CN117746220B

CN117746220B - Identification detection method, device, equipment and medium for intelligent gateway authenticity license plate

Info

Publication number: CN117746220B
Application number: CN202311748574.2A
Authority: CN
Inventors: 肖勇善; 陈国彬; 罗胜文; 吴杜
Original assignee: Guangdong Ankuai Intelligent Science & Technology Co ltd
Current assignee: Guangdong Ankuai Intelligent Science & Technology Co ltd
Priority date: 2023-12-18
Filing date: 2023-12-18
Publication date: 2024-06-14
Anticipated expiration: 2043-12-18
Also published as: CN117746220A

Abstract

The application relates to a recognition and detection method, a device, equipment and a medium for an intelligent gateway true and false license plate, wherein the method comprises the steps of responding to information of a detection range of a vehicle and acquiring a license plate image; acquiring a license plate image distance and a license plate shooting angle according to the license plate image; acquiring a current license plate shadow area representing the shadow on the predicted license plate image according to the license plate shooting angle and the license plate image distance; identifying the license plate image to obtain a shadow area, and comparing the shadow area with the current license plate shadow area to obtain a comparison result; judging whether the license plate is abnormal or not according to the comparison result, and obtaining a license plate authenticity judgment result. The application has the effect of improving the accuracy of the counterfeit license plate identified by the barrier gate.

Description

Identification detection method, device, equipment and medium for intelligent gateway authenticity license plate

Technical Field

The invention relates to the technical field of license plate recognition, in particular to a recognition and detection method, device, equipment and medium for an intelligent barrier gate true and false license plate.

Background

With the development of science and technology and economy, more and more ordinary families start to purchase automobiles so as to improve the life quality of family members, and the quantity of the automobiles kept is also larger and larger. Therefore, more parking lots need to be built to meet the parking needs of a large number of automobiles. The traditional parking lot generally arranges staff to manage the access of vehicles at the access, but the access management work of the parking lot is simpler, and the number of the parking lots is also large, if each parking lot is provided with staff, the waste of labor cost can be caused. Therefore, related enterprises develop and produce intelligent banisters for replacing manual parking lots, and the intelligent banisters are used for managing the entering and exiting of vehicles, so that the management efficiency is greatly improved, and the labor cost is saved.

However, in order to avoid the charge, some owners can use fake license plates or refit license plates, so that the license plates of vehicles entering and exiting are inconsistent, in the related art, the accuracy of the intelligent barrier gate for identifying the fake license plates is low, the situation that timing charge cannot be carried out on the parking of the vehicles can be caused when the intelligent barrier gate identifies the fake license plates, and further the vehicles can freely enter and exit a parking lot without paying parking fees, loss is caused to the parking lot, and trouble is caused to management of the parking lot.

Disclosure of Invention

In order to improve the accuracy of counterfeit license plates identified by the barrier gate, the application provides an identification and detection method, device and equipment for intelligent barrier gate fake license plates and a medium.

In a first aspect, the above object of the present application is achieved by the following technical solutions:

the identification and detection method for the intelligent barrier authenticity license plate comprises the following steps:

Responding to the information of the vehicle entering the detection range, and acquiring a license plate image;

Acquiring a license plate image distance and a license plate shooting angle according to the license plate image;

Acquiring a current license plate shadow area representing the shadow on the predicted license plate image according to the license plate shooting angle and the license plate image distance;

identifying the license plate image to obtain a shadow area, and comparing the shadow area with the current license plate shadow area to obtain a comparison result;

judging whether the license plate is abnormal or not according to the comparison result, and obtaining a license plate authenticity judgment result.

By adopting the technical scheme, the general car owner evades parking fee by using the fake license plate to be placed in front of the camera of the barrier, for example, a hand painted license plate, a paper license plate and an electronic display screen license plate image, if the barrier recognizes characters in the image photographed by the camera, the car owner can be deceived by the method, therefore, when the car enters the recognition range of the intelligent barrier, the high-definition camera on the intelligent barrier photographs the license plate image, the distance and the angle between the camera on the intelligent barrier and the license plate are obtained, the shadow area formed on the license plate is predicted according to the photographing angle and the image distance of the license plate and the concave-convex part on the recognized license plate type, and the fake license plate is difficult to be reproduced at the concave-convex part on the real license plate, and the fake license plate with the real shadow effect is difficult to be manufactured.

The present application may be further configured in a preferred example to: before the current license plate shadow area representing the shadow on the predicted license plate image is obtained according to the license plate shooting angle and the license plate image distance, the identification and detection method of the intelligent barrier true-false license plate further comprises the following steps:

Judging whether the license plate image distance is within a preset abnormal range, if not, judging that the license plate is abnormal;

if yes, judging that the license plate distance is normal.

By adopting the technical scheme, before judging the shadow area of the license plate, judging the distance between the license plate on the photographed license plate image and the camera on the barrier gate, judging whether the license plate image distance is in a preset abnormal range, if the license plate image distance is in the preset abnormal range, judging that the distance between the license plate on the moment and the camera on the barrier gate is too close, and the distance between the license plate on the vehicle which normally runs and the camera on the barrier gate cannot be smaller than the preset abnormal range, at the moment, the license plate image photographed by the camera on the barrier gate is likely to be manually placed in front of the camera on the barrier gate, so that whether the license plate image distance is abnormal is judged, and before the depth recognition judgment, judging whether the license plate image distance is abnormal in advance, thereby improving the recognition detection efficiency and avoiding the waste of resources.

