CN111695410A - Violation reporting method and device, computer equipment and storage medium - Google Patents
Violation reporting method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111695410A CN111695410A CN202010333515.9A CN202010333515A CN111695410A CN 111695410 A CN111695410 A CN 111695410A CN 202010333515 A CN202010333515 A CN 202010333515A CN 111695410 A CN111695410 A CN 111695410A
- Authority
- CN
- China
- Prior art keywords
- violation
- image
- license plate
- user
- initial
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012795 verification Methods 0.000 claims abstract description 28
- 238000012550 audit Methods 0.000 claims abstract description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 238000003708 edge detection Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 17
- 238000012937 correction Methods 0.000 claims description 8
- 229910052704 radon Inorganic materials 0.000 claims description 8
- SYUHGPGVQRZVTB-UHFFFAOYSA-N radon atom Chemical compound [Rn] SYUHGPGVQRZVTB-UHFFFAOYSA-N 0.000 claims description 8
- 230000001629 suppression Effects 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 230000005484 gravity Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 3
- 230000008859 change Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000005530 etching Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a block chain technology, which is applied to the field of intelligent traffic and provides a violation reporting method, which comprises the following steps: acquiring a violation image uploaded by a user, wherein the user comprises a user id, and the violation image comprises reporting information; performing credit verification on the user according to the user id, and extracting the violation image uploaded by the user passing the verification as an initial violation image; carrying out license plate recognition on the initial violation image, and extracting a target license plate image; importing the target license plate image into a pre-trained license plate recognition model for license plate recognition, and outputting a license plate recognition result; and verifying the initial violation image based on the reported information, and if the verification is successful, sending the reported information and the license plate identification result to an auditing user for auditing. The accuracy of the audit user for obtaining the violation information is improved, and the working efficiency of the audit user is further improved. Wherein the violation information may be stored in a blockchain.
Description
Technical Field
The invention relates to a block chain technology, which is applied to the field of intelligent traffic, in particular to a violation reporting method, a violation reporting device, computer equipment and a storage medium.
Background
At present, the conventional vehicle violation reporting mode mainly comprises a centralized recording mode and a camera monitoring mode, wherein the centralized recording mode refers to that a user submits violation evidence to an auditing user, but has the problems of low evidence obtaining quality, such as inaccurate time and place, unclear license plate number and the like; the camera monitoring mode is that the violation images are shot by the camera and sent to an audit user for audit, but the problem that the violation images are not clear due to the fact that shooting angles cannot be fully covered exists. Therefore, the problem that the auditing user cannot accurately acquire violation information and the working efficiency is influenced is caused.
Disclosure of Invention
The embodiment of the invention provides a violation reporting method and device, computer equipment and a storage medium, and aims to solve the problems that the accuracy of violation information acquired by an auditing user is low and the working efficiency is influenced.
A violation reporting method comprising:
acquiring a violation image uploaded by a user, wherein the user comprises a user id, and the violation image comprises reporting information;
performing credit verification on the user according to the user id, and extracting the violation image uploaded by the user passing the verification as an initial violation image;
carrying out license plate recognition on the initial violation image, and extracting a target license plate image;
importing the target license plate image into a pre-trained license plate recognition model for license plate recognition, and outputting a license plate recognition result;
and verifying the initial violation image based on the reporting information, and if the verification is successful, sending the reporting information and the license plate identification result to an auditing user for auditing.
A violation reporting device comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a violation image uploaded by a user, the user comprises a user id, and the violation image comprises reporting information;
the auditing module is used for carrying out credit auditing on the user according to the user id and extracting the violation image uploaded by the user passing the auditing as an initial violation image;
the extraction module is used for carrying out license plate recognition on the initial violation image and extracting a target license plate image;
the recognition module is used for importing the target license plate image into a pre-trained license plate recognition model for license plate recognition and outputting a license plate recognition result;
and the sending module is used for verifying the initial violation image based on the reporting information, and if the verification is successful, sending the reporting information and the license plate identification result to an auditing user for auditing.
A computer device comprising a memory, a processor and a computer program stored in said memory and executable on said processor, said processor implementing the steps of the violation reporting method when executing said computer program.
A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned violation reporting method.
According to the violation reporting method, the violation reporting device, the computer equipment and the storage medium, the initial violation image is extracted in a mode of credit verification of the user corresponding to the violation image, then the license plate of the initial violation image is identified to extract the target license plate image, the license plate identification result is obtained according to the target license plate image, finally the initial violation image is verified according to the violation image containing reporting information, and if the verification is successful, the reporting information and the license plate identification result are sent to the verification user for verification. Interference of malicious users can be effectively avoided through a credit checking mode, license plate recognition results are extracted from the initial violation images, accuracy of license plate number recognition can be improved, the initial violation images are further checked, the checking users are notified under the condition that checking is successful, accuracy of obtaining violation information of the checking users is improved, and accordingly working efficiency of the users is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
FIG. 1 is a flow chart of a violation reporting method provided by an embodiment of the present invention;
fig. 2 is a flowchart of step S2 in the violation reporting method according to the embodiment of the present invention;
fig. 3 is a flowchart of step S3 in the violation reporting method according to the embodiment of the present invention;
fig. 4 is a flowchart of step S31 in the violation reporting method according to the embodiment of the present invention;
fig. 5 is a flowchart of step S5 in the violation reporting method according to the embodiment of the present invention;
FIG. 6 is a schematic diagram of a violation reporting device provided by an embodiment of the present invention;
fig. 7 is a block diagram of a basic mechanism of a computer device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
This scheme can be applied to in the wisdom traffic field to promote the construction in wisdom city. The violation reporting method is applied to the server side, and the server side can be specifically realized by an independent server or a server cluster consisting of a plurality of servers. In one embodiment, as shown in fig. 1, there is provided a violation reporting method, comprising the steps of:
s1: and acquiring a violation image uploaded by the user, wherein the user comprises a user id, and the violation image comprises reporting information.
