License Plate Image Processing Apparatus for Automobile Registration Number Recognition and License Plate Image Correction Method Using the Same

Abstract

Provided is a license plate image processing device for recognizing automobile registration numbers, comprising: a vehicle image acquisition unit that images a vehicle and acquires an image including the vehicle; a license plate detection unit that detects an image of the vehicle's license plate from the captured image and generates position data for the position of the image of the license plate in the captured image; a database unit that stores image correction data calculated in advance for each position of the image of the license plate in the captured image; a correction value generation unit that loads the image correction data corresponding to the position data from the database unit and generates an image correction value for the license plate based on the loaded image correction data; and a license plate image correction unit that corrects the image of the license plate based on the image correction value for the license plate.

Description

Technical Field

[0001] The present invention relates to a license plate image processing apparatus for recognizing a vehicle registration number and a license plate image correction method using the same. More specifically, the present invention relates to a license plate image processing apparatus for recognizing a vehicle registration number that can correct an image of a license plate imaged obliquely into its original shape with a relatively small amount of computation, and a license plate image correction method using the same.

Background Art

[0002] With the development of image recognition technology, it has become possible to automatically recognize a vehicle registration number using an image of a vehicle license plate. Currently, most vehicle access control systems adopt such a method.

[0003] An image of a license plate is obtained by imaging a vehicle using an imaging device installed at an entrance or exit of a place where vehicle access control is required, such as a parking lot. The recognition of a vehicle registration number is composed of a combination of steps of identifying a license plate from an imaged image, verifying the license plate, separating symbols (letters, numbers, symbols), and recognizing symbols, which is implemented by software and performed in a computer system.

[0004] FIG. 1 is a diagram showing a conventional license plate identification process for recognizing a vehicle registration number, and the identification of a license plate is performed by detecting the contour line of the license plate.

[0005] First, an incoming vehicle or an outgoing vehicle is imaged by a camera provided at the entrance or exit of a parking lot (step S11), and then the contour line of the license plate image included in the imaged vehicle image is extracted to finally obtain the license plate image. (Step S12)

[0006] On the one hand, the imaging device can be installed obliquely from the vehicle's approaching direction, or when the vehicle enters obliquely at the entrance or exit, the license plate of the vehicle can be imaged obliquely.

[0007] As shown in FIG. 1, the obliquely imaged license plate may have an aspect ratio different from the ratio of the general license plate standard, and has a shape rotated by a predetermined angle compared with the image of the license plate imaged from the front.

[0008] The image of such an oblique license plate is corrected to the original form of the license plate for accurate recognition of the vehicle registration number. However, in order to perform accurate correction, the contour line of the license plate must be accurately extracted.

[0009] At this time, the extraction of the contour of the license plate is performed by the Generalized Hough Transform. However, since this method calculates depending on pixels, it requires a high amount of computation.

[0010] However, the vehicle registration number recognition device installed at the entrance or exit has a problem that it is difficult to perform work with a high amount of computation because of the constraints on the processing capacity due to the installation location and the specifications of the device. In particular, when the quality of the vehicle image obtained due to problems such as focus is poor, the number of pixels forming the boundary of the license plate in the image decreases, and there is a problem that it becomes more difficult to accurately extract the contour line of the license plate.

Summary of the Invention

Problems to be Solved by the Invention

[0011] In order to solve the above problems, the technical problem to be solved by the present invention is to provide a license plate image processing device for recognizing a vehicle registration number and a license plate image correction method using the same, which can correct the image of the obliquely imaged license plate to the original shape with a relatively small amount of computation.

[0012] The technical problems to be achieved by the present invention are not limited to the technical problems mentioned above. Other technical problems not mentioned will be clearly understood by those with ordinary knowledge in the technical field to which the present invention pertains from the following description.

Means for Solving the Problems

[0013] In order to achieve the above technical problems, an embodiment of the present invention provides a license plate image processing apparatus for recognizing a vehicle registration number, including: a vehicle image acquisition unit that captures a vehicle to acquire a captured image including the vehicle; a license plate detection unit that detects an image of the license plate of the vehicle from the captured image and generates position data for the position of the license plate image in the captured image; a database unit in which image correction data calculated in advance for each position of the license plate image in the captured image is stored; a correction value generation unit that loads the image correction data corresponding to the position data from the database unit and generates an image correction value for the license plate based on the loaded image correction data; and a license plate image correction unit that corrects the license plate image based on the image correction value of the license plate.