The present application may be further configured in a preferred example to: and if so, judging that the license plate is preliminary normal, and before acquiring the current license plate shadow area representing the shadow on the predicted license plate image according to the license plate shooting angle and the license plate image distance, the intelligent barrier authenticity license plate recognition and detection method further comprises the following steps:

Generating license plate shape frame information for judging whether the shape of the license plate is deformed or not according to the license plate image distance and the license plate shooting angle;

Comparing the license plate image with the license plate shape frame information to obtain license plate frame deviation value information;

if the license plate frame deviation value information is larger than a preset license plate frame deviation threshold value, judging that the license plate is abnormal;

If the license plate frame deviation value information is smaller than a preset license plate frame deviation threshold value, judging that the license plate is normal in shape.

By adopting the technical scheme, the photographed license plate image is primarily identified, the position of the license plate in the whole license plate image is judged, the shape frame of the license plate on the vehicle which normally runs at the distance and the angle, namely the shape outline of the license plate, is generated according to the distance and the license plate photographing angle of the license plate image, the generated license plate shape frame is compared with the license plate on the license plate image, the deviation of the license plate on the license plate image and the generated license plate shape frame is judged, if the deviation of the license plate on the license plate image and the generated license plate shape frame is larger than the preset license plate frame deviation threshold, the license plate is judged to be deformed to the extent that the license plate number is difficult to identify, and the license plate is judged to be abnormal. Based on the method, before the depth recognition judgment is carried out, whether the license plate distance is abnormal or not is further judged, so that recognition and detection efficiency is further improved, and resource waste is avoided.

The present application may be further configured in a preferred example to: the obtaining, according to the license plate shooting angle and the license plate image distance, a current license plate shadow area representing a shadow on a predicted license plate image specifically includes:

Acquiring external environment information in real time, and acquiring an environment coefficient for adjusting the shadow area of a license plate according to the external environment information;

Acquiring a license plate shadow area representing the shadow on the predicted license plate image according to the license plate shooting angle and the license plate image distance;

and adjusting the license plate shadow area according to the environmental coefficient to obtain the current license plate shadow area.

Through adopting above-mentioned technical scheme, the external environment of the place of installation of banister can produce certain negative effect to banister discernment license plate, for example, thick fog and sleet weather can lead to the discernment visibility of camera on the banister to reduce and can lead to the shadow area on the license plate to reduce, and the illumination is sufficient and light can lead to the shadow area on the license plate to reduce etc. when just facing the license plate, consequently, obtain external environment information, including external weather condition and external lamp source illumination condition, the shadow area that can form on the license plate of adjustment prediction is corresponding according to external environment information, make the shadow area that can form on the license plate of prediction more accurate, thereby improve the correct rate that the banister discerned fake license plate.

The present application may be further configured in a preferred example to: the license plate image is identified, a shadow area is obtained, the shadow area is compared with the current license plate shadow area, and a comparison result is obtained, specifically comprising:

Identifying the license plate image to obtain a shadow area, a high light area and a reflective bright spot area;

acquiring a current license plate highlight area representing the highlight on the predicted current license plate image and a current license plate reflective bright spot area representing the reflective bright spot on the predicted current license plate image according to the environmental coefficient, the license plate shooting angle and the license plate image distance;

and respectively comparing the shadow area, gao Guangmian and the reflective bright spot area with the corresponding shadow area of the current license plate, the high-light area of the current license plate and the reflective bright spot area of the current license plate to obtain a comparison result.

Through adopting above-mentioned technical scheme, except the shade, when receiving the illumination, still can appear highlight part and reflection of light bright spot part on the license plate, consequently, except obtaining the shadow area that can form on the license plate of prediction, obtain the highlight area that can form on the license plate of prediction again and reflection of light bright spot area, contrast shadow area, highlight area and reflection of light bright spot area on the license plate image with the shadow area that can form on the license plate of corresponding prediction respectively, highlight area and reflection of light bright spot area, thereby further improve the barrier and discerned the correct rate of counterfeit fake license plate.

The present application may be further configured in a preferred example to: after judging whether the license plate is abnormal according to the comparison result and obtaining the license plate authenticity judgment result, the identification and detection method of the intelligent barrier authenticity license plate further comprises the following steps:

Identifying the license plate image and obtaining license plate information;

Acquiring variable license plate region information corresponding to the license plate information and representing a region which is easy to tamper on a license plate from a preset license plate information database;

Amplifying the part of the license plate image corresponding to the variable-change license plate region information to obtain variable-change license plate region amplified information;

identifying the variable change license plate region amplification information, judging whether the variable change license plate region amplification information is abnormal or not, and obtaining a judgment result;

and updating the license plate authenticity judgment result according to the judgment result.

By adopting the technical scheme, the method for avoiding parking fees for general owners not only uses fake license plates such as hand-drawn license plates, paper license plates, electronic display screen license plate images and the like to be placed in front of cameras of the barrier gate, but also can refit original real license plates and change a certain character on the license plates, thereby achieving the effect of fake license plates. Therefore, for the easy-to-tamper character in all the characters appearing on the license plate, the easy-to-tamper part of the easy-to-tamper character is judged, for example, the Arabic numerals 3 and 8 are easy to realize mutual transformation and tamper, the easy-to-tamper part judges whether the easy-to-tamper character is different from the other areas in the license plate image or not in the time of identifying and detecting the license plate by the barrier gate, and judges whether the character on the license plate corresponds to the character in the preset license plate information database, namely, judges whether the character on the license plate is the easy-to-tamper character, if the character on the license plate is the easy-to-tamper character, the easy-to-tamper character area information corresponding to the easy-to-tamper character in the preset license plate information database is obtained, the image corresponding to the area on the license plate image is amplified, and the amplified image is recognized more deeply, for example, the parameters such as the color rendering degree of the easy-to-tamper license plate area are different from the other areas in the license plate image are identified, or the line degree and pixel arrangement of the easy-to-tamper area are identified, so that the fake license plate can be identified more accurately, and the fake license plate can be identified is further.

