is different from the material of the first coin (for example, the current 500 yen coin), and another third coin (for example, the old 500 yen coin). When a second region (for example, a central portion) made of the same second material as the material (for example, white copper) is included, the damage information generation unit 21 damages the third coin from the image of the third coin. The information is generated, the pattern information generation unit 22 generates the pattern information of the second region from the image of the second region of the second coin, and the virtual currency information generation unit 23 is the damage information generation unit 21. From the damage information of the generated third coin and the pattern information of the second region generated by the pattern information generation unit 22, an image of a virtual second region in which these damage information and the pattern information are fused is obtained. Generate. As a result, not only the first region (for example, the ring portion) but also the virtual second region (for example, the central portion) having a desired degree of damage composed of the same second material as the material of the third coin. It is possible to generate an image of a typical second region.

In this case, a monetary information synthesizer that generates an image of the entire coin by synthesizing an image of a virtual first region (for example, a ring portion) and an image of a virtual second region (for example, a central portion). The control unit 20 may be provided, or the template generation unit 25 may generate template information from an image generated by the monetary information synthesis unit.

<Procedure for generating monetary information>
Next, the procedure of the processing performed by the monetary information generator 10A will be described with reference to FIGS. 4 and 5.

At the time of machine learning, as shown in FIG. 4, first, the damage information generation unit 21 transfers the first coin from the image of the first coin (input image for style) input to the money information generation device 10A. Damage information is generated (step S11).

Further, the pattern information generation unit 22 generates pattern information of the second coin from the image of the second coin (conversion source image) input to the money information generation device 10A (step S12).

Steps S11 and S12 may be executed in the order of steps S11 and S12 as shown in FIG. 4, may be executed in the order of steps S12 and S11, or may be executed in parallel.

Next, the virtual currency information generation unit 23 generates an image of a virtual coin in which the damage information and the pattern information are fused from the damage information generated in step S11 and the pattern information generated in step S12. (Step S13).

Next, the learning unit 24 learns each machine learning algorithm related to the damage information generation unit 21, the pattern information generation unit 22, and the virtual currency information generation unit 23. At this time, each machine learning algorithm related to the learning unit 24 itself also learns based on the virtual coin image generated in step S13 and the real coin image (training data) (step S14). ..

By performing the above steps S11 to S14 for a predetermined data set, the process related to machine learning is completed.

After machine learning, as shown in FIG. 5, first, the damage information generation unit 21 transfers the first coin from the image of the first coin (input image for style) input to the money information generation device 10A. Damage information is generated (step S21).

Further, the pattern information generation unit 22 generates pattern information of the second coin from the image of the second coin (conversion source image) input to the money information generation device 10A (step S22).

Steps S21 and S22 may be executed in the order of steps S21 and S22 as shown in FIG. 5, may be executed in the order of steps S22 and S21, or may be executed in parallel.

Next, the virtual currency information generation unit 23 generates an image of a virtual coin in which the damage information and the pattern information are fused from the damage information generated in step S21 and the pattern information generated in step S22. (Step S23).

By performing the above steps S21 to S23 for a predetermined sample, images of a plurality of virtual coins having the same pattern as the second coin while having different damage degrees are generated.

Then, the template generation unit 25 generates template information from the generated images of the plurality of virtual coins (step S24), and ends the process.

<Overall configuration of a money processing system or money processing device including a money information generator>
Next, the overall configuration of the money processing system and the money processing device including the money information generating device according to the first embodiment will be described with reference to FIGS. 6 to 8. As shown in FIG. 6, the money processing system 200 according to the present embodiment is constructed for, for example, a business store of a financial institution such as a bank, and has a money information generation device 10A and a money information generation device 10A. It is provided with a money processing device 100 that is communicatively connected to the money processing device 100.

