JP3244850B2 - License plate reader - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a license plate reading device applied to a vehicle type discriminating device on a toll road.

[0002]

2. Description of the Related Art A conventional license plate reader is configured as shown in FIG. In FIG. 1, reference numeral 101 denotes a pair of optical sensors for detecting the intrusion of the vehicle 105. An imaging device 102 captures an image of the front portion of the vehicle 105 that has entered the vehicle. An image processing apparatus 103 reads a license plate from an image captured by an imaging device (camera) 102. Reference numeral 104 denotes a vehicle intrusion path, and an image of the vehicle 105 that has entered the vehicle is captured by the imaging device 102.

In the license plate reading device configured as described above, when the vehicle 105 enters the vehicle intrusion path 104, the optical sensor 101 is shielded from light and the vehicle 105 is detected. A vehicle detection signal is output to 103. Upon receiving the vehicle detection signal, the image processing device 103 outputs an imaging command to the imaging device 102. Upon receiving the image capturing command, the image capturing device 102 captures an image of the front surface of the vehicle 105 that has entered the vehicle intrusion path 104 and sends the image signal to the image processing device 103. The image processing device 103 converts the image signal from the image pickup device 102 into an A / D signal.
After the (analog / digital) conversion, the license plate portion is read from the image of the front surface of the vehicle 105, and various image processes are performed on the image of the license plate portion.
Recognize characters in license plates. In this case, as shown in FIG. 11, since the image capturing apparatus 102 captures an image obliquely forward with respect to the vehicle entry direction, the actual image capturing range of the original image (FIG. 12A) captured by the image capturing apparatus 102 is as shown in FIG. 12
The area is trapezoidal as shown in FIG.

Accordingly, as shown in FIG. 13 (b), characters in a license plate that are regularly arranged on the plane to be imaged are also different from the original rectangular license plate in the original image captured in the image processing device 103. , FIG. 13 (a)
, The pitch and size of the characters become smaller as they are farther from the image pickup device 102, and the arrangement of the characters also becomes inclined. Therefore, in each process of the image processing apparatus 103, it is necessary to consider this distortion, and when the imaging conditions are changed, it is necessary to change various parameters used during the image processing.

[0005]

As described above, the license plate on the image captured by the image capturing device 102 is distorted into a trapezoid due to the relationship of the image capturing position shown in FIG. 11, so characters are cut out from the license plate. At this time, the character size and the pitch between characters, which should be standardized, are shown in FIG.
As shown in (a), the characters are not constant or the arrangement of the characters is inclined, so that the process of extracting the characters is complicated, and the number of recognition errors and unknowns increases. There is a problem that the distortion of the image greatly affects the recognition rate of license plate reading. Also,
Each time the installation condition of the imaging device 102 is changed, it is necessary to adjust various parameters of the character extraction processing and the character recognition processing.

SUMMARY OF THE INVENTION The present invention has been made in view of the above circumstances, and makes it easy to cut out characters and recognize characters, to reduce unknown or incorrect characters in character recognition results, and to reduce image pickup conditions such as image pickup distance and image pickup direction. It is an object of the present invention to provide a license plate reading device that can easily cope with a change.

[0007]

A license plate reader according to the present invention is provided with a vehicle detecting means for detecting a vehicle entering a gate lane, and is provided in the gate lane and outputted from the vehicle detecting means. An image capturing device that captures an image of the front surface of the intruding vehicle obliquely from the front with a vehicle detection signal, an image memory that stores an image captured by the image capturing device, and image data that is stored in the image memory. Perspective distortion of an object caused by imaging obliquely from the front is caused by a vertical parameter given by the installation condition of the imaging device with respect to the imaging target plane of the intruding vehicle.
Correction means for correcting according to the meter and the horizontal direction parameter, license plate cutting means for cutting out a license plate portion from the image data corrected by the correction means, and a license plate portion from the image of the cut out license plate portion. Character extracting means for extracting characters, and recognition means for recognizing the characters extracted by the character extracting means,
The license plate cutting means is provided by the correcting means.
A differentiating means for differentiating the corrected image data;
A first method of binarizing a differential image by a dividing means with a predetermined threshold value
Binarizing means for extracting a feature image from the binary image;
And dividing the feature image into unit images, and
A compression method that extracts the maximum value as the representative point from the pixels
And a characteristic image compressed by the compression means.
A second binarizing means for binarizing with a threshold value, and the second binary
Plate position from the image binarized by the binarization means
Estimate and cut out the license plate
Characterized in that that.