In a second aspect, the above object of the present application is achieved by the following technical solutions:

the utility model provides a recognition detection device of intelligent barrier true and false license plate, recognition detection device of intelligent barrier true and false license plate includes:

The license plate image acquisition module is used for responding to the information of the entering detection range of the vehicle to acquire a license plate image;

the license plate and camera angular distance acquisition module is used for acquiring a license plate image distance and a license plate shooting angle according to the license plate image;

The current license plate shadow area acquisition module is used for acquiring the current license plate shadow area representing the shadow on the predicted license plate image according to the license plate shooting angle and the license plate image distance;

The comparison result acquisition module is used for identifying the license plate image, obtaining a shadow area, and comparing the shadow area with the current license plate shadow area to obtain a comparison result;

And the license plate authenticity judgment result acquisition module is used for judging whether the license plate is abnormal according to the comparison result to acquire a license plate authenticity judgment result.

Optionally, the identification and detection device for the intelligent gateway true and false license plate further comprises:

the license plate image distance judging module is used for judging whether the license plate image distance is in a preset abnormal range or not, and judging that the license plate is abnormal if the license plate image distance is not in the preset abnormal range;

and the license plate image distance judging and normal module is used for judging that the license plate distance is normal if the license plate image distance is judged to be yes.

In a third aspect, the above object of the present application is achieved by the following technical solutions:

The computer equipment comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor realizes the steps of the identification and detection method of the intelligent barrier gate true and false license plate when executing the computer program.

In a fourth aspect, the above object of the present application is achieved by the following technical solutions:

A computer readable storage medium storing a computer program which when executed by a processor implements the steps of the method for identifying and detecting the authenticity of the intelligent barrier license plate.

In summary, the present application includes at least one of the following beneficial technical effects:

1. The shadow on the license plate is judged through the license plate shooting angle and the license plate image distance, so that whether the license plate image shot and identified by the barrier gate is an image under the condition of normal condition light shadow is judged, and the accuracy of the barrier gate for identifying fake license plates is improved;

2. before judging the shadow area of the license plate, judging whether the license plate image distance is abnormal or not, so that before carrying out depth identification judgment, judging whether the license plate distance is abnormal or not, improving the identification and detection efficiency and avoiding the waste of resources;

3. The depth identification judgment of the variable license plate region is further realized, so that the accuracy of the counterfeit license plate identified by the barrier gate is improved.

Drawings

FIG. 1 is a flowchart of a first implementation of a method for identifying and detecting authenticity of a license plate of an intelligent barrier according to an embodiment of the present application;

FIG. 2 is a flowchart of a second implementation of a method for identifying and detecting authenticity of a license plate of an intelligent barrier according to an embodiment of the present application;

FIG. 3 is a flowchart of a third implementation of a method for identifying and detecting authenticity of a license plate of an intelligent barrier according to an embodiment of the present application;

FIG. 4 is a flowchart of an implementation of S30 of a method for identifying and detecting authenticity of a license plate of an intelligent barrier according to an embodiment of the present application;

FIG. 5 is a flowchart of an implementation of S40 of a method for identifying and detecting authenticity of a license plate of an intelligent barrier according to an embodiment of the present application;

FIG. 6 is a flowchart of a fourth implementation of a method for identifying and detecting authenticity of a license plate of an intelligent barrier according to an embodiment of the present application;

FIG. 7 is a schematic block diagram of a device for identifying and detecting the authenticity of a license plate of an intelligent barrier according to an embodiment of the present application;

Fig. 8 is an internal structure diagram of a computer device for identifying and detecting the authenticity of a license plate of an intelligent barrier in an embodiment of the application.

Detailed Description

The application is described in further detail below with reference to fig. 1-8.

In an embodiment, as shown in fig. 1, the application discloses a method for identifying and detecting the authenticity of an intelligent barrier license plate, which specifically comprises the following steps:

s10: and acquiring a license plate image in response to the information of the vehicle entering the detection range.

In the present embodiment, the vehicle entry detection range information refers to information indicating an identification detection range of the vehicle entry into the intelligent barrier. The license plate image refers to an image of a license plate on a vehicle, which is shot by a camera on the intelligent barrier.

Specifically, the intelligent barrier refers to equipment which is installed in a parking lot and can identify license plate numbers to manage vehicles entering and exiting the parking lot, after the vehicles enter the identification detection range of the intelligent barrier, namely, in response to the information of the vehicle entering the detection range, a camera on the intelligent barrier shoots images of license plates on the vehicles to obtain license plate images, in the embodiment, the mode of triggering the camera on the intelligent barrier to shoot the images of the license plates on the vehicles can be selected as video identification triggering or ground induction triggering, namely, the video identification triggering after the vehicles enter the detection range or the triggering when the vehicles pass through a ground induction coil installed in advance.

Further, after the license plate image is obtained, the license plate image is identified and the license plate part in the license plate image is judged because the license plate image contains more than the license plate image.

S20: and acquiring a license plate image distance and a license plate shooting angle according to the license plate image.

In this embodiment, the license plate image distance refers to the distance between the camera on the intelligent barrier and the license plate. The license plate shooting angle is an angle value of a horizontal included angle formed between the shooting direction of a camera on the intelligent barrier and a license plate.

Specifically, the camera on the intelligent barrier in this embodiment is a high-definition camera with a ranging function, so when the camera on the intelligent barrier shoots a license plate image, the distance between the camera with the ranging function and the license plate is acquired simultaneously, the license plate image distance is obtained, and according to the shooting direction of the camera on the intelligent barrier, the angle value of a horizontal included angle formed between the shooting direction of the camera on the intelligent barrier and the license plate is calculated according to the shooting direction of the camera on the intelligent barrier and the license plate image distance, and the license plate shooting angle is obtained.