The money processing device 100 is, for example, a cashier that executes various processes including a deposit process and a withdrawal process. The money processing device 100 includes a storage unit 110 composed of a storage device such as a hard disk device and a non-volatile memory. The storage unit 110 stores the template information 111 generated by the money information generation device 10A, and the money processing device 100, particularly the built-in money identification device (not shown), stores the template information stored in the storage unit 110. The 111 can be used to identify the currency to be processed, particularly preferably to perform a positive / loss identification process.

As shown in FIG. 7, the money processing system 200 makes the money information generation device 10A into a cloud, and even if a plurality of money processing devices 100 in the market are communicably connected to the money information generation device 10A on the cloud. good. In this case, for example, the money information (money image) acquired by the money processing device 100 from one or more money processing devices 100 is transmitted to the money information generating device 10A on the cloud, and is sent to the money information generating device 10A on the cloud. Using the money information, machine learning and template generation are performed as described above, the created template information is transmitted to one or more money processing devices 100, and the template information transmitted by the money processing device 100 is used. The money may be identified. At this time, the template information created in the cloud may be used by the money processing device 100 that provided the money information (image of money) used for creating the template information, or may be used by a money processing device 100 other than the money processing device 100. It may also be shared with the money processing device 100.

As shown in FIG. 8, the above-mentioned money processing device 100 may include a money information generating device 10A. Also in this case, it is possible to perform the identification process of the currency to be processed, particularly preferably the positive / loss identification process, by using the template information 111 stored in the storage unit 110 of the currency processing device 100 (money identification device). ..

(Embodiment 2)
In the present embodiment, when the second coin (particularly its surface) has a plurality of regions each composed of a plurality of materials, the method of generating the virtual first and second regions is different. Since it is substantially the same as the first embodiment, the description of the overlapping contents will be omitted.

That is, in the present embodiment, the second coin (for example, a new 500-yen coin), particularly the surface thereof, is made of the same first material as the material (for example, nickel brass) of the first coin (for example, the current 500-yen coin). It is composed of the first region (for example, the ring part) and the second material which is different from the material of the first coin and is the same as the material (for example, white copper) of the third coin (for example, the old 500-yen coin). It is mainly assumed that the coin has a second region (for example, a central portion).

In this case, as described in the first embodiment, it is possible to create virtual images using the images of the first and third coins for each of the first and second regions, but those Since the first and second regions are formed of different materials, it is unclear whether these regions change with time in the same way. For example, it is unclear how the second region is soiled with respect to how the first region is soiled, or vice versa. Therefore, it is difficult to generate a virtual image considering the difference in the change of damage due to the change with time.

Therefore, in the present embodiment, a fourth coin including a third region (for example, a ring portion) made of the first material and a fourth region (for example, a central portion) made of the second material. Prepare multiple coins (for example, commemorative coins). That is, the third region of the fourth coin is composed of the same material as the first coin and the first region of the second coin, and the fourth region of the fourth coin is the third coin. , And the same material as the second area of the second coin. Then, from the images of those fourth coins, the feature amount in the third region and the feature amount in the fourth region are calculated respectively, and the correspondence relationship of the calculated feature amount (for example, the relationship of the calculated feature amount is shown. A relational expression) is created, and an image of a virtual second coin is generated based on this correspondence. This correspondence reflects the change in damage due to aging when the third region, that is, the material of the first coin, and the fourth region, that is, the material of the third coin, are present in the same coin. It becomes. Therefore, it is possible to generate a virtual image that reflects the difference in the change in damage due to the change over time. The degree of damage of the plurality of fourth coins is preferably different from each other, and this embodiment is particularly suitable when a large amount of the fourth coins cannot be obtained. The first embodiment is suitable when the fourth coin cannot be obtained. Hereinafter, the present embodiment will be described in more detail.

<Configuration of monetary information generator>
First, the configuration of the monetary information generation device 10B according to the present embodiment will be described with reference to FIG. Since the configuration at the time of machine learning is the same as that of the first embodiment, the description thereof will be omitted. As shown in FIG. 9, after machine learning, the control unit 20 of the money information generation device 10B adds the functions of the damage information generation unit 21, the pattern information generation unit 22, the virtual money information generation unit 23, and the template generation unit 25. , The feature amount calculation unit 26, the combination determination unit 27, and the monetary information synthesis unit 28. Further, the storage unit of the money information generator 10B (shown with a reference numeral 30 in FIG. 9) is created from the feature amount of the third region and the feature amount of the fourth region of the plurality of fourth coins. The corresponding correspondence 31, for example, the relational expression is stored. As the relational expression, for example, a subspace can be used.

