CN113326836A - License plate recognition method and device, server and storage medium - Google Patents
License plate recognition method and device, server and storage medium Download PDFInfo
- Publication number
- CN113326836A CN113326836A CN202010129455.9A CN202010129455A CN113326836A CN 113326836 A CN113326836 A CN 113326836A CN 202010129455 A CN202010129455 A CN 202010129455A CN 113326836 A CN113326836 A CN 113326836A
- Authority
- CN
- China
- Prior art keywords
- license plate
- points
- image
- groups
- determining
- 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 55
- 230000011218 segmentation Effects 0.000 claims abstract description 115
- 240000004282 Grewia occidentalis Species 0.000 claims abstract description 55
- 238000012545 processing Methods 0.000 claims description 27
- 230000009466 transformation Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 4
- 230000002411 adverse Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- GVVPGTZRZFNKDS-JXMROGBWSA-N geranyl diphosphate Chemical compound CC(C)=CCC\C(C)=C\CO[P@](O)(=O)OP(O)(O)=O GVVPGTZRZFNKDS-JXMROGBWSA-N 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- 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
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- 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)
- Computer Vision & Pattern Recognition (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the application discloses a license plate identification method, a license plate identification device, a server and a storage medium, wherein the license plate identification method comprises the following steps: acquiring a license plate image of a target vehicle; detecting the license plate image, and determining a license plate mask region in the license plate image and coordinate differences between the four groups of segmentation points and license plate corner points; determining a plurality of groups of license plate four-angle points according to the license plate mask region and the coordinate difference values of the four groups of segmentation points and the license plate angle points; determining license plate regions corresponding to the license plate four-corner points according to the plurality of groups of license plate four-corner points; and carrying out license plate recognition on the image of the license plate area to obtain the license plate number of the target vehicle. According to the method and the device, the plurality of groups of license plate angular points are determined through the license plate image, and the license plate regions corresponding to the license plate angular points are determined according to the plurality of groups of license plate four angular points, so that the license plate detection regions are more accurate, more background information or information loss cannot be caused, the license plate identification accuracy is improved, and the license plate identification robustness is high.
Description
Technical Field
The invention relates to the technical field of license plate recognition, in particular to a license plate recognition method, a license plate recognition device, a server and a storage medium.
Background
In recent years, due to the rapid development of social economy, motor vehicles are an important vehicle in life and are inseparable from people's life. However, as the number of motor vehicles is increasing, traffic jam, illegal parking and charge system disorder will also occur. To solve the above phenomena, a more efficient traffic control system is required, and the license plate is the most basic identity of the motor vehicle. Therefore, the development of a license plate detection and recognition system with excellent robustness is becoming reluctant.
However, most existing vision-based license plate detection and recognition systems are target detection schemes, but license plate regions detected by license plate targets are possibly too large and contain large-area background information except the license plate regions. The detected license plate area is too small, so that license plate information is lost, and adverse effects are brought to the subsequent license plate identification process; in addition, the license plate region in the image is searched in a simple image segmentation mode, and the problem that the segmentation region in the target detection scheme is too large or too small can also occur. However, the segmented boundary is an uneven curve, so that the correction process of the image before license plate recognition is more difficult, and further the overall recognition accuracy of the license plate is low and the recognition efficiency is low.
Disclosure of Invention
The embodiment of the invention provides a license plate recognition method, a license plate recognition device, a server and a storage medium, so that the region for detecting the license plate is more accurate, more background information or information loss cannot be caused, the license plate recognition accuracy is improved, and the license plate recognition robustness is high.
In one aspect, the present application provides a license plate recognition method, which further includes:
acquiring a license plate image of a target vehicle;
detecting the license plate image, and determining a license plate mask region in the license plate image and coordinate differences between the four groups of segmentation points and license plate corner points;
determining a plurality of groups of license plate four-angle points according to the license plate mask region and the coordinate difference values of the four groups of segmentation points and the license plate angle points;
determining license plate regions corresponding to the license plate four-corner points according to the plurality of groups of license plate four-corner points;
and carrying out license plate recognition on the image of the license plate area to obtain the license plate number of the target vehicle.
In some embodiments of the present application, the detecting the license plate image to determine a license plate mask region in the license plate image and coordinate differences between four sets of segmentation points and license plate corner points includes:
performing channel regression processing on the license plate image, and determining coordinate differences of four groups of segmentation points to license plate corner points;
and performing semantic segmentation processing on the license plate image to determine a license plate mask region in the license plate image.
In some embodiments of the present application, the detecting the license plate image to determine a license plate mask region in the license plate image and coordinate differences between four sets of segmentation points and license plate corner points includes:
and detecting the license plate image by adopting a preset license plate segmentation network model, and determining a license plate mask region in the license plate image and coordinate difference values of four groups of segmentation points and license plate corner points.
In some embodiments of the present application, the license plate segmentation network model comprises a channel regression sub-network model and a license plate semantic segmentation sub-network model;
the method comprises the following steps of detecting the license plate image by adopting a preset license plate segmentation network model, and determining a license plate mask region and coordinate difference values of four groups of segmentation points and license plate corner points in the license plate image, wherein the steps comprise:
performing channel regression processing on the license plate image by adopting the channel regression sub-network model, and determining coordinate difference values of four groups of segmentation points to license plate angular points, wherein the coordinate difference values of the four groups of segmentation points to the license plate angular points comprise four groups of segmentation points to license plate angular points, and coordinate difference values in the x and y directions in a coordinate system of the channel regression sub-network model;
and adopting the license plate semantic segmentation sub-network model to perform license plate semantic segmentation processing on the license plate image and determine a license plate mask region in the license plate image.
In some embodiments of the present application, determining multiple sets of license plate four-corner points according to the license plate mask region and coordinate differences between the four sets of segmentation points and the license plate corner points includes:
respectively taking one pixel point in the license plate mask region as a target pixel point to obtain the coordinate of the target pixel point;
calculating coordinates of four license plate angular points according to the coordinates of the target pixel points and coordinate differences of the four groups of segmentation points and the license plate angular points, wherein the four license plate angular points form a set of license plate four angular points;
and obtaining a plurality of groups of license plate four-corner points after the coordinate calculation of the four license plate corner points corresponding to all the pixel points in the license plate mask region is completed.