[0014] The captured image is divided into a plurality of areas, the image correction data is calculated in advance for each area and stored in the database unit, and the correction value generation unit can load the image correction data corresponding to the area to which the position data belongs.

[0015] The image correction data can include a first correction value for correcting the scale of the license plate image and a second correction value for rotation correction of the license plate image.

[0016] The database unit further stores a reference value of the aspect ratio calculated in advance for each position of the license plate image in the captured image, and the correction value generation unit can correct at least one of the first correction value and the second correction value based on the difference between the reference value of the aspect ratio corresponding to the position data and the aspect ratio of the license plate image.

[0017] The vehicle image acquisition unit captures the vehicle at a predetermined imaging position, and the correction value generation unit corrects the position data based on the height difference between the ground at the position where the vehicle image acquisition unit is installed and the ground at the predetermined imaging position, and the correction value generation unit can load the image correction data corresponding to the corrected position data.

[0018] The correction value generation unit can further correct the position data using the ground inclination angle data at the predetermined imaging position.

[0019] The position data consists of two-dimensional coordinate data including a horizontal axis value and a vertical axis value, and the correction value generation unit can correct the vertical axis value of the position data based on the height difference.

[0020] The second correction value can be corrected based on the angle between the imaging direction of the vehicle image acquisition unit and the direction of the approach road where the vehicle was located at the time of imaging.

[0021] The license plate image correction unit can correct the scale of the license plate image based on the first correction value after rotation-correcting the license plate image based on the second correction value.

[0022] In order to achieve the above technical problem, an embodiment of the present invention provides a method for correcting a license plate image for recognizing a vehicle registration number, including: a) capturing an image of a vehicle to obtain a captured image including the vehicle, and detecting an image of a license plate from the captured image; b) generating position data for the position of the license plate image in the captured image; c) loading, from a database unit storing pre-calculated image correction data for each position of the license plate image in the captured image, the image correction data corresponding to the position data, and generating an image correction value for the license plate image based on the loaded image correction data; and d) correcting the license plate image based on the image correction value of the license plate image.

[0023] The captured image is divided into a plurality of regions, the image correction data is pre-calculated for each region and stored in the database unit, and in step c), the image correction data corresponding to the region to which the position data belongs can be loaded from the database unit.

[0024] The database unit further stores a reference value of an aspect ratio pre-calculated for each position of the license plate image in the captured image, and step c) can include: loading the image correction data corresponding to the position data from the database unit; and correcting the image correction data based on the difference between the reference value of the aspect ratio corresponding to the position data and the aspect ratio of the license plate image.

[0025] Step c) can include: loading the image correction data corresponding to the position data from the database unit; and correcting the image correction data based on the angle between the imaging direction of the vehicle image acquisition unit and the direction of the access road where the vehicle is located.

[0026] The captured image is acquired using a vehicle image acquisition unit that captures the vehicle, and between the step (b) and the step (c), a step of correcting the position data based on the height difference between the ground at the position where the vehicle image acquisition unit is installed and the ground at a predetermined imaging position can be further included.

[0027] The position data can be further corrected based on the inclination angle data of the ground at a predetermined imaging position.

[0028] The image correction data includes a first correction value for correcting the scale of the image of the license plate and a second correction value for rotationally correcting the image of the license plate. In the step (d), after rotationally correcting the image of the license plate based on the second correction value, the scale of the image of the license plate can be corrected based on the first correction value.

Advantages of the Invention

[0029] According to an embodiment of the present invention, the license plate image processing device can correct the image of the license plate using the image correction data calculated in advance for each position of the image of the license plate in the captured image. That is, the license plate image processing device can estimate the shape of the image of the license plate without going through a process of extracting the contour line using a complex operation such as the Generalized Hough Transform. Therefore, the license plate image processing device can correct the image of the license plate captured obliquely to the shape of the original license plate with a relatively small amount of computation.

[0030] Also, according to an embodiment of the present invention, the license plate image processing apparatus can store a reference value of the aspect ratio for each area of the captured image. Then, the license plate image processing apparatus corrects the image correction data based on the difference between the reference value of the aspect ratio of the area where the image of the captured license plate is located and the aspect ratio of the image of the captured license plate. Therefore, the image of the captured license plate can be corrected to be more similar to the standard shape of the license plate.

[0031] Also, according to an embodiment of the present invention, the license plate image processing apparatus corrects the image correction data based on the angle between the imaging direction of the vehicle image acquisition unit and the direction of the approach road where the vehicle to be imaged is located. Therefore, the correction of the license plate image can be accurately performed.