[0008]

When a vehicle enters a predetermined lane gate, an optical sensor installed at the entrance of the lane gate is shielded from light and the intrusion of the vehicle is detected, and the front of the vehicle is photographed by the image pickup device. An image captured by the imager is converted into an image and stored in an image memory. The original image stored in the image memory has a geometric distortion caused by capturing the vehicle obliquely from the front, and the geometric distortion is corrected according to a parameter given by an installation condition of the imaging device. This parameter is always constant under a certain condition of installation of the imaging device.

Then, a plate portion is cut out from the corrected image, and a character is cut out from the image of the plate portion. At this time, the size, position, etc. of the characters in the license plate have been standardized by the above-mentioned correction processing. Therefore, check the validity of the values of the features of the extracted characters. Can be. Then, by combining the feature amounts of the extracted characters, each character is sequentially recognized, and a result of “specific character” or “unknown” is output.

As described above, the geometric distortion of the entire image stored in the image memory is corrected in accordance with the parameters given by the installation conditions of the image pickup device, so that the subsequent character segmentation and recognition processing can be simplified. , The recognition rate can be improved. Further, even if the imaging position such as the imaging distance and the imaging direction is changed, it is only necessary to change the distortion correction parameters determined by the installation conditions of the imaging device, and it is possible to cope with the situation very easily.

[0011]

An embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a functional block diagram of a license plate reader according to one embodiment of the present invention. In FIG. 1, reference numeral 1 denotes an optical sensor, which is installed, for example, at the entrance of a tollgate gate lane on a toll road, and detects a vehicle entering the gate lane by blocking the optical sensor 1 from a vehicle entering the gate. I do. Reference numeral 2 denotes an I / F circuit, which is an interface between the optical sensor 1 and the control unit. Reference numeral 3 denotes an image pickup device, which is installed in a toll gate lane on a toll road, and images the front of the vehicle.
The image information is output to the vehicle number recognition device as an analog video signal.

Reference numeral 4 denotes an image pickup device I / F circuit which outputs an image pickup command to the image pickup device 3, A / D converts an analog video signal output from the image pickup device 3 at the front of the vehicle, and stores the converted signal in the image memory 5. Store. Reference numeral 5 denotes an image memory for storing an image of the front surface of the vehicle, which is an image to be processed by the imaging device 3, and an image subjected to various calculations. A control unit 6 controls the entire license plate reading device, controls input / output with external devices, performs plate cutting processing, character recognition processing, and the like. Reference numeral 7 denotes an image operation processing unit which performs a dedicated high-speed operation for image processing. 8
Is a distortion correction circuit that corrects geometric distortion caused by imaging the vehicle obliquely from the front in accordance with the parameters given by the installation conditions of the imaging device 3. The degree of correction by the distortion correction circuit 8, that is, the value of the parameter, is always constant under certain camera installation conditions. I above
The / F circuit 2, the imaging device I / F circuit 4, the image memory 5, the control unit 6, the image operation processing unit 7, and the distortion correction circuit 8 constitute an image processing device 9. Next, the overall processing operation of the above embodiment will be described with reference to the flowchart of FIG. (A1): Image capture

When a vehicle enters a lane gate at a tollgate on a toll road, the optical sensor 1 installed at the entrance of the lane gate is shielded from light and the vehicle is detected from entering the lane gate. Is output to the image processing apparatus 9. Upon receiving the vehicle detection signal, the image processing device 9 outputs an imaging command signal from the control unit 6 to the imaging device 3 through the imaging device I / F circuit 4. Upon receiving the imaging signal, the imaging device 3 performs a shutter operation, captures an image of the front surface of the vehicle at that time, A / D-converts the image signal by the imaging device I / F circuit 4, and converts the image signal. Digital multi-valued image memory 5
To store. The stored digital multi-valued image of the front part of the vehicle (hereinafter, referred to as an original image) is an image to be subjected to subsequent image processing. (A2): Image distortion correction

