JP7029732B2 - Vehicle number recognition device that analyzes multiple frames that make up the license plate image and recognizes the vehicle number. - Google Patents

Description

The present invention relates to a vehicle number recognition device that recognizes a vehicle number by analyzing a plurality of frames constituting a license plate image.

Recently, with the advent of various technologies related to electronic commerce, electronic commerce services for the convenience of users are attracting attention.

In particular, with the advent of mobile devices such as smartphones and tablet PCs that can be connected to the Internet, services related to electronic commerce using mobile devices are actively becoming widespread.

Recently, as the number of people using private cars has increased, a car called "drive-through" is a service that allows drivers to enter the sales floor without getting out of the vehicle and immediately purchase the products they want in the vehicle. -Commerce services are attracting attention.
In order to operate a car commerce service, it is necessary to introduce a technology that can automatically recognize the vehicle number of the entering vehicle when the vehicle enters the sales floor.

In connection with this, the existing vehicle number recognition technology used a method of recognizing the vehicle number by taking a picture of the license plate through a camera and then performing image processing from the picture taken. Such a method has a disadvantage that the recognition accuracy is lowered in that the vehicle number is recognized using only the vehicle number image of one cut.

Therefore, in order to solve such a problem, the license plate is photographed not as a photograph but as an image, and the vehicle number is detected from each of the plurality of frames constituting the image. Additional research is needed on techniques to improve cognitive accuracy.

The vehicle number recognition device according to the present invention captures a license plate of a vehicle through a camera, acquires a license plate image composed of a plurality of frames, and obtains a vehicle number from each of the plurality of frames constituting the license plate image. After extraction, the vehicle number having the maximum overlap among the vehicle numbers extracted from the plurality of frames is determined as the final vehicle number for the vehicle, so that the recognition accuracy of the vehicle number is improved.

The vehicle number recognition device that analyzes a plurality of frames constituting the license plate image according to the embodiment of the present invention and recognizes the vehicle number captures the license plate of the vehicle through a camera, and n (n is 3). Vehicles that detect n vehicle numbers by extracting vehicle numbers from each of the image acquisition unit that acquires the license plate image consisting of the above natural number) frames and the n frames that make up the license plate image. The number detection unit, the representative vehicle number extraction unit that extracts at least one representative vehicle number that does not overlap with each other constituting the detected n vehicle numbers from the detected n vehicle numbers, the at least one representative. For each of the vehicle numbers, a counting unit that counts the number of duplicates existing in the detected n vehicle numbers, and a vehicle number having the maximum number of duplicates among the at least one representative vehicle number is assigned to the vehicle. 1 Includes a vehicle number determination unit that determines a vehicle number, and a vehicle number display unit that displays the first vehicle number on the screen if the first vehicle number is determined.

The vehicle number recognition device according to the present invention captures a license plate of a vehicle through a camera, acquires a license plate image composed of a plurality of frames, and obtains a vehicle number from each of the plurality of frames constituting the license plate image. After extraction, the recognition accuracy of the vehicle number can be improved by determining the vehicle number having the maximum overlap among the vehicle numbers extracted from the plurality of frames as the final vehicle number for the vehicle.

It is a figure which shows the structure of the vehicle number recognition apparatus which performs the recognition of the vehicle number by analyzing a plurality of frames constituting the license plate image by one Embodiment of this invention. It is a flowchart which shows the operation method of the vehicle number recognition apparatus which analyzes a plurality of frames constituting the license plate image by one Embodiment of this invention and recognizes a vehicle number.

Hereinafter, embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Such description is not intended to limit the invention to any particular embodiment and must be understood as including all modifications, equivalents or alternatives contained within the ideas and technical scope of the invention. It doesn't become. Similar reference numerals will be attached to similar components in the description of each drawing, and unless otherwise defined, all terms used herein, including technical or scientific terms, are the present invention. It has the same meaning as what is generally understood by those with ordinary knowledge in the technical field to which it belongs.