In the present embodiment, the damage information generation unit 21 has a plurality of damages related to the first coin from images of a plurality of first coins (for example, the current 500-yen coin) having the same material and different degrees of damage. Generate information. Further, the damage information generation unit 21 generates a plurality of damage information related to the third coin from images of a plurality of third coins (for example, old 500-yen coins) having the same material and different damage degrees. .. The third coin is a coin whose material is different from that of the first coin. The types (denominations) of the plurality of first coins may be the same or different from each other. Similarly, the types (denominations) of the plurality of third coins may be the same or different from each other.

Similar to the first embodiment, the pattern information generation unit 22 generates pattern information of the second coin from the image of the second coin (for example, a new 500-yen coin).

The virtual currency information generation unit 23 is a plurality of first virtual coins in which each of the plurality of damage information related to the first coin and the pattern information are fused from the plurality of damage information and pattern information related to the first coin. Generate an image of the coin (either the entire coin or only the region corresponding to the first region). As a result, images of a plurality of coins (however, non-existent virtual ones) having the same degree of damage as each of the plurality of first coins and having the pattern of the second coin are generated. Further, the virtual currency information generation unit 23 has a plurality of second virtuals in which each of the plurality of damage information related to the third coin and the pattern information are fused from the plurality of damage information and pattern information related to the third coin. Generates an image of a coin (either the entire coin or only the region corresponding to the second region). As a result, images of a plurality of coins (however, non-existent virtual ones) having the same degree of damage as each of the plurality of third coins and having the pattern of the second coin are generated.

The feature amount calculation unit 26 obtains the first feature amount of the region corresponding to the first region (for example, the ring portion) from the images of the plurality of first virtual coins generated by the virtual money information generation unit 23, respectively. calculate. Further, the feature amount calculation unit 26 is a second feature amount of a region corresponding to a second region (for example, a central portion) from an image of a plurality of second virtual coins generated by the virtual money information generation unit 23. Are calculated respectively.

Here, the above-mentioned feature amounts (the first and second feature amounts, the feature amount in the third region, and the feature amount in the fourth region) are not particularly limited, but are, for example, the average of the brightness (pixel value). Values can be used. Alternatively, the dispersion value of the brightness (pixel value), the average value of the edge strength, the dispersion value, and the like may be used.

The combination determination unit 27 has a plurality of first feature quantities related to the first virtual coin and a plurality of second features related to the second virtual coin based on the correspondence relationship 31 (for example, a relational expression). The optimum combination of the first feature amount and the second feature amount is determined from the feature amount. For example, the combination with the smallest distance from the relational expression (subspace) is determined.

The monetary information synthesis unit 28 is an image of the first virtual coin and a second virtual coin corresponding to the optimum first feature amount and the second feature amount determined by the combination determination unit 27, respectively. From the image, an image of the first virtual coin in the region corresponding to the first region (for example, an image of the ring portion) and an image of the second virtual coin in the region corresponding to the second region (for example, an image of the ring portion). The image of the central part) is combined to generate an image of a third virtual coin including both images. The monetary information synthesis unit 28 generates an image of a third virtual coin from an image of the first virtual coin and an image of the second virtual coin for each combination determined by the combination determination unit 27. do.

Then, the template generation unit 25 generates template information from the images of the plurality of third virtual coins generated by the money information synthesis unit 28.

