JPH10105873A - Device for recognizing number plate of vehicle - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide the number plate recognition device for a vehicle, which can easily and most suitably adjust an image pickup means and which can always obtain satisfactory recognition performance. SOLUTION: An image pickup camera 5 picks up an image containing the number plate of traveling vehicle. A number plate recognition part 7 independently recognizes number plate information constituted of plural items from the image which is picked up by the image pickup camera 5 for every item. A parameter analysis part 24 analyzes the size and the area of a vehicle number, the histogram of a number plate area and a detection position from the image which is picked up by the image pickup camera 5 in a vehicle number detection part 17. A control part 25 controls the zoom, the focus and the iris of the image pickup lens 8 of the image pickup camera 5 in accordance with the analysis result of the parameter analysis part 24.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

The present invention relates to a vehicle number displayed on a license plate of a vehicle such as an automobile, for example.
The present invention relates to a vehicle number plate recognition device that recognizes number plate information such as a classification number, a land transportation branch office code, and kana characters.

[0002]

2. Description of the Related Art In general, in this type of number plate recognizing device, a running vehicle (automobile) is detected by a vehicle detection sensor using infrared rays or ultrasonic waves, and an imaging camera is detected at the detection timing. Is operated to capture an image including the license plate of the vehicle. The captured image is processed by the license plate recognition unit, so that license plate information including a plurality of items displayed on the license plate is independently recognized for each of the plurality of items.

In general, the number plate information includes a plurality of items (vehicle number, classification number, land transportation branch office code, kana character, plate size, business / private type) as shown in FIG. By recognizing such information as described above, for example, unmanned management of a parking lot, measurement of travel time, automatic discovery of a specific vehicle such as a arranged vehicle, and the like are performed. In this case, whether or not all items need to be recognized depends on these applications (uses), and is selected as necessary.

[0004]

However, in the conventional number plate recognizing device, the vehicle number is detected by evaluating the area, size, pitch, alignment, etc. in the process of detecting the vehicle number from the captured image. For this reason, there is a problem that the recognition performance greatly varies depending on how the imaging camera is installed, and that if sufficient recognition performance is to be ensured, a great deal of labor is required for installation and adjustment of the imaging camera. In particular, in adjusting the imaging camera, it is necessary to manually adjust the zoom, focus, iris and the like of the imaging lens, which requires a great deal of labor.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a vehicle number plate recognizing apparatus which can easily and easily adjust an image pickup means optimally and always obtain good recognition performance.

[0006]

According to the present invention, there is provided an apparatus for recognizing a license plate of a vehicle, comprising: an imaging unit having a controllable imaging lens for capturing an image including a license plate of the vehicle; and an image captured by the imaging unit. A recognition means for independently recognizing number plate information consisting of a plurality of items for each of a plurality of items; an analysis means for analyzing an image taken by the imaging means; and Control means for controlling the imaging lens of the imaging means.

Further, a vehicle number plate recognition apparatus according to the present invention comprises: an image pickup means having a controllable image pickup lens for picking up an image including a vehicle number plate; and a plurality of images picked up by the image pickup means. Recognizing means for independently recognizing number plate information consisting of items for each of a plurality of items, display means for displaying the recognition result of the recognizing means, and indicating whether or not the recognition result displayed on the display means is correct. A first input unit for inputting information; a second input unit for inputting information indicating a cause of the erroneous recognition when the erroneous recognition is input by the first input unit; And control means for controlling the imaging lens of the imaging means in accordance with the information input by the second input means and representing the cause of the erroneous recognition.

Further, a vehicle number plate recognition apparatus according to the present invention includes an image pickup means having a controllable image pickup lens for picking up an image including a vehicle number plate, and a plurality of images obtained by the image pickup means. Recognition means for independently recognizing number plate information consisting of items for each of a plurality of items; analysis means for analyzing an image taken by the imaging means; display means for displaying a recognition result of the recognition means; Input means for inputting information indicating whether or not the recognition result displayed on the display means is correct; and when an erroneous recognition is input by the input means, an imaging lens of the imaging means according to the analysis result of the analysis means And control means for controlling

Further, the vehicle number plate recognizing device of the present invention comprises: an image pickup means provided with a controllable image pickup lens for picking up an image including the vehicle number plate; and a plurality of images picked up by the image pickup means. Recognizing means for independently recognizing number plate information consisting of items for each of a plurality of items, display means for displaying the recognition result of the recognizing means, and indicating whether or not the recognition result displayed on the display means is correct. Input means for inputting information, storage means for accumulating and storing information input by the input means, analysis means for analyzing the contents stored in the storage means, and the imaging means according to the analysis result of the analysis means Control means for controlling the imaging lens of the means.

The vehicle number plate recognizing device of the present invention captures an image including an image including a vehicle number plate, and captures the image captured by the image capturing means, and changes the capturing position. Possible capturing means, recognition means for independently recognizing number plate information consisting of a plurality of items from the image captured by the capturing means, and an image captured by the image capturing means. An analyzing means for analyzing, and a control means for changing and controlling an image taking position by the taking means in accordance with an analysis result of the analyzing means.