The original image stored in the image memory 5 is
Geometric distortion is caused by imaging the vehicle obliquely from the front. The geometric distortion is corrected by the distortion correction circuit 8 in accordance with the parameters given by the installation conditions of the imaging device 3. Details of the correction operation by the distortion correction circuit 8 will be described later. (A3): Cut out the plate frame from the corrected image Next, the license plate frame is cut out from the image corrected by the above (A2). The cutout procedure will be described with reference to the flowchart shown in FIG. (B1): Differential in the horizontal direction

The image stored in the image memory 5 is input to an image processing unit 7 where the image is differentiated in the horizontal direction. That is, the density difference between adjacent images is obtained, and the absolute value is output. (B2): Binarization

The differential pixel generated in the above (B1) is binarized by a predetermined threshold value in the image calculation processing section 7.
That is, a point having a density difference larger than the threshold value is set to “1”, and the other points are set to “0”. (B3): Feature extraction

In the license plate portion of the image, since the density difference between the character and the ground is large, when differentiation is performed, many points having high values appear. Therefore, "1" is obtained by binarization.
Becomes more points. The position of the plate is estimated by paying attention to the way in which the "1" points are collected.
For this purpose, the image calculation processing unit 7 uses the number of “1” existing in the vicinity (horizontal direction) of each point on the image as information of the point (the image at this stage is referred to as a “feature image”). ). (B4): Image compression

Next, the characteristic image is divided into unit images (for example, 16 pixels (horizontal) × 1 pixel), and the maximum value is extracted as a representative point from the pixels of each unit. That is, it is compressed. In addition, since the compression is performed by the method of “extracting the maximum value”, the feature amount is not lost in the plate portion. (B5): Binarization

The compressed feature image is binarized at a predetermined threshold. The point "1" means "there are many points of high density in the vicinity". That is, it indicates that it is highly likely that the plate is a part of the plate. (B6): Estimation of plate position

Until now, the extraction has been performed by paying attention to the horizontal characteristics of the plate, but in the next step, the plate existence position is estimated by paying attention to the vertical arrangement of the extracted portion. This processing is performed by the image calculation processing unit 7. (B7): Plate frame cut-out Next, the control unit 6 cuts out the plate frame based on the above processing results. (A4): Characters are cut out from the image of the license plate portion Using the image of the license plate cut out as described above, feature amounts such as the height and width of the character are recalculated.

Since the size and position of the characters in the license plate portion are originally standardized by the distortion correction process (A2), the value of the feature to be calculated can be easily estimated. Then, the validity of the value of the feature amount of the character extracted from the image of the license plate portion can be confirmed. (A5): Recognize Characters Combining the feature amounts calculated in (A4) above, each character is recognized in turn, and a result of "specific character" or "unknown" is output.

Next, the correction operation by the distortion correction circuit 8 will be described. Utilizing the fact that the positional relationship between the imaging device 3 and the imaging plane is known as shown in FIG. 4, perspective distortion caused by imaging from an oblique direction is corrected as follows. FIG. 4 shows image distortion correction parameters.
(A) is a vertical parameter, and (b) is a horizontal parameter. In FIG. 4, H is the height (mm) of the plane A to be imaged, W is the width (mm) of the plane A to be imaged, α is the swing angle of the imager 3 in the horizontal direction, and β is the vertical angle of the imager 3. The swing angle of the direction, a is 1/2 of the horizontal angle of view, and b is 1 / of the vertical angle of view.
2, f is the distance from the imaging device 3 at the optical axis center B to the plane A to be imaged.

(1) As shown in FIG. 5, two coordinate systems θ-X
In the YZ system and the θ-X'Y'Z 'system, the conversion from the θ-XYZ system to the θ-X'Y'Z' system is performed. Where θ-X
The YZ system is space fixed coordinates in which the installation position of the image pickup device 3 is the origin θ, the Y axis is the vertical direction, the X axis is the road crossing direction, and the Z axis is parallel to the lane. Θ−X′Y′Z 'Is θ-XY
In the Z system, the image pickup device 3 is rotated by α (RAD) around the Y axis toward the road side, and the X ′ axis is turned upward by β (RAD) rotation so that the θZ ′ axis becomes the optical axis center of the image pickup device 3. It is a thing. The conversion equation at this time is shown in the following equation (1).

