CN117437646A - License plate recognition method, license plate recognition device, computer equipment and storage medium - Google Patents

License plate recognition method, license plate recognition device, computer equipment and storage medium Download PDF

Info

Publication number
CN117437646A
CN117437646A CN202311469574.9A CN202311469574A CN117437646A CN 117437646 A CN117437646 A CN 117437646A CN 202311469574 A CN202311469574 A CN 202311469574A CN 117437646 A CN117437646 A CN 117437646A
Authority
CN
China
Prior art keywords
license plate
vehicle
region
area
target image
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
Application number
CN202311469574.9A
Other languages
Chinese (zh)
Inventor
吴喆
王浩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Jieshun Science and Technology Industry Co Ltd
Original Assignee
Shenzhen Jieshun Science and Technology Industry Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Jieshun Science and Technology Industry Co Ltd filed Critical Shenzhen Jieshun Science and Technology Industry Co Ltd
Priority to CN202311469574.9A priority Critical patent/CN117437646A/en
Publication of CN117437646A publication Critical patent/CN117437646A/en
Pending legal-status Critical Current

Links

Classifications

    • 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
    • G06V30/19—Recognition using electronic means
    • G06V30/19007—Matching; Proximity measures
    • G06V30/1908—Region based matching

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a license plate matching method, a license plate matching device, computer equipment and a storage medium, wherein the license plate matching method comprises the following steps: acquiring a target image comprising a plurality of vehicles and at least one license plate; performing image recognition processing on the target image, and determining a vehicle region corresponding to each vehicle in the target image and a license plate region corresponding to each license plate; and generating a matching result according to the vehicle region corresponding to each vehicle and the license plate region corresponding to each license plate. In the embodiment of the invention, compared with the mode of confirming the matching relationship between a plurality of vehicles and at least one license plate according to the vehicle identification frame and the license plate identification frame in the prior art, the matching relationship between the plurality of vehicles and the at least one license plate is confirmed according to the vehicle region corresponding to each vehicle and the license plate region corresponding to each license plate, so that the matching of the license plate and the vehicle is accurately confirmed, and the accuracy of the matching result is further improved.