The vehicle number plate recognizing device of the present invention captures an image including an image of a vehicle number plate and captures the image captured by the image capturing means, and changes the capturing position. Possible capture means, recognition means for independently recognizing number plate information consisting of a plurality of items from an image captured by the capture means, and a recognition result of the recognition means are displayed. Display means; first input means for inputting information indicating whether or not the recognition result displayed on the display means is correct; and when the first input means inputs an erroneous recognition, a cause of the erroneous recognition is provided. A second input means for inputting information representing the misrecognition, and when the first input means inputs an erroneous recognition, the input is performed in accordance with the information representing the cause of the erroneous recognition inputted by the second input means. Image capture position by capture means And a control means for changing control.

Further, the vehicle number plate recognition device of the present invention captures an image captured by the image capturing means for capturing an image including the vehicle number plate, and changes the capturing position. Possible capturing means, recognition means for independently recognizing number plate information consisting of a plurality of items from the image captured by the capturing means, and an image captured by the image capturing means. Analysis means for analyzing, display means for displaying a recognition result of the recognition means, input means for inputting information indicating whether or not the recognition result displayed on the display means is correct; And control means for changing and controlling an image capturing position of the image capturing means in response to an analysis result of the analysis means.

Further, the vehicle number plate recognizing device of the present invention captures the image captured by the image capturing means for capturing an image including the vehicle number plate, and changes the capturing position. Possible capture means, recognition means for independently recognizing number plate information consisting of a plurality of items from an image captured by the capture means, and a recognition result of the recognition means are displayed. Display means;
Input means for inputting information indicating whether the recognition result displayed on the display means is correct, storage means for accumulating and storing the information input by the input means, and analyzing the contents stored in the storage means And a control unit for changing and controlling the image capturing position of the image capturing unit according to the analysis result of the analyzing unit.

According to the present invention, the taken image is analyzed, and the zoom, focus, iris and the like of the image pickup lens in the image pickup means are controlled in accordance with the analysis result, so that the image pickup means can be easily and easily optimized. It can be adjusted and good recognition performance is always obtained.

Further, according to the present invention, the operator can judge the recognition result and make various settings, thereby making it possible to perform adjustment with higher accuracy. Moreover, since the operator simply inputs using the recognition result and the information indicating the cause of the erroneous recognition, the adjustment can be performed much more easily than in the conventional manual adjustment.

According to the present invention, correct / incorrect information for the recognition result determined and input by the operator is accumulated and stored, and the stored content is analyzed, and the zooming of the imaging lens in the imaging means is performed in accordance with the analysis result. focus,
By controlling the iris and the like, the overall tendency of the recognition result can be grasped and adjusted according to the grasped tendency.

[0017]

Embodiments of the present invention will be described below with reference to the drawings.

First, a first embodiment will be described.

FIG. 1 schematically shows the configuration of a vehicle number plate recognition apparatus according to the present invention. In FIG. 1, reference numeral 1 denotes a traveling path of a vehicle 2, and the vehicle 2 travels in a direction indicated by an arrow. A vehicle detection sensor 3 that detects a running vehicle 2 using infrared rays or ultrasonic waves is provided on a side portion of the traveling path 1. In front of the vehicle detection sensor 3 at a predetermined distance, an imaging camera 5 is installed as an imaging unit that captures an image including the number plate 4 of the running vehicle 2 that has passed the vehicle detection sensor 3.

An illuminating device 6 for illuminating a portion of the number plate 4 of the vehicle 2 running at night, especially at night, is installed near the imaging camera 5. The lighting device 6 generally uses a light source that outputs near-infrared light so as not to hinder the driving of the vehicle 2. The output of the imaging camera 5 is sent to a number plate recognizing unit 7, which will be described in detail later, where the number plate information described on the number plate 4 is recognized.

FIG. 2 is a block diagram showing the configuration of the vehicle number plate recognition device according to the first embodiment.
In FIG. 2, the imaging camera 5 is constituted by, for example, an industrial television camera or the like, and includes an electrically controllable imaging lens 8. The zoom, focus, iris and the like of the imaging lens 8 are controlled by the lens controller 11.

Next, the number plate recognizing section 7 will be described. In the number plate recognizing unit 7, the A / D converter 12 captures the output (analog image signal) of the imaging camera 5, and converts the captured image into digital image data having, for example, 8-bit grayscale values. The input control unit 13
The change control of the image capturing position in the / D converter 12 is performed.

The image storage section 14 is a two-dimensional memory for storing digital image data, and temporarily stores processed images such as input images and binarized images. The image inverting unit 15 performs a process of inverting the gray value of an image. Binarization processing unit 16
Converts the image data having the 8-bit gray value into a binary value,
The image is converted into a binary image of 0 "and" 1 ". Such a binarization process is realized by, for example, a technique described in Japanese Patent Application No. 63-300744.

The vehicle number detecting section 17 performs, for example, a labeling process on the binary image stored in the image storing section 14, analyzes the measured coordinate information and area information, and detects a vehicle number character string.

The classification number detecting section 18 performs, for example, a labeling process on an area defined by the relative positional relationship with the vehicle number character string in the binary image stored in the image storing section 14 to perform measurement. The obtained coordinate information and area information are analyzed to detect a classification number character string.

The land transportation branch office detecting section 19 performs, for example, a labeling process on an area defined by the relative positional relationship with the vehicle number character string in the binary image stored in the image storing section 14 and measures the area. It analyzes the coordinate information, area information, etc., and detects the land transportation branch office code (character string).