Here, an example of a more specific process in the present embodiment will be described with reference to FIG. In this example, as shown in FIG. 10, first, as a fourth coin, images of a plurality of commemorative coins having different damage degrees are prepared. These commemorative coins are bicolor coins that have a ring part made of the same material as the current 500 yen coin and a central part made of the same material as the old 500 yen coin, but the denomination and pattern of each commemorative coin are particularly different. It is not limited, and may be the same or different from each other. Then, one side of the commemorative coin is separated into four regions (white regions in the figure) consisting of an engraved portion and a base portion, and a central portion (inside) and a ring portion (outside). Create a four-dimensional subspace with the average value of the brightness (pixel value) of the area as a feature (learning with commemorative coins).

Next, a plurality of current 500-yen coin style images having different damage conditions and a plurality of old 500-yen coin style images having different damage conditions are prepared, and the damage information generation unit 21 prepares the current style images. Generates a plurality of damage information related to a 500-yen coin and a plurality of damage information related to an old 500-yen coin.

Further, a conversion source image of the new 500-yen coin is prepared, and the pattern information generation unit 22 generates pattern information of the new 500-yen coin.

Then, depending on the virtual coin information generation unit 23, an image of a plurality of first virtual coins having the same degree of damage as each of the plurality of current 500-yen coins and having a pattern of a new 500-yen coin ( An image of a plurality of second virtual coins (first output image) is generated, and the damage is similar to that of each of the plurality of old 500-yen coins, and the pattern of the new 500-yen coin is used. 2 output image) is generated.

Subsequently, the feature amount calculation unit 26 calculates the average value of the brightness (pixel value) of the engraved portion and the base portion of the ring portion of the image of the plurality of first virtual coins, and also calculates the average value of the brightness (pixel value) of the plurality of second virtual coins. The average value of the brightness (pixel value) of the engraved portion and the base portion of the central portion of the virtual coin image is calculated.

Subsequently, the combination determination unit 27 determines the optimum combination of the image of the first virtual coin having the average value of the optimum brightness and the image of the second virtual coin based on the correspondence 31. do. Specifically, the distance of the average value of brightness from the four-dimensional subspace is the smallest between the images of the plurality of first virtual coins and the images of the plurality of second virtual coins. Find the optimal combination. As a result, the image of the first virtual coin and the image of the second virtual coin are associated with each other in a one-to-one relationship.

Then, the monetary information synthesis unit 28 synthesizes the image of the ring portion of the first virtual coin and the image of the central portion of the second virtual coin of each combination, and the image of the third virtual coin. To generate.

<Procedure for generating monetary information>
Next, the procedure of the processing performed by the monetary information generator 10B will be described with reference to FIG. Since the processing at the time of machine learning is the same as that of the first embodiment, the description thereof will be omitted.

After machine learning, in the present embodiment, as shown in FIG. 11, first, the damage information generation unit 21 starts from images of a plurality of first coins (style input images) input to the money information generation device 10B. , A plurality of damage information of the first coin is generated, and a plurality of damages of the third coin are generated from the images of the plurality of third coins (input images for style) input to the money information generator 10B. Information is generated (step S31).

Further, the pattern information generation unit 22 generates pattern information of the second coin from the image of the second coin (conversion source image) input to the money information generation device 10B (step S32).

Steps S31 and S32 may be executed in the order of steps S31 and S32 as shown in FIG. 11, may be executed in the order of steps S32 and S31, or may be executed in parallel.

Next, the virtual currency information generation unit 23 fused the damage information and the pattern information from the plurality of damage information related to the first coin generated in step S31 and the pattern information generated in step S32. While generating images of a plurality of first virtual coins, the damage information and the damage information from the plurality of damage information related to the third coin generated in step S31 and the pattern information generated in step S32 are used. An image of a plurality of second virtual coins in which pattern information is fused is generated (step S33).

Next, the feature amount calculation unit 26 calculates the first feature amount of the region corresponding to the first region (for example, the ring portion) from the images of the plurality of first virtual coins generated in step S33. At the same time, the second feature amount of the region corresponding to the second region (for example, the central portion) is calculated from the images of the plurality of second virtual coins generated in step S33 (step S34).