S30: and acquiring a current license plate shadow area representing the shadow on the predicted license plate image according to the license plate shooting angle and the license plate image distance.

In this embodiment, the current license plate shadow area refers to the area and position of the shadow portion of the license plate portion in the predicted license plate image.

Specifically, the surface of a general license plate is uneven, the concave-convex parts of the license plate are not only concave-convex parts formed by characters, but also concave-convex parts relative to the surface of the license plate formed by fixing parts similar to fixing bolts for installing the license plate, so that certain shadow is formed when light with a certain angle is irradiated onto the license plate, and therefore, according to the current time point, whether a light source at the moment except a light source on an intelligent barrier is provided with solar illumination or not is judged, the angle and intensity of illumination received by the license plate at the moment are obtained after comprehensive judgment, and then the horizontal included angle formed between the shooting direction of a camera on the intelligent barrier and the license plate and the distance between the camera on the intelligent barrier and the license plate are combined, so that the shadow area and the shadow position formed by the concave-convex parts of the license plate part in a license plate image are predicted and judged, and the current license plate shadow area is obtained.

Further, after the photographed license plate image is obtained, the license plate type of the license plate image is identified, and according to the type of the license plate, the generated current license plate shadow area is a shadow formed at the concave-convex part of the predicted license plate image corresponding to the type of the license plate.

S40: and identifying the license plate image, obtaining a shadow area, and comparing the shadow area with the current license plate shadow area to obtain a comparison result.

In the present embodiment, the shadow area refers to the area and position of the shadow of the license plate portion in the license plate image. The comparison result refers to the comparison result of the shadow area and the shadow area of the current license plate.

Specifically, before the acquired license plate image is identified, the license plate image can be subjected to preliminary processing by using a background homogenization algorithm according to the definition degree of the license plate image, the processed license plate image is identified, the color distribution of the license plate part in the license plate image is identified, the license plate part in the license plate image is analyzed to be a shadow part through a binarization algorithm, the shadow part which is not caused by the concave-convex part of the license plate is removed, for example, the shadow part which is larger than the common size and the shadow part which is not in the common position are removed by judging the common size and the position of the shadow part which is not in the common position of the license plate concave-convex part, so that the area and the position of the shadow part in the license plate image, namely the shadow area, are obtained, and the shadow area and the current shadow area are compared, so that a comparison result is obtained.

S50: judging whether the license plate is abnormal or not according to the comparison result, and obtaining a license plate authenticity judgment result.

In this embodiment, the license plate authenticity judgment result refers to a result indicating whether the judged license plate is authentic.

Specifically, according to a comparison result, the comparison result comprises the size of a distinguishing shadow area and the number of distinguishing shadow positions, wherein the size of the distinguishing shadow area is different from the current license plate shadow area, the size of the distinguishing shadow area in the comparison result is compared with a preset shadow area threshold value, the number of the distinguishing shadow area in the comparison result is compared with a preset shadow number threshold value, and if the distinguishing shadow area is larger than the preset shadow area threshold value and/or the number of the distinguishing shadow positions is larger than the preset shadow number threshold value, the license plate at the moment is judged to be an abnormal license plate, and a license plate authenticity judgment result for judging the license plate to be a fake license plate is obtained; if the difference shadow area is smaller than the preset shadow area threshold value and the number of the difference shadow positions is smaller than the preset shadow number threshold value, judging that the license plate at the moment is a normal license plate, and obtaining a judgment result of judging that the license plate is a normal license plate.

In an embodiment, as shown in fig. 2, before step S30, the method for identifying and detecting the license plate of the intelligent barrier further includes:

S301: judging whether the license plate image distance is within a preset abnormal range, and if not, judging that the license plate is abnormal.

Specifically, before judging the shadow area of the license plate image, firstly judging whether the acquired license plate image distance is within a preset abnormal range or not, if so, indicating that the license plate on the current vehicle is not on the vehicle which normally runs, and if so, judging that the distance between the license plate and a camera on the intelligent barrier is abnormal, and judging that the license plate in the license plate image is an abnormal license plate.

S302: if yes, judging that the license plate distance is normal.

Specifically, if the license plate image distance is judged to be within the preset abnormal range, the license plate on the current vehicle is indicated to be on the vehicle which normally runs, and the distance between the license plate at the moment and the camera on the intelligent barrier gate is judged to be normal.

In an embodiment, as shown in fig. 3, after step S302, before step S30, the method for identifying and detecting the license plate of the smart barrier further includes:

S3021: and generating license plate shape frame information for judging whether the license plate shape is deformed or not according to the license plate image distance and the license plate shooting angle.

In this embodiment, license plate shape frame information refers to outline frame graphic information representing a normal license plate.

Specifically, the photographed license plate image is primarily identified, the position of a license plate part in the whole license plate image is judged, and a contour frame figure of the license plate on a vehicle which normally runs and is used for judging whether the shape of the license plate is deformed or not under the distance and the angle is generated according to the distance of the license plate image and the license plate photographing angle, namely license plate shape frame information.

Further, when the photographed license plate image is primarily identified, the type and the position of the license plate are identified, the generated license plate shape frame information is license plate shape frame information corresponding to the outline frame of the license plate, and the position of the generated license plate shape frame information corresponds to the outline frame graph of the license plate in the license plate image.

S3022: and comparing the license plate image with license plate shape frame information to obtain license plate frame deviation value information.

In this embodiment, license plate frame deviation value information refers to information indicating the degree of deviation of a contour frame pattern of a license plate in a license plate image from a license plate shape frame.