Description

License plate recognition method, license plate recognition device, computer equipment and storage medium
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a license plate recognition method, a license plate recognition device, a computer device, and a storage medium.
Background
With the development of information technology, the license plate recognition mode is more and more intelligent, and the license plate recognition technology of vehicles is widely applied. At present, a license plate is generally identified by acquiring a picture shot by a camera, identifying a vehicle identification frame where a vehicle is located in the picture and a license plate identification frame where the license plate is located, and determining a matching result between the license plate and the vehicle according to the position relationship between the vehicle identification frame and the license plate identification frame.
However, there may be a situation that the number of vehicles is not matched with the license plate data in the picture shot by the camera, for example, the number of vehicles is greater than the number of license plates, and it cannot be accurately determined which vehicle the license plate is matched with in such a scene, so as to generate an incorrect matching result.
Disclosure of Invention
Based on the above, it is necessary to provide a license plate matching method, device, computer equipment and storage medium to solve the technical problem that in the license plate scene, it is not possible to accurately determine which vehicle the license plate is matched with, and further an incorrect matching result is generated.
A license plate matching method comprising:
acquiring a target image comprising a plurality of vehicles and at least one license plate;
performing image recognition processing on the target image, and determining a vehicle region corresponding to each vehicle in the target image and a license plate region corresponding to each license plate;
generating a matching result according to the vehicle region corresponding to each vehicle and the license plate region corresponding to each license plate; the matching result is used for representing the matching relation between the vehicles and the at least one license plate.
A license plate matching device, comprising:
the acquisition module is used for acquiring a target image comprising a plurality of vehicles and at least one license plate;
the determining module is used for carrying out image recognition processing on the target image and determining a vehicle area corresponding to each vehicle in the target image and a license plate area corresponding to each license plate;
the generation module is used for generating a matching result according to the vehicle region corresponding to each vehicle and the license plate region corresponding to each license plate; the matching result is used for representing the matching relation between the vehicles and the at least one license plate.
A computer device comprising a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, the processor implementing the license plate matching method described above when executing the computer readable instructions.
One or more readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform a license plate matching method as described above.
The license plate matching method, the license plate matching device, the computer equipment and the storage medium, wherein the license plate matching method comprises the following steps: acquiring a target image comprising a plurality of vehicles and at least one license plate; performing image recognition processing on the target image, and determining a vehicle region corresponding to each vehicle in the target image and a license plate region corresponding to each license plate; generating a matching result according to the vehicle region corresponding to each vehicle and the license plate region corresponding to each license plate; the matching result is used to characterize a matching relationship between the plurality of vehicles and the at least one license plate. In the embodiment of the invention, compared with the mode of confirming the matching relationship between a plurality of vehicles and at least one license plate according to the vehicle identification frame and the license plate identification frame in the prior art, the matching relationship between the plurality of vehicles and the at least one license plate is confirmed according to the vehicle region corresponding to each vehicle and the license plate region corresponding to each license plate, so that the matching of the license plate and the vehicle is accurately confirmed, and the accuracy of the matching result is further improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of an application environment of a license plate matching method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a license plate matching method according to an embodiment of the invention;
FIG. 3 is a schematic diagram of an application scenario of a license plate matching method according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of another application scenario of the license plate matching method according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of another application scenario of the license plate matching method according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a license plate matching device according to an embodiment of the invention;
FIG. 7 is a schematic diagram of a computer device in accordance with an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The license plate matching method provided by the embodiment can be applied to an application environment as shown in fig. 1, wherein a client communicates with a server. Clients include, but are not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server may be implemented by a stand-alone server or a server cluster formed by a plurality of servers.
In an embodiment, as shown in fig. 2, a license plate matching method is provided, and the method is applied to the server in fig. 1 for illustration, where the method includes the following steps:
s210, acquiring a target image comprising a plurality of vehicles and at least one license plate.
As described above, the license plate matching method provided by the invention can be applied to a server, the server can be in communication connection with a camera, and the camera can transmit a shot image to the server.
In this embodiment, a target image is acquired, where the target image includes a plurality of vehicles and at least one license plate.
In an optional application scene, the camera sends the shot image to the server in real time or at fixed time, the server performs image feature recognition on the image sent by the camera, and if the image obtained by recognition comprises a plurality of vehicle features and at least one license plate feature, the image is determined to be a target image.
In another optional application scenario, the camera performs image feature recognition on the shot image, if the image obtained by recognition includes a plurality of vehicle features and at least one license plate feature, the image is determined to be a target image, and the target image is sent to the server.
In other application scenarios, the server may also receive the target image sent by the other electronic devices connected in communication.
S220, performing image recognition processing on the target image, and determining a vehicle region corresponding to each vehicle in the target image and a license plate region corresponding to each license plate.
In the step, after a target image is acquired, image recognition processing is performed on the target image, and a vehicle region corresponding to each vehicle in the target image and a license plate region corresponding to each license plate are determined. The vehicle region may be understood as a display region occupied by a vehicle in the target image, and the license plate region may be understood as a display region occupied by a license plate in the target image.