Next, the combination determination unit 27 determines the optimum combination of the first feature amount and the second feature amount based on the correspondence 31 (step S35).

Next, the monetary information synthesis unit 28 displays an image of the first virtual coin and a second virtual coin corresponding to the optimum first feature amount and the second feature amount determined in step S35, respectively. From the image of, the image of the first virtual coin in the region corresponding to the first region and the image of the second virtual coin in the region corresponding to the second region are combined to form a third image. An image of a virtual coin is generated (step S36). This step S36 is executed for each combination determined in step S35.

Next, the template generation unit 25 generates template information from the images of the plurality of third virtual coins generated in step S36 (step S37), and ends the process.

In this embodiment, the image of the third virtual coin may be generated by the following processing.

In this case, first, as in the case shown in FIG. 9, a four-dimensional subspace as the correspondence relationship 31 is created (learning with a commemorative coin), a plurality of damage information related to the current 500-yen coin, and the old 500-yen coin. Generate multiple damage information related to coins. In addition, the pattern information generation unit 22 generates pattern information for a new 500-yen coin.

Subsequently, the feature amount calculation unit 26 calculates the average value of the brightness (pixel value) of the engraved portion and the base portion of the ring portion of the image of the plurality of current 500-yen coins, and also calculates the average value of the brightness (pixel value) of the plurality of old 500-yen coins. The average value of the brightness (pixel value) of the engraved portion and the base portion of the central portion of the image is calculated.

Next, the combination determination unit 27 determines the distance of the average value of the brightness from the correspondence 31 (four-dimensional subspace) between the images of the plurality of current 500-yen coins and the images of the plurality of old 500-yen coins. Find the combination that minimizes.

Then, depending on the virtual currency information generation unit 23, the current 500-yen coin damage information, the old 500-yen coin damage information, and the new 500-yen coin pattern information regarding the optimum combination are used to obtain the current ring unit. An image (output image) of a virtual coin with a pattern of a new 500-yen coin, which is as damaged as a 500-yen coin, while the central part is as damaged as an old 500-yen coin. Generate.

As described above, in the above embodiment, the damage information of the first coin is generated from the image of the first coin, and the pattern information of the second coin is generated from the image of the second coin. From these damage information and pattern information, an image of a virtual coin in which these damage information and pattern information are fused is generated. Therefore, based on the images of the first and second coins which are real coins, the first It is possible to generate an image of a virtual coin having the same degree of damage as the first coin and having the pattern of the second coin. Therefore, even in a situation where the actual second coin with the desired degree of damage is not available, it is possible to generate an image of the corresponding virtual coin.

When the second coin has a plurality of regions each made of a plurality of materials, the following method may be used instead of the method described in the above embodiment. That is, a plurality of fourth coins (for example, commemorative coins) made of the same material as the second coin are used as an image of the first coin (input image for style), and the degree of damage is the same as that of each fourth coin. , And an image of a virtual coin having a pattern of a second coin (for example, a new 500-yen coin) may be directly generated. This method is particularly suitable when a large number of fourth coins are available.

Further, in the above embodiment, the case where the damage information of the first coin is generated from the image of the first coin (input image for style) has been described, but from the image of the first coin (input image for style). , The counterfeit information which is the information regarding the counterfeiting of the first coin may be generated and used. In the above embodiment, when the actual money of the recast money is not available, the case of generating the virtual money information of the money corresponding to the money is described. When the real thing is not available, it may generate monetary information of virtual money corresponding to the counterfeit money.

Specifically, for example, as shown in FIGS. 12 and 13, during machine learning and after machine learning, the control unit 20 of the monetary information generation device 10C replaces the damage information generation unit 21 with the counterfeit information generation unit 29. It has a function.

The counterfeit information generation unit 29 generates (extracts) counterfeit information, which is information related to counterfeiting of the first currency, specifically, for example, a feature amount related to counterfeiting from the image of the first currency (input image for style). do.