The kana character detection unit 20 performs, for example, a labeling process on an area limited by the relative positional relationship with the vehicle number character string in the binary image stored in the image storage unit 14 to perform measurement. By analyzing the coordinate information and the area information, etc., the kana character is detected.

The size discriminating section 21 discriminates the size of the plate 4, for example, as disclosed in Japanese Patent Laid-Open No. 1-2763.
No. 74 or the like is used. The character recognizing unit 22 as a recognizing unit performs character recognition by applying a technique such as pattern matching to each detected character pattern. As the recognition result, a character code for each character pattern and a similarity indicating the certainty of the recognition result are output.

The lens communication unit 23 controls the lens controller 11 to zoom, focus,
A control signal for controlling iris and the like is sent. The parameter analysis unit 24 analyzes the size and area of the vehicle number detected by the vehicle number detection unit 17, the histogram of the license plate area, and the detection position.

The control unit 25 controls the entire apparatus. The general-purpose memory 26 as a storage unit stores a parameter used for analyzing the connection area, a result of character recognition, a database of license plate information for a specific vehicle, and the like.

The collating unit 27 as collating means collates the recognition result stored in the general-purpose memory 26 with a database of license plate information to find a specific vehicle. The communication unit 28 transmits information such as discovery of a specific vehicle to an external computer (external device).

The image bus 29 is a dedicated bus for transferring image data, and is used for exchanging images between the image storage unit 14 and each processing unit. The general-purpose bus 30 is a general-purpose data transfer bus, and is used for exchanging control data and data such as character recognition results between the control unit 25 and each processing unit.

Next, a process of recognizing the license plate information and finding, for example, a specific vehicle will be described with reference to a flowchart shown in FIG. First, step S
At 1, a recognition process of the license plate information is performed.
The recognition process of the license plate information is performed, for example, as follows.

That is, an image including the license plate 4 of the vehicle 2 captured by the imaging camera 5 is captured by the A / D converter 12, and the A / D converter 12 converts, for example, an 8-bit gray value. The digital image data is converted into digital image data and temporarily stored in the image storage unit 14. FIG. 4 shows an example of the captured image.

The image data stored in the image storage unit 14 is, in the binarization processing unit 16, for example, as shown in FIG. 5, a character portion having a value of "1" and a background portion having a value of "0". Converted to a value image. When contrast exists between a character portion and a background portion like a vehicle number, binarization by contrast detection is effective. As a binarization method using such contrast detection, for example, a method described in Japanese Patent Application No. 63-300744 is used.

In the vehicle number detecting section 17, the binarization processing section 1
By analyzing the binary image obtained from 6, the vehicle number character string is detected. The detection of the vehicle number character string is performed, for example, according to a flowchart shown in FIG.

That is, first, for example, a labeling process is performed on the binary image to detect coordinate information and area information of the connected area. Next, the coordinate information and the area information of the detected connected area are analyzed, and an area that seems to be a vehicle number character is selected. As is well known, the vehicle number is described in accordance with the dimensional rules, so that the vehicle number can be detected by evaluating the size and area of the connection area, the pitch in the horizontal direction, the manner of alignment in the vertical direction, and the like.

As shown in FIG. 7B, the number plate for the business is inverted from the number plate for the private use (see FIG. 7A). If the vehicle number character string is not detected in the processing up to this point, the image inverting unit 15 inverts the grayscale value, and then performs the same process after binarization to try to detect the vehicle number character string. At this point, the discrimination between private use and business use can also be made automatically.

As described above, the characters on the number plate 4 are described in accordance with the dimensional rules. Therefore, the position of the classification number, the land transportation branch office code, the kana character, and the like can limit the area to be searched from the relative positional relationship with the vehicle number character string.

As shown in FIG. 8, the classification number detector 18 binarizes the detection area E1 limited by the relative positional relationship with the vehicle number N in the same manner as the detection of the vehicle number.
The classification number is detected by analyzing the connection region.

Similarly, the land transportation branch office detecting section 19 performs binarization and analysis of the connection area with respect to the detection area E2 limited by the relative positional relationship with the vehicle number N, as shown in FIG. By doing so, the land transportation branch office code is detected.

Similarly, in the kana character detecting section 20, FIG.
As shown in (2), the kana character is detected by performing binarization and analysis of the connection region for the detection region E3 limited by the relative positional relationship with the vehicle number N.

The vehicle number, classification number,
The land transportation branch office code and the kana character are subjected to character recognition in the character recognizing unit 22 by applying, for example, a known pattern matching method to each character pattern. As the recognition result, a character code for each character pattern and a similarity indicating the certainty of the recognition result are output.

The size discriminating section 21 uses, for example, a method described in Japanese Patent Application Laid-Open No. 1-276374.
The size of the number plate 4 is determined.

These series of processes are controlled by the control unit 25. The parameters used for analyzing the connected area and the recognition results of the character recognition unit 22 are stored in the general-purpose memory 26 in a format as shown in FIG. 11, for example.