In particular, reference is made to the following embodiments for determining the technical solutions of the vehicle region and the license plate region.
S230, generating a matching result according to the vehicle region corresponding to each vehicle and the license plate region corresponding to each license plate.
In this step, in determining the vehicle region corresponding to the vehicle and the license plate region corresponding to each license plate, optionally, a matching result may be generated based on a positional relationship between each vehicle region and each license plate region. The matching result is used for representing the matching relation between a plurality of vehicles and at least one license plate.
It should be noted that if the matching result indicates that the vehicle a matches the license plate B, the license plate B is the license plate of the vehicle a; if the matching result indicates that the vehicle A and the license plate B are not matched, the license plate B is not the license plate of the vehicle A.
In the embodiment of the invention, compared with the mode of confirming the matching relationship between a plurality of vehicles and at least one license plate according to the vehicle identification frame and the license plate identification frame in the prior art, the matching relationship between the plurality of vehicles and the at least one license plate is confirmed according to the vehicle region corresponding to each vehicle and the license plate region corresponding to each license plate, so that the matching of the license plate and the vehicle is accurately confirmed, and the accuracy of the matching result is further improved.
Optionally, image processing is performed on the target image, and determining a vehicle region corresponding to each vehicle in the target image and a license plate region corresponding to each license plate includes:
performing image feature recognition on the target image, and determining a vehicle recognition frame corresponding to each vehicle feature and a license plate recognition frame corresponding to each license plate feature in the target image;
if license plate recognition frames in the overlapping area among the plurality of vehicle recognition frames exist, determining license plate areas corresponding to each license plate feature and vehicle areas corresponding to each vehicle feature.
In this embodiment, after the target image is obtained, image feature recognition is performed on the target image. Alternatively, image feature point extraction, a local binary pattern (Local Binary Patterns, LBP) algorithm, a Scale-invariant feature transform (SIFT) algorithm, or other types of algorithms may be applied, without specific limitation herein.
In the process of carrying out image feature recognition on the target image, a vehicle recognition frame for marking the vehicle features and a license plate recognition frame for marking the license plate features are generated, and it is understood that the vehicle recognition frame and the license plate recognition frame are rectangular frames, a part of display areas of the vehicle recognition frame are vehicle areas, and a part of display areas of the license plate recognition frame are license plate areas.
For ease of understanding, referring to fig. 3, as shown in fig. 3, a sign D1 and a sign D2 respectively represent a vehicle a and a vehicle B, and a sign D3 represents a license plate a.
Further, the position relation between the vehicle identification frames and the license plate identification frames is judged, if the license plate identification frames in the overlapping area among the plurality of vehicle identification frames exist in the target image, the license plate area corresponding to each license plate feature and the vehicle area corresponding to each vehicle feature are determined, so that the license plate corresponding to the license plate identification frames in the overlapping area is accurately judged, and the vehicle belongs to.
For ease of understanding, referring to fig. 3, in the application scenario shown in fig. 3, the license plate recognition frame D3 is located in the overlapping area of the vehicle recognition frame D1 and the vehicle recognition frame D2, and in this scenario, it is necessary to further determine the license plate area of the license plate a corresponding to the license plate recognition frame D3, the vehicle area of the vehicle a corresponding to the vehicle recognition frame D1, and the vehicle area of the vehicle B corresponding to the vehicle recognition frame D2.
In this embodiment, in a scenario in which the license plate recognition frames are located in an overlapping area between a plurality of vehicle recognition frames, a vehicle area corresponding to each vehicle and a license plate area corresponding to each license plate are determined, and then in a subsequent step, a matching relationship between a plurality of vehicles and at least one license plate is determined, so that it is accurately determined which vehicle the license plate is matched with.
Optionally, determining the license plate region corresponding to each license plate feature and the vehicle region corresponding to each vehicle feature includes:
image detection is carried out on each license plate feature and each vehicle feature in the target image, and a license plate image corresponding to each license plate feature and a vehicle image corresponding to each vehicle feature are obtained;
and determining the display area occupied by the vehicle image in the target image as a vehicle area, and determining the display area occupied by the license plate image in the target image as a license plate area.
In this embodiment, an optional implementation manner is to apply an example segmentation technique to detect each license plate feature and each vehicle feature in the target image to obtain a license plate image corresponding to each license plate feature and a vehicle image corresponding to each vehicle feature, further determine a display area occupied by the vehicle image in the target image as a vehicle area, and determine a display area occupied by the license plate image in the target image as a license plate area.
It should be noted that the above example segmentation technique is a Mask R-CNN-based image processing technique, and alternatively, mask R-CNN may be optimized in the following manner.
1. Basic network enhancement
A more powerful base network is used in the instance splitting technique, such as resnext101+fpn. By enhancing the basic network, features are extracted more accurately, and the segmentation effect is improved.
2. ROIAlign improvement
The ropooling in Mask R-CNN has a rounding during quantization operation, and produces a certain error, and by performing the ROIAlign improvement, the bilinear interpolation using the feature map can reduce the error.
3. Segmentation loss function improvement
The original polynomial cross entropy based on single pixel softmax in Mask R-CNN is modified into sigmoid binary cross entropy based on single pixel, and the segmentation accuracy is improved.
4. The mask is represented using a Discrete Cosine Transform (DCT). With DCT, a mask of size 128 x 128 can be represented with only 300 element vectors, and IoU of the reconstructed mask reaches 97%. The use of DCT to represent mask combines low complexity with high quality. The DCT Mask is fused into the Mask R-CNN, and the segmentation performance of the Mask R-CNN can be improved by only slightly changing the structure.
Optionally, determining the display area occupied by the vehicle image in the target image as the vehicle area, and determining the display area occupied by the license plate image in the target image as the license plate area includes:
marking a first pixel point in the target image, which constitutes the vehicle image, and marking a second pixel point in the target image, which constitutes the license plate image;
and clustering the first pixel points and the second pixel points to obtain a vehicle region generated based on the clustering result of the first pixel points and a license plate region generated based on the clustering result of the second pixel points.
In this embodiment, after the vehicle image and the license plate image are obtained, the pixel point of the vehicle image may be marked, and the pixel point of the vehicle image is determined as the first pixel point; and marking the pixel points of the license plate image, and determining the pixel points of the license plate image as second pixel points. For example, pixels constituting the vehicle image are marked red, and pixels constituting the license plate region are marked blue.
And further, clustering the first pixel points and the second pixel points to obtain a vehicle region generated based on the clustering result of the first pixel points and a license plate region generated based on the clustering result of the second pixel points. As an example, the pixel region composed of the first pixel points is determined as the vehicle region, and the pixel region composed of the second pixel points is determined as the license plate region.
For easy understanding of the above embodiments, please refer to fig. 4, in the application scenario shown in fig. 4, S1 represents a vehicle area of the vehicle a, S2 represents a vehicle area of the vehicle B, and S3 represents a license plate area of the license plate a. As shown in fig. 4, the license plate a indicated by the sign S3 is a partial area of the vehicle a indicated by the sign S1, and thus the license plate a is a license plate of the vehicle a.
Optionally, image feature recognition is performed on the target image, and after determining a vehicle recognition frame corresponding to each vehicle feature and a license plate recognition frame corresponding to each license plate feature in the target image, the method further includes:
if no license plate recognition frame exists in the overlapping area among the plurality of vehicle recognition frames, determining the area where the vehicle recognition frame is located as a vehicle area corresponding to the corresponding vehicle feature, and determining the area where the license plate recognition frame is located as a license plate area corresponding to the corresponding license plate feature.
In this embodiment, if the license plate recognition frame located in the overlapping area between the plurality of vehicle recognition frames does not exist in the target image, the matching relationship between the plurality of vehicles and the license plate may be determined according to the positional relationship between the vehicle recognition frame and the license plate recognition frame, that is, the area where the vehicle recognition frame is located may be determined as the vehicle area corresponding to the corresponding vehicle feature, and the area where the license plate recognition frame is located may be determined as the license plate area corresponding to the corresponding license plate feature.
Specifically, referring to fig. 5, in the application scenario shown in fig. 5, the identifier D1 represents a vehicle identification frame of the vehicle a, the identifier D2 represents a vehicle identification frame of the vehicle B, and the identifier D3 represents a license plate identification frame of the license plate a, as shown in fig. 5, the license plate identification frame of the license plate a is located within the vehicle identification frame of the vehicle a, and there is no overlapping area between the vehicle identification frame of the vehicle a and the vehicle identification frame of the vehicle B, so that it can be determined that the license plate a is the license plate of the vehicle a.
In this embodiment, when the license plate recognition frame in the overlapping area between the plurality of vehicle recognition frames does not exist in the target image, the area where the vehicle recognition frame is located may be directly determined as the vehicle area corresponding to the corresponding vehicle feature, the area where the license plate recognition frame is located may be determined as the license plate area corresponding to the corresponding license plate feature, and then the matching relationship between the plurality of vehicles and the license plate is determined according to the vehicle area and the license plate area, so that the image detection of the target image is not required, and therefore, the operation steps in the license plate matching process are reduced, and the matching efficiency is improved.
Optionally, generating a matching result according to the vehicle region corresponding to each vehicle and the license plate region corresponding to each license plate includes:
acquiring the position information of a vehicle region corresponding to each vehicle and the position information of a license plate region corresponding to each license plate;
and generating a matching result based on the position information of each vehicle region and the position information of each license plate region.
In this embodiment, after determining the vehicle region corresponding to each vehicle and the license plate region corresponding to each license plate, the location information of the vehicle region corresponding to each vehicle and the location information of the license plate region corresponding to each license plate may be obtained. Alternatively, the above-mentioned position information may be coordinate information in the image.
Further, based on the position information of each vehicle region and the position information of each license plate region, a matching relationship between each vehicle and each license plate is determined, and a matching result is generated.
For example, a coordinate range of a vehicle region on a target image and a coordinate range of a license plate region on the target image are acquired. If the coordinate range of a license plate region is included between the coordinate ranges of a certain vehicle region, a matching relationship between the license plate corresponding to the license plate region and the vehicle corresponding to the vehicle region is established.
In the embodiment, the position information of each vehicle region and the position information of each license plate region are obtained, and then the matching result between the vehicle and the license plate is determined based on the position information of each vehicle region and the position information of each license plate region; the matching result is determined based on the position relationship between the vehicle region and the license plate region, so that the accuracy of the matching result is improved.
Optionally, generating a matching result based on the location information of each vehicle region and the location information of each license plate region includes:
if the position information of the first vehicle area and the position information of the first vehicle license plate area represent that the first vehicle license plate area is a partial area of the first vehicle area, determining that the license plate corresponding to the first vehicle license plate area is matched with the vehicle corresponding to the first vehicle area;
the first vehicle region is any vehicle region in the plurality of vehicle regions, and the first license plate region is any license plate region in the at least one license plate region.