In the embodiment of the invention, when the user selects the violation image and clicks the uploading function at the client, the client sends the violation image to the server, and if the server detects the violation image uploaded by the user, the violation image is acquired, and the user id corresponding to the user is acquired at the same time.
The violation image is an image for reflecting the violation of the vehicle.
The reported information includes the type of violation, the location of the violation and the time of the violation.
S2: and performing credit verification on the user according to the user id, and extracting the violation image uploaded by the user passing the verification as an initial violation image.
In the embodiment of the invention, whether the user id belongs to a normal user is judged according to the credit grade by acquiring the credit grade corresponding to the user id, and if the user id belongs to the normal user, the violation image uploaded by the normal user is acquired as the initial violation image.
S3: and (4) carrying out license plate recognition on the initial violation image, and extracting a target license plate image.
In the embodiment of the invention, the initial violation image is imported into a preset identification port for license plate identification processing, and a target license plate image after license plate identification processing is obtained. The preset identification port is a processing port which is specially used for identifying a target license plate image in an initial violation image.
S4: and importing the target license plate image into a pre-trained license plate recognition model for license plate recognition, and outputting a license plate recognition result.
In the embodiment of the invention, the license plate recognition model refers to a network model which is used for carrying out license plate recognition training on a neural network model by a user by using a large number of training samples and can accurately recognize license plates contained in images after being trained.
Specifically, a license plate recognition result after license plate recognition is obtained by importing a target license plate image into a pre-trained license plate recognition model for license plate recognition.
S5: and verifying the initial violation image based on the reported information, and if the verification is successful, sending the reported information and the license plate identification result to an auditing user for auditing.
In the embodiment of the invention, whether the vehicle violation condition in the initial violation image is the same as the reported information or not is judged according to the reported information, if the vehicle violation condition is the same as the reported information, the verification is successful, and the reported information and the license plate identification result are sent to an auditing user for auditing according to a preset mode.
The preset mode may specifically be in the form of an email, or may be set according to the actual needs of the user, and is not limited herein.
It is emphasized that the violation information may also be stored in a node of a block chain in order to further ensure the privacy and security of the violation information.
In the embodiment, an initial violation image is extracted in a mode of credit verification of a user corresponding to the violation image, then license plate recognition is performed on the initial violation image to extract a target license plate image, a license plate recognition result is obtained according to the target license plate image, finally verification processing is performed on the initial violation image according to the violation image containing reporting information, and if verification is successful, the reporting information and the license plate recognition result are sent to a verification user for verification. Interference of malicious users can be effectively avoided through a credit checking mode, license plate recognition results are extracted from the initial violation images, accuracy of license plate number recognition can be improved, the initial violation images are further checked, the checking users are notified under the condition that checking is successful, accuracy of obtaining violation information of the checking users is improved, and accordingly working efficiency of the users is improved.
In an embodiment, as shown in fig. 2, in step S2, performing a credit check on the user according to the user id, and extracting the violation image uploaded by the user who passes the credit check as the initial violation image includes the following steps:
s21: and matching the user id with a legal id in a preset credit library, wherein the preset credit library comprises the legal id and a credit level corresponding to the legal id.
In the embodiment of the invention, the preset credit library comprises different legal ids, the legal ids in the preset credit library are obtained, and the user id is matched with each legal id. The preset credit library is a database which is specially used for storing different legal ids and credit levels corresponding to the legal ids.
It should be noted that the valid id refers to a registered user corresponding to the client, and each registered user has a credit level corresponding thereto, that is, the valid id has a credit level corresponding thereto, and the malicious user can be effectively removed through the credit level.
S22: and if the user id is the same as the legal id, acquiring a credit level corresponding to the legal id as a target credit level corresponding to the user id.
Specifically, according to the matching method in step S21, if the user id is the same as the valid id, it indicates that the valid id and the user id are the same user, and obtains the credit level corresponding to the valid id as the target credit level corresponding to the user id.
S23: and comparing the target credit level with a preset credit level, and if the target credit level is greater than or equal to the preset credit level, determining the user corresponding to the user id as a valid user.
In the embodiment of the present invention, according to the target credit level obtained in step S22, the target credit level is compared with a preset credit level, and if the target credit level is greater than or equal to the preset credit level, it indicates that the credit condition of the user corresponding to the target credit level belongs to credibility, that is, the user corresponding to the user id belongs to a credible user, and determines the user corresponding to the user id as a valid user.