In some embodiments of the present application, the determining license plate regions corresponding to the license plate four-corner points according to the plurality of sets of license plate four-corner points includes:
determining a coordinate set corresponding to four corners of the license plate from the plurality of groups of four corners of the license plate;
voting according to the coordinate sets corresponding to the four corners and the occurrence times to determine the coordinates of the four corners of the license plate;
and determining license plate areas corresponding to the four corners of the license plate according to the coordinates of the four corners of the license plate.
In some embodiments of the present application, the voting for determining the coordinates of the four corner points of the license plate according to the coordinate sets corresponding to the four corners comprises
Voting to determine four corner coordinates with the largest occurrence frequency from the coordinate sets corresponding to the four corners;
and determining the coordinates of the four corners as the coordinates of the four corners of the license plate.
In some embodiments of the present application, the performing license plate recognition on the image of the license plate region to obtain the license plate number of the target vehicle includes:
carrying out perspective transformation on the image of the license plate area to obtain a preset width and height rectangular license plate image;
and carrying out license plate recognition on the rectangular license plate image to obtain the license plate number of the target vehicle.
In another aspect, the present application provides a license plate recognition apparatus, including:
the system comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring a license plate image of a target vehicle;
the first determining unit is used for detecting the license plate image and determining a license plate mask area in the license plate image and coordinate difference values of four groups of segmentation points and license plate corner points;
the second determining unit is used for determining a plurality of groups of license plate four-corner points according to the license plate mask region and the coordinate difference values of the four groups of segmentation points and the license plate corner points;
the third determining unit is used for determining license plate areas corresponding to the four corners of the license plate according to the plurality of groups of four corners of the license plate;
and the license plate recognition unit is used for carrying out license plate recognition on the image of the license plate area to obtain the license plate number of the target vehicle.
In some embodiments of the present application, the first determining unit is specifically configured to:
performing channel regression processing on the license plate image, and determining coordinate differences of four groups of segmentation points to license plate corner points;
and performing semantic segmentation processing on the license plate image to determine a license plate mask region in the license plate image.
In some embodiments of the present application, the first determining unit is specifically configured to:
and detecting the license plate image by adopting a preset license plate segmentation network model, and determining a license plate mask region in the license plate image and coordinate difference values of four groups of segmentation points and license plate corner points.
In some embodiments of the present application, the license plate segmentation network model comprises a channel regression sub-network model and a license plate semantic segmentation sub-network model;
the first determining unit is specifically configured to: performing channel regression processing on the license plate image by adopting the channel regression sub-network model, and determining coordinate difference values of four groups of segmentation points to license plate angular points, wherein the coordinate difference values of the four groups of segmentation points to the license plate angular points comprise four groups of segmentation points to license plate angular points, and coordinate difference values in the x and y directions in a coordinate system of the channel regression sub-network model;
and adopting the license plate semantic segmentation sub-network model to perform license plate semantic segmentation processing on the license plate image and determine a license plate mask region in the license plate image.
In some embodiments of the present application, the second determining unit is specifically configured to:
respectively taking one pixel point in the license plate mask region as a target pixel point to obtain the coordinate of the target pixel point;
calculating coordinates of four license plate angular points according to the coordinates of the target pixel points and coordinate differences of the four groups of segmentation points and the license plate angular points, wherein the four license plate angular points form a set of license plate four angular points;
and obtaining a plurality of groups of license plate four-corner points after the coordinate calculation of the four license plate corner points corresponding to all the pixel points in the license plate mask region is completed.
In some embodiments of the present application, the third determining unit is specifically configured to:
determining a coordinate set corresponding to four corners of the license plate from the plurality of groups of four corners of the license plate;
voting according to the coordinate sets corresponding to the four corners and the occurrence times to determine the coordinates of the four corners of the license plate;
and determining license plate areas corresponding to the four corners of the license plate according to the coordinates of the four corners of the license plate.
In some embodiments of the present application, the third determining unit is specifically configured to:
voting to determine four corner coordinates with the largest occurrence frequency from the coordinate sets corresponding to the four corners;
and determining the coordinates of the four corners as the coordinates of the four corners of the license plate.
In some embodiments of the present application, the license plate recognition unit is specifically configured to:
carrying out perspective transformation on the image of the license plate area to obtain a preset width and height rectangular license plate image;
and carrying out license plate recognition on the rectangular license plate image to obtain the license plate number of the target vehicle.
In another aspect, the present application further provides a server, including:
one or more processors;
a memory; and
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the license plate recognition method.
In another aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is loaded by a processor to execute the steps in the license plate recognition method.
In the embodiment of the application, the license plate image of the target vehicle is obtained; detecting the license plate image, and determining a license plate mask region in the license plate image and coordinate differences between the four groups of segmentation points and license plate corner points; determining a plurality of groups of license plate four-angle points according to the license plate mask region and the coordinate difference values of the four groups of segmentation points and the license plate angle points; determining license plate regions corresponding to the license plate four-corner points according to the plurality of groups of license plate four-corner points; and carrying out license plate recognition on the image of the license plate area to obtain the license plate number of the target vehicle. On the basis that the existing license plate recognition adopts a detection and recognition mode, the region for detecting the license plate is not the accurate position of the license plate, contains more background information or information loss, and has low license plate recognition accuracy and low robustness, the license plate recognition method determines a plurality of groups of license plate angular points through the license plate image, and determines the license plate regions corresponding to the four corners of the license plate according to the four corners of the plurality of groups of license plates, so that the region for detecting the license plate is more accurate, more background information or information loss can not be caused, the license plate recognition accuracy is improved, and the license plate recognition robustness is high.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments 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 to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a scene schematic diagram of a license plate recognition system according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of an embodiment of a license plate recognition method according to an embodiment of the present invention;
FIG. 3 is a flowchart of one embodiment of step 202 provided in embodiments of the present invention;
FIG. 4 is a flowchart of one embodiment of step 203 provided in embodiments of the present invention;
FIG. 5 is a schematic diagram of an embodiment of license plate corner determination provided in an embodiment of the present invention;
fig. 6 is a schematic diagram of an embodiment of a license plate provided in an embodiment of the present invention after four corner points of the license plate are determined;
fig. 7 is a schematic structural diagram of an embodiment of a license plate recognition device provided in an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an embodiment of the server provided in the 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 only a part of the embodiments of the present invention, and not all of the embodiments. 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.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be considered as limiting the present invention. Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
In this application, the word "exemplary" is used to mean "serving as an example, instance, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the invention. In the following description, details are set forth for the purpose of explanation. It will be apparent to one of ordinary skill in the art that the present invention may be practiced without these specific details. In other instances, well-known structures and processes are not shown in detail to avoid obscuring the description of the invention with unnecessary detail. Thus, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.