In this embodiment, after the position information of each vehicle region and the position information of each license plate region are obtained, if the position information of the first vehicle region and the position information of the first license plate region represent that the first license plate region is a partial region of the first vehicle region, and represent that the first license plate is a license plate of the first vehicle, it is determined that the license plate corresponding to the first license plate region is matched with the vehicle corresponding to the first vehicle region, where the first vehicle region is any vehicle region of the plurality of vehicle regions, and the first license plate region is any vehicle region of the at least one license plate region.
In other embodiments, if the position information of a certain vehicle region and the position information of the license plate region indicate that the license plate region is not a partial region of the vehicle region, and indicate that the license plate corresponding to the license plate region is not a license plate of a vehicle corresponding to the vehicle region, then it is determined that the license plate corresponding to the license plate region is not matched with the vehicle corresponding to the vehicle region.
In an embodiment, a license plate matching device is provided, where the license plate matching device corresponds to the license plate matching method in the above embodiment one by one. As shown in fig. 6, the license plate matching apparatus 600 includes an acquisition module 610, a determination module 620, and a generation module 630.
The functional modules are described in detail as follows:
an acquisition module 610 for acquiring a target image including a plurality of vehicles and at least one license plate;
the determining module 620 is configured to perform image recognition processing on the target image, and determine a vehicle region corresponding to each vehicle in the target image and a license plate region corresponding to each license plate;
the generating module 630 is configured to generate a matching result according to a vehicle region corresponding to each vehicle and a license plate region corresponding to each license plate; the matching result is used to characterize a matching relationship between the plurality of vehicles and the at least one license plate.
Optionally, the determining module 620 is specifically configured to:
performing image feature recognition on the target image, and determining a vehicle recognition frame corresponding to each vehicle feature and a license plate recognition frame corresponding to each license plate feature in the target image;
if license plate recognition frames in the overlapping area among the plurality of vehicle recognition frames exist, determining license plate areas corresponding to each license plate feature and vehicle areas corresponding to each vehicle feature.
Optionally, the determining module 620 is further specifically configured to:
image detection is carried out on each license plate feature and each vehicle feature in the target image, and a license plate image corresponding to each license plate feature and a vehicle image corresponding to each vehicle feature are obtained;
and determining the display area occupied by the vehicle image in the target image as a vehicle area, and determining the display area occupied by the license plate image in the target image as a license plate area.
Optionally, the determining module 620 is further specifically configured to:
marking a first pixel point in the target image, which constitutes the vehicle image, and marking a second pixel point in the target image, which constitutes the license plate image;
and clustering the first pixel points and the second pixel points to obtain a vehicle region generated based on the clustering result of the first pixel points and a license plate region generated based on the clustering result of the second pixel points.
Optionally, the determining module 620 is further specifically configured to:
if no license plate recognition frame exists in the overlapping area among the plurality of vehicle recognition frames, determining the area where the vehicle recognition frame is located as a vehicle area corresponding to the corresponding vehicle feature, and determining the area where the license plate recognition frame is located as a license plate area corresponding to the corresponding license plate feature.
Optionally, the generating module 630 is specifically configured to:
acquiring the position information of a vehicle region corresponding to each vehicle and the position information of a license plate region corresponding to each license plate;
and generating a matching result based on the position information of each vehicle region and the position information of each license plate region.
Optionally, the generating module 630 is further specifically configured to:
if the position information of the first vehicle area and the position information of the first vehicle license plate area represent that the first vehicle license plate area is a partial area of the first vehicle area, determining that the license plate corresponding to the first vehicle license plate area is matched with the vehicle corresponding to the first vehicle area;
the first vehicle region is any vehicle region in the plurality of vehicle regions, and the first license plate region is any license plate region in the at least one license plate region.
For specific limitations of the license plate matching device, reference may be made to the above limitations of the license plate matching method, and no further description is given here. All or part of each module in the license plate matching device can be realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a readable storage medium, an internal memory. The readable storage medium stores an operating system, computer readable instructions, and a database. The internal memory provides an environment for the execution of an operating system and computer-readable instructions in a readable storage medium. The database of the computer device is used for storing data related to the license plate matching method. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer readable instructions when executed by the processor implement a license plate matching method. The readable storage medium provided by the present embodiment includes a nonvolatile readable storage medium and a volatile readable storage medium.
In one embodiment, a computer device is provided, which may be a terminal device, and the internal structure thereof may be as shown in fig. 7. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a readable storage medium. The readable storage medium stores computer readable instructions. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer readable instructions when executed by the processor implement a license plate matching method. The readable storage medium provided by the present embodiment includes a nonvolatile readable storage medium and a volatile readable storage medium.
In one embodiment, a computer device is provided that includes a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, which when executed by the processor implement the steps of the license plate matching method as described above.
In one embodiment, a readable storage medium is provided, the readable storage medium storing computer readable instructions that when executed by a processor implement the license plate matching method steps as described above. Those skilled in the art will appreciate that implementing all or part of the above described embodiment methods may be accomplished by instructing the associated hardware by computer readable instructions, which may be stored on a non-volatile readable storage medium or a volatile readable storage medium, which when executed may comprise the above described embodiment methods. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.