[0024]

(Equation 1)

(2) From the θ-X'Y'Z 'system,
Conversion is performed to a coordinate θ′-x′y ′ system in which the plane of the image of the imaging device that has been translated by f along the Z′-axis is θ′-x′y ′. The projection of the θ-X′Y′Z ′ system onto the plane θ′-x′y ′ can be expressed by the following equation (2). [X ', y', z '] = [X' * (f / Z '), Y' * (f / Z '), 0] (2)

(3) Convert the θ′-x′y′z ′ system into a digital image display system θ ″ -IX.IY system.First, as shown in FIG. 2a (RAD),
Assuming that the vertical angle of view is 2b (RAD) and the effective size of one screen of the original image is vertical isx (pixel) × horizontal isy (pixel), the pixel resolution (g _x , g _y ) is g _x = 2f · tan a / isx g _y = 2f · tan b / isy (3)

[0027]

(Equation 2) Is obtained. [Isx / 2, isy / 2] is the origin θ ′
Is given to the upper left corner θ ″ of the imaging plane. When the above equations (2) and (3) are substituted into the equation (4), IX = (1 + X ′ / (Z ′ · tan a) · isx / 2 IY = (1 + Y ′ / (Z ′ · tan b) · isy / 2... (5) By applying the above equations (1) and (5) to the entire imaging plane, a perspective distortion is obtained. Is corrected.
The space fixed coordinate system θ-XYZ is converted to the digital image display system θ ″-
The expression to be converted into IX and IY is the following expression obtained by substituting expression (1) into expression (5). IX = ｛1+ (Xcos α-Ysin β) / ((Xsin α · cos β-Ysin β + Zcos α · cos β) tan a｝ isx / 2 IY = ｛1+ (Xsin β · cos β + Ycos β + Zcos α · sin β) / ((Z sin α · cos β−Y sin β + Z cos α · cos β) tan bisy / 2 (6) where α, β, and Z are parameters (fixed values) determined by the installation position of the imaging device 3. ) And a, b, isx,
isy is a fixed value determined by the imaging device 3 and a circuit for D / A converting the video signal.

From the above equation (6), since the coordinates of the θ ″ IX and IY systems with respect to the arbitrary coordinates of the XY plane of the θ-XYZ system are uniquely displayed, the XY plane of the θ-XYZ system is
divided into grids of x and horizontal isy, and θ ″ −
If the pixel values of the IX and IY system coordinates are coordinate-transformed as the pixel values of the grid, perspective distortion of the image can be corrected. Here, A = (sin α · cos β · tan a + cos α) · (isx /
2) B = (− sin β · tan a−sin β) · (isx / 2) C = cos α · cos β · tana · (isx / 2) D = sin α · cos β · tan a E = − sin β · tan a F = cos α · cos β · tan a G = (sin α · cos βtan b + sin β · cos β) · (i
sy / 2) H = (− sin β · tan b + cos) β · (isy / 2) I = cos α · cos β · tan b · (isy / 2) J = sin α · cos β · tan b K = − Assuming that sin β · tan b L = cos α · cos β · tan b, from equation (6), IX = (A × X + B + Y) / (D × X + E−Y + F) IY = (G × X + H−Y + I) / (J · X + KY · Y + L) (7) where A, B, C, D, E, F, G, H, I, J, K,
L is a fixed value.

As shown in FIG. 4, since the parameters for correcting the perspective distortion of the image generated when the vehicle is imaged obliquely from the front are known, the distortion of the original image can be corrected. The subsequent character extraction and recognition processing can be simplified. Next, a specific circuit configuration for performing the above-described correction processing will be described. FIG. 6 is a block diagram showing an example of the input / output circuit of the image memory 5.
FIG. 7 is a timing chart showing the operation of the image memory input / output circuit shown in FIG.

In FIG. 6, read address generating circuit 1
1 is a read address 31 (R
A0, RA1, RA2,...) Are generated in synchronization with the clock 30 and output to the address selector 13. The write address generation circuit 12 generates a write address 32 (WA0, WA1, WA2,...) Of the input data from the arithmetic unit in synchronization with the clock 30 and outputs the write address 32 to the address selector 13. The read / write control circuit 14 generates a read signal 34, a write signal 35, and a read / write switching signal 36 for the image memory 5. The read / write switching signal 36 becomes "H" (high) in the first half of one clock cycle and "L" (low) in the second half, whereby the image memory 5 performs a write operation in the first half of one clock cycle. The read operation is performed in the latter half.

When the read / write switching signal 36 is "L", the address selector 13 reads the read address 3
1 and the write address 32 is output to the image memory address bus 33 when the switching signal 36 is "H".