Next, in steps S2 and S3, a matching process is performed between the recognition result of the license plate information and the license plate information of the specific vehicle for automatically finding the specific vehicle. That is, the recognition result of the license plate information obtained in the above-described recognition processing and the license plate information of a plurality of specific vehicles to be found (collated) are stored in the general-purpose memory 26 as shown in FIG. 12, for example.

Here, the license plate information of a plurality of specific vehicles to be compared is stored in the general-purpose memory 26 as shown in FIG. 12 by being input from an external computer (not shown) via the communication unit 28, for example. It is supposed to be.

The collating unit 27 collates the recognition result of the license plate information in the general-purpose memory 26 with the license plate information of the specific vehicle. If there is license plate information of the specific vehicle that matches the recognition result, the process proceeds to step S4. Proceed,
The information to that effect is transmitted to an external computer or the like via the communication unit 28, for example. In this way, a specific vehicle can be automatically found.

Next, a procedure for installing the above-described number plate recognition apparatus will be described with reference to a flowchart shown in FIG. First, the vehicle detection sensor 3, the imaging camera 5, and the illuminating device 6 are attached to the image captured by the imaging camera 5 at the moment when the vehicle detection sensor 3 detects the running vehicle 2. Is set to have an appropriate size and a sufficient contrast.

Next, the number plate recognizing section 7 is made to recognize the number plate 4 of the vehicle 2 as described above. At this time, the parameter analysis unit 24 checks the vehicle number detection unit 17
The analysis of the size and area of the vehicle number, the histogram of the number plate area, and the detection position detected in step (1), and sends the analysis result to the control unit 25.

The control unit 25 transmits a control command for controlling the imaging lens 8 of the imaging camera 5 to the lens controller 11 via the lens communication unit 23 according to the analysis result, or performs A / D A control command for changing the image capturing position of the conversion unit 12 is transmitted to the input control unit 13.

Here, an example of a method of analyzing the size and area of the vehicle number, the histogram of the number plate area, and the detection position in the parameter analysis unit 24 will be described.

The parameter analyzer 24 determines the size (width w, height h) of the circumscribed rectangle C1 of the vehicle number detected by the vehicle number detector 17 (see FIG. 15). Next, the size (width w, height h) of the circumscribed rectangle C1 of the obtained vehicle number and the size (width) of the circumscribed rectangle C0 of the vehicle number of the standard number plate stored in advance in the parameter analysis unit 24 w0, height h0), and the size of the circumscribed rectangle C1 of the vehicle number detected by the vehicle number detection unit 17 is larger than the size of the circumscribed rectangle C0 of the vehicle number of the standard number plate stored in advance. If it is larger, a command to reduce the focal length of the imaging lens 8 is issued to the circumscribed rectangle C0 of the vehicle number of the standard number plate in which the size of the circumscribed rectangle C1 of the vehicle number detected by the vehicle number detector 17 is stored in advance. Is smaller than the size of the imaging lens 8, a command to increase the focal length of the imaging lens 8 is transmitted from the lens communication unit 23 to the lens controller 11, so that the Adjust the focal length.

For example, FIGS. 14 and 15 show examples in which the size of the vehicle number is smaller than the set value, and FIG. 14A shows the imaged number plate area.
14B shows the detected vehicle number, and FIG. 14C shows a standard number plate pattern. FIG. 15A shows the size of the detected vehicle number, and FIG. 15B shows the size of the standard vehicle number stored in advance.

In the case of this example, the width w of the circumscribed rectangle C1 of the vehicle number detected by the vehicle number detection unit 17 is "5" and the height h
Is "10", and the circumscribed rectangle C0 of the vehicle number of the standard number plate stored in the parameter analysis unit 24 has a width w0 of "8" and a height h0 of "16". The circumscribed rectangle C1 of the vehicle number detected at 17
Is smaller than the circumscribed rectangle C0 of the vehicle number of the standard number plate stored in advance. Therefore, the command sent from the lens communication unit 23 to the lens controller 11 is a command to increase the focal length of the imaging lens 8.

When the image captured by the imaging camera 5 is an out-of-focus image, for example, as shown in FIG. 16A, the boundary between the vehicle number portion of the number plate 4 and the background is blurred and binarized. Since the character at that time becomes thicker as shown in FIG. 16B, its area also becomes larger. Note that FIG.
(C) shows the pattern of the standard number plate. Therefore, when the binarized character is larger than the area of the character stored in advance, if the focus control of the imaging lens 8 is performed, the imaging camera 5 is detected at the moment when the vehicle detection sensor 3 detects the traveling vehicle 2. Can focus the captured image.

FIG. 17A shows the size and area of the detected vehicle number for the out-of-focus image shown in FIG. 16, and FIG. 17B shows the size of the standard vehicle number stored in advance. And the area are shown.

Next, an example of a method for controlling the imaging lens 8 will be described below. When the parameter analysis unit 24 detects that the image is out of focus, the lens communication unit 23 sends a command to bring the focus of the imaging lens 8 closer (farther) to the lens controller 11, and the detection is performed in the next number plate recognition process. If the area of the selected vehicle number becomes far from the set value, a command to move far (near) is sent, and if near, a command to move near (far) is sent.

By repeating this processing until the area of the vehicle number falls within the set value, the image captured by the imaging camera 5 is brought into focus at the moment when the vehicle detection sensor 3 detects the traveling vehicle 2. Can be.