The preset credit level is a level for distinguishing the credit condition of the user according to the actual requirement of the user.
S24: and acquiring the violation image uploaded by the effective user as an initial violation image.
Specifically, the violation image uploaded by the effective user is directly obtained from the preset database, and the violation image is used as the initial violation image. The preset database is specially used for storing violation images uploaded by valid users.
In the embodiment, the user id is matched with the legal id in the preset credit library, the target credit level corresponding to the user id is obtained, the target credit level is compared with the preset credit level, if the target credit level is greater than or equal to the preset credit level, the user corresponding to the user id is determined as the effective user, and the violation image uploaded by the effective user is obtained and used as the initial violation image. Through the mode of auditing the user, the malicious user can be effectively eliminated, the effectiveness of the initial violation image is ensured, the accuracy of acquiring violation information by subsequent auditing users is further improved, and the working efficiency of the user is improved.
In an embodiment, as shown in fig. 3, in step S3, the license plate recognition is performed on the initial violation image, and the extracting of the target license plate image includes the following steps:
s31: and acquiring the upper boundary of the license plate and the lower boundary of the license plate in the initial violation image through an edge detection algorithm.
Specifically, the initial violation image is shot and uploaded by a user, the shooting angle, the shooting distance and other factors influence in the shooting process, the shot initial violation image comprises a license plate area and also comprises non-license plate images outside the license plate area, the non-license plate images can interfere with subsequent license plate recognition, therefore, in order to improve the accuracy of the subsequent license plate recognition, an edge inspection algorithm is needed to find out the upper boundary of the license plate and the lower boundary of the license plate in the initial violation image, and the license plate range in the initial violation image is determined.
In the embodiment of the present invention, the purpose of edge detection is to identify points in a license plate image where brightness changes are obvious, that is, points of a license plate boundary, where significant changes in image attributes generally reflect important events and changes of the attributes, and the image attributes include but are not limited to: discontinuities in depth, surface orientation discontinuities, material property changes, scene lighting changes, and the like.
The edge of the image refers to a region with a sharp change in gray level in the image, and the change in gray level of the image can be reflected by the gradient of the gray level distribution.
Commonly used edge detection algorithms include, but are not limited to: a Sobel operator (Sobel operator) edge detection algorithm, a laplacian operator edge detection algorithm, a Roberts Cross edge detection (Roberts Cross operator) algorithm, a Canny multi-level edge detection algorithm, and the like.
Preferably, the edge detection algorithm adopted by the embodiment of the invention is a Canny multi-stage edge detection algorithm.
It is worth to be noted that, according to the edge detection algorithm, the upper boundary of the license plate and the lower boundary of the license plate are obtained as two line segments. That is, the obtained upper boundary of the license plate includes two vertices, and the obtained lower boundary of the license plate includes two vertices.
S32: and determining a range image of the license plate according to the upper boundary of the license plate and the lower boundary of the license plate.
Specifically, the upper boundary of the license plate obtained in step S31 is connected to the lower boundary of the license plate, that is, the left vertex of the upper boundary of the license plate is connected to the left vertex of the lower boundary of the license plate, and the right vertex of the upper boundary of the license plate is connected to the right vertex of the lower boundary of the license plate, so as to obtain a quadrangle, and the image in the quadrangle range is used as the range image of the license plate.
S33: and performing tilt correction on the range image by using Radon transformation to obtain a corrected basic image.
Specifically, due to the influence of the shooting angle and distance, the obtained initial violation image can be inclined, the obtained range image is also inclined, and in order to improve the accuracy of subsequent license plate recognition, the range image is subjected to inclination correction through radon transformation, so that a corrected basic image is obtained.
The Radon transform (Radon transform) is a method for finding an angle of a maximum projection value by performing directional projection superposition, determining an image inclination angle, and then correcting to obtain a corrected image.
S34: and cutting the basic image by taking the gravity center of the basic image as a center to obtain a target license plate image.
Specifically, the basic image obtained in step S33 is cropped with the center of gravity of the basic image as the center, a as the horizontal side length, and b as the vertical side length, so as to obtain a rectangular target license plate image with a size of a × b pixels, where a and b are positive integers, and the values thereof can be preset according to actual needs.
Preferably, in the embodiment of the present invention, a is 140 and b is 28, that is, the final target license plate image of 140 × 28 pixels is obtained.
For example, in one embodiment, the barycenter of the base image is (82, 21), the horizontal side length is 140, and the vertical side length is 28, then the top left corner vertex coordinates (12, 7), the top right corner vertex coordinates (152, 7), the bottom left corner vertex coordinates (12, 35), and the bottom right corner vertex coordinates (152, 35) are obtained, a rectangle of 140 × 28 pixels is formed by the four vertices, and the base image is clipped along the rectangle, so as to obtain the image in the range of the rectangle, i.e., the target license plate image.
Preferably, after the target license plate image is obtained, the embodiment of the invention further performs mean value removal and normalization on the target license plate image, so as to eliminate the difference between different dimensionality image data in the target license plate image.