Specifically, when the license plate image is primarily identified, the outline frame graph of the license plate part in the license plate image is identified, the generated license plate shape frame information is corresponding to the position of the license plate part in the license plate image, the outline frame graph of the license plate in the license plate image is compared with the outline frame graph expressed by the license plate shape frame, the overlapping degree of the outline frame graph of the license plate in the license plate image and the outline frame graph expressed by the license plate shape frame is judged, and the deviation degree of the outline frame graph of the license plate in the corresponding license plate image and the license plate shape frame, namely license plate frame deviation value information is obtained.

S3023: if the license plate frame deviation value information is larger than a preset license plate frame deviation threshold value, judging that the license plate is abnormal.

Specifically, if the deviation degree of the outline frame graph of the license plate in the license plate image represented by the license plate frame deviation value information and the license plate shape frame is larger than a preset license plate frame deviation threshold value, judging that the license plate belongs to the degree that the license plate number is deformed to be difficult to recognize, and judging that the license plate in the license plate image is abnormal.

S3024: if the license plate frame deviation value information is smaller than a preset license plate frame deviation threshold value, judging that the license plate is normal in shape.

Specifically, if the deviation degree of the outline frame graph of the license plate in the license plate image represented by the license plate frame deviation value information and the license plate shape frame is smaller than a preset license plate frame deviation threshold value, judging that the shape of the license plate in the license plate image is normal.

In one embodiment, as shown in fig. 4, in step S30, a current license plate shadow area representing a shadow on a predicted license plate image is obtained according to a license plate photographing angle and a license plate image distance, and specifically includes:

s31: and acquiring external environment information in real time, and acquiring an environment coefficient for adjusting the shadow area of the license plate according to the external environment information.

In this embodiment, the external environment information refers to the illumination condition and weather condition information of the current intelligent barrier installation site. The environmental coefficient is a coefficient for adjusting a shadow area of a license plate portion in a license plate image.

Specifically, in the operation process of the intelligent barrier, the external illumination condition and weather condition information, namely the external environment information, of the current intelligent barrier mounting place are obtained in real time, wherein the external illumination condition of the current intelligent barrier mounting place comprises the external light source illumination intensity and angle and the sun illumination angle and intensity, therefore, if the weather condition information indicates that the current weather condition is rainy, snowy, thick fog and cloudy days, corresponding weather coefficients are obtained from a preset weather coefficient database in a summarizing mode, each different weather condition corresponds to different weather coefficients, the weather coefficients indicate the influence degree of the current weather condition on the shadow formed by the license plate part in the license plate image, the corresponding illumination coefficients are obtained from the preset illumination coefficient database according to the illumination condition of the current intelligent barrier mounting place, and similarly, the illumination coefficients indicate the influence degree of the current external illumination on the shadow formed by the license plate part in the license plate image, and the sum of the obtained illumination coefficients and the weather coefficients are calculated, so that the environment coefficients for adjusting the shadow area of the license plate part in the image are obtained.

Further, in the preset illumination coefficient database, the illumination coefficients corresponding to different external illumination angles under the same external illumination intensity are different, and the illumination coefficients corresponding to the different illumination angles under the same external illumination intensity are also related to the license plate shooting angles, for example, the external illumination intensity and the external illumination angle corresponding to a plurality of illumination coefficients are the same, but the corresponding license plate shooting angles are different, and the plurality of illumination coefficients are also different, because the illumination coefficients not only consider the influence of the illumination intensity on the formation of shadows on license plate parts in license plate images, but also consider the influence of illumination at different angles on the formation of shadows on license plate parts in license plate images, so that the smaller the difference between the external illumination angle and the license plate shooting angle is, the smaller the corresponding illumination coefficient is.

S32: and acquiring a license plate shadow area representing the shadow on the predicted license plate image according to the license plate shooting angle and the license plate image distance.

In this embodiment, the license plate shadow area refers to a shadow area on a license plate image that is not subjected to environmental coefficient adjustment.

Specifically, according to the license plate shooting angle and the license plate image distance, and the illumination intensity and the angle of a light source on an intelligent barrier gate to a license plate, predicting and judging the shadow part of the license plate part in the license plate image at the moment to obtain a license plate shadow area, wherein the license plate shadow area comprises the size of the shadow area and the number of the shadow positions.

S33: and adjusting the license plate shadow area according to the environmental coefficient to obtain the current license plate shadow area.

Specifically, the license plate shadow area is adjusted according to the environmental coefficient, namely, the value of the environmental coefficient is used, the size of the shadow area and the number of the shadow positions in the license plate shadow area in the license plate image are correspondingly reduced or increased, and the current license plate shadow area of the shadow of the license plate part in the predicted license plate image after the environmental coefficient adjustment is obtained.

In one embodiment, as shown in fig. 5, in step S40, a license plate image is identified, a shadow area is obtained, and the shadow area is compared with a current license plate shadow area to obtain a comparison result, which specifically includes:

s41: and identifying license plate images to obtain shadow areas, high light areas and reflective bright spot areas.

In this embodiment, the highlight area refers to the area and position of the highlight of the license plate portion in the license plate image. The reflective bright spot area refers to the area and the position of the reflective bright spot of the license plate part in the license plate image.

Specifically, a license plate image is identified, the color distribution of a license plate part in the license plate image is identified, the parts which are shadows, highlights and reflective bright spots in the license plate image are analyzed through a binarization algorithm, and the shadow parts which are not caused by the concave-convex parts of the license plate and the reflective bright spot parts which are caused by the reflective of non-license plate materials are removed, for example, the shadow parts which are larger than the common size and the shadows which are not in the common position are removed by judging the common size and the positions of the shadows which are generated by the concave-convex parts of the license plate, the materials of the license plate of the type are judged by the type of the license plate, and the areas and the positions of the shadows, highlights and the reflective bright spot parts which are not caused by the materials of the reflective bright spots are removed, so that the shadow areas, the highlights and the reflective bright spot areas of the license plate parts in the license plate image are obtained.

