JP2021135654A - Information processing program, information processor, and information processing method - Google Patents

Abstract

To reduce the probability of erroneous identification of a non-counterfeit QR code as counterfeit in determining a QR code that transitions stochastically.SOLUTION: An information processor 1 determines whether any stain is found on an image of a QR code to be processed, and when any stain is found in the image of the QR code, determines whether QR code transitions stochastically based on the positional relation between the stained area and the area of error bits included in the QR code.SELECTED DRAWING: Figure 1

Description

The present invention relates to an information processing program.

In recent years, a method for counterfeiting a QR code (registered trademark) has been devised, and detection of counterfeiting has become a common issue in the QR code industry. Regarding the QR code forgery method, a probabilistic QR code forgery technique was devised in June 2018 (see, for example, Non-Patent Document 1). The QR code referred to here refers to a coding method in which digital data is represented by a black-and-white dot pattern arranged vertically and horizontally on a plane. FIG. 6 is a diagram showing a reference example of a counterfeit QR code. As shown in FIG. 6, by embedding a dot at a predetermined position of a normal QR code, normal decoded data has a certain probability of being converted into a malicious website URL (Uniform Resource Locator) as abnormal decoded data. It is decrypted. As a result, cyber attacks are possible.

The QR code utilizes an error correction coding technique called a Reed Solomon (RS) code. The error correction coding technique can correct an error even if the read data has an error of several bits, and can decode it normally. The number of bits that can correct an error has a limit value called an error correction capability. The decoding process can decode the read data into normal data as long as the number of noises is within the error correction capability. For example, normal decryption data indicates the URL of "http://www.aaaaaaa.com/".

On the other hand, in the decoding process, if the number of noises in the read data exceeds the error correction capability, a read error occurs. Here, a special type of noise that cannot be read or can be read during the decoding process has been reported. In the decoding process, when a QR code containing a special type of noise is read, normal decoding data and abnormal decoding data are stochastically generated according to the reading result. A QR code that includes such a special format is called a QR code that transitions stochastically. A malicious person will notice forgery every time he / she decodes the data into abnormal data, and therefore forges such a QR code that stochastically transitions between the normal decoded data and the abnormal decoded data. For example, if noise is embedded in a special format such as decoding to the URL of "http://www.aabaaaa.com/" as abnormal decryption data, the decoding process will be performed if the number of noises is within the error correction capability. It may be done and, as a result, decrypted into unhealthy data.

A forgery determination method is known in which the number of error correction bits at the time of decoding is counted for such QR code forgery, and when the number is equal to or greater than a threshold value, the QR code is determined to be a forgery code. The threshold value indicates, for example, a value of error correction capability × 0.8.

Okuma, Takida, Morii, "Existence of QR Code that Guides to Malignant Sites and Counterfeit Attacks Using It", Shingaku Giho, vol. 118, no.109, ICSS2018-6, pp.33-38, June 2018

However, in determining a QR code that transitions stochastically, there is a problem that a QR code that has not been forged is erroneously determined to be a QR code that transitions stochastically. For example, when the error correction capability is 5, the threshold value for determining forgery is the error correction capability × 0.8. That is, it is assumed that the threshold value is 4. Then, in the conventional determination process, when the number of error correction bits is 4, it is determined to be counterfeit. However, when the QR code is soiled or torn, the number of error correction bits becomes 4 or more, and the QR code may be erroneously determined to be counterfeit even though it is not counterfeit.

One aspect of the present invention is to reduce the probability that a non-counterfeit QR code is erroneously determined to be counterfeit in determining a QR code that transitions stochastically.

In the first plan, the information processing program performs the first determination process of determining whether or not the image of the QR code to be processed has stains, and when the image of the QR code has stains. , It is determined whether or not the QR code is a QR code that transitions probabilistically based on the positional relationship between the area where the QR code is contaminated and the area of the error bit included in the QR code. The second determination process to be performed is executed by the computer.

According to one embodiment, in determining a QR code that transitions stochastically, it is possible to reduce the probability that a non-counterfeit QR code is erroneously determined as counterfeit.

FIG. 1 is a diagram showing a functional configuration of an information processing device according to an embodiment. FIG. 2 is a diagram showing an example of an exception to counterfeiting. FIG. 3 is a diagram showing an example of a code word of a 2-M type QR code. FIG. 4 is a diagram showing an example of a flowchart of determination according to an embodiment. FIG. 5 is a diagram showing an example of a computer that executes an information processing program. FIG. 6 is a diagram showing a reference example of a counterfeit QR code. FIG. 7 is a diagram showing a reference example of erroneously determining forgery.