[0032] Also, according to an embodiment of the present invention, the license plate image processing apparatus corrects the position data based on the height difference between the ground at the position where the vehicle image acquisition unit is installed and the ground at a predetermined imaging position. Therefore, the correction of the license plate image can be accurately performed.

[0033] 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 at a predetermined imaging position. Therefore, the correction of the license plate image can be performed more accurately.

[0034] The effects of the present invention are not limited to the above-described effects, but include all effects that can be inferred from the configuration of the invention described in the description or claims of the present invention.

Brief Description of the Drawings

[0035]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Embodiments for Carrying Out the Invention

[0036] Hereinafter, the present invention will be described with reference to the accompanying drawings. However, the present invention can be embodied in various different forms, and thus is not limited to the embodiments described herein. And in the drawings, in order to clearly explain the present invention, parts not related to the explanation are omitted, and the same parts throughout the specification are denoted by the same reference numerals.

[0037] Throughout the specification, when a part is "connected (joined, in contact with, coupled)" to another part, this includes not only the case where it is "directly connected", but also the case where it is "indirectly connected" with other members intervening therebetween. Also, when a part "includes" a certain component, this means that, unless otherwise stated to the contrary, it does not exclude other components, and it can further include other components.

[0038] The terms used in this specification are merely used to describe specific embodiments and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates a different meaning. In this specification, terms such as "include" or "comprise" mean that the features, numbers, steps, operations, components, parts, or combinations thereof described in the specification exist, and do not preclude the existence or addition possibility of one or more other features, numbers, steps, operations, components, parts, or combinations thereof in advance.

[0039] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0040] FIG. 2 is a block diagram schematically showing a license plate image processing apparatus 100 according to an embodiment of the present invention. And FIG. 3 is a diagram for explaining an example of an image of a license plate taken obliquely.

[0041] As shown in FIG. 2, the license plate image processing apparatus 100 can include a vehicle image acquisition unit 110, a license plate detection unit 120, a correction value generation unit 130, a license plate image correction unit 140, and a database unit D.

[0042] The vehicle image acquisition unit 110 can image the vehicle 1 and acquire a captured image including the vehicle 1. For example, the vehicle image acquisition unit 110 may be a camera installed at the entrance and exit of a place where vehicle access control is required.

[0043] The license plate detection unit 120 can detect an image of the license plate of the vehicle 1 from the captured image. At this time, the license plate can be imaged obliquely as shown in FIG. 3a. In order to accurately recognize the vehicle registration number from the image of the license plate, the obliquely imaged license plate image Pa can be corrected to the license plate image Pb having the original shape as shown in FIG. 3b. For this purpose, the license plate detection unit 120 can generate position data for the position of the license plate image in the captured image. Specific examples of the utilization of the position data will be described in detail later with reference to FIGS. 5 to 7.

[0044] The database unit D can store image correction data calculated in advance for each position of the license plate image in the captured image. The image correction data can be used for correcting the license plate image.

[0045] The correction value generation unit 130 can load the image correction data corresponding to the position data from the database unit D. That is, the correction value generation unit 130 can load different image correction data according to the position of the license plate image in the captured image. Then, the correction value generation unit 130 can generate an image correction value for the license plate based on the loaded image correction data.

[0046] Then, the license plate image correction unit 140 can correct the license plate image using the image correction value of the license plate.

[0047] In FIG. 2, the case where each component of the license plate image processing apparatus 100 is integrated and installed at the entrance and exit of a place where vehicle access control is required is described as an example. However, each component of the license plate image processing apparatus 100 may be installed at different positions from each other. For example, the vehicle image acquisition unit 110 is installed at the entrance and exit of the vehicle 1, and the other components may be provided at another location or mounted on an external server to communicate with the vehicle image acquisition unit 110.

[0048] FIG. 4 is a detailed block diagram showing a license plate image processing apparatus 100 according to an embodiment of the present invention.

[0049] As shown in FIG. 4, the license plate detection unit 120 can receive a captured image from the vehicle image acquisition unit 110. The captured image may be an image including a vehicle.

[0050] The license plate detection unit 120 can include a license plate image detection unit 121 and a license plate position determination unit 122.

[0051] The license plate image detection unit 121 can detect an image of a license plate in the captured image. That is, the license plate image detection unit 121 can generate an image of the license plate.