In this document, when a component is referred to as "contains" a component, this does not exclude other components unless otherwise stated, and may further include other components. do. Also, in various embodiments of the invention, each component, functional block or means may be composed of one or more subcomponents, the electrical, electronic and mechanical functions performed by each component. May be realized by various known elements or mechanical elements such as electronic circuits, integrated circuits, ASICs (Application Specific Integrated Circuits), etc., each of which is individually realized or two or more integrated into one. May be realized.

On the other hand, the blocks of the attached block diagram and the steps of the flowchart are installed in the processor and memory of a device capable of data processing such as a general-purpose computer, a special computer, a portable notebook computer, and a network computer, and perform specified functions. It can be interpreted as meaning the computer program instructions to be executed. Since these computer program instructions can be stored in the memory provided in the computer equipment or in the computer readable memory, the functions described in the blocks of the block diagram or the steps in the flowchart are produced in the product including the instruction means to execute it. May be done. In addition, each block or step can represent part of a module, segment, or code that contains one or more executable instructions to perform a particular logical function. It should also be noted that in some alternative embodiments, the functions mentioned in the blocks or steps can be performed out of a defined order. For example, the two blocks or steps shown below may be executed substantially simultaneously or in reverse order, and in some cases may be executed with some blocks or steps omitted. You may.
FIG. 1 is a diagram showing a structure of a vehicle number recognition device that recognizes a vehicle number by analyzing a plurality of frames constituting a license plate image according to an embodiment of the present invention.

Referring to FIG. 1, the vehicle number recognition device 110 that analyzes a plurality of frames constituting the license plate image according to the present invention and recognizes a vehicle number includes an image acquisition unit 111, a vehicle number detection unit 112, and a representative vehicle. It includes a number extraction unit 113, a count unit 114, a vehicle number determination unit 115, and a vehicle number display unit 116.

The image acquisition unit 111 photographs the license plate of the vehicle 140 through the camera, and acquires the license plate image composed of n (n is a natural number of 3 or more) frames.
The vehicle number detection unit 112 detects n vehicle numbers by extracting vehicle numbers from each of the n frames constituting the license plate image.

The representative vehicle number extraction unit 113 extracts at least one representative vehicle number that constitutes the detected n vehicle numbers and does not overlap with each other from the detected n vehicle numbers.

For example, when assuming "n = 5", the image acquisition unit 111 can photograph the license plate of the vehicle 140 through the camera and acquire the license plate image composed of five frames.

At this time, the vehicle number detection unit 112 extracts the vehicle numbers "3511", "3512", "3511", "3513", and "3514" from each of the five frames constituting the license plate image. It is possible to detect five vehicle numbers, "3511, 3512, 3511, 3513, 3514".

Then, the representative vehicle number extraction unit 113 has the five detected vehicle numbers "3511, 3512, 3511, 3513" from the five detected vehicle numbers "3511, 3512, 3511, 3513, 3514". It is possible to extract at least one representative vehicle number "3511, 3512, 3513, 3514" that constitutes "3514" and does not overlap with each other.
The counting unit 114 counts the number of duplicates existing in the detected n vehicle numbers for each of the at least one representative vehicle number.
The vehicle number determination unit 115 determines the vehicle number having the maximum number of duplicates among the at least one representative vehicle number as the first vehicle number for the vehicle 140.
When the first vehicle number is determined, the vehicle number display unit 116 displays the first vehicle number on the screen.

For example, as in the above-mentioned example, "n = 5", the five detected vehicle numbers are "3511, 3512, 3511, 3513, 3514", and the at least one representative vehicle number is "3511," Assuming "3512, 3513, 3514", the counting unit 114 has the five detected vehicle numbers "3511," for each of the at least one representative vehicle number "3511, 3512, 3513, 3514". The number of duplicates existing in "3512, 3511, 3513, 3514" can be counted.

At this time, the vehicle number determination unit 115 determines the vehicle number "3511" having the largest number of duplicates among the at least one representative vehicle number "3511, 3512, 3513, 3514" as the first vehicle number for the vehicle 140. be able to.

In this way, if the first vehicle number "3511" is determined, the vehicle number display unit 116 can display the first vehicle number "3511" on the screen.