Hereinafter, examples of the information processing program, the information processing apparatus, and the information processing method disclosed in the present application will be described in detail with reference to the drawings. The present invention is not limited to the examples.

First, a reference example for erroneously determining forgery will be described with reference to FIG. 7. FIG. 7 is a diagram showing a reference example of erroneously determining forgery. It is assumed that the error correction capability is 5. It is assumed that the threshold value for determining forgery is 5 × 0.8 (= 4). FIG. 7 It is assumed that the number of error correction bits of the QR code as shown in the upper figure is 4. Then, in the decoding process, since the number of error correction bits is equal to or greater than the threshold value, it is determined to be counterfeit. Further, it is assumed that the number of error correction bits of the dirty QR code as shown in the lower figure of FIG. 7 is 4. Then, in the decoding process, since the number of error correction bits is equal to or greater than the threshold value, it is erroneously determined as counterfeit even if it is not counterfeit. This is because, for example, the error bits generated when reading the QR code are also counted. In addition, although the QR code in the lower figure of FIG. 7 is dirty, it may be dirty such as torn.

Therefore, in the following examples, an information processing device that reduces the probability that a non-counterfeit QR code is erroneously determined to be counterfeit in determining a QR code that transitions stochastically will be described.

FIG. 1 is a diagram showing a functional configuration of an information processing device according to an embodiment. The information processing device 1 shown in FIG. 1 is not forged as an exception of the QR code that transitions stochastically when stains are detected in the image of the QR code when the QR code that transitions stochastically is determined. Is determined.

As shown in FIG. 1, the information processing device 1 has a control unit 10 and a storage unit 20.

The control unit 10 corresponds to an electronic circuit such as a CPU (Central Processing Unit). Then, the control unit 10 has an internal memory for storing programs and control data that define various processing procedures, and executes various processes by these. The control unit 10 includes a reading unit 11, an error detection unit 12, a stain determination unit 13, a forgery determination unit 14, an error correction unit 15, and a decoding result output unit 16. The stain determination unit 13 is an example of the first determination processing unit. The counterfeit determination unit 14 is an example of a second determination processing unit.

The storage unit 20 is, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory (Flash Memory), or a storage device such as a hard disk or an optical disk. The storage unit 20 has a threshold value of 21. The threshold value 21 indicates a constant value used for determining forgery. An example of the threshold value 21 is an error correction capability × 0.8. The threshold value 21 may be an error correction capability × 0.9, an error correction capability × 0.7, or can be changed.

The reading unit 11 reads the QR code using the decoder. The decoder may be a dedicated application for recognizing a QR code, or may have a reading function using hardware such as a camera.

The error detection unit 12 detects an error by using the RS code from the image of the QR code read by the reading unit 11. For example, the error detection unit 12 reads format information from the image of the QR code read by the reading unit 11. The error correction level is stored in the format information. The error detection unit 12 releases the mask processing from the image of the QR code. The error detection unit 12 reads the symbol from the image of the QR code that has been unmasked. The error detection unit 12 decodes the QR code data (information code, filling code) and the correction code (error correction block) from the symbol. Then, the error detection unit 12 detects an error in the data from the decrypted correction code.

The stain determination unit 13 determines whether or not the image of the QR code read by the reading unit 11 has stains when determining the QR code that transitions stochastically.

As an example, the stain determination unit 13 predicts whether or not the QR code image read by the reading unit 11 has stains by using machine learning. That is, the stain determination unit 13 inputs the image of the QR code into the learning device that has learned the stain in advance, and predicts whether or not the stain exists. The learner uses these teacher data as negative teacher data for a QR code that has stains such as stains and tears on the QR code and positive teacher data for a QR code that does not have stains, and stains the QR code. You just have to learn if it exists. As a result, the stain determination unit 13 can accurately predict the presence of stains on the image of the QR code by using the learning device.

As another example, the stain determination unit 13 predicts whether or not the QR code image read by the reading unit 11 has stains by using pattern recognition. That is, the stain determination unit 13 collates the QR code image with the QR code image in which the stain is present, and predicts whether or not the stain is present based on the degree of similarity. As a result, the stain determination unit 13 can accurately predict the presence of stains on the image of the QR code by using pattern recognition.

Although it has been explained that the stain determination unit 13 determines whether or not there is stain by taking machine learning or pattern recognition as an example, the method is not limited to these methods.

If the image of the QR code has stains, the counterfeit determination unit 14 determines whether or not the QR code is a QR code that makes a stochastic transition based on the positional relationship between the stain area and the error portion included in the QR code. Is determined.