[0052] The license plate position determination unit 122 can generate position data indicating the position of the license plate image in the captured image. The position data may be two-dimensional coordinate data with a specific position in the captured image as a reference point. The position data can have a horizontal axis value and a vertical axis value. The position data may be in polar coordinates. The position data may be the coordinates of the center point of the license plate image. For example, the center point can be the center of gravity of the license plate image.

[0053] On the other hand, the position data may be data indicating a specific area in the captured image.

[0054] Specifically, the captured image can be divided into a plurality of areas. Then, the license plate position determination unit 122 can determine which area the position of the license plate image (for example, the position of the center point of the license plate image) belongs to. And the license plate position determination unit 122 can generate information of the area as the position data.

[0055] Then, the license plate detection unit 120 can transmit the image and position data of the license plate to the correction value generation unit 130.

[0056] The correction value generation unit 130 can generate the image correction value of the license plate necessary for correcting the image of the license plate.

[0057] The correction value generation unit 130 can include an image correction data loading unit 131, an aspect ratio correction unit 132, an imaging direction correction unit 133, and a ground height correction unit 134.

[0058] The image correction data loading unit 131 can load the image correction data corresponding to the position data from the database unit D.

[0059] At this time, the database unit D may be in a state where the image correction data calculated in advance for each position of the license plate image in the captured image is stored. For example, the image correction data can 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 area of the captured image.

[0060] Then, the correction value generation unit 130 can select the loaded image correction data as the license plate image correction value.

[0061] On the other hand, in order to correct the license plate image more accurately, the correction value generation unit 130 can correct the loaded image correction data using the aspect ratio correction unit 132, the imaging direction correction unit 133, and the ground height correction unit 134.

[0062] This is because the position or direction of the vehicle at the time of calculating the image correction data can be slightly different from the position or direction of the vehicle at the time of imaging.

[0063] The aspect ratio correction unit 132 can correct the image correction data loaded based on the aspect ratio of the license plate image obtained by imaging. At this time, the database unit D may store the reference value of the aspect ratio. The reference value of the aspect ratio may be the aspect ratio of the license plate image calculated in advance for each position of the license plate image in the captured image.

[0064] Specifically, the aspect ratio correction unit 132 can correct the image correction data based on the difference between the reference value of the aspect ratio corresponding to the position data and the aspect ratio of the license plate image. A specific example of aspect ratio correction will be described in detail later with reference to FIG. 8.

[0065] The imaging direction correction unit 133 can correct the image correction data based on the angle between the imaging direction of the vehicle image acquisition unit 110 and the direction of the approach road where the vehicle to be imaged is located.

[0066] This is because the vehicle image acquisition unit 110 may be installed at an oblique position with respect to the vehicle approach road. For example, the imaging direction correction unit 133 can correct the second correction value of the image correction data by adding or subtracting the angle between the imaging direction of the vehicle image acquisition unit 110 and the direction of the approach road where the vehicle to be imaged is located. A specific example of imaging direction correction will be described in detail later with reference to FIG. 9.

[0067] The ground height correction unit 134 can correct the position data using the height difference between the ground at the position where the vehicle image acquisition unit 110 is installed and the ground at the imaging position.

[0068] This is because when the height of the ground at the position where the vehicle image acquisition unit 110 is installed is different from the height of the ground at the preset imaging position, even if the position of the center point of the license plate is the same, the imaging angle of the license plate may be different. A specific example of ground height correction will be described in detail later with reference to FIG. 10.

[0069] Then, the correction value generation unit 130 can select the finally corrected image correction data as the image correction value of the license plate.

[0070] The license plate image correction unit 140 can correct the image of the license plate by using the image correction value of the license plate.

[0071] The license plate image correction unit 140 can include a scale correction unit 141 and a rotation correction unit 142.

[0072] The scale correction unit 141 can correct the scale of the license plate image by using the first correction value. For example, the scale correction unit 141 can stretch or shrink the license plate image in the left - right or up - down direction. And the rotation correction unit 142 can correct the rotation of the license plate image by using the second correction value.

[0073] FIG. 5 is a diagram showing an example of a captured image acquired by the vehicle image acquisition unit 110 according to an embodiment of the present invention.

[0074] FIG. 5 shows an example of a captured image including first to third vehicles C1, C2, and C3 in one captured image in order to explain examples of captured images captured in different environments (positions).

[0075] As shown in FIG. 5, the position and shape of the license plate of the captured vehicle can vary depending on the relative position between the vehicle and the image acquisition unit 110. That is, the position and shape of the license plate can vary depending on the distance and the imaging direction between the vehicle and the vehicle image acquisition unit 110.