That is, the vehicle number recognition device 110 captures the license plate of the vehicle 140 through the camera, acquires the license plate image consisting of n frames, and then from each of the n frames constituting the license plate image. By extracting the vehicle numbers, n vehicle numbers are detected, and at least one representative vehicle number that does not overlap with each other constituting the detected n vehicle numbers is extracted from the detected n vehicle numbers. Then, for each of the at least one representative vehicle number, the number of duplicates existing in the detected n vehicle numbers is counted, and the vehicle number having the maximum number of duplicates among the at least one representative vehicle number is counted. Is determined as the first vehicle number for the vehicle 140, and if the first vehicle number is determined, the first vehicle number is displayed on the screen to provide more accurate vehicle number recognition information to the driver. be able to.
According to one embodiment of the present invention, the vehicle number recognition device 110 can further include a diffusion degree calculation unit 117 and a message display unit 118.

The diffusion degree calculation unit 117 calculates the ratio of the number of duplicates of each of the at least one representative vehicle number to the total number of the detected n vehicle numbers, and then the detected n vehicle numbers are calculated based on the ratio. Calculate the degree of diffusion that indicates how the vehicle numbers are evenly distributed.
At this time, according to one embodiment of the present invention, the diffusion degree calculation unit 117 can calculate the diffusion degree based on the following equation 1.

Here, I is the degree of diffusion, x _i is the number of duplicates of the i-th representative vehicle number among the at least one representative vehicle number, n is the total number of the detected n vehicle numbers, and J is the at least the above. It means the total number of one representative vehicle number.

The closer the value of the degree of diffusion calculated by the number 1 is to "0", the more the detected n vehicle numbers are concentrated and exist, and the value of the degree of diffusion is "1". The closer it is, the more the detected n vehicle numbers are evenly distributed and exist.

In connection with this, according to the above-mentioned example, the five detected vehicle numbers are set to "3511, 3512, 3511, 3513, 3514", and the at least one representative vehicle number is set to "3511, 3512, 3513, 3514". Suppose to.

At this time, since J is the total number of the at least one representative vehicle number "3511, 3512, 3513, 3514", it becomes "4", and n is the detected five vehicle numbers. Since it is the total number of certain "3511, 3512, 3511, 3513, 3514", it becomes "5", and x _1/5 is the five detected vehicle numbers "3511, 3512, 3511, 3513, 3514". Because it is the ratio of the number of duplicates of the first representative vehicle number "3511" out of the at least one representative vehicle number "3511, 3512, 3513, 3514" to the total number of "", it becomes "2/5". x _2/5 is 2 of the at least one representative vehicle number "3511, 3512, 3513, 3514" with respect to the total number of the five detected vehicle numbers "3511, 3512, 3511, 3513, 3514". Since it is the ratio of the number of duplicates of the second representative vehicle number "3512", it becomes "1/5", and x _3/5 is the five detected vehicle numbers "3511, 3512, 3511, 3513, 3514". Because it is the ratio of the number of duplicates of the third representative vehicle number "3513" out of the at least one representative vehicle number "3511, 3512, 3513, 3514" to the total number of "", it becomes "1/5". x _4/5 is 4 of the at least one representative vehicle number "3511, 3512, 3513, 3514" with respect to the total number of the five detected vehicle numbers "3511, 3512, 3511, 3513, 3514". Since it is the ratio of the number of duplicates of the second representative vehicle number "3514", it becomes "1/5".
In consideration of such a thing, if the degree of diffusion according to the number 1 is calculated, the degree of diffusion is calculated as "0.72".

When it is determined that the calculated diffusivity exceeds the critical value already set, the message display unit 118 displays a message on the screen instructing the license plate of the vehicle 140 to be re-recognized.