Embodiments of the present invention provide a license plate recognition method, a license plate recognition device, a server, and a storage medium, which are described in detail below.
Referring to fig. 1, fig. 1 is a schematic view of a license plate recognition system according to an embodiment of the present invention, where the license plate recognition system may include a server 100, and a license plate recognition device, such as the server in fig. 1, is integrated in the server 100.
The server 100 in the embodiment of the invention is mainly used for acquiring a license plate image of a target vehicle; detecting the license plate image, and determining a license plate mask region in the license plate image and coordinate differences between the four groups of segmentation points and license plate corner points; determining a plurality of groups of license plate four-angle points according to the license plate mask region and the coordinate difference values of the four groups of segmentation points and the license plate angle points; determining license plate regions corresponding to the license plate four-corner points according to the plurality of groups of license plate four-corner points; and carrying out license plate recognition on the image of the license plate area to obtain the license plate number of the target vehicle.
In this embodiment of the present invention, the server 100 may be an independent server, or may be a server network or a server cluster composed of servers, for example, the server 100 described in this embodiment of the present invention includes, but is not limited to, a computer, a network host, a single network server, a plurality of network server sets, or a cloud server composed of a plurality of servers. Among them, the Cloud server is constituted by a large number of computers or web servers based on Cloud Computing (Cloud Computing). In the embodiment of the present invention, the server and the User terminal may implement communication through any communication manner, including but not limited to mobile communication based on the third Generation Partnership Project (3 GPP), Long Term Evolution (LTE), Worldwide Interoperability for Microwave Access (WiMAX), or computer network communication based on the TCP/IP Protocol Suite (TCP/IP), User Datagram Protocol (UDP) Protocol, and the like.
Those skilled in the art will understand that the application environment shown in fig. 1 is only one application scenario related to the present application, and does not constitute a limitation on the application scenario of the present application, and that other application environments may further include more or less drones than that shown in fig. 1, or a server network connection relationship, for example, only 1 server is shown in fig. 1, and it is understood that the license plate recognition system may further include one or more other drones connected to the server network, and is not limited herein.
As shown in fig. 1, the license plate recognition system may further include a memory 200 for storing license plate data, such as a license plate video stream, a license plate image, and the like.
In addition, it is understood that the license plate recognition system may further include one or more camera devices (not shown in fig. 1) for shooting license plates, for example, the camera devices for shooting license plates are disposed at the doorways of garages such as crossing office buildings, districts, etc., and the specific arrangement form and number are not limited herein.
It should be noted that the scene schematic diagram of the license plate recognition system shown in fig. 1 is only an example, the license plate recognition system and the scene described in the embodiment of the present invention are for more clearly illustrating the technical solution of the embodiment of the present invention, and do not form a limitation on the technical solution provided in the embodiment of the present invention.
First, an embodiment of the present invention provides a license plate recognition method, where an execution subject of the license plate recognition method is a server, and the license plate recognition method includes: acquiring a license plate image of a target vehicle; detecting the license plate image, and determining a license plate mask region in the license plate image and coordinate differences between the four groups of segmentation points and license plate corner points; determining a plurality of groups of license plate four-angle points according to the license plate mask region and the coordinate difference values of the four groups of segmentation points and the license plate angle points; determining license plate regions corresponding to the license plate four-corner points according to the plurality of groups of license plate four-corner points; and carrying out license plate recognition on the image of the license plate area to obtain the license plate number of the target vehicle.
In the embodiment of the application, the license plate image of the target vehicle is obtained; detecting the license plate image, and determining a license plate mask region in the license plate image and coordinate differences between the four groups of segmentation points and license plate corner points; determining a plurality of groups of license plate four-angle points according to the license plate mask region and the coordinate difference values of the four groups of segmentation points and the license plate angle points; determining license plate regions corresponding to the license plate four-corner points according to the plurality of groups of license plate four-corner points; and carrying out license plate recognition on the image of the license plate area to obtain the license plate number of the target vehicle. On the basis that the existing license plate recognition adopts a detection and recognition mode, the region for detecting the license plate is not the accurate position of the license plate, contains more background information or information loss, and has low license plate recognition accuracy and low robustness, the license plate recognition method determines a plurality of groups of license plate angular points through the license plate image, and determines the license plate regions corresponding to the four corners of the license plate according to the four corners of the plurality of groups of license plates, so that the region for detecting the license plate is more accurate, more background information or information loss can not be caused, the license plate recognition accuracy is improved, and the license plate recognition robustness is high.
As shown in fig. 2, which is a schematic flow chart of an embodiment of a license plate recognition method according to an embodiment of the present invention, the license plate recognition method includes:
201. and acquiring a license plate image of the target vehicle.
Specifically, the license plate image of the target vehicle may be a license plate image of the target vehicle captured by a target camera device disposed at an intersection, a cell, an office building, or the like.
It should be noted that, in the embodiment of the present invention, the license plate image of the target vehicle may be a license plate image including only one license plate information, so that subsequent identification may be more convenient, and therefore, to ensure this point, acquiring the license plate image of the target vehicle may include: the method comprises the steps of obtaining an original license plate image, detecting the original license plate image, determining whether license plate mask regions in the original license plate image are multiple or not, and if yes, determining a plurality of license plate images corresponding to the number of the license plate mask regions in the original license plate image, wherein the license plate images comprise license plate images of target vehicles.