Although there is a method of directly using the area of the character, the size of the number plate 4 included in the image captured by the imaging camera 5 varies. The area (s) and the area of the circumscribed rectangle of the vehicle number detected by the vehicle number detection unit 17 (w ×
It is better to use the ratio of h) (s / (w × h)).

The parameter analysis unit 24 controls the iris of the imaging lens 8 by creating a histogram near the detection position of the vehicle number detected by the vehicle number detection unit 17 and analyzing the created histogram. .
For example, as shown in FIG. 18, when the histogram is concentrated on the higher luminance side, a control command indicating that the iris of the imaging lens 8 is to be narrowed is transmitted from the lens communication unit 23 to the lens controller 11, and FIG. As shown in
When the histogram is concentrated on the lower luminance side, the vehicle communication sensor 23 sends a control command to the lens controller 11 to open the iris of the imaging lens 8 so that the vehicle detection sensor 3 controls the traveling vehicle 2. A good image in which the number plate portion of the image captured by the imaging camera 5 at the moment of detection is not too dark or too bright can be obtained.

When the detection position of the vehicle number is shifted left, right, up and down, the input control unit 13 controls the A / D conversion unit 12.
Is changed so that the number plate 4 is positioned at the center of the captured image, so that the number of images captured by the imaging camera 5 at the moment when the vehicle detection sensor 3 detects the traveling vehicle 2. 4 can be prevented from being chipped as shown in FIGS.

Next, a second embodiment will be described.

FIG. 24 is a block diagram showing a configuration of a vehicle number plate recognition device according to the second embodiment. The difference between the second embodiment and the first embodiment is that the D / A converter 3 converts the display data into digital data.
1. Display unit 32 as display means for simultaneously displaying the recognition result supplied via D / A conversion unit 31 and the corresponding captured image on the screen, and whether the recognition result displayed on display unit 32 by the operator is correct. A result input unit (keyboard or the like) 33 is added as an input means for inputting the check result, and the parameter analysis unit 24 is deleted. Other components are the same as those of the first embodiment. Therefore, the same portions are denoted by the same reference numerals and description thereof will be omitted.

Hereinafter, a procedure for installing the above-described number plate recognition apparatus will be described with reference to flowcharts shown in FIGS. First, the vehicle detection sensor 3, the imaging camera 5, and the illuminating device 6 are attached to the image captured by the imaging camera 5 at the moment when the vehicle detection sensor 3 detects the running vehicle 2. Is set to have an appropriate size and a sufficient contrast.

Next, the number plate recognition unit 7 recognizes the number plate 4 of the vehicle 2 as described above, and sends the recognition result to the display unit 32 via the D / A conversion unit 31.
indicate. At this time, a captured image captured by the image capturing camera 5 and corresponding to the recognition result is also displayed on the display unit 32 at the same time.

The operator confirms whether the recognition result is correct by comparing the recognition result displayed on the display unit 32 with the captured image. As a result of the confirmation, if the information of the number plate 4 is erroneously recognized, the operator uses the result input unit 33 to input the information indicating that the recognition is erroneous together with the code indicating the erroneous cause (see FIG. 28).
When information indicating that recognition is incorrect and a code indicating an erroneous cause are input by the result input unit 33, the control unit 25 operates the lens so that the imaging lens 8 performs an operation corresponding to the code indicating the cause. A control command is transmitted to the lens controller 11 via the communication unit for communication 23, and a control command for changing the image capturing position is transmitted to the input control unit 13.

FIG. 28 shows an example of a code (number) representing an erroneous recognition input by the operator through the result input unit 33. In the case of FIG. 28, "0" is input when the recognition result of the number plate information is correct, and when it is determined that the number plate is not detected because the number plate is small, BIT0 is displayed and the number plate is too large. BIT1 when it is determined that the
However, if it is determined that the recognition of the number plate is out of focus and the recognition is incorrect, BIT2 is determined. If the recognition of the number plate is too dark or the recognition is incorrect, BIT3 is determined and the number plate is bright. If it is determined that the recognition was too erroneous, BIT4 would not be detected because the number plate part was cut off to the right. If it was determined that BIT5 was not detected because the number plate part was cut to the left, it could not be detected. BI
When T6 determines that the detection was not possible because the number plate portion was cut off, BIT7 was determined, and when T6 determined that the detection was not possible because the number plate portion was cut off, BIT8 was "1". Enter a number that will be For example, if the number plate is too small and too bright, enter a numerical value “17”.