S42: and acquiring a current license plate highlight area representing the highlight on the predicted current license plate image and a current license plate reflective bright spot area representing the reflective bright spot on the predicted current license plate image according to the environmental coefficient, the license plate shooting angle and the license plate image distance.

In this embodiment, the current license plate highlight area refers to the area and position of the highlight part of the license plate part in the predicted license plate image after the environmental coefficient is adjusted. The current license plate reflective bright spot area refers to the area and the position of the reflective bright spot part of the license plate part in the predicted license plate image after the environmental coefficient is adjusted.

Specifically, according to the illumination coefficient and the weather coefficient in the environment coefficient, the corresponding weather coefficient can also represent the influence degree of the current weather condition on the formation of shadows on the license plate, besides the influence degree of the current weather condition on the formation of highlights and light reflection bright spots on the license plate part in the license plate image, because if the current weather condition is bad, the transmission of light is also unfavorable, and further the formation of highlights and light reflection bright spots on the license plate part in the license plate image is influenced, the illumination coefficient represents the influence degree of the current external illumination condition on the formation of shadows on the license plate part in the license plate image, and simultaneously represents the current external illumination intensity and angle, so that the illumination coefficient can also be used for the influence degree of the current external illumination condition on the formation of highlights and light reflection bright spots on the license plate part in the license plate image. Therefore, according to the license plate shooting angle and the license plate image distance, and the illumination intensity and angle of the light source on the intelligent barrier gate to the license plate, the area and the quantity of the highlight part of the license plate part in the license plate image at the moment and the area and the quantity of the light reflecting bright point part are predicted and judged, namely the license plate highlight area and the license plate light reflecting bright point area, and then the value of the environment coefficient is used for correspondingly reducing or increasing the corresponding highlight area and the corresponding quantity of the position and the quantity of the light reflecting bright point area in the license plate highlight area, so that the area and the position of the highlight part of the license plate part in the predicted license plate image after the adjustment of the environment coefficient, namely the current license plate highlight area and the position of the light reflecting bright point part of the license plate part in the predicted license plate image, namely the current license plate light reflecting bright point area are obtained.

S43: and respectively comparing the shadow area, the high-light area and the reflective bright spot area with the corresponding shadow area of the current license plate, the high-light area of the current license plate and the reflective bright spot area of the current license plate to obtain a comparison result.

The method comprises the steps of respectively comparing a shadow area, a highlight area and a reflective bright spot area with a corresponding current license plate shadow area, a current license plate highlight area and a current license plate reflective bright spot area, namely respectively comparing the shadow area size and the shadow position number represented by the shadow area with the shadow area size and the shadow position number represented by the current license plate shadow area, comparing the highlight area size and the highlight position number represented by the highlight area with the highlight area size and the highlight position number represented by the current license plate highlight area, and comparing the reflective bright spot area size and the reflective bright spot position number represented by the reflective bright spot area with the reflective bright spot area size and the reflective bright spot position number represented by the current license plate reflective bright spot area to obtain a comparison result.

Further, after a comparison result is obtained, the comparison result comprises a difference shadow area size and a difference shadow position number, wherein the shadow area size is different from the current license plate shadow area, the difference shadow position number and the difference highlight position number are different from the current license plate highlight area, and a difference light reflection bright spot area size and a difference light reflection bright spot position number, wherein the light reflection bright spot area is different from the current license plate light reflection bright spot area; at this time, six conditions for judging the authenticity of the license plate are respectively

First: the distinguishing shadow area is larger than a preset shadow area threshold value and/or the number of distinguishing shadow positions is larger than a preset shadow number threshold value;

second,: the number of the different shadow areas is larger than a preset shadow area threshold value or the number of the different shadow positions is larger than a preset shadow number threshold value;

Third,: the distinguishing highlight area is larger than a preset highlight area threshold value, and the distinguishing highlight position number is larger than a preset highlight number threshold value;

Fourth,: the distinguishing highlight area is larger than a preset highlight area threshold value or the distinguishing highlight position number is larger than a preset highlight number threshold value;

Fifth,: the area of the distinguishing reflective bright spots is larger than a preset reflective bright spot area threshold value, and the number of the distinguishing reflective bright spots is larger than a preset reflective bright spot number threshold value;

Sixth: the area of the distinguishing reflective bright spots is larger than a preset reflective bright spot area threshold value or the number of the distinguishing reflective bright spots is larger than a preset reflective bright spot number threshold value;

When four or more than four of the six conditions are met, judging that the license plate at the moment is an abnormal license plate, and obtaining a license plate authenticity judgment result for judging that the license plate is a fake license plate; if the number of the license plate is only three or less than three of the six conditions, judging that the license plate at the moment is a normal license plate, and obtaining a judgment result of judging that the license plate is a normal license plate.

In an embodiment, as shown in fig. 6, after step S50, the method for identifying and detecting the license plate of the intelligent barrier further includes:

s60: and identifying license plate images and obtaining license plate information.

In this embodiment, the license plate information refers to character information on the license plate.

Specifically, a license plate part in a license plate image is identified, and character information, namely license plate information, on a license plate is obtained.

S70: and acquiring variable license plate region information corresponding to license plate information and representing a region which is easy to tamper on a license plate from a preset license plate information database.

In this embodiment, the variable license plate region information refers to a region on the license plate that is easily tampered with.

