KR102339686B1 - License plate image processing device for car number recognition and license plate image correction method using the same - Google Patents

Abstract

The present invention provides a license plate image processing device for recognizing vehicle numbers to correct a license plate image taken at an angle to an original license plate shape. According to one embodiment of the present invention, the license plate image processing device comprises: a vehicle image acquisition unit photographing a vehicle to acquire a photographed image including the vehicle; a license plate detection unit detecting a license plate image of the vehicle from the photographed image and generating position data for the position of the license plate image in the photographed image; a database unit storing image correction data calculated for each position of the license plate image in the photographed image; a correction value generation unit loading the image correction data corresponding to the position data from the database unit and generating a license plate image correction value on the basis of the loaded image correction data; and a license plate image correction unit correcting the license plate image on the basis of the license plate image correction value.

Description

License plate image processing device for vehicle number recognition and license plate image correction method using the same

The present invention relates to a license plate image processing apparatus for license plate recognition and a license plate image correction method using the same, and more specifically, to a license plate image that can be corrected in its original form with a relatively small amount of computation. It relates to a license plate image processing apparatus and a license plate image correction method using the same.

With the development of image recognition technology, automatic license plate recognition using the license plate image of the vehicle has become possible, and most vehicle access management systems are currently adopting this method.

The license plate image is obtained by photographing the vehicle using a photographing device installed at the entrance of a place requiring vehicle access management, such as a parking lot. And the recognition of the license plate consists of a combination of the steps of license plate identification from a photographed image, license plate verification, code (letters, numbers, symbols) separation, and sign recognition, and is implemented in software and performed in a computer system.

1 is a view showing a conventional license plate identification process for vehicle number recognition, the identification of the license plate is made in a way that detects the outline of the license plate.

First, the vehicle entering or leaving the vehicle is photographed through a camera provided at the entrance or exit of the parking lot. (S11) And the outline of the license plate image included in the photographed vehicle image is extracted to finally obtain the license plate image. (S12)

On the other hand, when the photographing device is installed obliquely from the entrance direction of the vehicle, or when the vehicle enters the entrance at an angle, the license plate of the vehicle may be photographed obliquely.

As shown in FIG. 1, the license plate photographed at an angle may have a horizontal and vertical ratio different from the standard ratio of a general license plate, and has a shape rotated at a predetermined angle in comparison with the image photographed from the front of the license plate.

As such, the oblique license plate image is corrected to the original license plate form for accurate license plate recognition. For accurate correction, the outline of the license plate must be accurately extracted.

At this time, the extraction of the license plate outline is usually performed through the Generalized Hough Transform, which requires a high amount of computation because it is calculated depending on the pixel.

However, there is a problem in that it is difficult to perform a high computational amount because the license plate recognition devices installed at the entrance have limitations in processing performance due to the problem of the installation location or device specifications. In particular, when the quality of the vehicle image acquired due to a problem such as focus is low, there is a problem in that the accurate extraction of the license plate outline becomes more difficult because the pixels forming the boundary of the license plate in the image are reduced.

Korean Patent Publication No. 10-2016-0083226

The technical problem to be achieved by the present invention in order to solve the above problems is a license plate image processing device for recognizing a license plate number capable of correcting an obliquely photographed license plate image in its original form with a relatively small amount of computation, and a license plate image correction method using the same will provide

The technical problems to be achieved by the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned can be clearly understood by those of ordinary skill in the art to which the present invention belongs from the description below. There will be.

In order to achieve the above technical problem, an embodiment of the present invention includes a vehicle image acquisition unit for acquiring a photographed image including the vehicle by photographing the vehicle; a license plate detection unit for detecting the license plate image of the vehicle from the photographed image, and generating position data for the position of the license plate image in the photographed image; a database unit storing image correction data calculated in advance for each position of the license plate image in the photographed image; a correction value generating unit for loading the image correction data corresponding to the position data from the database unit, and generating a license plate image correction value based on the loaded image correction data; and a license plate image correction unit for correcting the license plate image based on the license plate image correction value.

The photographed image is divided into a plurality of regions, the image correction data is calculated in advance for each region and stored in the database unit, and the correction value generation unit generates the image correction data corresponding to the region to which the position data belongs. can be loaded

The image correction data may include a first correction value for correcting the scale of the license plate image, and a second correction value for rotating the license plate image.