When the read / write switching signal 36 is "L", the data switching circuit 18 reads the read data RD0, RD1, RD2,.
To the data output flip-flop 21. When the switching signal 36 is "H", the input data 38 (WD0, WD1, WD2,...) From the arithmetic unit is output to the image memory data bus 39.

The flip-flop 21 stores the data RD0, RD1, RD2,... Transmitted from the image memory 5.
Is synchronized with the clock 30 and sent to the arithmetic unit as output data 37.

The write address generation circuit 12 is provided with the configuration shown in FIG.
The read address generation circuit 11 generates the address by executing the operation shown in the above equation (7), so that the image is distorted due to the installation position of the imaging device 3. Is corrected.

FIG. 9 shows an address generating section of the X coordinate system in the read address generating circuit 11. This read address generation circuit 11
1a to 41f, multipliers 42 to 45, adders 46 and 47,
It is constituted by a divider 48. Registers 41a to 41f
Are initialized by the CPU. The output of the register 41a is output to the multiplier 42, the output of the register 41b is output to the multiplier 43, the output of the register 41d is output to the multiplier 44, and the output of the register 41e is output to the multiplier 45. You. Also,
The X address is input to the multipliers 42 and 44,
Y addresses are input to 3 and 45. The X address and the Y address are the X and Y coordinates of the image corresponding to the address generated by the write address generation circuit 12.

The multiplication results of the multipliers 42 and 43 and the data held in the register 41c are input to the adder 46.
The multiplication results of the multipliers 44 and 45 and the data held in the register 41f are input to the adder 47. Adders 46 and 47
Add each input data and output to the divider 48. The divider 48 performs a division operation on the addition result of the adders 46 and 47, and sets the result as a read address IX. The read address IX in this case indicates the X coordinate of the image corresponding to the read address.

The read address generating circuit 11 includes an address generating section of a Y coordinate system configured similarly to the circuit shown in FIG. 9, and obtains the read address IY in the same manner as in FIG. The read address IY in this case indicates the Y coordinate of the image corresponding to the read address. The coordinates IX and IY of the lead image are obtained as described above,
A read address can be generated.

In the above embodiment, the case where the original image stored in the image memory 5 is subjected to distortion correction and then the plate portion is cut out has been described. The plate portion may be cut out first, and then the image of the plate portion may be subjected to distortion correction. When the license plate portion is cut out before the distortion correction as described above, the area for the distortion correction becomes small, and the processing can be speeded up. Further, the present invention can be applied to a parking lot system, an entrance / exit management system, and the like, in addition to being applied to a vehicle type discriminating apparatus on a toll road.

[0039]

As described above in detail, according to the present invention, the geometric distortion of the entire image caused by imaging the front of the vehicle obliquely from the front is corrected in accordance with the parameters given by the installation conditions of the imaging device. Characters are cut out and recognized from the original standardized license plate without distortion, so character extraction and recognition processing can be simplified, and the recognition result can be less unclear and errors. Can be improved.
Further, even if the imaging position such as the imaging distance and the imaging direction is changed, it is only necessary to change the distortion correction parameters determined by the installation conditions of the imaging device, and it is possible to cope with the situation very easily.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of a license plate reading device according to one embodiment of the present invention.

FIG. 2 is a flowchart showing a vehicle number recognition process according to the embodiment.

FIG. 3 is a flowchart showing a plate cutting process according to the embodiment.

FIG. 4 is a view showing image distortion correction parameters according to the embodiment.

FIG. 5 is an exemplary view showing a coordinate system used in distortion correction processing according to the embodiment.

FIG. 6 is a block diagram showing an example of an image memory input / output circuit according to the embodiment.

FIG. 7 is a timing chart showing the operation of the image memory input / output circuit shown in FIG. 6;

FIG. 8 is a view for explaining a write address generation operation for performing a raster scan of the write address generation circuit in FIG. 6;

FIG. 9 is a block diagram showing a configuration of a read address generation circuit in FIG. 6;

FIG. 10 is a diagram showing a general configuration of a license plate reading device.