In this case, the style input image (image of the first currency) is an image of the first currency having some forgery characteristics, and may have an arbitrary pattern (pattern, engraving). The conversion source image (image of the second currency) is an image of the second currency that wants to give the forgery feature of the style input image, and does not have the forgery feature.

Then, the virtual currency information generation unit 23 fuses (synthesizes) the counterfeit information and the pattern information generated by the counterfeit information generation unit 29 and the pattern information generated by the pattern information generation unit 22. T) Generate a virtual currency image (image information). As a result, it is possible to generate an image of money (however, a virtual one that does not exist) having the same forgery characteristics as the first money and the pattern of the second money.

The counterfeit information generation unit 29 is also constructed from the trained model, preferably by the trained model using CNN. The CNN of the virtual currency information generation unit 23 is combined with the CNN of the counterfeit information generation unit 29 and each CNN of the pattern information generation unit 22.

The learning unit 24 has a machine learning algorithm and pattern information related to the generation of counterfeit information by the counterfeit information generation unit 29 so that the image of the virtual money generated by the virtual currency information generation unit 23 looks like an existing counterfeit money. The machine learning algorithm related to the generation of pattern information by the generation unit 22 and the machine learning algorithm related to the generation of virtual money money information by the virtual money information generation unit 23 are machine-learned. As a result of this learning, trained models of the counterfeit information generation unit 29, the pattern information generation unit 22, and the virtual currency information generation unit 23 are created, respectively. It is preferable that each machine learning algorithm utilizes CNN as in the trained model described above.

The learning unit 24 includes a machine learning algorithm (preferably one using CNN), and is an image of virtual money (output image) generated by the virtual money information generation unit 23 and an image of existing counterfeit money. Machine learning is performed based on (training data). That is, using the virtual coin image and the real coin image, it is more accurate to determine whether the virtual coin image generated by the virtual money information generation unit 23 is virtual or real. Learn so that you can distinguish between. Then, the learning unit 24 relates to the learning unit 24, the counterfeit information generation unit 29, the pattern information generation unit 22, and the virtual currency information generation unit 23, using the error between the output by the learning unit 24 and the desired output (correct answer) as a teacher signal. By giving it to the machine learning algorithm, the coupling coefficient of each CNN is gradually changed so that the correct output is finally obtained.

The template generation unit 25 is the same as the second coin, although the feature quantities related to counterfeiting generated by using the machine-learned counterfeit information generation unit 29, the pattern information generation unit 22, and the virtual currency information generation unit 23 are different from each other. Generate template information from multiple virtual coin images with patterns.

In the money processing system or the money processing device (both not shown) including the money information generating device 10C, the money processing device, particularly the built-in money identification device, is similar to the money processing system 200 or the money processing device 100 of the first embodiment. However, using the template information stored in the storage unit, it is possible to perform the processing of identifying the money to be processed, particularly preferably the processing of authenticity identification.

Further, in the above-described embodiment and modified embodiment, the case where each trained model and each machine learning algorithm uses CNN has been described, but each trained model and each machine learning algorithm is machine learning (preferably deep layer). It is not particularly limited as long as it is used for learning), and a deep neural network (DNN) other than CNN or ResNet (Deep Residual Network) may be used.

Further, in the above-described embodiment and the modified form, the case where each monetary information generator is configured as one device has been described, but each function of the monetary information generator is realized by a distributed processing system appropriately distributed to a plurality of devices. May be good. For example, at the time of machine learning, the functions of the damage information generation unit 21, the pattern information generation unit 22, and the virtual currency information generation unit 23 and the functions of the learning unit 24 may be distributed to different devices. Further, after machine learning, the functions of the pattern information generation unit 22 and the virtual currency information generation unit 23 and the functions of the template generation unit 25 may be distributed to different devices.

Although the embodiments of the present invention have been described above with reference to the drawings, the present invention is not limited to the above embodiments. Further, the configurations of the respective embodiments may be appropriately combined or modified as long as they do not deviate from the gist of the present invention.

As described above, the present invention is a technique useful for generating virtual coin information of money corresponding to the money even when the actual money having a desired degree of damage is not available.