Claims (10)

1. A license plate matching method, the method comprising:
acquiring a target image comprising a plurality of vehicles and at least one license plate;
performing image recognition processing on the target image, and determining a vehicle region corresponding to each vehicle in the target image and a license plate region corresponding to each license plate;
generating a matching result according to the vehicle region corresponding to each vehicle and the license plate region corresponding to each license plate; the matching result is used for representing the matching relation between the vehicles and the at least one license plate.
2. The method of claim 1, wherein the performing image processing on the target image to determine a vehicle region corresponding to each vehicle in the target image, and a license plate region corresponding to each license plate, comprises:
performing image feature recognition on the target image, and determining a vehicle recognition frame corresponding to each vehicle feature and a license plate recognition frame corresponding to each license plate feature in the target image;
if license plate recognition frames in the overlapping area among the plurality of vehicle recognition frames exist, determining license plate areas corresponding to each license plate feature and vehicle areas corresponding to each vehicle feature.
3. The method of claim 2, wherein the determining the license plate region corresponding to each license plate feature and the vehicle region corresponding to each vehicle feature comprises:
image detection is carried out on each license plate feature and each vehicle feature in the target image, and a license plate image corresponding to each license plate feature and a vehicle image corresponding to each vehicle feature are obtained;
and determining a display area occupied by the vehicle image in the target image as the vehicle area, and determining a display area occupied by the license plate image in the target image as the license plate area.
4. The method of claim 3, wherein the determining the display area occupied by the vehicle image in the target image as the vehicle area and the display area occupied by the license plate image in the target image as the license plate area comprises:
marking a first pixel point in the target image, which constitutes the vehicle image, and marking a second pixel point in the target image, which constitutes the license plate image;
and clustering the first pixel points and the second pixel points to obtain a vehicle region generated based on the clustering result of the first pixel points and a license plate region generated based on the clustering result of the second pixel points.
5. The method according to claim 2, wherein after performing image feature recognition on the target image and determining a vehicle recognition frame corresponding to each vehicle feature and a license plate recognition frame corresponding to each license plate feature in the target image, the method further comprises:
if no license plate recognition frame exists in the overlapping area among the plurality of vehicle recognition frames, determining the area where the vehicle recognition frame is located as a vehicle area corresponding to the corresponding vehicle feature, and determining the area where the license plate recognition frame is located as a license plate area corresponding to the corresponding license plate feature.
6. The method of claim 1, wherein the generating a matching result according to the vehicle region corresponding to each vehicle and the license plate region corresponding to each license plate comprises:
acquiring the position information of a vehicle area corresponding to each vehicle and the position information of a license plate area corresponding to each license plate;
and generating a matching result based on the position information of each vehicle region and the position information of each license plate region.
7. The method of claim 6, wherein generating a matching result based on the location information of each vehicle region and the location information of each license plate region comprises:
if the position information of the first vehicle area and the position information of the first vehicle plate area represent that the first vehicle plate area is a partial area of the first vehicle area, determining that a license plate corresponding to the first vehicle plate area is matched with a vehicle corresponding to the first vehicle area;
the first vehicle region is any vehicle region of a plurality of vehicle regions, and the first license plate region is any license plate region of at least one license plate region.
8. A license plate matching device, comprising:
the acquisition module is used for acquiring a target image comprising a plurality of vehicles and at least one license plate;
the determining module is used for carrying out image recognition processing on the target image and determining a vehicle area corresponding to each vehicle in the target image and a license plate area corresponding to each license plate;
the generation module is used for generating a matching result according to the vehicle region corresponding to each vehicle and the license plate region corresponding to each license plate; the matching result is used for representing the matching relation between the vehicles and the at least one license plate.
9. A computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the license plate matching method of any one of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the license plate matching method of any of claims 1 to 7.
CN202311469574.9A 2023-11-02 2023-11-02 License plate recognition method, license plate recognition device, computer equipment and storage medium Pending CN117437646A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311469574.9A CN117437646A (en) 2023-11-02 2023-11-02 License plate recognition method, license plate recognition device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311469574.9A CN117437646A (en) 2023-11-02 2023-11-02 License plate recognition method, license plate recognition device, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN117437646A true CN117437646A (en) 2024-01-23