FIG. 11 is a diagram showing a positional relationship between an image pickup device and a plane to be imaged in FIG. 10;

FIG. 12 is a diagram illustrating a relationship between an imaging range and an image captured by an imaging device in FIG. 10;

FIG. 13 is a view showing distortion of a license plate on an original image captured by the image pickup apparatus of FIG. 10;

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 ... Optical sensor, 2 ... I / F circuit, 3 ... Imaging machine, 4 ... Imaging machine I / F circuit, 5 ... Image memory, 6 ... Control part, 7 ... Image calculation processing part, 8 ... Distortion correction circuit, 9 ... Image processing device, 1
DESCRIPTION OF SYMBOLS 1 ... Read address generation circuit, 12 ... Write address generation circuit, 13 ... Address selector, 14 ... Read / write control circuit, 18 ... Data switching circuit, 21 ... Flip-flop, 30 ... Clock, 31 ... Read address, 3
2 ... write address, 33 ... image memory address bus,
34 read signal, 35 write signal, 36 read /
Write switch signal, 37 output data, 38 input data, 39 image memory data bus, 41a-41e register, 42-45 multiplier, 46, 47 adder, 4
8. Divider.

────────────────────────────────────────────────── ─── Continuation of the front page (51) Int.Cl. ⁷ Identification symbol FI G08G 1/04 G06F 15/62 380 (56) References JP-A-5-28321 (JP, A) JP-A-2-66690 ( JP, A) JP-A-3-232100 (JP, A) JP-A-5-101221 (JP, A) JP-A-2-83798 (JP, A) Hirokazu Onoe, Mitsuru Shiono, numbers including kanji characters Character recognition experiment of whole plate, IEICE technical report, Japan, November 1992, pp. 15-22 (58) Fields investigated (Int. Cl. ⁷ , DB name) G08G 1/017 G01B 11/24 G06K 9/20 330 G06K 9/32 G06T 1/00 G08G 1/04

Claims (2)

(57) [Claims] A vehicle detecting means for detecting a vehicle entering the gate lane; a vehicle detecting signal installed in the gate lane, and a front part of the invading vehicle being obliquely forwardly detected by a vehicle detection signal output from the vehicle detecting means. an imaging device for capturing, an image memory for storing the image captured by the imaging unit, the image data stored in the image memory, a far object caused by imaging from diagonally forward the vehicle
A vertical parameter given by the installation conditions of the imaging device with respect to the plane to be imaged of the invading vehicle,
Correction means for correcting in accordance with a horizontal direction parameter; license plate cutting means for cutting out a license plate portion from the image data corrected by the correction means; and character cutout for cutting out characters from the image of the cut out license plate portion. Means; and recognition means for recognizing characters cut out by the character cutout means, wherein the license plate cutout means is provided by the correction means.
A differentiating means for differentiating the corrected image data;
A first method of binarizing a differential image by a dividing means with a predetermined threshold value
Binarizing means for extracting a feature image from the binary image;
And dividing the feature image into unit images, and
A compression method that extracts the maximum value as the representative point from the pixels
And a characteristic image compressed by the compression means.
A second binarizing means for binarizing with a threshold value, and the second binary
Plate position from the image binarized by the binarization means
Estimate and cut out the license plate
License plate reader, characterized in that that. 2. A vehicle detecting means for detecting a vehicle entering the gate lane, and a vehicle detecting signal installed in the gate lane and obliquely moving a front portion of the invading vehicle from a front by a vehicle detection signal output from the vehicle detecting means. An image pickup device for picking up an image, an image memory for storing an image picked up by the image pickup device, a license plate cutting unit for cutting out a license plate portion from image data stored in the image memory, and the cut out number. Perspective generated by imaging the vehicle obliquely from the front of the image of the plate portion
Vertical parameters and horizontally given distortion at the installation condition of the imaging device with respect to the imaging plane of the entering vehicle
Correction means for correcting according to the direction parameter; character extraction means for extracting characters from the image of the license plate portion corrected by the correction means; and recognition means for recognizing the characters extracted by the character extraction means. , Said license plate cutting means
Differentiates image data stored in the image memory
A differentiating means, and a differential image generated by the differentiating means is provided with a predetermined threshold value.
A first binarizing means for binarizing the image with
Means for extracting a signature image, and dividing the feature image into unit images.
Divide the maximum value from the pixels of each unit as the representative point.
Compression means for extracting
Binarizing means for binarizing the feature image with a predetermined threshold
From the image binarized by the second binarization means.
Estimate the location of the plate and determine the number plate
A license plate reading device, comprising: a cutting means .