The method for determining the number of the license plate images corresponding to the number of the license plate mask regions in the original license plate image may be: and respectively taking the license plate mask area in the original license plate image as a target license plate mask area, and adjusting the license plate mask area outside the target license plate mask area to be background color to obtain a plurality of license plate images with only one license plate mask area.
202. And detecting the license plate image, and determining a license plate mask area in the license plate image and coordinate differences between the four groups of segmentation points and license plate corner points.
As shown in fig. 3, in an embodiment of the present application, the detecting the license plate image to determine a license plate mask region in the license plate image and coordinate differences between four sets of segmentation points and license plate corner points may further include:
301. and performing channel regression processing on the license plate image, and determining coordinate difference values of the four groups of segmentation points to the license plate corner points.
The Regression processing is a process of performing Bounding-Box Regression (Bounding-Box Regression) on an image to obtain information of a Bounding Box of the image, and the channel Regression processing in the present application refers to a process of obtaining relative position information of four corner points of a license plate by using a multi-channel form Regression, for example, obtaining relative position information of four corner points of a plurality of license plates (for example, coordinate difference values of the corner points of the license plates from a partition point).
302. And performing semantic segmentation processing on the license plate image to determine a license plate mask region in the license plate image.
Semantic segmentation, where we need to classify visual input into different semantically interpretable classes, is a fundamental task in computer vision, where "interpretability of semantics", i.e. classification classes, are meaningful in the real world. For example, it may be desirable to distinguish all pixels in an image that belong to a car and generate mask information for the corresponding vehicle pixels of the image.
The detecting the license plate image to determine a license plate mask region and coordinate difference values between four groups of segmentation points and license plate corner points in the license plate image may also be implemented by using a preset license plate segmentation network model, and specifically, the detecting the license plate image to determine the license plate mask region and the coordinate difference values between the four groups of segmentation points and license plate corner points in the license plate image includes: and detecting the license plate image by adopting a preset license plate segmentation network model, and determining a license plate mask region in the license plate image and coordinate difference values of four groups of segmentation points and license plate corner points.
Further, the license plate segmentation network model may include a dual-branch network model, for example, the license plate segmentation network model includes a channel regression sub-network model and a license plate semantic segmentation sub-network model; at this time, the detecting the license plate image by using a preset license plate segmentation network model, and determining a license plate mask region in the license plate image and coordinate differences between four groups of segmentation points and license plate angular points, includes: performing channel regression processing on the license plate image by adopting the channel regression sub-network model, and determining coordinate difference values of four groups of segmentation points to license plate angular points, wherein the coordinate difference values of the four groups of segmentation points to the license plate angular points comprise four groups of segmentation points to license plate angular points, and coordinate difference values in the x and y directions in a coordinate system of the channel regression sub-network model; and adopting the license plate semantic segmentation sub-network model to perform license plate semantic segmentation processing on the license plate image and determine a license plate mask region in the license plate image.
Specifically, the license plate segmentation network model may be a dual-branch convolutional neural network model, that is, the channel regression sub-network model and the license plate semantic segmentation sub-network model are respectively a channel regression convolutional sub-convolutional network model and a license plate semantic segmentation sub-convolutional network model, and the channel regression convolutional sub-convolutional network is an 8-channel regression sub-convolutional network model and outputs coordinate difference values of four sets of segmentation points to the license plate corner points. The division points are pixel points in the license plate mask area.
In addition, in the embodiment of the present application, the license plate segmentation network model, or the channel regression sub-network model, the license plate semantic segmentation sub-network model, and the like, may be obtained by training an initial network model (such as a convolutional neural network model) with image data acquired by the model in advance, and the specific training process is not described herein again.
203. And determining a plurality of groups of license plate four-corner points according to the license plate mask region and the coordinate difference values of the four groups of segmentation points and the license plate corner points.
In an embodiment of the present application, as shown in fig. 4, the determining a plurality of sets of license plate four-corner points according to the license plate mask region and coordinate differences between the four sets of segmentation points and the license plate corner points may further include:
401. and respectively taking one pixel point in the license plate mask region as a target pixel point to obtain the coordinates of the target pixel point.
402. And calculating coordinates of four license plate angular points according to the coordinates of the target pixel points and coordinate differences of the four groups of segmentation points and the license plate angular points, wherein the four license plate angular points form a set of license plate four angular points.
403. And obtaining a plurality of groups of license plate four-corner points after the coordinate calculation of the four license plate corner points corresponding to all the pixel points in the license plate mask region is completed.
In one embodiment, assume that the target pixel point is M (x)i，yi) The coordinate difference dx and dy between the four groups of division points and the corner points of the license plate are respectively
At this time, the target pixel point M (x)i，yi) The corresponding dx, dy is:
the coordinate difference value of the left upper corner point of the license plate, the coordinate difference value of the left lower corner point of the license plate, the coordinate difference value of the right upper corner point of the license plate and the coordinate difference value of the right lower corner point of the license plate are respectively corresponded to.
According to the target pixel point M (x)i，yi) The coordinates and the coordinate differences between the four groups of segmentation points and the license plate angular points can be calculated to obtain the coordinates of the four license plate angular points, which comprises the following steps:
and when all the pixel points in the license plate mask region finish calculating the coordinates of the four license plate angular points, obtaining a plurality of groups of license plate four angular points.
204. And determining license plate regions corresponding to the four corners of the license plate according to the plurality of groups of four corners of the license plate.
Further, determining license plate regions corresponding to the license plate four-corner points according to the plurality of sets of license plate four-corner points may include: determining a coordinate set corresponding to four corners of the license plate from the plurality of groups of four corners of the license plate; voting according to the coordinate sets corresponding to the four corners and the occurrence times to determine the coordinates of the four corners of the license plate; and determining license plate areas corresponding to the four corners of the license plate according to the coordinates of the four corners of the license plate.
Determining coordinates of four corner points of the license plate by voting according to the coordinate sets corresponding to the four corners and the occurrence times may include: voting to determine four corner coordinates with the largest occurrence frequency from the coordinate sets corresponding to the four corners; and determining the coordinates of the four corners as the coordinates of the four corners of the license plate.