The database unit further stores an aspect ratio reference value calculated in advance for each position of the license plate image in the photographed image, and the correction value generator is based on a difference between the aspect ratio reference value corresponding to the position data and the aspect ratio of the license plate image At least one of the first correction value and the second correction value may be corrected.

The vehicle image obtaining unit photographs the vehicle on a predetermined photographing position, and the correction value generating unit corrects the position data based on a height difference between the ground at the location where the vehicle image obtaining unit is installed and the ground at the predetermined photographing location. and the correction value generator may load the image correction data corresponding to the corrected position data.

The correction value generator may further correct the position data by using the data of the inclination angle of the ground of the predetermined photographing position.

The position data may include two-dimensional coordinate data including a horizontal axis value and a vertical axis value, and the correction value generator may correct a vertical axis value of the position data based on the height difference.

The second correction value may be corrected based on an angle between a photographing direction of the vehicle image acquisition unit and a direction of an access road in which the vehicle is located during the photographing.

After the license plate image correction unit rotationally corrects the license plate image based on the second correction value, the scale of the license plate image may be corrected based on the first correction value.

In order to achieve the above technical problem, an embodiment of the present invention comprises the steps of: a) photographing a vehicle to obtain a photographed image including the vehicle, and detecting a license plate image from the photographed image; b) generating position data for the position of the license plate image in the photographed image; c) loading the image correction data corresponding to the position data from the database unit in which image correction data calculated in advance for each position of the license plate image in the photographed image is stored, and a license plate image correction value based on the loaded image correction data creating a; and d) correcting the license plate image based on the license plate image correction value.

The photographed image is divided into a plurality of regions, the image correction data is calculated in advance for each region and stored in the database unit, and the step c) includes the image correction data corresponding to the region to which the position data belongs. It can be loaded from the database unit.

The database unit further stores an aspect ratio reference value calculated in advance for each position of the license plate image in the photographed image, and the step c) includes: loading image correction data corresponding to the position data from the database unit; and correcting the image correction data based on the difference between the aspect ratio reference value corresponding to the position data and the aspect ratio of the license plate image.

Step c) may include: loading image correction data corresponding to the position data from a database unit; and correcting the image correction data based on an angle between a photographing direction of the vehicle image acquisition unit and a direction of an access road in which the vehicle is located.

The photographed image is acquired using a vehicle image acquisition unit for photographing the vehicle, and between steps b) and c), the location based on the height difference between the ground at the location where the vehicle image acquisition unit is installed and the ground at the predetermined photographing location The method may further include correcting the data.

The location data may be further corrected based on the data of the inclination angle of the ground of the predetermined photographing location.

The image correction data includes a first correction value for correcting the scale of the license plate image, and a second correction value for rotating the license plate image, wherein step d) is based on the second correction value. After correcting the rotation, it may be to correct the scale of the license plate image based on the first correction value.

According to an embodiment of the present invention, the license plate image processing apparatus may correct the license plate image using image correction data calculated in advance for each position of the license plate image in the photographed image. That is, the license plate image processing apparatus can estimate the shape of the license plate image without the process of extracting the outline using a complex operation such as the generalized Hough transform. Therefore, the license plate image processing apparatus can correct the license plate image taken at an angle with a relatively small amount of calculation to the original license plate form.

Also, according to an embodiment of the present invention, the license plate image processing apparatus may store an aspect ratio reference value for each area of the photographed image. And the license plate image device corrects the image correction data based on the difference between the aspect ratio reference value of the area where the photographed license plate image is located and the aspect ratio of the photographed license plate image, so the photographed license plate image can be corrected more similarly to the license plate standard shape have.

Also, according to an embodiment of the present invention, the license plate image processing device corrects the image correction data based on the angle between the shooting direction of the vehicle image acquisition unit and the direction of the access road where the vehicle to be filmed is located, so the correction of the license plate image can be done accurately .

In addition, according to an embodiment of the present invention, the license plate image processing device corrects the position data based on the height difference between the ground of the location where the vehicle image acquisition unit is installed and the ground of the predetermined shooting location, so the correction of the license plate image can be done accurately .

In addition, according to an embodiment of the present invention, the license plate image processing apparatus further corrects the position data based on the inclination angle data of the ground of the predetermined shooting position, so the correction of the license plate image can be made more accurately.

The effects of the present invention are not limited to the above effects, but it should be understood to include all effects that can be inferred from the configuration of the invention described in the description or claims of the present invention.