Family

ID=89554993

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311469574.9A Pending CN117437646A (en) 2023-11-02 2023-11-02 License plate recognition method, license plate recognition device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117437646A (en)

Similar Documents

Publication Publication Date Title
US11609968B2 (en) Image recognition method, apparatus, electronic device and storage medium
CN109886077B (en) Image recognition method and device, computer equipment and storage medium
US10410315B2 (en) Method and apparatus for generating image information
WO2020098422A1 (en) Encoded pattern processing method and device , storage medium and electronic device
CN110378230B (en) Missing face recognition method, device, computer equipment and storage medium
CN110517186B (en) Method, device, storage medium and computer equipment for eliminating invoice seal
CN111191568A (en) Method, device, equipment and medium for identifying copied image
CN111968134B (en) Target segmentation method, device, computer readable storage medium and computer equipment
CN111259915A (en) Method, device, equipment and medium for recognizing copied image
CN110659638B (en) License plate recognition method and device, computer equipment and storage medium
CN111860582B (en) Image classification model construction method and device, computer equipment and storage medium
CN111291741A (en) Receipt identification method and device, computer equipment and storage medium
CN113298187B (en) Image processing method and device and computer readable storage medium
CN112241646A (en) Lane line recognition method and device, computer equipment and storage medium
CN111797642B (en) Bar code identification method and terminal
CN111680716B (en) Identification comparison method, device, computer equipment and storage medium
CN109784379B (en) Updating method and device of textile picture feature library
CN117437646A (en) License plate recognition method, license plate recognition device, computer equipment and storage medium
CN112579810A (en) Printed circuit board classification method and device, computer equipment and storage medium
CN109493280B (en) Image processing method, device, terminal and storage medium
CN110909733A (en) Template positioning method and device based on OCR picture recognition and computer equipment
CN113344961B (en) Image background segmentation method, device, computing equipment and storage medium
WO2021164329A1 (en) Image processing method and apparatus, and communication device and readable storage medium
CN111401477B (en) Image processing method, apparatus, electronic device, and computer-readable storage medium
CN112733565A (en) Two-dimensional code coarse positioning method, equipment 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