Specifically, after the coordinates of four license plate corner points are calculated by all pixel points in the license plate masking area, a plurality of sets of license plate four corner points are obtained, the coordinates of the plurality of sets of license plate four corner points are also determined, coordinate sets corresponding to four license plate corners are obtained, and the coordinate sets respectively correspond to a license plate upper left corner point coordinate set, a license plate lower left corner point coordinate set, a license plate upper right corner coordinate set and a license plate lower right corner coordinate set; and voting to determine coordinates of four corner points of the license plate according to the occurrence times according to the coordinate sets corresponding to the four corners, for example, the number of times of occurrence of a coordinate of a point A in the coordinate set of the upper left corner point of the license plate is the largest, the number of times of occurrence of a coordinate of a point B in the coordinate set of the lower left corner point of the license plate is the largest, the number of times of occurrence of a coordinate of a point C in the coordinate set of the upper right corner point of the license plate is the largest, the number of times of occurrence of a coordinate of a point D in the coordinate set of the lower right corner point of the license plate is the largest, and then the representing points A, B, C, D are the four corner points of the license plate respectively.
The process can be understood as a process of voting for the license plate corner points, and assuming that the license plate mask region has N pixel points, the step of determining the four corner points of the license plate is performed on all the N pixel points of the license plate mask region, so that N groups of four corner points of the voted license plate can be obtained, as shown in fig. 5 below. The 4 corner points of the license plate voted out are not unique, and the coordinate points with the most voted number are taken as the final 4 corner points of the license plate in each license plate corner point category (upper left, upper right, lower left and lower right).
205. And carrying out license plate recognition on the image of the license plate area to obtain the license plate number of the target vehicle.
Due to the shooting angle or the imaging distortion of the camera and the like, the license plate region determined in the step 204 has the problems of inclination, irregular shape and the like. And adverse effects are brought to subsequent license plate recognition. In order to improve the robustness of the algorithm, the invention corrects the license plate image by using perspective transformation. Since the coordinates of 4 license plate corners can be determined in step 204, the irregular quadrangle of the license plate region can be determined, and the license plate region is mapped to a new image space through perspective transformation, wherein the license plate region has a preset width and height Twidth，TheightA rectangular area of (a). Namely, the license plate recognition of the image of the license plate area is carried out to obtain the license plate number of the target vehicle, and the method comprises the following steps: carrying out perspective transformation on the image of the license plate area to obtain a preset width and height rectangular license plate image; and carrying out license plate recognition on the rectangular license plate image to obtain the license plate number of the target vehicle.
The license plate image after perspective transformation meets the requirement of license plate recognition, and can be sent to the license plate recognition, so that the accuracy of subsequent license plate recognition can be further improved.
In order to better implement the license plate recognition method in the embodiment of the present invention, based on the license plate recognition method, an embodiment of the present invention further provides a license plate recognition apparatus, which is located in a server, and as shown in fig. 7, the license plate recognition apparatus 700 includes:
an obtaining unit 701, configured to obtain a license plate image of a target vehicle;
a first determining unit 702, configured to detect the license plate image, and determine a license plate mask region in the license plate image and coordinate differences between four groups of segmentation points and license plate corner points;
a second determining unit 703, configured to determine multiple sets of license plate four corner points according to the license plate mask region and coordinate differences between the four sets of segmentation points and the license plate corner points;
a third determining unit 704, configured to determine license plate regions corresponding to the four corners of the license plate according to the multiple sets of four corners of the license plate;
and a license plate recognition unit 705, configured to perform license plate recognition on the image of the license plate region to obtain a license plate number of the target vehicle.
In the embodiment of the application, the license plate image of the target vehicle is acquired through an acquisition unit 701; a first determining unit 702 detects the license plate image, and determines a license plate mask region in the license plate image and coordinate differences between four groups of segmentation points and license plate corner points; the second determining unit 703 determines a plurality of groups of license plate four-corner points according to the license plate mask region and the coordinate difference values between the four groups of segmentation points and the license plate corner points; a third determining unit 704 determines license plate regions corresponding to the license plate four-corner points according to the plurality of groups of license plate four-corner points; the license plate recognition unit 705 performs license plate recognition on the image of the license plate region to obtain the license plate number of the target vehicle. On the basis that the existing license plate recognition adopts a detection and recognition mode, the region for detecting the license plate is not the accurate position of the license plate, contains more background information or information loss, and has low license plate recognition accuracy and low robustness, the license plate recognition method determines a plurality of groups of license plate angular points through the license plate image, and determines the license plate regions corresponding to the four corners of the license plate according to the four corners of the plurality of groups of license plates, so that the region for detecting the license plate is more accurate, more background information or information loss can not be caused, the license plate recognition accuracy is improved, and the license plate recognition robustness is high.
In some embodiments of the present application, the first determining unit 702 is specifically configured to:
performing channel regression processing on the license plate image, and determining coordinate differences of four groups of segmentation points to license plate corner points;
and performing semantic segmentation processing on the license plate image to determine a license plate mask region in the license plate image.
In some embodiments of the present application, the first determining unit 702 is specifically configured to:
and detecting the license plate image by adopting a preset license plate segmentation network model, and determining a license plate mask region in the license plate image and coordinate difference values of four groups of segmentation points and license plate corner points.
In some embodiments of the present application, the license plate segmentation network model comprises a channel regression sub-network model and a license plate semantic segmentation sub-network model;
the first determining unit 702 is specifically configured to: performing channel regression processing on the license plate image by adopting the channel regression sub-network model, and determining coordinate difference values of four groups of segmentation points to license plate angular points, wherein the coordinate difference values of the four groups of segmentation points to the license plate angular points comprise four groups of segmentation points to license plate angular points, and coordinate difference values in the x and y directions in a coordinate system of the channel regression sub-network model;
and adopting the license plate semantic segmentation sub-network model to perform license plate semantic segmentation processing on the license plate image and determine a license plate mask region in the license plate image.