The control unit 25 transmits a control command for controlling the imaging lens 8 to the lens controller 11 via the lens communication unit 23 in accordance with the numerical value input by the result input unit 33, For example, a control command for changing the image capturing position is transmitted to the unit 13. For example, in the case of FIG. 28, if the numerical value BIT0 input by the result input unit 33 is "1", the lens communication unit 23 transmits a control command instructing the lens controller 11 to zoom the imaging lens 8, and the BIT 1 of the numerical value input by the result input unit 33 is “1”
Then, the lens communication unit 23 to the lens controller 11
Is transmitted to the lens controller 11 from the lens communication unit 23 to the lens controller 11 if the numerical value BIT 2 input by the result input unit 33 is “1”. Is transmitted, and the result input unit 3
If BIT 3 of the numerical value input by 3 is “1”, a control command instructing the lens controller 11 to open the aperture of the imaging lens 8 is transmitted from the lens communication unit 23, and the numerical value input by the result input unit 33. BIT4
Is "1", a control command for instructing the lens controller 11 to close the aperture of the imaging lens 8 is transmitted from the lens communication unit 23 to the lens controller 11, and if the numerical value BIT5 input by the result input unit 33 is "1", The input control unit 13 shifts the image capturing start position in the A / D conversion unit 12 to the left, and sets the value B
If IT6 is “1”, the input control unit 13 shifts the image capturing start position in the A / D conversion unit 12 to the right,
If the BIT 7 of the numerical value input by the result input unit 33 is “1”, the input control unit 13 controls the A / D conversion unit 12
Is shifted downward, and if the BIT 8 of the numerical value input by the result input unit 33 is “1”, the input control unit 13 raises the image capture start position in the A / D conversion unit 12. Shift to For example, when a numerical value “17” is input from the result input unit 33, control is performed to increase the focal length of the imaging lens 8 and close the aperture.

Of course, the input value from the result input unit 33 need not be a numerical value. For example, a switch corresponding to each of the above bits is prepared, and the number plate is too small.
If it is too bright, a method of turning on a switch indicating that the number plate is too small and a method of turning on a switch indicating that the number plate is too bright may be used. In this case, an equivalent result can be obtained by regarding ON / OFF of each switch as “1” or “0” of each bit in the case of the above numerical value.

According to the above-described second embodiment, since the recognition result is determined by the operator and various settings are made, it is possible to set and adjust with higher precision than in the above-described first embodiment. is there. In addition, since the operator merely inputs using the recognition result and the code (number) representing the cause of the erroneous recognition, it is possible to set and adjust the lens controller much more easily than manually adjusting the lens controller as in the related art.

In the above-described second embodiment, the operator inputs a code representing the cause of the misrecognition from the result input unit 33, and controls the imaging lens 8 based on the input code. A case has been described in which the take-in position is changed and controlled. However, a similar control may be performed without inputting a code from the result input unit 33 by the operator.

That is, as shown in FIG. 29, a parameter analyzer 24 similar to that used in the first embodiment of FIG. 2 is added to the second embodiment of FIG. When information indicating erroneous recognition is input from the input unit 33,
Based on the analysis result of the corresponding parameter analysis unit 24, the imaging lens 8 may be controlled or the image capturing position may be changed and controlled in the same manner as described above.

Next, a third embodiment will be described.

FIG. 30 is a block diagram showing a configuration of a vehicle number plate recognition device according to the third embodiment. The difference of the third embodiment from the above-described second embodiment is that the correctness information storage as storage means for accumulating and storing confirmation results (correctness determination results) for the recognition results input by the operator from the result input unit 33. And a recognition performance analysis unit 35 for analyzing the storage contents of the correct / incorrect information storage unit 34, and the other parts are the same as those of the second embodiment. The description is omitted.

In the above-described second embodiment, each time the result input unit 33 makes a correct / wrong determination, the lens communication unit 2
3 transmits a control command to control the imaging lens 8 to the lens controller 11 or changes an image capturing position by the input control unit 13. However, in the third embodiment, correct / incorrect information storage is performed. Unit 34 and a recognition performance analysis unit 35, and accumulates and stores the correctness judgment result input by the result input unit 33 in the correctness information storage unit 34 for a predetermined number of times,
The stored contents are analyzed by the recognition performance analysis unit 35, whereby the overall tendency of the recognition result is grasped, and the lens communication unit 23 transmits the lens controller 1 according to the grasped tendency.
A control command for controlling the imaging lens 8 is transmitted to the control unit 1, and a control command for changing an image capturing position is transmitted to the input control unit 13.

FIG. 31 shows an example of the right / wrong judgment result stored in the right / wrong information storage unit 34. In this example, B
Since the number of determination results in which IT1 is “1” is very large, the recognition performance analysis unit 35 analyzes the stored contents and recognizes incorrectly because the number plate is too small in the screen. It is determined that there is a lens communication unit 2
3 transmits a control command to the lens controller 11 to zoom the imaging lens 8.

In the above embodiment, it goes without saying that the quantization precision of the captured image is not limited to 8 bits. The binarization method is disclosed in Japanese Patent Application No. 63-30074.
The method is not limited to the method disclosed in Japanese Patent Publication No. In addition, the analysis of the connected area
Not only labeling but also a method using projection information can be applied. In addition, the method of character recognition is not limited to the pattern matching method, but may be a method such as structural analysis. Furthermore, the recognition accuracy is not limited to the example of the embodiment, and the priority of the recognition items associated therewith is not limited to the embodiment.

[0079]

As described above in detail, according to the vehicle number plate recognition apparatus of the present invention, a captured image is analyzed,
By controlling the zoom, focus, iris and the like of the imaging lens in the imaging means according to the analysis result, the imaging means can be optimally adjusted easily and easily, and good recognition performance is always obtained.

Further, according to the vehicle number plate recognition apparatus of the present invention, the recognition result can be determined by the operator and various settings can be made, so that the adjustment can be performed with higher accuracy. Moreover, since the operator simply inputs using the recognition result and the information indicating the cause of the erroneous recognition, the adjustment can be performed much more easily than in the conventional manual adjustment.