The normalization is to normalize the image feature amplitude in the target license plate image to the same range, namely to divide the standard deviation of all image features by each image feature and to use the obtained result as the image feature after the image feature normalization.
The mean value removing means that all dimensions of image features in the target license plate image are centered to be 0, namely the central point of the target license plate image is pulled back to the origin of a coordinate system.
In the embodiment, the upper boundary of the license plate and the lower boundary of the license plate in the initial violation image are obtained through an edge detection algorithm, the range image of the license plate is determined according to the upper boundary of the license plate and the lower boundary of the license plate, the range image is subjected to tilt correction by using Radon transformation to obtain a corrected basic image, the basic image is cut by taking the gravity center of the basic image as the center to obtain the target license plate image, so that when the basic image is subsequently used for identification, identification errors caused by interference and tilt factors of the image outside the range of the license plate are avoided, the quality of the target license plate image is enhanced, and the accuracy of subsequent license plate identification is improved.
In an embodiment, as shown in fig. 4, the step S31 of obtaining the upper boundary of the license plate and the lower boundary of the license plate in the initial violation image through an edge detection algorithm includes the following steps:
s311: and carrying out noise removal on the initial violation image through Gaussian blur to obtain a denoised license plate image.
Specifically, the edge of the license plate image in the initial violation image is a high-frequency signal, but the noise of the image is also concentrated in the high-frequency signal and is easily identified as the edge by mistake, so that the noise of the image needs to be removed, and the interference of the noise of the image on the determined edge is avoided. In the embodiment of the invention, the initial violation image is subjected to noise removal by adopting Gaussian blur to obtain the denoised license plate image.
The edge of the license plate image refers to an area with sharp change of gray scale in the image at the junction of the license plate area and the non-license plate area. The change of the image gray scale can be reflected by the gradient of the gray scale distribution.
The noise of the image, that is, the noise of the image, refers to unnecessary or redundant interference information existing in the image data, and the existence of the noise seriously affects the quality of the image, so the noise must be corrected before the image enhancement processing and the classification processing.
Among them, Gaussian Blur (also called Gaussian smoothing) is an image Blur filter that uses a normal distribution to calculate the transformation of each pixel in an image, and is commonly used to reduce image noise and detail level.
It should be noted that both the image edge and the noise are high frequency signals, so the radius selection of gaussian blur is important, too large radius easily makes some weak edge points undetected, and the specific setting of the radius can be adjusted according to the actual situation, which is not limited here.
S312: and calculating the gradient value of the denoised license plate image in the horizontal direction and the gradient value of the denoised license plate image in the vertical direction by using a preset gradient operator to obtain an initial gradient value set.
Specifically, the edges of the images can point to different directions, and gradient values in the horizontal direction and the vertical direction of the denoised license plate image are calculated by using a preset operator to obtain an initial gradient value set.
The digital image is a discrete point spectrum or a two-dimensional discrete function, the gradient of the image is the result of the derivation of the two-dimensional discrete function, and the gradient operator is the method for calculating the gradient.
Wherein the preset gradient operator includes but is not limited to: sobel operator, Prewitt operator, Roberts operator and Canny operator.
Preferably, the gradient operator used in the embodiment of the present invention is a Canny operator.
S313: and performing edge refinement processing on the initial gradient value set by adopting a non-maximum value suppression mode to obtain a gradient edge with the width of a single pixel.
Specifically, edge refinement processing is performed on the initial gradient value set in a non-maximum suppression mode to obtain a gradient edge with a width of a single pixel.
Where Non Maximum Suppression (NMS) is an element where Suppression is not Maximum, it can be understood that a Maximum search is performed locally to help preserve the local Maximum gradient while suppressing all other gradient values, which means that only the sharpest position in the gradient change is preserved.
For example, in one embodiment, in the vertical direction, a local region is formed by gradient values with a width of 4 pixels, and a non-maximum suppression mode is adopted in the local region to search out a pixel point with the maximum gradient value in the local gradient values as a gradient edge, thereby realizing edge refinement.
S314: and filtering weak edge points in the gradient edge by using a preset double threshold value to obtain strong edge points in the gradient edge.
Specifically, edge pixels are distinguished by setting dual thresholds, i.e., a high threshold and a low threshold. If the gradient value of the edge pixel point is greater than the high threshold, the edge pixel point is considered to be a strong edge point, if the gradient value of the edge pixel point is less than the high threshold and greater than the low threshold, the edge pixel point is marked as a weak edge point, and the point less than the low threshold is suppressed.
S315: and determining the upper boundary of the license plate and the lower boundary of the license plate according to the strong edge points.
Specifically, according to the strong edge points, the upper boundary of the license plate and the lower boundary of the license plate are obtained through image processing such as corrosion extension.
Wherein the etching eliminates individual ones of the strong edge points and the extension connects adjacent but unconnected strong edge points.
In the embodiment, the initial violation image is subjected to noise removal through Gaussian blur to obtain a denoised license plate image, gradient values of the denoised license plate image in the horizontal direction and the vertical direction are calculated by using a preset gradient operator to obtain an initial gradient value set, edge refinement is performed on the initial gradient value set by adopting a non-maximum suppression mode to obtain a gradient edge with a wide pixel, weak edge points in the gradient edge are filtered by using a preset double threshold value to obtain strong edge points in the gradient edge, and then an upper boundary of the license plate and a lower boundary of the license plate are determined according to the strong edge points, so that the accuracy of license plate edge detection is improved, and the subsequent determination of the license plate range is facilitated.