In some embodiments of the present application, the second determining unit 703 is specifically configured to:
respectively taking one pixel point in the license plate mask region as a target pixel point to obtain the coordinate of the target pixel point;
calculating coordinates of four license plate angular points according to the coordinates of the target pixel points and coordinate differences of the four groups of segmentation points and the license plate angular points, wherein the four license plate angular points form a set of license plate four angular points;
and obtaining a plurality of groups of license plate four-corner points after the coordinate calculation of the four license plate corner points corresponding to all the pixel points in the license plate mask region is completed.
In some embodiments of the present application, the third determining unit 704 is specifically configured to:
determining a coordinate set corresponding to four corners of the license plate from the plurality of groups of four corners of the license plate;
voting according to the coordinate sets corresponding to the four corners and the occurrence times to determine the coordinates of the four corners of the license plate;
and determining license plate areas corresponding to the four corners of the license plate according to the coordinates of the four corners of the license plate.
In some embodiments of the present application, the third determining unit 704 is specifically configured to:
voting to determine four corner coordinates with the largest occurrence frequency from the coordinate sets corresponding to the four corners;
and determining the coordinates of the four corners as the coordinates of the four corners of the license plate.
In some embodiments of the present application, the license plate recognition unit 705 is specifically configured to:
carrying out perspective transformation on the image of the license plate area to obtain a preset width and height rectangular license plate image;
and carrying out license plate recognition on the rectangular license plate image to obtain the license plate number of the target vehicle.
The embodiment of the present invention further provides a server, which integrates any one of the license plate recognition devices provided by the embodiments of the present invention, and the server includes:
one or more processors;
a memory; and
one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the processor for performing the steps of the license plate recognition method in any of the above embodiments of the license plate recognition method.
The embodiment of the invention also provides a server, which integrates any license plate recognition device provided by the embodiment of the invention. Fig. 8 is a schematic diagram showing a structure of a server according to an embodiment of the present invention, specifically:
the server may include components such as a processor 801 of one or more processing cores, memory 802 of one or more computer-readable storage media, a power supply 803, and an input unit 804. Those skilled in the art will appreciate that the server architecture shown in FIG. 8 is not meant to be limiting, and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
Wherein:
the processor 801 is a control center of the server, connects various parts of the entire server using various interfaces and lines, and performs various functions of the server and processes data by running or executing software programs and/or modules stored in the memory 802 and calling data stored in the memory 802, thereby performing overall monitoring of the server. Alternatively, processor 801 may include one or more processing cores; preferably, the processor 801 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 801.
The memory 802 may be used to store software programs and modules, and the processor 801 executes various functional applications and data processing by operating the software programs and modules stored in the memory 802. The memory 802 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to the use of the server, and the like. Further, the memory 802 may include high speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 802 may also include a memory controller to provide the processor 801 access to the memory 802.
The server further includes a power supply 803 for supplying power to the various components, and preferably, the power supply 803 may be logically connected to the processor 801 via a power management system, so that functions of managing charging, discharging, and power consumption are performed via the power management system. The power supply 803 may also include one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and any like components.
The server may further include an input unit 804, and the input unit 804 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.
Although not shown, the server may further include a display unit and the like, which will not be described in detail herein. Specifically, in this embodiment, the processor 801 in the server loads the executable file corresponding to the process of one or more application programs into the memory 802 according to the following instructions, and the processor 801 runs the application programs stored in the memory 802, thereby implementing various functions as follows:
acquiring a license plate image of a target vehicle; detecting the license plate image, and determining a license plate mask region in the license plate image and coordinate differences between the four groups of segmentation points and license plate corner points; determining a plurality of groups of license plate four-angle points according to the license plate mask region and the coordinate difference values of the four groups of segmentation points and the license plate angle points; determining license plate regions corresponding to the license plate four-corner points according to the plurality of groups of license plate four-corner points; and carrying out license plate recognition on the image of the license plate area to obtain the license plate number of the target vehicle.
It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions or by associated hardware controlled by the instructions, which may be stored in a computer readable storage medium and loaded and executed by a processor.
To this end, an embodiment of the present invention provides a computer-readable storage medium, which may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like. The license plate recognition method comprises a step of identifying a license plate, a step of identifying the license plate, and a step of executing the steps of the license plate recognition method. For example, the computer program may be loaded by a processor to perform the steps of:
acquiring a license plate image of a target vehicle; detecting the license plate image, and determining a license plate mask region in the license plate image and coordinate differences between the four groups of segmentation points and license plate corner points; determining a plurality of groups of license plate four-angle points according to the license plate mask region and the coordinate difference values of the four groups of segmentation points and the license plate angle points; determining license plate regions corresponding to the license plate four-corner points according to the plurality of groups of license plate four-corner points; and carrying out license plate recognition on the image of the license plate area to obtain the license plate number of the target vehicle.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and parts that are not described in detail in a certain embodiment may refer to the above detailed descriptions of other embodiments, and are not described herein again.
In a specific implementation, each unit or structure may be implemented as an independent entity, or may be combined arbitrarily to be implemented as one or several entities, and the specific implementation of each unit or structure may refer to the foregoing method embodiment, which is not described herein again.
The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.
The license plate recognition method, the license plate recognition device, the license plate recognition server and the storage medium provided by the embodiment of the invention are described in detail, a specific embodiment is applied in the text to explain the principle and the implementation mode of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for those skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (11)
1. A license plate recognition method is characterized by further comprising the following steps:
acquiring a license plate image of a target vehicle;
detecting the license plate image, and determining a license plate mask region in the license plate image and coordinate differences between the four groups of segmentation points and license plate corner points;
determining a plurality of groups of license plate four-angle points according to the license plate mask region and the coordinate difference values of the four groups of segmentation points and the license plate angle points;
determining license plate regions corresponding to the license plate four-corner points according to the plurality of groups of license plate four-corner points;
and carrying out license plate recognition on the image of the license plate area to obtain the license plate number of the target vehicle.
2. The license plate recognition method of claim 1, wherein the detecting the license plate image to determine a license plate mask region and coordinate differences between four sets of segmentation points and license plate corner points in the license plate image comprises:
performing channel regression processing on the license plate image, and determining coordinate differences of four groups of segmentation points to license plate corner points;
and performing semantic segmentation processing on the license plate image to determine a license plate mask region in the license plate image.