1 is a view showing a conventional license plate identification process for vehicle number recognition.
Figure 2 is a block diagram schematically showing a license plate image processing apparatus according to an embodiment of the present invention.
3 is a view for explaining an example of a license plate image taken obliquely.
Figure 4 is a detailed block diagram showing a license plate image processing apparatus according to an embodiment of the present invention.
5 is a diagram illustrating an example of a photographed image acquired by a vehicle image acquisition unit according to an embodiment of the present invention.
6 is a view showing the standardized shape of the license plate image of each zone in the photographed image according to an embodiment of the present invention.
7 is a view for explaining an image correction data table that is calculated and stored in advance for each area of a photographed image according to an embodiment of the present invention.
8 is a view for explaining an example in which the aspect ratio corrector corrects image correction data according to an embodiment of the present invention.
9 is a view for explaining an example of correcting image correction data by a photographing direction correcting unit according to an embodiment of the present invention.
10 is a view for explaining an example in which the ground height corrector corrects position data according to an embodiment of the present invention.
11 is a flowchart illustrating a license plate image correction method using a license plate image processing apparatus according to an embodiment of the present invention.
12 is a diagram illustrating detailed steps of step S220 according to an embodiment of the present invention.

Hereinafter, the present invention will be described with reference to the accompanying drawings. However, the present invention may be embodied in several different forms, and thus is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is said to be “connected (connected, contacted, coupled)” with another part, it is not only “directly connected” but also “indirectly connected” with another member interposed therebetween. "Including cases where In addition, when a part "includes" a certain component, this means that other components may be further provided without excluding other components unless otherwise stated.

The terminology used herein is used only to describe specific embodiments, and is not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present specification, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features It should be understood that this does not preclude the existence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

2 is a block diagram schematically showing a license plate image processing apparatus 100 according to an embodiment of the present invention. And Figure 3 is a view for explaining an example of the license plate image taken at an angle.

As shown in FIG. 2 , the license plate image processing device 100 includes a vehicle image acquisition unit 110 , a license plate detection unit 120 , a correction value generating unit 130 , a license plate image correcting unit 140 and a database unit (D). may include

The vehicle image acquisition unit 110 may acquire a photographed image including the vehicle 1 by photographing the vehicle 1 . For example, the vehicle image acquisition unit 110 may be a camera installed at an entrance of a place requiring vehicle access management.

The license plate detection unit 120 may detect a license plate image of the vehicle 1 from the photographed image. At this time, the license plate may be photographed at an angle as shown in (a) of FIG. 3 . In order to accurately recognize the license plate number from the license plate image, the obliquely photographed license plate image (Pa) may be corrected to a license plate image (Pb) having an original shape as shown in Fig. 3 (b). To this end, the license plate detection unit 120 may generate position data for the position of the license plate image in the photographed image. A specific application example of location data will be described in detail with reference to FIGS. 5 to 7 .

The database unit (D) may store image correction data calculated in advance for each position of the license plate image in the photographed image. The image correction data may be used to correct the license plate image.

The correction value generator 130 may load image correction data corresponding to the position data from the database unit D. That is, the correction value generating unit 130 may load different image correction data according to the position of the license plate image in the photographed image. And the correction value generating unit 130 may generate a license plate image correction value based on the loaded image correction data.

And the license plate image correction unit 140 may correct the license plate image using the license plate image correction value.

In FIG. 2, the case where each configuration of the license plate image processing apparatus 100 is integrated and installed at the entrance of a place requiring vehicle access management has been described as an example. However, each component of the license plate image processing apparatus 100 may be installed in different locations. For example, the vehicle image acquisition unit 110 may be installed at the entrance of the vehicle 1 , and other components may be provided in a separate location or mounted on an external server to communicate with the vehicle image acquisition unit 110 .

4 is a detailed block diagram illustrating a license plate image processing apparatus 100 according to an embodiment of the present invention.

As shown in FIG. 4 , the license plate detection unit 120 may receive a photographed image from the vehicle image acquisition unit 110 . The photographed image may be an image including a vehicle.

The license plate detection unit 120 may include a license plate image detection unit 121 and a license plate position determination unit 122 .

The license plate image detection unit 121 may detect a license plate image in the photographed image. That is, the license plate image detection unit 121 may generate a license plate image.

The license plate position determination unit 122 may generate position data indicating the position of the license plate image in the photographed image. The position data may be two-dimensional coordinate data using a specific position of the photographed image as a reference point. The location data may have a horizontal axis value and a vertical axis value. The location data may be polar coordinates. The location data may be coordinates of the license plate image center point. For example, the center point may be the center of gravity of the license plate image.