[0076] For example, when the ground at the imaging position is located on the northwest side compared to the ground at the installation position of the vehicle image acquisition unit 110, an image P1 of a license plate such as that of the first vehicle C1 can be obtained.

[0077] For example, when the ground at the installation position of the vehicle image acquisition unit 110 is located in front of the ground at the imaging position, an image P2 of a license plate such as the second vehicle C2 can be obtained.

[0078] For example, when the ground at the imaging position is located on the southeast side compared to the ground at the installation position of the vehicle image acquisition unit 110, an image P3 of a license plate such as the third vehicle C3 can be obtained.

[0079] FIG. 6 is a diagram showing the shapes of license plate images in each area of the captured image according to an embodiment of the present invention in a fixed form. And FIG. 7 is a diagram for explaining an image correction data table calculated in advance for each area of the captured image according to an embodiment of the present invention.

[0080] In the embodiments of FIGS. 6 and 7, it is assumed that the captured image is divided into 15 areas of 5 columns × 3 rows, and image correction data is assigned to each area.

[0081] The license plate images shown in each area in the captured image of FIG. 6 show the shapes of the license plate images estimated when the license plate is imaged in that area. Since the vehicle access road that the license plate image processing apparatus 100 is looking at is fixed, the shapes of the license plate images imaged in each area can be estimated.

[0082] For example, since the license plate of the first vehicle C1 in FIG. 5 is located in the first area A1, it can be estimated that it has the shape S1 of the first license plate image. And the image correction data loading unit 131 can load the image correction data corresponding to the first area A1 from the database unit D. Referring to FIG. 7, the first correction value ALP_RATIO1 and the second correction value ALP_ANGLE1 are stored as image correction data in the first area A1.

[0083] At this time, the first correction value ALP_RATIO1 and the second correction value ALP_ANGLE1 in the first area A1 can be correction values for converting the shape S1 of the image of the first license plate into the shape of the image of the already set license plate. Here, the shape of the image of the already set license plate can be the shape when the license plate is imaged from the front, that is, the standard shape of the license plate.

[0084] Based on the same principle, since the license plate of the second vehicle C2 is located in the second area A2, it can be estimated that it has the shape S2 of the image of the second license plate. Then, the image correction data loading unit 131 can load the first correction value ALP_RATIO8 and the second correction value ALT_ANGLE8 of the image correction data corresponding to the second area A2 from the database unit D in order to correct the image of the license plate of the second vehicle C2.

[0085] Also, since the license plate of the third vehicle C3 is located in the third area A3, it can be estimated that it has the shape S3 of the image of the third license plate. Then, the image correction data loading unit 131 can load the first correction value ALP_RATIO15 and the second correction value ALT_ANGLE15 of the image correction data corresponding to the third area A3 from the database unit D in order to correct the image of the license plate of the third vehicle C3.

[0086] According to this, the license plate image processing device 100 can estimate the shape of the image of the license plate without the process of extracting the contour line using a complicated operation such as the Generalized Hough Transform. That is, the license plate image processing device 100 can correct the image of the license plate imaged obliquely to the original shape with a small amount of calculation.

[0087] FIG. 8 is a diagram for explaining an example in which the aspect ratio correction unit 132 according to the embodiment of the present invention corrects image correction data. The image of the license plate in FIG. 8 is an image of the license plate of a fourth vehicle (not shown) imaged in the fourth area A4. At this time, the image of the license plate of the fourth vehicle may have a slightly different shape S4 and aspect ratio from the image of the fourth license plate in the fourth area A4. This is because, as described above, the position or direction of the vehicle at the time of calculating the image correction data can be slightly different from the position or direction of the vehicle at the time of imaging.

[0088] For this correction, the database unit D can further store reference values of aspect ratios calculated in advance for each position of the license plate image in the captured image. Needless to say, such reference values of aspect ratios may be calculated in advance for each area.

[0089] Then, the aspect ratio correction unit 132 can correct the image correction data based on the difference between the reference value of the aspect ratio corresponding to the position data and the aspect ratio of the license plate image (for example, P4w / P4h). Specifically, the aspect ratio correction unit 132 can correct at least one of the first correction value and the second correction value included in the image correction data.

[0090] According to this, since the image correction data is corrected based on the aspect ratio of the captured license plate image, the captured license plate image can be corrected to be more similar to the standard shape of the license plate.

[0091] FIG. 9 is a diagram for explaining an example in which the imaging direction correction unit 133 according to the embodiment of the present invention corrects image correction data.

[0092] As shown in FIG. 9, when the imaging direction W1 of the image acquisition unit 110 and the vehicle entry path direction W2 are oblique, the imaging direction correction unit 133 can correct the image correction data based on the angle T between the imaging direction of the vehicle image acquisition unit 110 and the direction of the entry path where the vehicle was located at the time of imaging. At this time, the image correction data to be corrected can be the second correction value.

[0093] For example, the imaging direction correction unit 133 can correct the second correction value of the image correction data by adding or subtracting the angle between the imaging direction W1 of the vehicle image acquisition unit 110 and the direction W2 of the entry path where the vehicle to be imaged is located. At this time, the direction W2 of the entry path where the vehicle is located may of course be replaced by the forward direction of the vehicle 1.

[0094] For example, the angle T between the imaging direction of the vehicle image acquisition unit 110 and the direction of the entry path where the vehicle 1 to be imaged is located may be a value measured at the time of installation of the license plate image processing unit 100 and input to the imaging direction correction unit 133.

[0095] According to this, even if the vehicle image acquisition unit 110 is installed so as to image the license plate obliquely, the image of the imaged license plate can be corrected to be similar to the standard shape of the license plate.

[0096] FIG. 10 is a diagram for explaining an example in which the ground height correction unit 134 according to the embodiment of the present invention corrects position data.

[0097] As shown in FIG. 10, the ground height at the position where the vehicle image acquisition unit 110 is installed and the ground height at the imaging position may be different from each other. At this time, the imaging position means the position where the license plate is imaged. Such an imaging position can be determined in advance according to the focus and imaging performance of the vehicle image acquisition unit 110.

[0098] FIG. 10a is a diagram showing a case where the ground at the imaging position is higher than the ground at the position where the vehicle image acquisition unit 110 is installed. In FIG. 10a, the imaging position is R1, and the difference in height between the ground at the position where the vehicle image acquisition unit 110 is installed and the ground at the R1 position is H1.

[0099] Then, the ground height correction unit 134 can 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 correction unit 134 can correct the vertical axis value of the position data.

[0100] Note that FIG. 10b is a diagram showing a case where the height of the ground at the imaging position R2 is equal to the height of the position where the vehicle image acquisition unit 110 is provided. In this case, the ground height correction unit 134 can omit the correction of the position data.

[0101] FIG. 10c is a diagram showing a case where the ground at the imaging position is lower than the ground at the position where the vehicle image acquisition unit 110 is installed. In FIG. 10c, the imaging position is R3, and the difference in height between the ground at the position where the image acquisition unit 110 is installed and the ground at the R3 position is H3.

[0102] Then, the ground height correction unit 134 can correct the position data based on the H3 value on the same principle as in FIG. 10a.

[0103] On the other hand, the ground height correction unit 134 can further correct the position data using the inclination angle data of the ground at the imaging position. This is because even if the ground height in front of the vehicle where the number plate is located is the same as the ground height at the position where the image acquisition unit 110 is installed, the ground height at the rear of the vehicle may be different.

[0104] FIG. 11 is a flowchart showing a number plate image correction method using the number plate image processing apparatus 100 according to an embodiment of the present invention.

[0105] First, the license plate image processing device 100 can capture an image of a vehicle to obtain a captured image including the vehicle, and detect an image of the license plate from the captured image (S200).

[0106] Then, the license plate image processing device 100 can generate position data indicating the position of the license plate image in the captured image (S210).

[0107] Furthermore, the license plate image processing device 100 can load image correction data corresponding to the position data from the database unit D, and generate an image correction value for the license plate based on the loaded image correction data (S220).

[0108] Also, the license plate image processing device 100 can correct the image of the license plate using the image correction value of the license plate (S230).

[0109] In step S230, the image of the license plate can be corrected in terms of scale based on the first correction value after being rotationally corrected based on the second correction value.

[0110] FIG. 12 is a diagram showing the detailed steps of step S220 according to an embodiment of the present invention.

[0111] As shown in FIG. 12, step S220 can include a step of correcting the position data based on the height difference between the ground at the position where the image acquisition unit 110 is installed and the ground at a predetermined imaging position (S221).

[0112] For example, when the position data is two-dimensional coordinate data having a horizontal axis value and a vertical axis value, the position data can be corrected by the following formula 1.

[0113]

Equation

[0114] 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 within the captured image. Center Y % height may be a value indicating the position of the vertical axis of the center point of the license plate image within the captured image.

[0115] For example, when the captured image is partitioned into 5 columns × 3 rows as shown in FIG. 5, if the position of the horizontal axis of the center point of the license plate image is within 0 to 20%, and the position of the vertical axis is within 66.6 to 100%, ALP_Ratio[Center X% width][Center Y% height] may be the first correction value of the image correction data corresponding to the first area A1.

[0116] At this time, if Enterance Height Diff is calculated as a negative value due to the height difference between the ground at the position where the image acquisition unit 110 is installed and the ground at a predetermined imaging position, ALP_Ratio[Center X% width][(Center Y + Entrance Height Diff)% height] can be the first correction value of the image correction data corresponding to the area located below the first area A1.

[0117] And the Alpha value may be a preset correction ratio coefficient depending on 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 captured image. If W_H_Ratio is calculated as a negative value, the Alpha value can be set to a negative value.

[0118] On the other hand, the predetermined imaging position may be a position predetermined according to the focus and imaging performance of the vehicle image acquisition unit 110. Also, if Entrance Height Diff is 0, that is, if there is no height difference between the respective grounds, step S221 may be omitted.

[0119] Next, a step of loading image correction data corresponding to the position data from the database unit D can be performed (S222).

[0120] And a step of correcting the image correction data based on the difference between the reference value of the aspect ratio corresponding to the position data and the aspect ratio of the image of the license plate can be performed (S223).

[0121] For example, the image correction data can include a first correction value for scale correction of the image of the license plate and a second correction value for rotation correction of the image of the license plate. And in step S223, at least one of the first correction value and the second correction value can be corrected.

[0122] For example, the first correction value can be corrected by the following formula 2, and the second correction value can be corrected by formula 3.

[0123]

Equation

[0124] In formula 2, Center X% width may be a value indicating the position of the horizontal axis of the center point of the image of the license plate in the captured image. Center Y % height may be a value indicating the position of the vertical axis of the center point of the image of the license plate in the captured image.

[0125] For example, when the captured image is partitioned into 5 columns × 3 rows as shown in FIG. 5, if the horizontal axis position of the center point of the license plate image 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 the first correction value of the 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 device 100. W_H_Ratio may be the aspect ratio of the license plate image extracted from the captured image. If W_H_Ratio is calculated as a negative value, the Alpha value can be set to a negative value.

[0126]

Number

[0127] In Equation 3, Center X% width may be a value indicating the horizontal axis position of the center point of the license plate image within the captured image. Center Y % height may be a value indicating the vertical axis position of the center point of the license plate image within the captured image.

[0128] For example, when the captured image is partitioned into 5 columns × 3 rows as shown in FIG. 5, if the horizontal axis position of the center point of the license plate image 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 the second correction value of the 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 device 100. W_H_Ratio may be the aspect ratio of the license plate image extracted from the captured image. If W_H_Ratio is calculated as a negative value, the Beta value can be set to a negative value.

[0129] And, based on the angle between the imaging direction of the vehicle image acquisition unit 110 and the direction of the approach road where the vehicle to be imaged is located, a step of correcting the image correction data can be performed (S224).

[0130] For example, the image correction data can have the second correction value corrected by the following Equation 4.

[0131]

Equation

[0132] Equation 4 is different from Equation 3 in that it corrects the second correction value using LP_CAR_Photo_Angle, which represents the angle between the imaging direction of the vehicle image acquisition unit 110 and the direction of the approach road where the vehicle to be imaged is located.

[0133] The above description of the present invention is for illustrative purposes, and those with ordinary knowledge in the field to which the technology belongs should be able to understand that it can be easily deformed into other specific forms without changing the technical idea and essential features of the present invention. Therefore, the embodiments described above should be understood as being illustrative in all aspects and not limiting. For example, each component described as a single type may be implemented in a distributed manner, and similarly, the components described as being distributed may also be implemented in a combined form.

[0134] The scope of the present invention is defined by the claims described below, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts are included in the scope of the present invention.

Industrial Applicability

[0135] The license plate image processing apparatus for recognizing a vehicle registration number according to an embodiment of the present invention and a license plate image correction method using the same can store a reference value of an aspect ratio for each area of a captured image, and corrects image correction data based on the difference between the reference value of the aspect ratio of the area where the image of the captured license plate is located and the aspect ratio of the image of the captured license plate. Therefore, by correcting the image of the license plate to its original shape with a relatively small amount of computation, it can be carried out under various conditions and in industrial sites.