3. The license plate recognition method of claim 2, wherein the detecting the license plate image to determine a license plate mask region and coordinate differences between four sets of segmentation points and license plate corner points in the license plate image comprises:
and detecting the license plate image by adopting a preset license plate segmentation network model, and determining a license plate mask region in the license plate image and coordinate difference values of four groups of segmentation points and license plate corner points.
4. The license plate recognition method of claim 3, wherein the license plate segmentation network model comprises a channel regression sub-network model and a license plate semantic segmentation sub-network model;
the method comprises the following steps of detecting the license plate image by adopting a preset license plate segmentation network model, and determining a license plate mask region and coordinate difference values of four groups of segmentation points and license plate corner points in the license plate image, wherein the steps comprise:
performing channel regression processing on the license plate image by adopting the channel regression sub-network model, and determining coordinate difference values of four groups of segmentation points to license plate angular points, wherein the coordinate difference values of the four groups of segmentation points to the license plate angular points comprise four groups of segmentation points to license plate angular points, and coordinate difference values in the x and y directions in a coordinate system of the channel regression sub-network model;
and adopting the license plate semantic segmentation sub-network model to perform license plate semantic segmentation processing on the license plate image and determine a license plate mask region in the license plate image.
5. The license plate recognition method of any one of claims 2 to 4, wherein the determining a plurality of sets of license plate four-corner points according to the license plate mask region and coordinate differences between the four sets of segmentation points and the license plate corner points comprises:
respectively taking one pixel point in the license plate mask region as a target pixel point to obtain the coordinate of the target pixel point;
calculating coordinates of four license plate angular points according to the coordinates of the target pixel points and coordinate differences of the four groups of segmentation points and the license plate angular points, wherein the four license plate angular points form a set of license plate four angular points;
and obtaining a plurality of groups of license plate four-corner points after the coordinate calculation of the four license plate corner points corresponding to all the pixel points in the license plate mask region is completed.
6. The license plate recognition method of any one of claims 2 to 4, wherein the determining license plate regions corresponding to the license plate four-corner points according to the plurality of sets of license plate four-corner points comprises:
determining a coordinate set corresponding to four corners of the license plate from the plurality of groups of four corners of the license plate;
voting according to the coordinate sets corresponding to the four corners and the occurrence times to determine the coordinates of the four corners of the license plate;
and determining license plate areas corresponding to the four corners of the license plate according to the coordinates of the four corners of the license plate.
7. The license plate recognition method of claim 6, wherein the voting for determining the coordinates of the four corners of the license plate according to the coordinate sets corresponding to the four corners by the occurrence number comprises:
voting to determine four corner coordinates with the largest occurrence frequency from the coordinate sets corresponding to the four corners;
and determining the coordinates of the four corners as the coordinates of the four corners of the license plate.
8. The license plate recognition method of claim 1, wherein the performing license plate recognition on the image of the license plate region to obtain the license plate number of the target vehicle comprises:
carrying out perspective transformation on the image of the license plate area to obtain a preset width and height rectangular license plate image;
and carrying out license plate recognition on the rectangular license plate image to obtain the license plate number of the target vehicle.
9. A license plate recognition device, characterized in that the license plate recognition device comprises:
the system comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring a license plate image of a target vehicle;
the first determining unit is used for detecting the license plate image and determining a license plate mask area in the license plate image and coordinate difference values of four groups of segmentation points and license plate corner points;
the second determining unit is used for determining a plurality of groups of license plate four-corner points according to the license plate mask region and the coordinate difference values of the four groups of segmentation points and the license plate corner points;
the third determining unit is used for determining license plate areas corresponding to the four corners of the license plate according to the plurality of groups of four corners of the license plate;
and the license plate recognition unit is used for carrying out license plate recognition on the image of the license plate area to obtain the license plate number of the target vehicle.
10. A server, characterized in that the server comprises:
one or more processors;
a memory; and
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the license plate recognition method of any of claims 1-8.
11. A computer-readable storage medium, having stored thereon a computer program which is loaded by a processor to perform the steps of the license plate recognition method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010129455.9A CN113326836A (en) | 2020-02-28 | 2020-02-28 | License plate recognition method and device, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010129455.9A CN113326836A (en) | 2020-02-28 | 2020-02-28 | License plate recognition method and device, server and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113326836A true CN113326836A (en) | 2021-08-31 |
Family
ID=77412733
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010129455.9A Pending CN113326836A (en) | 2020-02-28 | 2020-02-28 | License plate recognition method and device, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113326836A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113850238A (en) * | 2021-11-29 | 2021-12-28 | 北京世纪好未来教育科技有限公司 | Document detection method and device, electronic equipment and storage medium |
| CN113963060A (en) * | 2021-09-22 | 2022-01-21 | 腾讯科技（深圳）有限公司 | Vehicle information image processing method and device based on artificial intelligence and electronic equipment |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103268489A (en) * | 2013-05-29 | 2013-08-28 | 电子科技大学 | Motor vehicle plate identification method based on sliding window searching |