Meanwhile, the location data may be data indicating a specific area in the captured image.

Specifically, the captured image may be divided into a plurality of regions. And the license plate position determining unit 122 may determine to which zone the position of the license plate image (eg, the position of the license plate image center point) belongs. And the license plate location determination unit 122 may generate the information of the corresponding area as location data.

And the license plate detection unit 120 may transmit the license plate image and position data to the correction value generating unit 130 .

The correction value generating unit 130 may generate a license plate image correction value required for correction of the license plate image.

The correction value generating unit 130 may include an image correction data loading unit 131 , an aspect ratio correcting unit 132 , a photographing direction correcting unit 133 , and a ground height correcting unit 134 .

The image correction data loading unit 131 may load image correction data corresponding to the position data from the database unit D.

At this time, the database unit (D) may be in a state in which the image correction data calculated in advance for each position of the license plate image in the photographed image is stored. For example, the image correction data may include a first correction value for scale correction of the license plate image, and a second correction value for rotation correction of the license plate image. Also, the image correction data may be data calculated in advance for each region of the captured image.

And, the correction value generating unit 130 may select the loaded image correction data as the license plate image correction value.

On the other hand, the correction value generating unit 130 is to correct the image correction data loaded using the aspect ratio correction unit 132, the shooting direction correcting unit 133 and the ground height correcting unit 134 in order to more accurately correct the license plate image. can

This is because the position or direction of the vehicle when the image correction data is calculated may be slightly different from the position or direction of the vehicle at the time of photographing.

The aspect ratio correction unit 132 may correct the loaded image correction data based on the aspect ratio of the license plate image obtained through shooting. In this case, the aspect ratio reference value may be stored in the database unit D. The aspect ratio reference value may be an aspect ratio of the license plate image calculated in advance for each position of the license plate image in the photographed image.

Specifically, the aspect ratio correction unit 132 may correct the image correction data based on the difference between the aspect ratio reference value corresponding to the position data and the aspect ratio of the license plate image. A specific example in which aspect ratio correction is performed will be described in detail with reference to FIG. 8 .

The photographing direction corrector 133 may correct the image correction data based on an angle between the photographing direction of the vehicle image obtaining unit 110 and the direction of the approach road in which the photographing target vehicle is located.

This is because the vehicle image acquisition unit 110 may be installed at an angle to the vehicle access road. For example, the photographing direction correcting unit 133 may add or subtract an angle between the photographing direction of the vehicle image obtaining unit 110 and the direction of the approach road in which the photographing target vehicle is located to the second corrected value of the image correction data by adding or subtracting the second correction value. can be corrected. A specific example in which the photographing direction correction is performed will be described in detail with reference to FIG. 9 .

The ground height corrector 134 may correct the position data using a height difference value between the ground at the location where the vehicle image obtaining unit 110 is installed and the ground at the photographing location.

This is because, when the ground height of the location where the vehicle image acquisition unit 110 is installed and the ground height of the preset shooting location are different from each other, the photographing angle of the license plate may be different even if the center point of the license plate is the same. A specific example in which the ground height correction is made will be described in detail with reference to FIG. 10 .

And, the correction value generator 130 may select the final corrected image correction data as the license plate image correction value.

The license plate image correction unit 140 may correct the license plate image using the license plate image correction value.

The license plate image correcting unit 140 may include a scale correcting unit 141 and a rotation correcting unit 142 .

The scale correction unit 141 may correct the scale (Scale) of the license plate image by using the first correction value. For example, the scale correction unit 141 may increase or decrease the number plate image in the left and right or up and down directions. And the rotation correction unit 142 may use the second correction value to correct the rotation of the license plate image.

5 is a diagram illustrating an example of a photographed image acquired by the vehicle image acquisition unit 110 according to an embodiment of the present invention.

5 illustrates that the first to third vehicles C1, C2, and C3 are included in one photographed image to explain examples of photographed images photographed in different environments (locations).

As shown in FIG. 5 , the position and shape of the license plate of the photographed vehicle may vary depending on the relative position of the vehicle and the vehicle image acquisition unit 110 . That is, the position and shape of the license plate may vary depending on the distance between the vehicle and the vehicle image acquisition unit 110 and the shooting direction.

For example, when the ground of the photographing location is located to the northwest compared to the ground of the installation location of the vehicle image acquisition unit 110, a license plate image P1 such as the first vehicle C1 may be obtained.