10A, 10B, 10C: Money information generation device 20: Control unit 21: Damage information generation unit 22: Pattern information generation unit 23: Money information generation unit 24: Learning unit 25: Template generation unit 26: Feature amount calculation unit 27: Combination Decision unit 28: Money information synthesis unit 29: Counterfeit information generation unit 30, 110: Storage unit 31: Correspondence relationship 100: Money processing device 111: Template information 200: Money processing system

Claims (24)

From the monetary information of the first currency, damage information which is information on the damage of the first currency is generated.
From the monetary information of the second currency, pattern information which is information about the pattern of the second currency is generated.
A monetary information generation device including a control unit that generates virtual monetary information in which the damage information and the pattern information are fused from the damage information and the pattern information. The control unit has a machine learning algorithm related to the generation of the damage information, a machine learning algorithm related to the generation of the pattern information, and the virtual money so that the monetary information of the virtual money becomes genuine. The monetary information generation device according to claim 1, wherein the machine learning algorithm related to the generation of monetary information is machine-learned. The first currency is a loss currency,
The monetary information generation device according to claim 1 or 2, wherein the second currency is a new currency. The first currency is a new currency,
The monetary information generation device according to claim 1 or 2, wherein the second currency is a loss currency. The monetary information generator according to any one of claims 1 to 4, wherein the first monetary type is different from the second monetary type. The money information generator according to any one of claims 1 to 5, wherein the material of the first money is the same as the material of the second money. The second currency has a first region made of the same first material as the material of the first coin, and a second region made of the second material.
The control unit generates pattern information, which is information about the pattern of the first region, from the monetary information of the first region.
A claim characterized by generating virtual monetary information of a first region in which the damage information and the pattern information of the first region are fused from the damage information and the pattern information of the first region. Item 4. The monetary information generator according to any one of Items 1 to 5. The second material is different from the material of the first currency and is the same material as the material of the other third currency.
The control unit generates damage information, which is information on damage to the third currency, from the currency information of the third currency.
Pattern information, which is information about the pattern of the second region, is generated from the monetary information of the second region.
A virtual second region in which the damage information of the third currency and the pattern information of the second region are fused from the damage information of the third currency and the pattern information of the second region. The monetary information generation device according to claim 7, wherein the monetary information of the above is generated. The second currency has a first region made of the same first material as the material of the first currency, and a material of another third currency that is different from the material of the first currency and is different from the material of the first currency. It has a second region made of the same second material and has
Features of the third region generated from monetary information of a fourth currency including a third region composed of the first material and a fourth region composed of the second material. A storage unit that stores the correspondence between the amount and the feature amount in the fourth region is further provided.
The monetary information generation device according to any one of claims 1 to 5, wherein the control unit generates monetary information of the virtual monetary based on the correspondence. The control unit generates a plurality of damage information related to the first currency from the currency information of the plurality of first coins of the same material and different degrees of damage.
A plurality of damage information related to the third currency is generated from the currency information of a plurality of third coins having the same material but different degrees of damage.
From the plurality of damage information relating to the first currency and the pattern information, the currency information of the plurality of first virtual currency in which each of the plurality of damage information relating to the first currency and the pattern information are fused. To generate
From the plurality of damage information relating to the third currency and the pattern information, the currency information of the plurality of second virtual currency in which each of the plurality of damage information relating to the third currency and the pattern information are fused. To generate
The first feature amount of the region corresponding to the first region is calculated from the monetary information of the plurality of first virtual coins, respectively.
The second feature amount of the region corresponding to the second region is calculated from the monetary information of the plurality of second virtual coins, respectively.
Based on the correspondence, the optimum combination of the first feature amount and the second feature amount is determined from the plurality of the first feature amounts and the plurality of the second feature amounts.
Corresponding to the first region from the optimal monetary information of the first virtual currency and the monetary information of the second virtual currency corresponding to the first feature amount and the second feature amount, respectively. Generates monetary information of a third virtual monetary including the monetary information of the first virtual monetary of the region and the monetary information of the second virtual monetary of the region corresponding to the second region. 9. The monetary information generator according to claim 9. The monetary information generator according to any one of claims 1 to 10, wherein the damage information is information on damage to the base of the first currency. The type of the first currency is the same as the type of the second currency.