Further, according to the vehicle number plate recognizing device of the present invention, correct / incorrect information corresponding to the recognition result determined and input by the operator is accumulated and stored, and the stored content is analyzed, and the image is taken in accordance with the analysis result. By controlling the zoom, focus, iris and the like of the imaging lens in the means, the overall tendency of the recognition result can be grasped and adjusted according to the grasped tendency.

[Brief description of the drawings]

FIG. 1 is a configuration diagram schematically showing a configuration of a vehicle number plate recognition device according to an embodiment of the present invention.

FIG. 2 is a block diagram showing a configuration of a vehicle number plate recognition device according to the first embodiment.

FIG. 3 is a flowchart illustrating a process of recognizing license plate information and finding a specific vehicle.

FIG. 4 is a diagram showing an example of a captured image.

FIG. 5 is a diagram showing an example of a binarized image.

FIG. 6 is a flowchart illustrating a vehicle number character string detection process.

FIG. 7 is a diagram showing an example of a private / business plate.

FIG. 8 is a diagram for explaining a classification number detection process.

FIG. 9 is a diagram for explaining a detection process of a land transportation branch office code.

FIG. 10 is a view for explaining kana character detection processing.

FIG. 11 is a diagram showing a memory map of a general-purpose memory.

FIG. 12 is a diagram showing another memory map of the general-purpose memory.

FIG. 13 is a flowchart illustrating a procedure for installing a vehicle number plate recognition device in the first embodiment.

14A and 14B are diagrams for explaining a case where the size of a vehicle number is smaller than a set value, wherein FIG. 14A is a diagram illustrating a captured license plate area, and FIG. 14B is a diagram illustrating a detected vehicle number; FIG. 2C is a diagram showing a pattern of a standard number plate.

15A and 15B are diagrams for explaining a case where the size of a vehicle number is smaller than a set value, wherein FIG. 15A is a diagram showing the size of a detected vehicle number, and FIG. The figure which shows the magnitude | size of the standard vehicle number which exists.

16A and 16B are diagrams for explaining a case where a captured image is an out-of-focus image, where FIG. 16A is a diagram illustrating a license plate image, FIG. 16B is a diagram illustrating a binarized image, and FIG. FIG. 3 shows a pattern of a standard number plate.

17A and 17B are diagrams for explaining a case where a captured image is an out-of-focus image, wherein FIG. 17A is a diagram showing the size and area of a detected vehicle number, and FIG. The figure which shows the magnitude | size and area of the vehicle number of FIG.

FIG. 18 is a diagram illustrating a histogram when the number plate is too bright.

FIG. 19 is a diagram showing a histogram when the number plate is too dark.

FIG. 20 is a diagram illustrating an example of a captured image when a number plate is shifted to the left.

FIG. 21 is a diagram illustrating an example of a captured image when a number plate is shifted to the right.

FIG. 22 is a diagram illustrating an example of a captured image when a number plate is shifted upward;

FIG. 23 is a view showing an example of a captured image when the number plate is shifted downward.

FIG. 24 is a block diagram showing a configuration of a vehicle number plate recognition device according to a second embodiment.

FIG. 25 is a flowchart illustrating a procedure for installing a vehicle number plate recognition device according to the second embodiment.

FIG. 26 is a flowchart illustrating a procedure for installing a vehicle number plate recognition device according to the second embodiment.

FIG. 27 is a flowchart illustrating a procedure for installing a vehicle number plate recognition device in the second embodiment.

FIG. 28 is a diagram showing an example of a code representing a cause of erroneous recognition.

FIG. 29 is a block diagram showing a configuration of a vehicle number plate recognition device according to a modification of the second embodiment.

FIG. 30 is a block diagram showing a configuration of a vehicle number plate recognition device according to a third embodiment.

FIG. 31 is a diagram illustrating an example of a correctness / incorrectness determination result stored in a correctness / error information storage unit.

FIG. 32 is a view showing an example of number plate information displayed on a number plate.

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 ... Traveling path, 2 ... Vehicle (automobile), 4 ... Number plate, 5 ... Imaging camera (imaging means), 7 ... Number plate recognition unit, 8 ... Imaging lens, 11 ... Lens controller, 12 A / D conversion unit, 13 Input control unit, 17 Vehicle number detection unit, 18 Classification number detection unit, 19 Land transportation branch office detection unit, 20 Kana character detection unit, 21 ... Size discriminating section, 22... Character recognizing section (recognizing means), 23... Lens communication section, 24... Parameter analyzing section (analyzing means), 25. .., 27... Collating unit (collating means), 32
... Display part (display means), 33... Result input part (input means), 34... True / false information storage part (storage means), 35.
Recognition performance analysis unit (analysis means).