In an embodiment, the reporting information includes a violation type, a violation location, and a violation time, as shown in fig. 5, in step S5, the verifying process is performed on the initial violation image based on the reporting information, and if the verification is successful, the sending of the reporting information and the license plate recognition result to the verifying user for verification includes the following steps:
s51: and importing the initial violation image into a pre-trained violation identification model for identification, and outputting a violation identification result.
In the embodiment of the invention, the pre-trained violation identification model can directly identify the violation identification result corresponding to the initial violation image according to the input initial violation image. And importing the initial violation image into a violation identification model for identification, and outputting a violation identification result.
S52: and matching the violation identification result with the violation type, and determining the initial violation image with the same matching as an effective image.
Specifically, a violation identification result is matched with a violation type, if the violation identification result is the same as the violation type, the violation condition of an initial violation image corresponding to the violation identification result is indicated, and the initial violation image is determined as an effective image; and if the violation identification result is different from the violation type, indicating that the initial violation image corresponding to the violation identification result does not have the violation condition, and not processing.
S53: and analyzing the effective image through a preset analysis port to obtain a target location and target time.
Specifically, the Base64 is called to convert the effective image into a data stream, and then the data stream is led into a preset analysis port to be analyzed, so that a target location and a target time contained in the effective image are obtained.
Where Base64 refers to a processing tool dedicated to converting images into data streams.
The preset analysis port refers to a processing port which is specially used for directly reading a target place and a target time contained in the data stream.
S54: the target location is compared to the violation location and the target time is compared to the violation time.
Specifically, the target location obtained in step S53 is compared with the violation location, and the target time is compared with the violation time.
S55: and if the target location is the same as the violation location and the target time is the same as the violation time, sending the reported information and the license plate identification result to an auditing user for auditing.
Specifically, if the target location is the same as the violation location and the target time is the same as the violation time, the violation condition of the effective image is indicated to be true, and the reporting information and the license plate identification result are sent to an auditing user for auditing.
In the embodiment, the violation identification result is identified from the initial violation image, the effective image is determined according to the violation identification result and the violation type, the effective image is analyzed to obtain the target location and the target time, and the reporting information and the license plate identification result are sent to the auditing user for auditing under the condition that the target location is the same as the violation location and the target time is the same as the violation time. The unqualified images can be effectively eliminated by obtaining the effective images, so that redundant operation on the unqualified images is avoided, and the working efficiency of the system is improved; by means of the method for auditing the target location and the target time, whether the reported information is accurate or not can be accurately identified, so that a subsequent auditing user can accurately obtain violation information conveniently, and the working efficiency is improved.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
In one embodiment, a violation reporting device is provided, and the violation reporting device corresponds to the violation reporting method in the above embodiments one to one. As shown in fig. 6, the violation reporting device includes a first obtaining module 61, an auditing module 62, an extracting module 63, an identifying module 64 and a sending module 65. The functional modules are explained in detail as follows:
the first acquisition module 61 is used for acquiring a violation image uploaded by a user, wherein the user comprises a user id, and the violation image comprises reporting information;
the auditing module 62 is used for carrying out credit auditing on the user according to the user id and extracting the violation image uploaded by the user passing the auditing as an initial violation image;
the extraction module 63 is used for carrying out license plate recognition on the initial violation image and extracting a target license plate image;
the recognition module 64 is used for importing the target license plate image into a pre-trained license plate recognition model for license plate recognition and outputting a license plate recognition result;
and the sending module 65 is configured to perform verification processing on the initial violation image based on the reporting information, and send the reporting information and the license plate identification result to an audit user for auditing if the verification is successful.
Further, the audit module 62 includes:
the matching sub-module is used for matching the user id with the legal id in a preset credit library, wherein the preset credit library comprises the legal id and a credit level corresponding to the legal id;
the matching identity submodule is used for acquiring a credit level corresponding to the legal id as a target credit level corresponding to the user id if the user id is identical to the legal id;
the first comparison submodule is used for comparing the target credit level with a preset credit level, and if the target credit level is greater than or equal to the preset credit level, determining a user corresponding to the user id as a valid user;
and the second obtaining submodule is used for obtaining the violation image uploaded by the effective user as the initial violation image.
Further, the extraction module 63 includes:
the third acquisition sub-module is used for acquiring the upper boundary of the license plate and the lower boundary of the license plate in the initial violation image through an edge detection algorithm;
the range image determining submodule is used for determining a range image of the license plate according to the upper boundary of the license plate and the lower boundary of the license plate;
the correction submodule is used for carrying out inclination correction on the range image by using Radon transformation to obtain a corrected basic image;
and the cutting submodule is used for cutting the basic image by taking the gravity center of the basic image as the center to obtain the target license plate image.