For example, the forgery determination unit 14 determines that the QR code does not transition stochastically when the area of the error bit matches the contaminated area. That is, when the image of the QR code is stained, the counterfeit determination unit 14 increases the number of error bits and embeds noise equal to or greater than the error correction capability in the QR code, so that the QR code transitions stochastically. It is determined that it is not a QR code.

Then, the counterfeit determination unit 14 determines whether or not the image of the QR code is counterfeit when the region of the error bit does not match the soiled region. As an example, the counterfeit determination unit 14 determines whether or not the number of error bits in the image of the QR code exceeds the threshold value 21. When the number of error bits in the image of the QR code exceeds the threshold value 21, the counterfeit determination unit 14 determines that the QR code is a QR code that stochastically transitions to the QR code. When the number of error bits in the image of the QR code is 21 or less, the counterfeit determination unit 14 determines that the QR code is not a QR code that stochastically transitions.

If it is determined that the error is not counterfeit, the error correction unit 15 corrects the error in the QR code. For example, when the error correction unit 15 determines that the QR code is not a probabilistic transition by the counterfeit determination unit 14, the error correction unit 15 uses the error correction block of the QR code to detect an error detected by the error detection unit 12. correct. That is, the error correction unit 15 corrects the error according to the error correction level (error correction capability) stored in the format information.

The decoding result output unit 16 outputs the decoding result of the QR code when it is determined that the QR code does not transition stochastically.

[Example of counterfeit exception]
FIG. 2 is a diagram showing an example of an exception to counterfeiting. The QR code shown in FIG. 2 has a 2-M type code arrangement.

The left figure of FIG. 2 shows an example in which the QR code is dirty. In the image of the QR code, an error occurs in the block corresponding to the dirt from the upper right to the lower left. The counterfeit determination unit 14 determines that the QR code that only has such stains is not a QR code that transitions stochastically. That is, the error detection unit 12 detects an error from the image of the read QR code by using the RS code. The stain determination unit 13 determines that the image of the read QR code has stains, for example, by using pattern recognition. Since the region of the error bit coincides with the fouled region, the counterfeit determination unit 14 determines that the QR code does not transition stochastically. Further, when the image of the QR code is found to be dirty, the counterfeit determination unit 14 increases the number of error bits, so that the QR code transitions stochastically so as to embed noise exceeding the error correction capability in the QR code. Judge that it is not.

The middle figure of FIG. 2 is an example in which the QR code has stains such as tears. In the image of the QR code, an error occurs in the block corresponding to the stain such as the tear in the lower right. The counterfeit determination unit 14 determines that the QR code that only has such stains such as tears is not a QR code that transitions stochastically. That is, the error detection unit 12 detects an error from the image of the read QR code by using the RS code. The stain determination unit 13 determines that the image of the read QR code has stains, for example, by using pattern recognition. Since the region of the error bit coincides with the fouled region, the counterfeit determination unit 14 determines that the QR code does not transition stochastically. Further, the counterfeit determination unit 14 probabilistically transitions so as to embed noise exceeding the error correction capability in the QR code because the number of error bits becomes large when stains such as tears are detected in the image of the QR code. It is determined that the QR code is not used.

The right figure of FIG. 2 is an example in which the QR code is not contaminated. In the QR code image, there is an error in the "D6" block, but there is no error due to contamination. The stain determination unit 13 determines that there is no stain on the image of the QR code when determining the QR code that transitions stochastically. For a QR code in which such contamination does not exist, the counterfeit determination unit 14 uses the number of error bits of the QR code and the threshold value 21 to determine whether or not the QR code is a QR code that transitions stochastically. do. Then, when it is determined that the error correction unit 15 is not a QR code that transitions probabilistically, the QR code data (emphasized "D6" block) and the QR code error correction block (emphasized "emphasized" ". Use the block of "E") to correct the error of the error bit.

[Example of codeword of 2-M type QR code]
Here, an example of the code word of the 2-M type QR code will be described with reference to FIG. FIG. 3 is a diagram showing an example of a code word of a 2-M type QR code.

As shown in FIG. 3, the code word of the QR code includes an information code, a grass-filling code, and an error correction block. It is assumed that "http://www.aaaaaaa.com/" is embedded as a URL in the QR code. In such a case, the information code converts "http://www.aaaaaaa,com/" into a 1-byte code of Shift JIS, adds a mode indicator and a character number indicator in front of the converted data, and converts. A terminal pattern is added after the resulting data, and the obtained data is divided by 8 bits. The mode indicator is an identifier indicating the type of character data (numerical mode, alphanumeric character mode, 8-bit byte mode, kanji mode) that can be embedded in the QR code. Here, as an example, a bit string indicating an 8-bit byte mode is set in the mode indicator. The character number indicator is a bit string that defines the length of the data character string embedded in the QR code. Here, as an example, a bit string (00010110) indicating 22 characters is set in the character number indicator.

The padding code is a code word in which a temporary code word that does not represent data is embedded until the total amount of data is reached when the total amount of data of the QR code is less than the total amount of data. In addition, 236 (11101100) and 17 (00010001) are repeatedly padded on the grass filling code as a fixed bit pattern. The information code and the grass-filling code are QR code data and are encoded by the RS code. The QR code data is the block indicated by "D" in the QR code code arrangement shown in FIG.

The error correction block is information that can correct and decode an error in the data of the QR code. This error correction block is the block indicated by "E" in the code arrangement of the QR code shown in FIG.

[Forgery judgment flowchart]
Here, an example of the flowchart of the forgery determination according to the embodiment will be described with reference to FIG. FIG. 4 is a diagram showing an example of a flowchart for forgery determination according to an embodiment.

As shown in FIG. 4, the reading unit 11 reads the QR code using the decoder (step S11). Then, the error detection unit 12 detects an error in the data from the image of the read QR code by using the RS code (step S12).

Then, the stain determination unit 13 determines whether or not the image of the read QR code has stains (step S13). As an example, the stain determination unit 13 determines whether or not the scanned QR code image is stained by using machine learning. As another example, the stain determination unit 13 determines whether or not the scanned QR code image is stained by using pattern recognition.

When it is determined that the image of the read QR code is not stained (step S13; No), the forgery determination unit 14 proceeds to step S14 in order to make a forgery determination.

On the other hand, when it is determined that the image of the read QR code has stains (step S13; Yes), the forgery determination unit 14 determines whether or not the stain area and the error portion of the data match. (Step S13A). When it is determined that the soiled area and the error portion of the data do not match (step S13A; No), the forgery determination unit 14 proceeds to step S14 in order to make a forgery determination.

On the other hand, when it is determined that the contaminated area and the error portion of the data match (step S13A; Yes), the forgery determination unit 14 considers it as an exception to the forgery and proceeds to step S15.

In step S14, the counterfeit determination unit 14 determines whether or not the read QR code image is counterfeit (step S14). For example, the counterfeit determination unit 14 determines whether or not the QR code image is counterfeit by determining whether or not the number of error bits of the QR code image exceeds the threshold value 21.

When it is determined that the image of the QR code is forged (step S14; Yes), the forgery determination unit 14 outputs that the QR code is forged (step S17). Then, the forgery determination process ends.

On the other hand, when it is determined that the image of the QR code is not forged (step S14; No), the error correction unit 15 corrects the data error (step S15). Then, the decoding result output unit 16 outputs the error-corrected data (step S16). That is, the decoding result output unit 16 outputs the decoding result of the QR code in which the error has been corrected. Then, the forgery determination process ends.

It was explained that the forgery determination unit 14 determines that the QR code does not transition stochastically when the area of the error bit matches the foul area. However, the match here does not necessarily have to be an exact match. Therefore, the forgery determination unit 14 may be in the case where the region of the error bit includes a fouled region. Further, the forgery determination unit 14 may be in the case where the pattern similarity between the error bit region and the fouled region is equal to or higher than a certain degree.

[Effect of Examples]
According to the above embodiment, the information processing apparatus 1 determines whether or not the image of the QR code to be processed has stains. When the image of the QR code has stains, the information processing device 1 probabilistically transitions the QR code based on the positional relationship between the region where the stains exist and the region of the error bits included in the QR code. It is determined whether or not it is. According to this configuration, the information processing apparatus 1 erroneously determines that the non-counterfeit QR code is counterfeit by using the positional relationship between the fouled region and the error bit region in determining the QR code that transitions probabilistically. It is possible to reduce the probability that it will end up. That is, the information processing device 1 can accurately determine the QR code that transitions stochastically.

Further, according to the above embodiment, the information processing apparatus 1 determines that the QR code does not transition stochastically when the area of the error bit coincides with the contaminated area. According to such a configuration, the information processing apparatus 1 erroneously determines that the non-counterfeit QR code is counterfeit by determining that the QR code that does not transition stochastically is not a QR code that transitions stochastically when the region of the error bit matches the soiled region. It is possible to reduce the probability of doing so.

Further, according to the above embodiment, the information processing apparatus 1 predicts whether or not the image of the QR code has stains by using a learning device that has learned the stains in advance. According to such a configuration, the information processing apparatus 1 can accurately predict the presence of stains on the image of the QR code by using the learning device.

Further, according to the above embodiment, the information processing apparatus 1 uses pattern recognition to predict whether or not the image of the QR code has stains. According to such a configuration, the information processing apparatus 1 can accurately predict the presence or absence of stains on the image of the QR code by using pattern recognition.

[others]
It should be noted that each component of the information processing device 1 shown does not necessarily have to be physically configured as shown in the figure. That is, the specific embodiment of the distribution / integration of the information processing apparatus 1 is not limited to the one shown in the drawing, and all or part of the information processing apparatus 1 may be functionally or physically in an arbitrary unit according to various loads and usage conditions. It can be distributed and integrated. For example, the reading unit 11 and the error detecting unit 12 may be integrated as one unit. Further, the forgery determination unit 14 may be dispersed into a determination unit for determining a forgery exception and a determination unit for determining forgery after excluding the forgery exception. Further, the storage unit 20 may be connected as an external device of the information processing device 1 via a network.

Further, the various processes described in the above embodiment can be realized by executing a program prepared in advance on a computer such as a personal computer or a workstation. Therefore, in the following, an example of a computer that executes an information processing program including information processing that realizes the same functions as the information processing device 1 shown in FIG. 1 will be described. FIG. 5 is a diagram showing an example of a computer that executes an information processing program.

As shown in FIG. 5, the computer 200 includes a CPU 203 that executes various arithmetic processes, an input device 215 that receives data input from a user, and a display control unit 207 that controls the display device 209. Further, the computer 200 has a drive device 213 that reads a program or the like from a storage medium, and a communication control unit 217 that exchanges data with another computer via a network. Further, the computer 200 has a memory 201 for temporarily storing various information and an HDD 205. The memory 201, CPU 203, HDD 205, display control unit 207, drive device 213, input device 215, and communication control unit 217 are connected by a bus 219.

The drive device 213 is, for example, a device for the removable disk 211. The HDD 205 stores the information processing program 205a and the information processing-related information 205b.

The CPU 203 reads the information processing program 205a, expands it in the memory 201, and executes it as a process. Such a process corresponds to each functional unit of the information processing apparatus 1. The information processing-related information 205b corresponds to the threshold value 21 and the like. Then, for example, the removable disk 211 stores each information such as the information processing program 205a.

The information processing program 205a does not necessarily have to be stored in the HDD 205 from the beginning. For example, the program is stored in a "portable physical medium" such as a flexible disk (FD), a CD-ROM, a DVD disk, a magneto-optical disk, or an IC card inserted into the computer 200. Then, the computer 200 may read the information processing program 205a from these and execute it.

1 Information processing device 10 Control unit 11 Reading unit 12 Error detection unit 13 Contamination judgment unit 14 Counterfeit judgment unit 15 Error correction unit 16 Decoding result output unit 20 Storage unit 21 Threshold

Claims (6)

The first determination process for determining whether or not the image of the QR code to be processed has stains, and
When the image of the QR code has stains, the QR code is probable based on the positional relationship between the region where the stains exist in the QR code and the region of the error bit included in the QR code. A second determination process for determining whether or not the QR code is a transitional QR code, and
An information processing program characterized by having a computer execute. The information processing program according to claim 1, wherein the second determination process determines that the QR code does not transition stochastically when the error bit region coincides with the fouling region. The information processing program according to claim 1, wherein the first determination process predicts whether or not the image of the QR code has stains by using a learning device that has learned the stains in advance. The information processing program according to claim 1, wherein the first determination process predicts whether or not the image of the QR code has stains by using pattern recognition. When determining a QR code that transitions stochastically, a first determination processing unit that determines whether or not the image of the QR code to be processed has stains, and a first determination processing unit.
When the first determination processing unit determines that the image of the QR code has stains, it is based on the positional relationship between the region where the stains exist and the region of the error bit included in the QR code. A second determination processing unit that determines whether or not the QR code transitions stochastically, and
An information processing device characterized by having. When determining a QR code that transitions stochastically, it is determined whether or not the image of the QR code to be processed has stains.
If the image of the QR code has stains, whether or not there is a QR code that transitions stochastically based on the positional relationship between the region where the stains exist and the region of the error bit included in the QR code. To judge whether
An information processing method characterized in that a computer executes processing.

Images