Specifically, according to the characters on the license plate represented by the license plate information, the region which is easy to tamper and corresponds to the characters on the license plate, namely the region information of the license plate which is easy to change, for example, the standard Arabic numerals 3 in the standard field character lattice are easy to tamper and change the left half of the Arabic numerals 3 into Arabic numerals 8, so that when the characters on the license plate are Arabic numerals 3, the corresponding region information of the license plate which is easy to change is the left half of the Arabic numerals 3 on the license plate.

S80: and amplifying the part corresponding to the variable license plate region information on the license plate image to obtain variable license plate region amplified information.

In this embodiment, the variable-change license plate region enlarged information refers to information obtained by enlarging a portion of the license plate image corresponding to the variable-change license plate region information.

Specifically, if characters on a license plate in the license plate image have corresponding variable license plate region information, amplifying a part of the corresponding variable license plate region information in the license plate image, namely amplifying the license plate image of the part, and obtaining the amplified image of the part and the information of the image of the part, namely amplifying the variable license plate region information.

S90: and identifying the variable license plate region amplification information, judging whether the variable license plate region amplification information is abnormal, and obtaining a judging result.

In this embodiment, the determination result refers to a result of determining whether or not the variable license plate region enlarged information is abnormal.

Specifically, the enlarged information of the variable license plate area is identified, namely, whether the color rendering degree of the variable license plate area is different from other areas in the license plate image is identified and judged, whether the line fluency and the pixel arrangement uniformity of the variable license plate area are different from other areas in the license plate image is identified and judged, and if the color rendering degree of the variable license plate area is different from other areas in the license plate image and/or the line fluency and the pixel arrangement uniformity of the variable license plate area are different from other areas in the license plate image is identified and judged, a judging result indicating that the license plate is suspected to be tampered is obtained, and if the color rendering degree of the variable license plate area is the same as the other areas in the license plate image and the line fluency and the pixel arrangement uniformity of the variable license plate area are the same as the other areas in the license plate image, a judging result indicating that the license plate is not tampered is obtained.

S100: and updating the license plate authenticity judgment result according to the judgment result.

Specifically, if the license plate authenticity judgment result is that the license plate is normal, and the judgment result indicates that the license plate is suspected to be tampered, updating the license plate authenticity judgment result to be that the license plate is suspected to be tampered; if the license plate authenticity judgment result is that the license plate is a normal license plate, the license plate is not tampered, and the license plate authenticity judgment result does not need to be updated; if the license plate is judged to be abnormal, and the license plate is judged to be suspected to be tampered, the judgment result is associated and combined to the license plate true and false judgment result; if the license plate authenticity judgment result is that the license plate is an abnormal license plate and the judgment result indicates that the license plate is not tampered, the license plate authenticity judgment result does not need to be updated.

It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present application.

In an embodiment, a device for identifying and detecting an intelligent barrier authenticity license plate is provided, where the device for identifying and detecting an intelligent barrier authenticity license plate is in one-to-one correspondence with the method for identifying and detecting an intelligent barrier authenticity license plate in the above embodiment. As shown in fig. 7, the identification and detection device for the intelligent barrier authenticity license plate comprises a license plate image acquisition module, a license plate and camera angle distance acquisition module, a current license plate shadow area acquisition module, a comparison result acquisition module and a license plate authenticity judgment result acquisition module. The functional modules are described in detail as follows:

the license plate and camera angular distance acquisition module is used for acquiring a license plate image distance and a license plate shooting angle according to a license plate image;

The comparison result acquisition module is used for identifying license plate images, obtaining shadow areas, and comparing the shadow areas with the current license plate shadow areas to obtain comparison results;

the license plate shape frame information generating module is used for generating license plate shape frame information for judging whether the shape of the license plate is deformed or not according to the license plate image distance and the license plate shooting angle;

The license plate frame deviation value information acquisition module is used for comparing the license plate image with license plate shape frame information to acquire license plate frame deviation value information;

the license plate abnormality judging module is used for judging that the license plate is abnormal if the license plate frame deviation value information is larger than a preset license plate frame deviation threshold value;

The license plate shape normal judging module is used for judging that the license plate shape is normal if the license plate frame deviation value information is smaller than a preset license plate frame deviation threshold value.

Optionally, the current license plate shadow area obtaining module includes:

the environment coefficient acquisition sub-module is used for acquiring external environment information in real time and acquiring an environment coefficient for adjusting the shadow area of the license plate according to the external environment information;

The license plate shadow area acquisition sub-module is used for acquiring a license plate shadow area representing the shadow on the predicted license plate image according to the license plate shooting angle and the license plate image distance;

The current license plate shadow area obtaining sub-module is used for adjusting the license plate shadow area according to the environmental coefficient to obtain the current license plate shadow area.

Optionally, the comparison result obtaining module includes:

various special area acquisition sub-modules are used for identifying license plate images and acquiring shadow areas, high light areas and reflective bright spot areas;

The prediction special area acquisition sub-module is used for acquiring a current license plate highlight area representing highlight on a predicted current license plate image and a current license plate reflective bright spot area representing reflective bright spots on the predicted current license plate image according to the environmental coefficient, the license plate shooting angle and the license plate image distance;

The comparison result obtaining submodule is used for respectively comparing the shadow area, the high-light area and the reflective bright spot area with the corresponding shadow area of the current license plate, the high-light area of the current license plate and the reflective bright spot area of the current license plate to obtain a comparison result.

The license plate information acquisition module is used for identifying license plate images and acquiring license plate information;

the variable license plate region information acquisition module is used for acquiring variable license plate region information of a region which corresponds to license plate information and is easy to tamper on a license plate from a preset license plate information database;

The variable license plate region amplified information acquisition module is used for amplifying the part corresponding to the variable license plate region information on the license plate image to acquire variable license plate region amplified information;

The judging result acquisition module is used for identifying the variable license plate region amplified information, judging whether the variable license plate region amplified information is abnormal or not and acquiring a judging result;

and the license plate authenticity judgment result updating module is used for updating the license plate authenticity judgment result according to the judgment result.