Further, the third obtaining sub-module includes:
the denoising unit is used for removing noise from the initial violation image through Gaussian blur to obtain a denoised license plate image;
the computing unit is used for computing the gradient value of the denoised license plate image in the horizontal direction and the gradient value of the denoised license plate image in the vertical direction by using a preset gradient operator to obtain an initial gradient value set;
the edge thinning unit is used for carrying out edge thinning processing on the initial gradient value set in a non-maximum value inhibition mode to obtain a gradient edge with the width of a single pixel;
the filtering unit is used for filtering weak edge points in the gradient edge by using a preset double threshold value to obtain strong edge points in the gradient edge;
and the determining unit is used for determining the upper boundary of the license plate and the lower boundary of the license plate according to the strong edge points.
Further, the sending module 65 includes:
the import submodule is used for importing the initial violation image into a violation identification model trained in advance for identification and outputting a violation identification result;
the effective image determining submodule is used for matching the violation identification result with the violation type and determining the initial violation image with the same matching as an effective image;
the analysis submodule is used for analyzing the effective image through a preset analysis port to obtain a target place and target time;
the second comparison submodule is used for comparing the target location with the violation location and comparing the target time with the violation time;
and the second comparison identical submodule is used for sending the reported information and the license plate identification result to an auditing user for auditing if the target location is identical to the violation location and the target time is identical to the violation time.
It is emphasized that the violation information may also be stored in a node of a block chain in order to further ensure the privacy and security of the violation information.
Some embodiments of the present application disclose a computer device. Referring specifically to fig. 7, a basic structure block diagram of a computer device 90 according to an embodiment of the present application is shown.
As illustrated in fig. 7, the computer device 90 includes a memory 91, a processor 92, and a network interface 93 communicatively connected to each other through a system bus. It is noted that only a computer device 90 having components 91-93 is shown in FIG. 7, but it is understood that not all of the illustrated components are required to be implemented, and that more or fewer components may alternatively be implemented. As will be understood by those skilled in the art, the computer device is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.
The computer device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The computer equipment can carry out man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch panel or voice control equipment and the like.
The memory 91 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the storage 91 may be an internal storage unit of the computer device 90, such as a hard disk or a memory of the computer device 90. In other embodiments, the memory 91 may also be an external storage device of the computer device 90, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, provided on the computer device 90. Of course, the memory 91 may also include both internal and external memory units of the computer device 90. In this embodiment, the memory 91 is generally used for storing an operating system and various types of application software installed in the computer device 90, such as program codes of the violation reporting method and the like. Further, the memory 91 may also be used to temporarily store various types of data that have been output or are to be output.
The processor 92 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 92 is typically used to control the overall operation of the computer device 90. In this embodiment, the processor 92 is configured to run program code stored in the memory 91 or process data, such as program code for running the violation reporting method.
The network interface 93 may include a wireless network interface or a wired network interface, and the network interface 93 is generally used to establish a communication connection between the computer device 90 and other electronic devices.
The present application further provides another embodiment of a computer readable storage medium having stored thereon a violation information entry program executable by at least one processor for causing the at least one processor to perform the steps of any of the violation reporting methods described above.
Further, the computer usable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a computer device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
Finally, it should be noted that the above-mentioned embodiments illustrate only some of the embodiments of the present application, and are therefore not to be considered limiting of its scope, for the invention may admit to other equally effective embodiments. This application is capable of embodiments in many different forms and is provided for the purpose of enabling a thorough understanding of the disclosure of the application. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that the present application may be practiced without modification or with equivalents of some of the features described in the foregoing embodiments. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields and are within the protection scope of the present application.
Claims (10)
1. A violation reporting method is characterized by comprising the following steps:
acquiring a violation image uploaded by a user, wherein the user comprises a user id, and the violation image comprises reporting information;
performing credit verification on the user according to the user id, and extracting the violation image uploaded by the user passing the verification as an initial violation image;
carrying out license plate recognition on the initial violation image, and extracting a target license plate image;
importing the target license plate image into a pre-trained license plate recognition model for license plate recognition, and outputting a license plate recognition result;
and verifying the initial violation image based on the reporting information, and if the verification is successful, sending the reporting information and the license plate identification result to an auditing user for auditing.
2. The violation reporting method of claim 1 wherein said step of performing a credit audit on said user based on user id and extracting said violation image uploaded by the approved user as an initial violation image comprises:
matching the user id with a legal id in a preset credit library, wherein the preset credit library comprises the legal id and a credit level corresponding to the legal id;
if the user id is the same as the legal id, acquiring a credit level corresponding to the legal id as a target credit level corresponding to the user id;
comparing the target credit level with a preset credit level, and if the target credit level is greater than or equal to the preset credit level, determining the user corresponding to the user id as a valid user;
and acquiring the violation image uploaded by the effective user as the initial violation image.
3. The violation reporting method of claim 1 wherein said license plate identification of said initial violation image and said step of extracting a target license plate image comprises:
acquiring an upper boundary of a license plate and a lower boundary of the license plate in the initial violation image through an edge detection algorithm;
determining a range image of the license plate according to the upper boundary of the license plate and the lower boundary of the license plate;
performing tilt correction on the range image by using Radon transformation to obtain a corrected basic image;
and cutting the basic image by taking the gravity center of the basic image as a center to obtain the target license plate image.