Claims

1. A vehicle image acquisition unit that captures an image of a vehicle and acquires a captured image including the vehicle; A license plate detection unit that detects an image of the license plate of the vehicle from the captured image and generates position data for the position of the license plate image in the captured image; A database unit in which image correction data calculated in advance for each position of the license plate image in the captured image is stored; A correction value generation unit that loads the image correction data corresponding to the position data from the database unit and generates an image correction value for the license plate based on the loaded image correction data; A license plate image correction unit that corrects the license plate image based on the image correction value of the license plate; Including, The captured image is divided into a plurality of areas, The image correction data is calculated in advance for each area and stored in the database unit, The correction value generation unit loads the image correction data corresponding to the area to which the position data belongs, The image correction data includes a first correction value for correcting the scale of the license plate image and a second correction value for rotationally correcting the license plate image, The database unit further stores a reference value of the aspect ratio calculated in advance for each position of the license plate image in the captured image, The correction value generation unit corrects at least one of the first correction value and the second correction value based on the difference between the reference value of the aspect ratio corresponding to the position data and the aspect ratio of the license plate image A license plate image processing apparatus for recognizing a vehicle registration number, characterized in that.

2. The vehicle image acquisition unit captures the vehicle at a predetermined imaging position, The correction value generation unit corrects the position data based on the height difference between the ground at the position where the vehicle image acquisition unit is installed and the ground at the predetermined imaging position, The correction value generation unit loads the image correction data corresponding to the corrected position data The license plate image processing apparatus for recognizing a vehicle registration number according to claim 1.

3. The correction value generation unit further corrects the position data using the ground inclination angle data at the predetermined imaging position The license plate image processing apparatus according to claim 2.

4. The position data consists of two-dimensional coordinate data including a horizontal axis value and a vertical axis value, The correction value generation unit corrects the vertical axis value of the position data based on the difference in height The number plate image processing apparatus for recognizing a vehicle registration number according to claim 2.

5. The second correction value is corrected based on an angle between an imaging direction of the vehicle image acquisition unit and a direction of an approach road where the vehicle is located at the time of imaging. The number plate image processing apparatus for recognizing a vehicle registration number according to claim 1.

6. The number plate image correction unit rotates and corrects the image of the number plate based on the second correction value, and then corrects the scale of the image of the number plate based on the first correction value. The number plate image processing apparatus for recognizing a vehicle registration number according to claim 1.

7. a) imaging a vehicle to obtain an imaging image including the vehicle, and detecting an image of a number plate from the imaging image; b) generating position data for the position of the image of the number plate in the imaging image; c) loading, from a database unit storing image correction data calculated in advance for each position of the image of the number plate in the imaging image, the image correction data corresponding to the position data, and generating an image correction value for the image of the number plate based on the loaded image correction data; d) correcting the image of the number plate based on the image correction value of the number plate; including The imaging 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, In step c), loading, from the database unit, the image correction data corresponding to the region to which the position data belongs; The database unit further stores a reference value of an aspect ratio calculated in advance for each position of the image of the number plate in the imaging image, Step c) loading the image correction data corresponding to the position data from the database unit; correcting the image correction data based on a difference between the reference value of the aspect ratio corresponding to the position data and the aspect ratio of the image of the number plate; including A method for correcting an image of a number plate for recognizing a vehicle registration number, characterized by the above.

8. The captured image is acquired using a vehicle image acquisition unit that captures the vehicle. The step c) includes a step of loading, from a database unit, image correction data corresponding to the position data, and a step of correcting the image correction data based on an angle between an imaging direction of the vehicle image acquisition unit and a direction of an approach road where the vehicle is located. and includes The method for correcting a number plate image for recognizing a vehicle registration number according to claim 7.

9. The captured image is acquired using a vehicle image acquisition unit that captures the vehicle. Further included between the step b) and the step c) is a step of correcting the position data based on a height difference between the ground at the position where the vehicle image acquisition unit is installed and the ground at a predetermined imaging position. The method for correcting a number plate image for recognizing a vehicle registration number according to claim 7.

10. The position data is further corrected based on inclination angle data of the ground at the predetermined imaging position. The method for correcting a number plate image for recognizing a vehicle registration number according to claim 9.

11. The image correction data includes a first correction value for correcting the scale of the image of the number plate and a second correction value for rotationally correcting the image of the number plate. In the step d), after rotationally correcting the image of the number plate based on the second correction value, the scale of the image of the number plate is corrected based on the first correction value. The method for correcting a number plate image for recognizing a vehicle registration number according to claim 7.

Images