Claims (13)

[Claims] 1. An image pickup means having a controllable image pickup lens for picking up an image including a number plate of a vehicle, and, from an image picked up by the image pickup means, number plate information comprising a plurality of items for each of a plurality of items. A recognition unit for independently recognizing the image, an analysis unit for analyzing an image captured by the imaging unit, and a control unit for controlling an imaging lens of the imaging unit according to an analysis result of the analysis unit. A number plate recognizing device for a vehicle. 2. An image pickup means having a controllable image pickup lens for picking up an image including a number plate of a vehicle, and from the image picked up by the image pickup means, number plate information consisting of a plurality of items for each of a plurality of items. A first input unit for inputting information indicating whether the recognition result displayed on the display unit is correct or not; a first input unit for inputting information indicating whether the recognition result displayed on the display unit is correct; When erroneous recognition is input by the first input means, second input means for inputting information indicating a cause of the erroneous recognition;
Control means for controlling the imaging lens of the imaging means in accordance with the information indicating the cause of the erroneous recognition input by the input means. 3. An image pickup means having a controllable image pickup lens for picking up an image including a number plate of a vehicle, and number plate information comprising a plurality of items is obtained from the image picked up by the image pickup means for each of a plurality of items. Recognition means for independently recognizing the image, analysis means for analyzing an image taken by the imaging means, display means for displaying the recognition result of the recognition means, and whether the recognition result displayed on the display means is correct. Input means for inputting information indicating whether or not erroneous recognition is input by the input means, and control means for controlling an imaging lens of the imaging means according to an analysis result of the analysis means. A vehicle number plate recognizing device characterized by the above-mentioned. 4. An image pickup means having a controllable image pickup lens for picking up an image including a number plate of a vehicle, and from the image picked up by the image pickup means, number plate information consisting of a plurality of items for each of a plurality of items. Recognizing means for independently recognizing the recognition result; display means for displaying the recognition result of the recognizing means; input means for inputting information indicating whether the recognition result displayed on the display means is correct; Storage means for accumulatively storing the information input in step 1, analysis means for analyzing the contents stored in the storage means, control means for controlling the imaging lens of the imaging means according to the analysis result of the analysis means, A number plate recognition device for a vehicle, comprising: 5. The plurality of items recognized by the recognizing means include at least one of items such as a vehicle number, a classification number, a land transportation branch office code, a kana character, a plate size, and a private / business item displayed on a number plate. 5. The vehicle number plate recognition device according to claim 1, wherein the number is two or more. 6. The method according to claim 1, wherein controlling the imaging lens of the imaging means includes controlling at least one of zoom, focus, and iris of the imaging lens.
5. The vehicle number plate recognition device according to 2, 3, or 4. 7. The apparatus according to claim 1, wherein said analysis means analyzes the size and area of a vehicle number in an image picked up by said image pickup means, a histogram of a number plate area, a detection position, and the like. The vehicle number plate recognition device according to claim 3. 8. An image capturing means for capturing an image including a number plate of a vehicle, capturing means for capturing an image captured by the image capturing means, the capturing position of which can be changed, and the capturing means. Recognition means for independently recognizing number plate information consisting of a plurality of items from the image captured in the above step, analysis means for analyzing an image taken by the imaging means, and analysis by the analysis means Control means for changing and controlling an image capturing position by the capturing means in accordance with a result; and a vehicle number plate recognizing device. 9. An image capturing means for capturing an image including a number plate of a vehicle, capturing means for capturing an image captured by the image capturing means, the capturing position being changeable, and the capturing means. A recognizing means for independently recognizing the number plate information composed of a plurality of items for each of the plurality of items from the image captured in step, a display means for displaying a recognition result of the recognizing means, and a display means for displaying the recognition result. First input means for inputting information indicating whether or not the recognition result is correct; and second input means for inputting information representing the cause of the erroneous recognition when the first input means inputs erroneous recognition. When an erroneous recognition is input by the first input means, the second input
Control means for changing and controlling an image capturing position of the image capturing means in accordance with information indicating a cause of erroneous recognition input by the input means. 10. An image capturing means for capturing an image including a number plate of a vehicle, capturing means for capturing an image captured by the image capturing means, the capturing position of which can be changed, and the capturing means. Recognition means for independently recognizing number plate information consisting of a plurality of items for each of a plurality of items from the image captured in step 1, analysis means for analyzing an image taken by the imaging means, and recognition of the recognition means Display means for displaying the result; input means for inputting information indicating whether or not the recognition result displayed on the display means is correct; and, when erroneous recognition is input by the input means, the analysis result of the analysis means Control means for changing and controlling the position at which the image is taken by the taking means in accordance with the following. 11. An image pickup means for picking up an image including a number plate of a vehicle, an image pickup means for picking up an image picked up by the image pickup means, and a changeable position of the image pickup means. A recognizing means for independently recognizing the number plate information composed of a plurality of items for each of the plurality of items from the image captured in step, a display means for displaying a recognition result of the recognizing means, and a display means for displaying the recognition result. Input means for inputting information indicating whether or not the recognition result is correct; storage means for accumulating and storing information input by the input means; analysis means for analyzing the contents stored in the storage means; Control means for changing and controlling an image capturing position of the image capturing means in accordance with an analysis result of the means. 12. The plurality of items recognized by the recognizing means include at least one of items such as a vehicle number, a classification number, a land transportation branch office code, a kana character, a plate size, and a private / business item displayed on a number plate. The vehicle number plate recognition device according to claim 8, 9, 10, or 11, wherein the number is two or more. 13. The apparatus according to claim 8, wherein said analyzing means analyzes a size and an area of a vehicle number, a histogram of a number plate area, a detection position, and the like in the image taken by said image taking means. The vehicle number plate recognition device according to claim 10.