| CN106778737A (en) * | 2016-11-24 | 2017-05-31 | 北京文安智能技术股份有限公司 | A kind of car plate antidote, device and a kind of video acquisition device |
| CN108830213A (en) * | 2018-06-12 | 2018-11-16 | 北京理工大学 | Car plate detection and recognition methods and device based on deep learning |
| WO2018219054A1 (en) * | 2017-06-02 | 2018-12-06 | 杭州海康威视数字技术股份有限公司 | Method, device, and system for license plate recognition |
| KR101932631B1 (en) * | 2017-08-25 | 2018-12-27 | 서울과학기술대학교 산학협력단 | The appratus and method for recognizing car number using three chnnel radar and k-nn algorithm |
| CN109858327A (en) * | 2018-12-13 | 2019-06-07 | 安徽清新互联信息科技有限公司 | A kind of character segmentation method based on deep learning |
| CN109886896A (en) * | 2019-02-28 | 2019-06-14 | 闽江学院 | A kind of blue License Plate Segmentation and antidote |
| CN110163199A (en) * | 2018-09-30 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Licence plate recognition method, license plate recognition device, car license recognition equipment and medium |
| CN110245673A (en) * | 2018-03-09 | 2019-09-17 | 浙江宇视科技有限公司 | Method for detecting parking stalls and device |
| CN110287955A (en) * | 2019-06-05 | 2019-09-27 | 北京字节跳动网络技术有限公司 | Target area determines model training method, device and computer readable storage medium |
| CN110414507A (en) * | 2019-07-11 | 2019-11-05 | 和昌未来科技（深圳）有限公司 | Licence plate recognition method, device, computer equipment and storage medium |
| CN110689000A (en) * | 2018-07-05 | 2020-01-14 | 山东华软金盾软件股份有限公司 | Vehicle license plate identification method based on vehicle license plate sample in complex environment |
-
2020
- 2020-02-28 CN CN202010129455.9A patent/CN113326836A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103268489A (en) * | 2013-05-29 | 2013-08-28 | 电子科技大学 | Motor vehicle plate identification method based on sliding window searching |
| CN106778737A (en) * | 2016-11-24 | 2017-05-31 | 北京文安智能技术股份有限公司 | A kind of car plate antidote, device and a kind of video acquisition device |
| WO2018219054A1 (en) * | 2017-06-02 | 2018-12-06 | 杭州海康威视数字技术股份有限公司 | Method, device, and system for license plate recognition |
| KR101932631B1 (en) * | 2017-08-25 | 2018-12-27 | 서울과학기술대학교 산학협력단 | The appratus and method for recognizing car number using three chnnel radar and k-nn algorithm |
| CN110245673A (en) * | 2018-03-09 | 2019-09-17 | 浙江宇视科技有限公司 | Method for detecting parking stalls and device |
| CN108830213A (en) * | 2018-06-12 | 2018-11-16 | 北京理工大学 | Car plate detection and recognition methods and device based on deep learning |
| CN110689000A (en) * | 2018-07-05 | 2020-01-14 | 山东华软金盾软件股份有限公司 | Vehicle license plate identification method based on vehicle license plate sample in complex environment |
| CN110163199A (en) * | 2018-09-30 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Licence plate recognition method, license plate recognition device, car license recognition equipment and medium |
| CN109858327A (en) * | 2018-12-13 | 2019-06-07 | 安徽清新互联信息科技有限公司 | A kind of character segmentation method based on deep learning |
| CN109886896A (en) * | 2019-02-28 | 2019-06-14 | 闽江学院 | A kind of blue License Plate Segmentation and antidote |
| CN110287955A (en) * | 2019-06-05 | 2019-09-27 | 北京字节跳动网络技术有限公司 | Target area determines model training method, device and computer readable storage medium |
| CN110414507A (en) * | 2019-07-11 | 2019-11-05 | 和昌未来科技（深圳）有限公司 | Licence plate recognition method, device, computer equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| M.WAFY: "Automatic license plate detection based on corner point and cluster", 2013 9TH INTERNATIONAL COMPUTER ENGINEERING CONFERENCE (ICENCO), 31 December 2013 (2013-12-31), pages 15 - 18, XP032565152, DOI: 10.1109/ICENCO.2013.6736469 * |
| 杜媛;: "基于图像分割与多特征模型的车牌识别算法", 国外电子测量技术, no. 08, pages 25 - 29 * |
| 杨飚;周文婷;: "基于East的大角度倾斜车牌检测算法研究", 现代计算机, no. 12, 25 April 2019 (2019-04-25), pages 53 - 56 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113963060A (en) * | 2021-09-22 | 2022-01-21 | 腾讯科技（深圳）有限公司 | Vehicle information image processing method and device based on artificial intelligence and electronic equipment |
| CN113963060B (en) * | 2021-09-22 | 2022-03-18 | 腾讯科技（深圳）有限公司 | Vehicle information image processing method and device based on artificial intelligence and electronic equipment |
| CN113850238A (en) * | 2021-11-29 | 2021-12-28 | 北京世纪好未来教育科技有限公司 | Document detection method and device, electronic equipment and storage medium |
| CN113850238B (en) * | 2021-11-29 | 2022-03-04 | 北京世纪好未来教育科技有限公司 | Document detection method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109815868B (en) | Image target detection method and device and storage medium | |
| CN108875723B (en) | Object detection method, device and system and storage medium | |
| CN112308095A (en) | Picture preprocessing and model training method and device, server and storage medium | |
| CN107633208B (en) | Electronic device, the method for face tracking and storage medium | |
| Peng et al. | A training-free nose tip detection method from face range images | |
| CN110619656B (en) | Face detection tracking method and device based on binocular camera and electronic equipment | |
| CN113326836A (en) | License plate recognition method and device, server and storage medium | |
| WO2019128504A1 (en) | Method and apparatus for image processing in billiards game, and terminal device | |
| WO2020125062A1 (en) | Image fusion method and related device | |
| CN111046746A (en) | License plate detection method and device | |
| CN114360261B (en) | Vehicle reverse running identification method and device, big data analysis platform and medium | |
| CN115249355A (en) | Object association method, device and computer-readable storage medium | |
| WO2021138893A1 (en) | Vehicle license plate recognition method and apparatus, electronic device, and storage medium | |
| CN115471439A (en) | Method and device for identifying defects of display panel, electronic equipment and storage medium | |
| CN114359231A (en) | Parking space detection method, device, equipment and storage medium | |
| CN113869163B (en) | Target tracking method and device, electronic equipment and storage medium | |
| CN111765892B (en) | Positioning method, positioning device, electronic equipment and computer readable storage medium | |
| CN114170576A (en) | Method and device for detecting repeated images | |
| CN115601684A (en) | Emergency early warning method and device, electronic equipment and storage medium | |
| CN113935425A (en) | Object identification method, device, terminal and storage medium | |
| CN114092904A (en) | Lane line detection method, lane line detection device, electronic device, and storage medium | |
| CN114529735A (en) | Edge starting point extraction method and related device | |
| CN114372993A (en) | Oblique-shooting shelf layered detection method and system based on image correction | |
| CN112257666A (en) | Target image content aggregation method, device, equipment and readable storage medium | |
| CN113538449A (en) | Image correction method, device, server and storage 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 |