For example, as in the example calculated above, the calculated diffusivity is assumed to be "0.72", and the already set critical value is assumed to be "0.64". The message display unit 118 instructs to re-recognize the license plate of the vehicle 140 by determining that the calculated diffusion degree "0.72" exceeds the already set critical value "0.64". Message can be displayed on the screen.
According to one embodiment of the present invention, the vehicle number recognition device 110 can further include a history information database 119 and a history information storage unit 120.
The history information database 119 stores vehicle number recognition history information for a plurality of vehicles.
Here, the vehicle number recognition history information means information composed of the recognized vehicle number and the time with respect to the recognition time of the vehicle number.
For example, the history information database 119 stores information as shown in Table 1 below.

When the first vehicle number is determined, the history information storage unit 120 has a first vehicle number recognition history composed of the first vehicle number and the time for the recognition time of the first vehicle number in the history information database 119. Information is generated and stored in the history information database 119.

For example, it is assumed that the first vehicle number is "3263" and the time for the recognition time of the first vehicle number "3263" is "19:30". If the first vehicle number "3263" is determined by the vehicle number recognition device 110, the history information storage unit 120 has the first vehicle number "3263" and the first vehicle number in the history information database 119 as shown in Table 1. The first vehicle number recognition history information composed of the time "19:30" with respect to the recognition time of the vehicle number "3263" can be generated and stored in the history information database 119 as shown in Table 1.

According to one embodiment of the present invention, the vehicle number recognition device 110 can further include an OTP storage unit 121, an Euclidean distance storage unit 122, a request unit 123, an authentication confirmation unit 124, and a history information transmission unit 125.

The OTP storage unit 121 stores a predetermined OTP (One Time Password) generation function that can generate a one-time password based on the current time value.

Here, OTP means a one-time password that is randomly generated instead of a fixed password, and the OTP generation function is a function that can be preset by the developer and is a one-time password based on the current time value. Can be set to be generated.

The Euclidean distance storage unit 122 stores information for an already set Euclidean distance (Euclidean Distance) for use in authentication of the administrator.
Here, the Euclidean distance means the distance between two vectors when two vectors exist, and can be calculated by the following equation 2.

In the above equation 2, D means the Euclidean distance, and Ai and _Bi mean the _i -th component contained in the two vectors. Generally, the smaller the Euclidean distance between two vectors, the more similar the two vectors can be seen, and the larger the Euclidean distance between the two vectors, the more dissimilar the two vectors can be seen. Can be done.

When the requesting unit 123 receives a transmission request for the second vehicle number recognition history information among the vehicle number recognition history information for the plurality of vehicles stored in the history information database 119 from the administrator terminal 130, the request unit 123 generates the OTP. A first one-time password corresponding to the current time value is generated based on the function, a number corresponding to a digit already set is confirmed from the first one-time password, and then a humming weight corresponding to the size of the number is obtained. A random vector having (Hamming Weight) and having an already set length is randomly generated, the random vector is transmitted to the administrator terminal 130, and the administrator terminal 130 corresponds to the random vector. Request the transmission of the feedback vector.

Here, the Hamming weight means the number of "1" in the data composed of the codes of "0" and "1", and the digit can be preset by the developer, and the number from the left side. It can be set to a number indicating whether it is a position.

For example, if the vehicle number recognition device 110 receives a transmission request for the second vehicle number recognition history information among the vehicle number recognition history information for the plurality of vehicles stored in the history information database 119 from the administrator terminal 130. , The requesting unit 123 can generate the first one-time password according to the current time value based on the OTP generation function, and provisionally, the first one-time password is generated in "12345" and has already been set. When the digit is 4, the requesting unit 123 can confirm the fourth digit "4" from the first one-time password "12345". After that, the requesting unit 123 can randomly generate a random vector having a Hamming weight corresponding to the magnitude of the number "4" and having the already set length. In connection with this, when the already set length is set to "6", the requesting unit 123 randomly generates a random vector having four "1" s and a length of six. can do.

For example, assuming that the random vector is generated in "[110110]", the requesting unit 123 transmits the random vector "[110110]" to the administrator terminal 130, and the random vector "[110110]" is transmitted to the administrator terminal 130. It is possible to request the transmission of the feedback vector corresponding to [110110].

At this time, according to one embodiment of the present invention, the administrator terminal 130 may store the already set Euclidean distance and the same verification OTP generation function as the OTP generation function in the memory.

If the random vector is received from the vehicle number recognition device 110 to the administrator terminal 130, the administrator terminal 130 responds to the current time value based on the verification OTP generation function stored in the memory. After generating the verification one-time password, the verification number corresponding to the already set digit is confirmed from the verification one-time password, and the Hamming weight of the random vector becomes the magnitude of the verification number. You can check if it matches the corresponding Hamming weight.

At this time, if it is confirmed that the Hamming weight of the random vector matches the Hamming weight corresponding to the magnitude of the verification number, the administrator terminal 130 stores the Euclidean distance from the random vector in the memory. The first feedback vector calculated at the already set Euclidean distance can be randomly generated and transmitted to the vehicle number recognition device 110.

In connection with this, the already set Euclidean distance stored in the memory is set to "D ₁ ", and the random vector "[110 110]" is received from the vehicle number recognition device 110 to the administrator terminal 130. If so, the administrator terminal 130 generates the verification one-time password "12345" according to the current time value based on the verification OTP generation function stored in the memory, and then the verification one. From the time password, the verification number "4" corresponding to the already set digit "4" can be confirmed.

After that, the administrator terminal 130 can confirm whether the Hamming weight of the random vector matches the Hamming weight corresponding to the magnitude of the verification number “4”.

In the present embodiment, the Hamming weight of the random vector is set to "4" and matches the verification number, and the Hamming weight "4" of the random vector and the verification number "4" match each other. It means that the random vector must have been generated based on the one-time password derived based on the same OTP generation function shared in advance by the vehicle number recognition device 110 and the administrator terminal 130.

Therefore, when it is confirmed that the Hamming weight of the random vector matches the Hamming weight corresponding to the magnitude of the verification number, the administrator terminal 130 stores the Euclidean distance from the random vector in the memory. A first feedback vector calculated at the already set Euclidean distance "D ₁ " can be randomly generated and transmitted to the vehicle number recognition device 110.

When the first feedback vector is received from the administrator terminal 130 as the feedback vector corresponding to the random vector, the authentication confirmation unit 124 calculates the first Euclidean distance between the first feedback vector and the random vector. Then, by confirming whether the first Euclidean distance is calculated to the already set Euclidean distance, the authentication to the administrator terminal 130 is completed.

When the authentication to the administrator terminal 130 is completed, the history information transmission unit 125 extracts the second vehicle number recognition history information stored in the history information database 119, and then sends the second vehicle number to the administrator terminal 130. Transmission recognition history information.

For example, it is assumed that the random vector is "[110110]", the already set Euclidean distance is "D ₁ ", and the second vehicle number recognition history information is "vehicle number recognition history information 2". If the first feedback vector is received by the vehicle number recognition device 110 as a feedback vector corresponding to the random vector "[110110]" from the administrator terminal 130, the authentication confirmation unit 124 will use the first feedback vector and the random. The administrator by calculating the first Euclidean distance to and from the vector "[110110]" and confirming whether the first Euclidean distance is calculated to "D ₁ " which is the already set Euclidean distance. Authentication for the terminal 130 can be completed.

In this way, when the authentication to the administrator terminal 130 is completed, the history information transmission unit 125 is the second vehicle number recognition history information "vehicle number" stored in the history information database 119 as shown in Table 1. After extracting the "recognition history information 2", the "vehicle number recognition history information 2" which is the second vehicle number recognition history information can be transmitted to the administrator terminal 130.

That is, the administrator terminal 130 has the Euclidean distance from the random vector only when the humming weight of the random vector matches the humming weight corresponding to the magnitude of the verification number based on the OTP generation function issued in advance. Randomly generates a first feedback vector stored in the memory and calculated to the already set Euclidean distance and transmits the first feedback vector to the vehicle number recognition device 110, and the vehicle number recognition device 110 receives the administrator terminal 130. When the first feedback vector is received as the feedback vector corresponding to the random vector, the first Euclidean distance between the first feedback vector and the random vector is calculated, and the first Euclidean distance is already obtained. Only when the authentication to the administrator terminal 130 is completed after confirming whether the calculation is performed to the set Euclidean distance, after extracting the second vehicle number recognition history information stored in the history information database 119, the administrator By transmitting the second vehicle number recognition history information to the terminal 130, it is possible to prevent an unauthenticated administrator from arbitrarily receiving the vehicle number recognition history information.

FIG. 2 is a flowchart showing an operation method of a vehicle number recognition device that analyzes a plurality of frames constituting a license plate image according to an embodiment of the present invention and recognizes a vehicle number.

In step (S210), the license plate of the vehicle is photographed through the camera, and the license plate image composed of n (n is a natural number of 3 or more) frames is acquired.
The step (S220) detects the n vehicle numbers by extracting the vehicle numbers from each of the n frames constituting the license plate image.

The step (S230) extracts at least one representative vehicle number that constitutes the detected n vehicle numbers and does not overlap with each other from the detected n vehicle numbers.
The step (S240) counts the number of duplicates existing in the detected n vehicle numbers for each of the at least one representative vehicle numbers.
The step (S250) determines the vehicle number having the maximum number of duplicates among the at least one representative vehicle number as the first vehicle number for the vehicle.
The step (S260) displays the first vehicle number on the screen once the first vehicle number is determined.

At this time, according to one embodiment of the present invention, in the operation method of the vehicle number recognition device, the ratio of the overlapping number of each of the at least one representative vehicle number to the total number of the detected n vehicle numbers is set. After the calculation, the step of calculating the degree of diffusion indicating how the detected n vehicle numbers are evenly distributed based on the ratio, and the critical value in which the calculated degree of diffusion has already been set are set. If it is determined to be exceeded, it may further include displaying a message on the screen instructing the vehicle to re-recognize the license plate.
At this time, according to one embodiment of the present invention, the step of calculating the degree of diffusion can calculate the degree of diffusion based on the number 1.

Further, according to one embodiment of the present invention, the operation method of the vehicle number recognition device is the vehicle number recognition history information for a plurality of vehicles (the vehicle number recognition history information is the recognition of the recognized vehicle number and the vehicle number). If the step for holding the history information database in which the information is composed of the time with respect to the time point) and the first vehicle number are determined, the first vehicle number and the first vehicle number are stored in the history information database. Further, a step of generating the first vehicle number recognition history information composed of the time with respect to the recognition time of the vehicle number and storing the first vehicle number recognition history information in the history information database can be included.

At this time, according to one embodiment of the present invention, the operation method of the vehicle number recognition device is an OTP storage in which a predetermined OTP generation function capable of generating a one-time password based on the current time value is stored. The step of holding the unit, the step of holding the Euclidean distance storage unit in which the information for the Euclidean distance already set for use in the authentication of the administrator is stored, and the step stored in the history information database from the administrator terminal. When a transmission request for the second vehicle number recognition history information among the vehicle number recognition history information for a plurality of vehicles is received, the first one-time password corresponding to the current time value is generated based on the OTP generation function, and the above-mentioned After confirming the number corresponding to the already set digit from the first one-time password, a random vector having a humming weight corresponding to the size of the number and having an already set length is randomly generated. Then, the step of transmitting the random vector to the administrator terminal and requesting the administrator terminal to transmit the feedback vector corresponding to the random vector, the first as a feedback vector corresponding to the random vector from the administrator terminal. One feedback vector (the first feedback vector is a vector generated so that the Euclidean distance to the random vector is calculated to the already set Euclidean distance already stored in the administrator terminal). Upon receipt, the first Euclidean distance between the first feedback vector and the random vector is calculated, and by checking whether the first Euclidean distance is calculated to the already set Euclidean distance. When the step of completing the authentication for the administrator terminal and the authentication for the administrator terminal are completed, the second vehicle number recognition history information stored in the history information database is extracted, and then the administrator terminal is used. A step of transmitting the second vehicle number recognition history information can be further included.

At this time, according to one embodiment of the present invention, the administrator terminal stores the already set Euclidean distance and the same verification OTP generation function as the OTP generation function in the memory, and the vehicle. When the random vector is received from the number recognition device, the verification one-time password corresponding to the current time value is generated based on the verification OTP generation function stored in the memory, and then the verification one. The verification number corresponding to the already set digit is confirmed from the time password, and it is confirmed whether or not the humming weight of the random vector matches the humming weight corresponding to the magnitude of the verification number. If it is confirmed that the humming weight of the random vector matches the humming weight corresponding to the magnitude of the verification number, the Euclidean distance to the random vector is set to the already set Euclidean distance stored in the memory. The calculated first feedback vector can be randomly generated and transmitted to the vehicle number recognition device.

As described above, with reference to FIG. 2, the operation method of the vehicle number recognition device for recognizing the vehicle number by analyzing a plurality of frames constituting the license plate image according to the embodiment of the present invention has been described. Here, the operation method of the vehicle number recognition device that analyzes a plurality of frames constituting the number plate image according to the embodiment of the present invention and recognizes the vehicle number is described by using the number plate image described with reference to FIG. Since it corresponds to the configuration related to the operation of the vehicle number recognition device 110 that analyzes the plurality of constituent frames and recognizes the vehicle number, detailed description thereof will be omitted.

The operation method of the vehicle number recognition device that recognizes the vehicle number by analyzing a plurality of frames constituting the license plate image according to the embodiment of the present invention is stored in a storage medium for execution by coupling with a computer. It may be realized by a computer program.

Further, the operation method of the vehicle number recognition device that recognizes the vehicle number by analyzing a plurality of frames constituting the license plate image according to the embodiment of the present invention is a program instruction form that can be executed via various computer means. It may be realized and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be those specially designed and configured for the present invention, or those known and usable by those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and floptic discs. Includes magnetic-optical media such as floppy disks, and hardware devices specially configured to store and execute program instructions such as ROMs, RAMs, flash memories, and the like. Examples of program instructions include machine language code, such as those created by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like.

As described above, the present invention has been described by means of specific matters such as specific components and limited embodiments and drawings, which are provided to aid in a more general understanding of the invention. However, the present invention is not limited to the above-described embodiment, and any person having ordinary knowledge in the field to which the present invention belongs can make various modifications and modifications from such a description.

Therefore, the idea of the present invention should not be limited to the described embodiments, and is not limited to the scope of claims described later, but anything having a modification equal to or equivalent to the scope of claims. Can be said to belong to the category of the idea of the present invention.

110 ・ ・ ・ Vehicle number recognition device that analyzes multiple frames that make up the license plate image and recognizes the vehicle number 111 ・ ・ ・ Video acquisition unit 112 ・ ・ ・ Vehicle number detection unit 113 ・ ・ ・ Representative vehicle number extraction Part 114 ・ ・ ・ Count part 115 ・ ・ ・ Vehicle number determination part 116 ・ ・ ・ Vehicle number display part 117 ・ ・ ・ Diffuse degree calculation part 118 ・ ・ ・ Message display part 119 ・ ・ ・ History information database 120 ・ ・ ・ History Information storage unit 121 ・ ・ ・ OTP storage unit 122 ・ ・ ・ Euclidean distance storage unit 123 ・ ・ ・ Request unit 124 ・ ・ ・ Authentication confirmation unit 125 ・ ・ ・ History information transmission unit 130 ・ ・ ・ Administrator terminal 140 ・ ・ ・vehicle

Claims (5)

An image acquisition unit that captures a vehicle number plate through a camera and acquires a number plate image consisting of n (n is a natural number of 3 or more) frames.
A vehicle number detection unit that detects n vehicle numbers by extracting vehicle numbers from each of the n frames constituting the license plate image.
A representative vehicle number extraction unit that extracts at least one representative vehicle number that does not overlap with each other constituting the detected n vehicle numbers from the detected n vehicle numbers.
A counting unit that counts the number of duplicates existing in the detected n vehicle numbers for each of the at least one representative vehicle number.
A vehicle number determination unit that determines the vehicle number having the largest number of duplicates among the at least one representative vehicle number as the first vehicle number for the vehicle, and if the first vehicle number is determined, the first vehicle number. Vehicle number display unit, which displays on the screen
After calculating the ratio of the overlapping number of each of the at least one representative vehicle number to the total number of the detected n vehicle numbers, how the detected n vehicle numbers are evenly distributed based on the ratio. Diffusion degree calculation unit that calculates the degree of diffusion that indicates whether or not it is done, and
When it is determined that the calculated diffusivity exceeds an already set critical value, a message display unit that displays a message instructing the vehicle to re-recognize the license plate on the screen.
A vehicle number recognition device that analyzes a plurality of frames constituting a license plate image and recognizes the vehicle number. The diffusion degree calculation unit is
A vehicle number recognition device that recognizes a vehicle number by analyzing a plurality of frames constituting the license plate image according to claim 1 , which calculates the degree of diffusion based on the following number 1.

Here, I is the degree of diffusion, x _i is the number of duplicates of the i-th representative vehicle number among the at least one representative vehicle number, n is the total number of the detected n vehicle numbers, and J is the at least the above. It means the total number of one representative vehicle number. A history information database in which vehicle number recognition history information for a plurality of vehicles (the vehicle number recognition history information is information composed of a recognized vehicle number and a time with respect to a recognition time of the vehicle number) is stored, and the above-mentioned When the first vehicle number is determined, the first vehicle number recognition history information composed of the first vehicle number and the time for the recognition time of the first vehicle number is generated in the history information database, and the history information is generated. A vehicle number recognition device that recognizes a vehicle number by analyzing a plurality of frames constituting the number plate image according to claim 1, further including a history information storage unit stored in a database. An OTP storage unit that stores a predetermined OTP (One Time Password) generation function that can generate a one-time password based on the current time value.
Euclidean distance storage unit, which stores information for the Euclidean distance that has already been set for use in administrator authentication.
If a transmission request for the second vehicle number recognition history information among the vehicle number recognition history information for the plurality of vehicles stored in the history information database is received from the administrator terminal, the current time is based on the OTP generation function. After generating the first one-time password according to the value and confirming the number corresponding to the digit already set from the first one-time password, the humming weight corresponding to the size of the number is provided. In addition, a random vector having an already set length is randomly generated, the random vector is transmitted to the administrator terminal, and the administrator terminal is requested to transmit a feedback vector corresponding to the random vector. Request department,
The first feedback vector as the feedback vector corresponding to the random vector from the administrator terminal (the first feedback vector is the already set Euclidean whose Euclidean distance from the random vector is already stored in the administrator terminal). (The vector generated to be calculated to the distance) is received, the first Euclidean distance between the first feedback vector and the random vector is calculated, and the first Euclidean distance is already set. The authentication confirmation unit that completes the authentication to the administrator terminal by confirming whether the Euclidean distance is calculated, and the authentication confirmation unit that is stored in the history information database if the authentication to the administrator terminal is completed. A plurality of components of the number plate image according to claim 3 , further including a history information transmission unit that transmits the second vehicle number recognition history information to the administrator terminal after extracting the second vehicle number recognition history information. A vehicle number recognition device that analyzes the frame and recognizes the vehicle number. The administrator terminal is
The Euclidean distance already set and the same verification OTP generation function as the OTP generation function are stored in the memory.
When the random vector is received from the vehicle number recognition device, the verification one-time password corresponding to the current time value is generated based on the verification OTP generation function stored in the memory, and then the verification is performed. Check the verification number corresponding to the already set digit from the one-time password, and check whether the humming weight of the random vector matches the humming weight corresponding to the size of the verification number. ,
When it is confirmed that the humming weight of the random vector matches the humming weight corresponding to the magnitude of the verification number, the Euclidean distance with the random vector is stored in the memory. The already set Euclidean distance. A vehicle that recognizes a vehicle number by analyzing a plurality of frames constituting the license plate image according to claim 4 , which randomly generates the first feedback vector calculated in 1 and transmits it to the vehicle number recognition device. Number recognition device.

Images