The control unit generates damage information, which is information on damage to the first surface, from the monetary information on the first surface of the first currency.
Pattern information, which is information about the pattern of the second surface, is generated from the monetary information of the second surface different from the first surface of the second currency.
A virtual second surface in which the damage information of the first surface and the pattern information of the second surface are fused from the damage information of the first surface and the pattern information of the second surface. The monetary information generator according to any one of claims 1 to 11, wherein the monetary information is generated. The monetary information generator according to any one of claims 1 to 12, wherein the monetary information is image information. The monetary information generator according to any one of claims 1 to 13.
A money processing device having a storage unit that stores template information based on the money information of the virtual money, and a money processing device.
A money processing system characterized by being equipped with. The monetary information generator according to any one of claims 1 to 13.
A storage unit that stores template information based on the monetary information of the virtual money, and a storage unit.
A money processing device characterized by being equipped with. A damage information generation unit that generates damage information, which is information on damage to the first currency, from the currency information of the first currency.
A pattern information generation unit that generates pattern information that is information about the pattern of the second currency from the currency information of the second currency, and
A virtual monetary information generation unit that generates virtual monetary information in which the damage information and the pattern information are fused from the damage information and the pattern information.
A monetary information generation system characterized by being equipped with. From the monetary information of the first currency, a step of generating damage information which is information on the damage of the first currency, and
A step of generating pattern information, which is information about the pattern of the second currency, from the currency information of the second currency, and
A step of generating virtual monetary information in which the damage information and the pattern information are fused from the damage information and the pattern information, and
A method for generating monetary information, which comprises. Computer,
A means for generating damage information, which is information on damage to the first currency, from the currency information of the first currency.
A means for generating pattern information which is information about the pattern of the second currency from the monetary information of the second currency, and a virtual fusion of the damage information and the pattern information from the damage information and the pattern information. A means of generating monetary information on money,
A monetary information generation program characterized by functioning as. From the monetary information of the first currency, forgery information, which is information on the counterfeiting of the first currency, is generated.
From the monetary information of the second currency, pattern information which is information about the pattern of the second currency is generated.
A monetary information generation device including a control unit that generates virtual monetary information in which the counterfeit information and the pattern information are fused from the counterfeit information and the pattern information. The monetary information generator according to claim 19 and
A money processing device having a storage unit that stores template information based on the money information of the virtual money, and a money processing device.
A money processing system characterized by being equipped with. The monetary information generator according to claim 19 and
A storage unit that stores template information based on the monetary information of the virtual money, and a storage unit.
A money processing device characterized by being equipped with. A counterfeit information generation unit that generates counterfeit information, which is information related to counterfeiting of the first currency, from the monetary information of the first currency.
A pattern information generation unit that generates pattern information that is information about the pattern of the second currency from the currency information of the second currency, and
A virtual currency information generation unit that generates virtual currency information in which the counterfeit information and the pattern information are fused from the counterfeit information and the pattern information.
A monetary information generation system characterized by being equipped with. A step of generating counterfeit information, which is information on counterfeiting of the first currency, from the monetary information of the first currency, and
A step of generating pattern information, which is information about the pattern of the second currency, from the currency information of the second currency, and
A step of generating virtual monetary information in which the counterfeit information and the pattern information are fused from the counterfeit information and the pattern information, and
A method for generating monetary information, which comprises. Computer,
A means for generating counterfeit information, which is information on counterfeiting of the first currency, from the currency information of the first currency.
A means for generating pattern information which is information about the pattern of the second currency from the monetary information of the second currency, and a virtual fusion of the counterfeit information and the pattern information from the counterfeit information and the pattern information. A means of generating monetary information on money,
A monetary information generation program characterized by functioning as.

Images