4. The violation reporting method of claim 3 wherein said step of obtaining the upper boundary of the license plate and the lower boundary of the license plate in the initial violation image via an edge detection algorithm comprises:
noise removal is carried out on the initial violation image through Gaussian blur, and a denoised license plate image is obtained;
calculating the gradient value of the denoised license plate image in the horizontal direction and the gradient value of the denoised license plate image in the vertical direction by using a preset gradient operator to obtain an initial gradient value set;
performing edge refinement processing on the initial gradient value set by adopting a non-maximum value suppression mode to obtain a gradient edge with the width of a single pixel;
filtering weak edge points in the gradient edge by using a preset double threshold value to obtain strong edge points in the gradient edge;
and determining the upper boundary of the license plate and the lower boundary of the license plate according to the strong edge points.
5. The violation reporting method of claim 1 wherein the reporting information includes violation type, violation location and violation time, the verifying of the initial violation image based on the reporting information is performed, and if the verifying is successful, the step of sending the reporting information and the license plate identification result to an audit user for audit comprises:
importing the initial violation image into a pre-trained violation identification model for identification, and outputting a violation identification result;
matching the violation identification result with the violation type, and determining the initial violation image with the same matching as an effective image;
analyzing the effective image through a preset analysis port to obtain a target location and target time;
comparing the target location with the violation location, and comparing the target time with the violation time;
and if the target place is the same as the violation place and the target time is the same as the violation time, sending the reporting information and the license plate identification result to an auditing user for auditing.
6. A violation reporting device, characterized in that the violation reporting device comprises:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a violation image uploaded by a user, the user comprises a user id, and the violation image comprises reporting information;
the auditing module is used for carrying out credit auditing on the user according to the user id and extracting the violation image uploaded by the user passing the auditing as an initial violation image;
the extraction module is used for carrying out license plate recognition on the initial violation image and extracting a target license plate image;
the recognition module is used for importing the target license plate image into a pre-trained license plate recognition model for license plate recognition and outputting a license plate recognition result;
and the sending module is used for verifying the initial violation image based on the reporting information, and if the verification is successful, sending the reporting information and the license plate identification result to an auditing user for auditing.
7. The violation reporting device of claim 6 wherein said audit module comprises:
the matching sub-module is used for matching the user id with a legal id in a preset credit library, wherein the preset credit library comprises the legal id and a credit level corresponding to the legal id;
the matching same submodule is used for acquiring a credit level corresponding to the legal id as a target credit level corresponding to the user id if the user id is the same as the legal id;
the first comparison submodule is used for comparing the target credit level with a preset credit level, and if the target credit level is greater than or equal to the preset credit level, determining the user corresponding to the user id as a valid user;
and the second obtaining submodule is used for obtaining the violation image uploaded by the effective user as the initial violation image.
8. The violation reporting device of claim 6 wherein said extraction module comprises:
the third obtaining sub-module is used for obtaining the upper boundary of the license plate and the lower boundary of the license plate in the initial violation image through an edge detection algorithm;
the range image determining submodule is used for determining a range image of the license plate according to the upper boundary of the license plate and the lower boundary of the license plate;
the correction submodule is used for carrying out inclination correction on the range image by using Radon transformation to obtain a corrected basic image;
and the cutting submodule is used for cutting the basic image by taking the gravity center of the basic image as the center to obtain the target license plate image.
9. A computer arrangement 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 violation reporting method as claimed in any one of claims 1 to 5.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the violation reporting method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010333515.9A CN111695410A (en) | 2020-04-24 | 2020-04-24 | Violation reporting method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010333515.9A CN111695410A (en) | 2020-04-24 | 2020-04-24 | Violation reporting method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111695410A true CN111695410A (en) | 2020-09-22 |
Family
ID=72476651
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010333515.9A Pending CN111695410A (en) | 2020-04-24 | 2020-04-24 | Violation reporting method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111695410A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112133097A (en) * | 2020-09-25 | 2020-12-25 | 重庆市盈科物联网信息技术有限公司 | Internet + -based traffic driving behavior management method and system |