For example, when the ground of the vehicle image acquisition unit 110 installation location is located in front of the photographing location ground, the same license plate image P2 as the second vehicle C2 may be obtained.

For example, when the ground of the photographing location is located in the southeast of the vehicle image acquisition unit 110 compared to the ground of the installation location, a license plate image P3 such as the third vehicle C3 may be obtained.

6 is a view showing the standardized shape of the license plate image of each zone in the photographed image according to an embodiment of the present invention. And, FIG. 7 is a diagram for explaining a pre-calculated image correction data table for each area of a photographed image according to an embodiment of the present invention.

6 and 7, it is assumed that the photographed image is divided into 15 areas of 5 columns and 3 rows, and image correction data is allocated to each area.

The license plate image shown in each zone in the photographed image of FIG. 6 represents the shape of the license plate image estimated when the license plate is photographed in the corresponding zone. Since the vehicle access path viewed by the license plate image processing device 100 is fixed, the shape of the license plate image photographed in each area can be estimated.

For example, since the license plate of the first vehicle C1 of FIG. 5 is located in the first area A1, it may be estimated to have the first license plate image shape S1. In addition, the image correction data loading unit 131 may load image correction data corresponding to the first area A1 from the database unit D. As shown in FIG. Referring to FIG. 7 , a first correction value ALP_RATIO1 and a second correction value ALP_ANGLE1 are stored in the first area A1 as image correction data.

In this case, the first correction value (ALP_RATIO1) and the second correction value (ALP_ANGLE1) of the first area (A1) may be a correction value for converting the first license plate image shape (S1) into a preset license plate image shape. Here, the preset license plate image shape may be a shape when the license plate is photographed from the front, that is, the standard shape of the license plate.

According to the same principle, since the license plate of the second vehicle C2 is located in the second area A2, it can be estimated to have the shape S2 of the second license plate image. And the image correction data load unit 131 is a first correction value (ALP_RATIO8) and a second correction value (ALT_ANGLE8) of the image correction data corresponding to the second area (A2) to correct the license plate image of the second vehicle (C2) ) can be loaded from the database unit (D).

Also, since the license plate of the third vehicle C3 is located in the third area A3, it can be estimated to have the shape S3 of the third license plate image. And the image correction data loading unit 131 is a first correction value (ALP_RATIO15) and a second correction value (ALT_ANGLE15) of the image correction data corresponding to the third area (A3) to correct the license plate image of the third vehicle (C3) ) can be loaded from the database unit (D).

According to this, the license plate image processing apparatus 100 can estimate the shape of the license plate image without a process of extracting an outline using a complex operation such as a generalized Hough transform. That is, the license plate image processing apparatus 100 can correct the image of the license plate taken obliquely to its original form even with a small amount of computation.

8 is a view for explaining an example in which the aspect ratio corrector 132 corrects image correction data according to an embodiment of the present invention. The license plate image of FIG. 8 is a license plate image of the fourth vehicle (not shown) taken in the fourth area A4. In this case, the license plate image of the fourth vehicle may have a slightly different aspect ratio from the fourth license plate image shape S4 of the fourth area A4. This is because, as described above, the vehicle position or direction when the image correction data is calculated may be slightly different from the vehicle position or direction at the time of photographing.

For this correction, the database unit (D) may further store the pre-calculated aspect ratio reference value for each position of the license plate image in the photographed image. Of course, the aspect ratio reference value may be calculated in advance for each zone.

And the aspect ratio correction unit 132 may correct the image correction data based on the difference between the aspect ratio reference value corresponding to the position data and the aspect ratio of the license plate image (eg, P4w / P4h). In detail, the aspect ratio corrector 132 may correct at least one of a first correction value and a second correction value included in the image correction data.

According to this, since the image correction data is corrected based on the aspect ratio of the photographed license plate image, the photographed license plate image can be corrected to be more similar to the license plate standard shape.

9 is a view for explaining an example in which the photographing direction correcting unit 133 corrects image correction data according to an embodiment of the present invention.

As shown in FIG. 9 , when the photographing direction W1 of the vehicle image obtaining unit 110 and the vehicle access road direction W2 are oblique, the photographing direction correcting unit 133 is configured to The image correction data may be corrected based on the angle T between the photographing direction and the direction of the approach road in which the vehicle is located at the time of photographing. In this case, the corrected image correction data may be a second correction value.

For example, the photographing direction correcting unit 133 adds or subtracts an angle between the photographing direction W1 of the vehicle image obtaining unit 110 and the direction W2 of the access road in which the photographing target vehicle is located to the second correction value of the image correction data. In this way, the second correction value may be corrected. In this case, it goes without saying that the direction W2 of the approach road where the vehicle is located may be replaced with the front direction of the vehicle 1 .

For example, the angle T between the photographing direction of the vehicle image acquisition unit 110 and the direction of the access road in which the vehicle 1 to be photographed is located is measured when the license plate image processing device 100 is installed, and the photographing direction correcting unit 133 It can be the value entered in .

According to this, even if the vehicle image acquisition unit 110 is installed to photograph the license plate at an angle, the photographed license plate image may be corrected similarly to the license plate standard shape.

10 is a view for explaining an example in which the ground height corrector 134 corrects position data according to an embodiment of the present invention.

As shown in FIG. 10 , the ground height of the location where the vehicle image acquisition unit 110 is installed and the ground height of the photographing location may be different from each other. In this case, the photographing position means a position where the photographing of the license plate is made. Such a photographing position may be predetermined according to the focus or photographing performance of the vehicle image acquisition unit 110 .

FIG. 10A is a diagram illustrating a case in which the ground of the photographing location is higher than the ground of the location where the vehicle image acquisition unit 110 is installed. In (a) of FIG. 10 , the photographing position is R1, and the height difference between the ground of the position where the vehicle image acquisition unit 110 is installed and the ground of the R1 position is H1.

In addition, the ground height corrector 134 may correct the position data based on the H1 value. For example, when the position data is two-dimensional coordinate data having a horizontal axis value and a vertical axis value, the ground height corrector 134 may correct a vertical axis value of the position data.

Meanwhile, FIG. 10B is a diagram illustrating a case in which the ground height of the photographing position R2 is the same as the ground height of the location where the vehicle image acquisition unit 110 is installed. In this case, the ground height correction unit 134 may omit correction of the position data.

FIG. 10C is a diagram illustrating a case where the ground of the photographing location is lower than the ground of the location where the vehicle image acquisition unit 110 is installed. In (c) of FIG. 10 , the photographing position is R3, and the height difference between the ground of the position where the vehicle image acquisition unit 110 is installed and the ground of the R3 position is H3.

In addition, the ground height corrector 134 may correct the position data based on the H3 value in the same principle as in FIG. 10A .

On the other hand, the ground height corrector 134 may further correct the position data using the inclination angle data of the photographing location ground. This is because even if the height of the ground in front of the vehicle where the license plate is located is the same as the height of the ground in which the vehicle image acquisition unit 110 is installed, the height of the ground in which the rear of the vehicle is located may be different.

11 is a flowchart illustrating a license plate image correction method using the license plate image processing apparatus 100 according to an embodiment of the present invention.

First, the license plate image processing apparatus 100 may capture a vehicle to obtain a photographed image including the vehicle, and detect a license plate image from the photographed image. (S200)

And the license plate image processing apparatus 100 may generate position data indicating the position of the license plate image in the photographed image. (S210)

And the license plate image processing apparatus 100 may load the image correction data corresponding to the position data from the database unit (D), and generate a license plate image correction value based on the loaded image correction data. (S220)

And the license plate image processing apparatus 100 may correct the license plate image using the license plate image correction value. (S230)

In step S230, the license plate image may be rotationally corrected based on the second correction value, and then the scale may be corrected based on the first correction value.

12 is a diagram illustrating detailed steps of step S220 according to an embodiment of the present invention.

12 , step S220 may include correcting location data based on a height difference between the ground at the location where the vehicle image obtaining unit 110 is installed and the ground at the predetermined photographing location. (S221)

For example, when the position data is two-dimensional coordinate data having a horizontal axis value and a vertical axis value, the position data may be corrected through the following [Equation 1].

[Formula 1]

In [Equation 1], Center X % width may be a value indicating the position of the horizontal axis of the center point of the license plate image in the photographed image. Center Y % height may be a value indicating the position of the vertical axis of the center point of the license plate image in the photographed image.

For example, if the photographed image is divided into 5 columns and 3 rows as shown in FIG. 5, if the horizontal axis position of the license plate image center point is within 0 to 20%, and the vertical axis position is within 66.6 to 100%, ALP_Ratio[Center X% width][Center Y % height] may be a first correction value of image correction data corresponding to the first area A1.

At this time, when the Enterance Height Diff is calculated as a negative number due to the height difference between the ground at the location where the vehicle image acquisition unit 110 is installed and the ground at the predetermined shooting location, ALP_Ratio[Center X% width][(Center Y + Entrance Height Diff)% height] may be a first correction value of image correction data corresponding to a region located below the first region A1.

And the Alpha value may be a correction ratio coefficient preset according to the installation location of the license plate image processing device 100 . W_H_Ratio may be the aspect ratio of the license plate image extracted from the photographed image. If W_H_Ratio is calculated as a negative value, the Alpha value may be set as a negative value.

Meanwhile, the predetermined photographing location may be a predetermined location according to the focus or photographing performance of the vehicle image acquisition unit 110 . Also, if the Entrance Height Diff is 0, that is, if there is no height difference between the respective surfaces, step S221 may be omitted.

Next, the step of loading image correction data corresponding to the position data from the database unit (D) may be performed. (S222)

And the step of correcting the image correction data based on the difference between the aspect ratio reference value and the aspect ratio of the license plate image corresponding to the position data may be performed. (S223)

For example, the image correction data may include a first correction value for scale correction of the license plate image, and a second correction value for rotation correction of the license plate image. In addition, at least one of the first correction value and the second correction value may be corrected in step S223.

For example, in the image correction data, a first correction value may be corrected through [Equation 2] below, and a second correction value may be corrected through [Equation 3].

[Formula 2]

In [Equation 2], Center X % width may be a value indicating the position of the horizontal axis of the center point of the license plate image in the photographed image. Center Y % height may be a value indicating the position of the vertical axis of the center point of the license plate image in the photographed image.

For example, if the photographed image is divided into 5 columns and 3 rows as shown in FIG. 5, if the horizontal axis position of the license plate image center point is within 0 to 20%, and the vertical axis position is within 66.6 to 100%, ALP_Ratio[Center X% width][Center Y % height] may be a first correction value of image correction data corresponding to the first area A1. And the Alpha value may be a correction ratio coefficient preset according to the installation location of the license plate image processing apparatus 100. W_H_Ratio may be the aspect ratio of the license plate image extracted from the photographed image. If W_H_Ratio is calculated as a negative value, the Alpha value may be set as a negative value.

[Formula 3]

In [Equation 3], Center X % width may be a value indicating the position of the horizontal axis of the center point of the license plate image in the photographed image. Center Y % height may be a value indicating the position of the vertical axis of the center point of the license plate image in the photographed image.

For example, if the photographed image is divided into 5 columns and 3 rows as shown in FIG. 5, if the horizontal axis position of the license plate image center point is within 0 to 20%, and the vertical axis position is within 66.6 to 100%, ALP_Angle[Center X% width][Center Y % height] may be a second correction value of image correction data corresponding to the first area A1. And the Beta value may be a correction ratio coefficient preset according to the installation location of the license plate image processing apparatus 100. W_H_Ratio may be the aspect ratio of the license plate image extracted from the photographed image. If W_H_Ratio is calculated as a negative value, the Beta value may be set as a negative value.

In addition, a step of correcting the image correction data may be performed based on the angle between the photographing direction of the vehicle image acquisition unit 110 and the direction of the approach road in which the vehicle to be photographed is located. (S224)

For example, in the image correction data, the second correction value may be corrected through the following [Equation 4].

[Formula 4]

[Equation 4] is different from [Equation 3] in that the second correction value is corrected using LP_CAR_Photo_Angle, which indicates the angle between the photographing direction of the vehicle image acquisition unit 110 and the direction of the approach road where the vehicle to be photographed is located.

The description of the present invention described above is for illustration, and those of ordinary skill in the art to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a dispersed form, and likewise components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the following claims, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be construed as being included in the scope of the present invention.

1: vehicle 100: license plate image processing device
110: vehicle image acquisition unit 120: license plate detection unit
121: license plate image detection unit 122: license plate position determination unit
130: correction value generating unit 131: image correction data loading unit
132: aspect ratio correcting unit 133: shooting direction correcting unit
134: ground height correction unit D: database unit
140: license plate image correction unit 141: scale correction unit
142: rotation compensation unit

Claims (16)

a vehicle image acquisition unit for photographing a vehicle and acquiring a photographed image including the vehicle;
a license plate detection unit for detecting the license plate image of the vehicle from the photographed image, and generating position data for the position of the license plate image in the photographed image;
a database unit storing image correction data calculated in advance for each position of the license plate image in the photographed image;
a correction value generating unit for loading the image correction data corresponding to the position data from the database unit, and generating a license plate image correction value based on the loaded image correction data; and
Comprising a license plate image correction unit for correcting the license plate image based on the license plate image correction value,
The photographed image is divided into a plurality of zones,
The image correction data is calculated in advance for each zone and stored in the database unit,
The correction value generating unit is a license plate image processing device for vehicle number recognition that loads the image correction data corresponding to the region to which the location data belongs.
delete The method of claim 1,
The image correction data is a license plate image processing apparatus for vehicle number recognition that includes a first correction value for correcting the scale of the license plate image, and a second correction value for rotating the license plate image.
4. The method of claim 3,
The database unit further stores an aspect ratio reference value calculated in advance for each position of the license plate image in the photographed image,
The correction value generator corrects at least one of the first correction value and the second correction value based on a difference between the aspect ratio reference value corresponding to the location data and the aspect ratio of the license plate image for vehicle number recognition License plate image processing unit.
4. The method of claim 3,
The vehicle image acquisition unit photographs the vehicle on a predetermined shooting location,
The correction value generating unit corrects the position data based on a difference in height between the ground at the location where the vehicle image obtaining unit is installed and the ground at the predetermined photographing location,
The license plate image processing device for vehicle number recognition that the correction value generating unit will load the image correction data corresponding to the corrected position data.
6. The method of claim 5,
The correction value generating unit license plate image processing device that further corrects the position data by using the inclination angle data of the ground of the predetermined shooting position.
6. The method of claim 5,
The position data consists of two-dimensional coordinate data including a horizontal axis value and a vertical axis value,
The license plate image processing device for vehicle number recognition that the correction value generating unit corrects the vertical axis value of the position data based on the height difference.
4. The method of claim 3,
The second correction value is a license plate image processing apparatus for vehicle number recognition that is corrected based on an angle between the photographing direction of the vehicle image acquisition unit and the direction of the access road in which the vehicle is located during the photographing.
4. The method of claim 3,
The license plate image correcting unit rotationally corrects the license plate image based on the second correction value, and then corrects the scale of the license plate image based on the first correction value. License plate image processing device for vehicle number recognition.
a) acquiring a photographed image including the vehicle by photographing the vehicle, and detecting a license plate image from the photographed image;
b) generating position data for the position of the license plate image in the photographed image;
c) load the image correction data corresponding to the position data from the database unit in which image correction data calculated in advance for each position of the license plate image in the photographed image is stored, and a license plate image correction value based on the loaded image correction data creating a; and
d) correcting the license plate image based on the license plate image correction value;
The photographed image is divided into a plurality of zones,
The image correction data is calculated in advance for each zone and stored in the database unit,
Step c) is
A license plate image correction method for vehicle number recognition that loads the image correction data corresponding to the zone to which the location data belongs from the database unit.
delete 11. The method of claim 10,
The database unit further stores an aspect ratio reference value calculated in advance for each position of the license plate image in the photographed image,
Step c) is
loading image correction data corresponding to the position data from a database unit; and
A license plate image correction method for vehicle number recognition comprising the step of correcting image correction data based on a difference between the aspect ratio reference value corresponding to the position data and the aspect ratio of the license plate image.
11. The method of claim 10,
The photographed image is obtained using a vehicle image acquisition unit for photographing the vehicle,
Step c) is
loading image correction data corresponding to the position data from a database unit; and
A license plate image correction method for vehicle number recognition comprising correcting the image correction data based on the angle between the photographing direction of the vehicle image acquisition unit and the direction of the access road where the vehicle is located.
11. The method of claim 10,
The photographed image is obtained using a vehicle image acquisition unit for photographing the vehicle,
between steps b) and c)
The license plate image correction method for vehicle number recognition further comprising the step of correcting the position data based on the difference in height between the ground at the location where the vehicle image acquisition unit is installed and the ground at the predetermined shooting location.
15. The method of claim 14,
The position data is a license plate image correction method for vehicle number recognition that is further corrected based on the inclination angle data of the ground of the predetermined shooting position.
11. The method of claim 10,
The image correction data includes a first correction value for correcting the scale of the license plate image, and a second correction value for rotating the license plate image,
Step d) is
After rotating the license plate image based on the second correction value, correcting the scale of the license plate image based on the first correction value, the license plate image correction method for vehicle number recognition.

Images