The specific limitation of the identification and detection device for the intelligent barrier authenticity license plate can be referred to the limitation of the identification and detection method for the intelligent barrier authenticity license plate hereinabove, and will not be described herein. All or part of each module in the intelligent barrier gate true-false license plate recognition and detection device can be realized through software, hardware and combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer equipment is used for storing lane images, license plate image distances, license plate shooting angles, current license plate shadow areas, comparison results, license plate authenticity judging results and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by the processor to realize a method for identifying and detecting the fake license plate of the intelligent barrier gate.

In one embodiment, a computer device is provided comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of when executing the computer program:

identifying a license plate image, obtaining a shadow area, and comparing the shadow area with the current license plate shadow area to obtain a comparison result;

In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.

The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.

Claims

1. The identification and detection method for the intelligent barrier authenticity license plate is characterized by comprising the following steps of:

Acquiring a license plate image distance and a license plate shooting angle according to the license plate image, wherein the license plate image distance refers to the distance between a camera on an intelligent barrier and a license plate;

Acquiring a predicted license plate shadow area on the license plate image according to the license plate shooting angle and the license plate image distance, wherein the predicted license plate shadow area refers to the size of the shadow area and the number of shadow positions of a predicted shadow part on the license plate image;

Identifying the license plate image to obtain an identified license plate shadow area, comparing the identified license plate shadow area with the predicted license plate shadow area to obtain a comparison result, wherein the identified license plate shadow area refers to the area and the position of a shadow part of a license plate part in the license plate image obtained by identifying the license plate image, and the identified license plate shadow area is obtained by processing the license plate image through a preset image identification algorithm;

judging whether the license plate is abnormal or not according to the comparison result, and obtaining a license plate authenticity judgment result;

The obtaining the predicted license plate shadow area on the license plate image according to the license plate shooting angle and the license plate image distance specifically comprises the following steps:

Acquiring a license plate shadow area representing predicted shadows on a license plate image according to the license plate shooting angle and the license plate image distance;

And adjusting the license plate shadow area according to the environmental coefficient to obtain a predicted license plate shadow area.

2. The method for identifying and detecting an intelligent barrier authenticity license plate according to claim 1, wherein before the license plate shadow area predicted on the license plate image is obtained according to the license plate shooting angle and the license plate image distance, the method for identifying and detecting an intelligent barrier authenticity license plate further comprises:

Judging whether the license plate image distance is within a preset abnormal range, if so, judging that the license plate is abnormal;

If not, judging that the license plate distance is normal.

3. The method for identifying and detecting an intelligent barrier authenticity license plate according to claim 2, wherein after the license plate distance is determined to be normal if the determination is no, the method for identifying and detecting an intelligent barrier authenticity license plate further comprises:

4. The method for identifying and detecting the authenticity of the license plate of the intelligent barrier according to claim 1, wherein the identifying the license plate image to obtain an identified license plate shadow area, and comparing the identified license plate shadow area with the predicted license plate shadow area to obtain a comparison result, specifically comprises:

Identifying the license plate image to obtain an identified license plate shadow area, an identified high light area and an identified reflective bright spot area;

Acquiring a predicted license plate highlight area representing a predicted highlight part on a license plate image and a predicted license plate reflective bright spot area representing a predicted reflective bright spot part on the license plate image according to the environmental coefficient, the license plate shooting angle and the license plate image distance;

and respectively comparing the identified license plate shadow area, the identified high-light area and the identified reflective bright spot area with the corresponding predicted license plate shadow area, the predicted license plate high-light area and the predicted license plate reflective bright spot area to obtain a comparison result.

5. The method for identifying and detecting the genuine-fake license plate of intelligent gateway according to claim 1, wherein after judging whether the license plate is abnormal according to the comparison result and obtaining the genuine-fake license plate judgment result, the method for identifying and detecting the genuine-fake license plate of intelligent gateway further comprises:

Identifying the license plate image and obtaining license plate information;

6. The utility model provides a discernment detection device of intelligence banister true and false license plate, its characterized in that, discernment detection device of intelligence banister true and false license plate includes:

the license plate and camera angle distance acquisition module is used for acquiring a license plate image distance and a license plate shooting angle according to the license plate image, wherein the license plate image distance refers to the distance between a camera on the intelligent barrier and a license plate;

The current license plate shadow area acquisition module is used for acquiring a predicted license plate shadow area on the license plate image according to the license plate shooting angle and the license plate image distance, wherein the predicted license plate shadow area refers to the size of the shadow area and the number of the shadow positions of the predicted shadow part on the license plate image;

the license plate image is obtained by processing the license plate image through a preset image recognition algorithm;

the license plate authenticity judging result obtaining module is used for judging whether the license plate is abnormal or not according to the comparison result to obtain a license plate authenticity judging result;

the current license plate shadow area acquisition module comprises:

The current license plate shadow area obtaining sub-module is used for adjusting the license plate shadow area according to the environmental coefficient to obtain the predicted license plate shadow area.

7. The intelligent barrier authenticity license plate identification and detection device according to claim 6, wherein the intelligent barrier authenticity license plate identification and detection device further comprises:

The license plate image distance judging module is used for judging whether the license plate image distance is in a preset abnormal range or not, and if so, judging that the license plate is abnormal;

and the license plate image distance judging and normal module is used for judging that the license plate distance is normal if the license plate image distance is judged to be not.

8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, carries out the steps of the method for identifying and detecting the authenticity of a smart barrier license plate according to any one of claims 1 to 5.

9. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor performs the steps of the method for identifying and detecting an authentic license plate of an intelligent barrier according to any one of claims 1 to 5.