| CN112509325A (en) * | 2020-12-04 | 2021-03-16 | 公安部交通管理科学研究所 | Video deep learning-based off-site illegal automatic discrimination method |
| CN112634090A (en) * | 2020-12-15 | 2021-04-09 | 深圳市彬讯科技有限公司 | Home decoration information reporting management method, system, computer device and storage medium |
| CN112818899A (en) * | 2021-02-22 | 2021-05-18 | 招联消费金融有限公司 | Face image processing method and device, computer equipment and storage medium |
| CN113076961A (en) * | 2021-05-12 | 2021-07-06 | 北京奇艺世纪科技有限公司 | Image feature library updating method, image detection method and device |
| CN113835582A (en) * | 2021-09-27 | 2021-12-24 | 青岛海信移动通信技术股份有限公司 | Terminal device, information display method and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512896A (en) * | 2014-09-25 | 2016-04-20 | 腾讯科技（深圳）有限公司 | Tip-off information processing method and system |
| CN106205144A (en) * | 2016-09-07 | 2016-12-07 | 东南大学 | Highway Emergency Vehicle Lane takies supervision punishment method and system |
| CN108109384A (en) * | 2017-12-19 | 2018-06-01 | 江苏本能科技有限公司 | Management method and system are captured in distributed vehicle illegal behavior |
| CN108417046A (en) * | 2018-04-28 | 2018-08-17 | 上海与德科技有限公司 | Driving behavior monitoring method, traffic monitoring method, apparatus, terminal and medium |
| CN109472262A (en) * | 2018-09-25 | 2019-03-15 | 平安科技（深圳）有限公司 | Licence plate recognition method, device, computer equipment and storage medium |
| CN110428351A (en) * | 2019-07-29 | 2019-11-08 | 电子科技大学 | Semi vehicle violation based on block chain reports method |
-
2020
- 2020-04-24 CN CN202010333515.9A patent/CN111695410A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512896A (en) * | 2014-09-25 | 2016-04-20 | 腾讯科技（深圳）有限公司 | Tip-off information processing method and system |
| CN106205144A (en) * | 2016-09-07 | 2016-12-07 | 东南大学 | Highway Emergency Vehicle Lane takies supervision punishment method and system |
| CN108109384A (en) * | 2017-12-19 | 2018-06-01 | 江苏本能科技有限公司 | Management method and system are captured in distributed vehicle illegal behavior |
| CN108417046A (en) * | 2018-04-28 | 2018-08-17 | 上海与德科技有限公司 | Driving behavior monitoring method, traffic monitoring method, apparatus, terminal and medium |
| CN109472262A (en) * | 2018-09-25 | 2019-03-15 | 平安科技（深圳）有限公司 | Licence plate recognition method, device, computer equipment and storage medium |
| CN110428351A (en) * | 2019-07-29 | 2019-11-08 | 电子科技大学 | Semi vehicle violation based on block chain reports method |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112133097A (en) * | 2020-09-25 | 2020-12-25 | 重庆市盈科物联网信息技术有限公司 | Internet + -based traffic driving behavior management method and system |
| CN112509325A (en) * | 2020-12-04 | 2021-03-16 | 公安部交通管理科学研究所 | Video deep learning-based off-site illegal automatic discrimination method |
| CN112634090A (en) * | 2020-12-15 | 2021-04-09 | 深圳市彬讯科技有限公司 | Home decoration information reporting management method, system, computer device and storage medium |
| CN112818899A (en) * | 2021-02-22 | 2021-05-18 | 招联消费金融有限公司 | Face image processing method and device, computer equipment and storage medium |
| CN113076961A (en) * | 2021-05-12 | 2021-07-06 | 北京奇艺世纪科技有限公司 | Image feature library updating method, image detection method and device |
| CN113076961B (en) * | 2021-05-12 | 2023-09-05 | 北京奇艺世纪科技有限公司 | Image feature library updating method, image detection method and device |
| CN113835582A (en) * | 2021-09-27 | 2021-12-24 | 青岛海信移动通信技术股份有限公司 | Terminal device, information display method and storage medium |
| CN113835582B (en) * | 2021-09-27 | 2024-03-15 | 青岛海信移动通信技术有限公司 | Terminal equipment, information display method and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111695410A (en) | Violation reporting method and device, computer equipment and storage medium | |
| WO2019169532A1 (en) | License plate recognition method and cloud system | |
| US9014432B2 (en) | License plate character segmentation using likelihood maximization | |
| CN111079772B (en) | Image edge extraction processing method, device and storage medium | |
| CN108875731B (en) | Target identification method, device, system and storage medium | |
| CN107169489B (en) | Method and apparatus for tilt image correction | |
| CN109492642B (en) | License plate recognition method, license plate recognition device, computer equipment and storage medium | |
| US11657644B2 (en) | Automatic ruler detection | |
| CN109740417B (en) | Invoice type identification method, invoice type identification device, storage medium and computer equipment | |
| US11354883B2 (en) | Image processing method and apparatus, and electronic device | |
| CN110502977B (en) | Building change classification detection method, system, device and storage medium | |
| CN111223078B (en) | Method for determining flaw level and storage medium | |
| CN110738216A (en) | Medicine identification method based on improved SURF algorithm | |
| CN112085721A (en) | Damage assessment method, device and equipment for flooded vehicle based on artificial intelligence and storage medium | |
| CN111353485A (en) | Seal identification method, device, equipment and medium | |
| CN115830651A (en) | Fingerprint image enhancement method and device, electronic equipment and storage medium | |
| CN108960246B (en) | Binarization processing device and method for image recognition | |
| CN111160339B (en) | License plate correction method, image processing equipment and device with storage function | |
| CN112036232A (en) | Image table structure identification method, system, terminal and storage medium | |
| CN107239776B (en) | Method and apparatus for tilt image correction | |
| CN108629219B (en) | Method and device for identifying one-dimensional code | |
| CN113239738B (en) | Image blurring detection method and blurring detection device | |
| CN112629828B (en) | Optical information detection method, device and equipment | |
| CN115798004A (en) | Face card punching method and device based on local area, electronic equipment and medium | |
| CN113792671A (en) | Method and device for detecting face synthetic image, electronic equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |