CN108701234A - Licence plate recognition method and cloud system - Google Patents
Licence plate recognition method and cloud system Download PDFInfo
- Publication number
- CN108701234A CN108701234A CN201880001017.5A CN201880001017A CN108701234A CN 108701234 A CN108701234 A CN 108701234A CN 201880001017 A CN201880001017 A CN 201880001017A CN 108701234 A CN108701234 A CN 108701234A
- Authority
- CN
- China
- Prior art keywords
- image
- license plate
- information
- plate image
- car
- 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
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
- G06V30/14—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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/243—Aligning, centring, orientation detection or correction of the image by compensating for image skew or non-uniform image deformations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Character Input (AREA)
- Image Analysis (AREA)
Abstract
This application provides licence plate recognition method and cloud system, the method includes:The image information got is detected, license plate image and its boundary information are obtained;Processing is corrected to the license plate image according to the boundary information, the license plate image after being corrected;Multiple character pictures in license plate image after extraction correction, and the multiple character picture is identified using multiple preset identification models, obtain the recognition result of car plate.Compared to traditional Car license recognition, the application meets the needs of being accurately identified to car plate under generic scenario, and is not limited to the special scenes such as bayonet, has stronger robustness.
Description
Technical field
This application involves depth learning technology fields, more particularly to licence plate recognition method and cloud system.
Background technology
With the explosive growth of vehicle fleet size, the management difficulty of vehicle is constantly increased, especially in vehicle peccancy
In monitoring and during fake-licensed car is investigated, the license plate number as vehicle identification characterization is the key message for needing to extract.Cause
This can effectively reduce the workload during vehicle management by the license board information of Computer Automatic Extraction vehicle, and liberation can
The human resources of sight, and Car license recognition includes mainly License Plate, character extracts and three steps of character recognition, it is specific as follows:
Traditional License Plate relies primarily on a certain specific feature, and searching in the picture may be the candidate of car plate
Frame is made whether it is that two classification of car plate judge, but answering due to vehicle local environment by grader to all candidate frames
It is miscellaneous changeable, effective position, therefore tradition can not be carried out to car plate under generic scenario using a certain or a variety of specific features
Car license recognition mainly for special scenes such as bayonets, greatly affected the popularization of Car license recognition in practical applications.
Traditional character extraction is broadly divided into connection domain method and sciagraphy, and connection domain method is to carry out two-value to the car plate of positioning
Change is handled, by realizing the segmentation to character to the analysis of connected domain, to extract the binary image of character;Sciagraphy is
The segmentation and extraction to character are realized according to the distribution situation of the Gray scale projection curve figure medium wave peak trough of car plate.In camera shooting head portrait
Element is relatively low or in the case that picture noise is excessive, the extraction of traditional character there are the problem of have:For being connected to domain method, noise causes
The error of binary conversion treatment is larger, is affected so as to cause to the character feature extracted;For sciagraphy, influence of noise wave
The distribution of spike paddy so that with respect to unobvious or there is extra wave crest and trough in wave crest and trough in curve graph, to
It is affected to the correct segmentation of character.As it can be seen that traditional character is extracted to the more demanding of hardware device, to Car license recognition
Application hinders larger.
Traditional character recognition is broadly divided into the recognition methods based on template matches and feature based grader, is based on template
Matched recognition methods is by building template library by the template matches in character to be identified and template library, realizing the knowledge to character
Not;The recognition methods of feature based grader is a certain feature by extracting character, is realized to word using feature classifiers
The identification of symbol.Two kinds of recognition methods there are the problem of have:Based on the recognition methods of template matches to the more demanding of environment, such as vehicle
The damage of board or illumination variation can all influence character to be identified and the matching result of template;The identification of feature based grader
Method needs to extract specific feature for specific scene, hinders its popularization under generic scenario larger.
As deep learning is in the continuous popularization of each technical field, start gradually to realize to vehicle using convolutional neural networks
The identification of board, and based on the smaller feature of character in license plate image, can not be compared with using the convolutional neural networks for having basic function
Good extraction character feature cannot achieve effective identification to character, and the character class of domestic car plate is more, causes traditional
The lasting popularization of Car license recognition at home is restricted.
Invention content
The embodiment of the present application proposes licence plate recognition method and cloud system, to solve existing Car license recognition mainly for bayonet
Etc. single scene, and to the more demanding of hardware device, lead to the technical problem that practicability is poor under generic scenario.
In one aspect, the embodiment of the present application provides a kind of licence plate recognition method, including:
The image information got is detected, license plate image and its boundary information are obtained;
Processing is corrected to the license plate image according to the boundary information, the license plate image after being corrected;
Multiple character pictures in license plate image after extraction correction, and using multiple preset identification models to described more
A character picture is identified, and obtains the recognition result of car plate.
On the other hand, the embodiment of the present application provides a kind of Car license recognition cloud system, including:
Detection module obtains license plate image and its boundary information for being detected to the image information got;
Correction module, for being corrected processing to the license plate image according to the boundary information, after being corrected
License plate image;
Identification module for extracting multiple character pictures in the license plate image after correcting, and utilizes multiple preset knowledges
The multiple character picture is identified in other model, obtains the recognition result of car plate.
On the other hand, the embodiment of the present application provides a kind of electronic equipment, and the electronic equipment includes:
Transceiver, memory, one or more processors;And
One or more modules, one or more of modules are stored in the memory, and are configured to by institute
One or more processors execution is stated, one or more of modules include the finger for executing each step in the above method
It enables.
On the other hand, the embodiment of the present application provides a kind of computer program production being used in combination with electronic equipment
Product, the computer program product include computer-readable storage medium and are embedded in computer program mechanism therein, institute
It includes the instruction for executing each step in the above method to state computer program mechanism.
It has the beneficial effect that:
In the present embodiment, by being detected to the image information got, license plate image and its boundary information, root are obtained
Processing is corrected to the license plate image according to the boundary information, the license plate image after being corrected, the vehicle after extraction correction
Multiple character pictures in board image, and the multiple character picture is identified using multiple preset identification models, it obtains
To the recognition result of car plate.Compared to traditional Car license recognition, the application meets the need accurately identified to car plate under generic scenario
It asks, and is not limited to the special scenes such as bayonet, there is stronger robustness.
Description of the drawings
The specific embodiment of the application is described below with reference to accompanying drawings, wherein:
Fig. 1 is the method schematic of Car license recognition in the embodiment of the present application one;
Fig. 2 is the car plate angle schematic diagram of Car license recognition in the embodiment of the present application one;
Fig. 3 is the cloud system structure chart of Car license recognition in the embodiment of the present application two;
Fig. 4 is the structural schematic diagram of electronic equipment in the embodiment of the present application three.
Specific implementation mode
Below by way of specific example, the essence for embodiment technical solution that the present invention is furture elucidated.
In order to which the technical solution and advantage that make the application are more clearly understood, below in conjunction with attached drawing to the exemplary of the application
Embodiment is described in more detail, it is clear that and described embodiment is only a part of the embodiment of the application, rather than
The exhaustion of all embodiments.And in the absence of conflict, the feature in the embodiment and embodiment in this explanation can be mutual
It is combined.
Inventor notices during invention:
License Plate, character extraction and three steps of character recognition that traditional Car license recognition includes exist certain
Drawback, it is complicated and changeable due to vehicle local environment for License Plate, it can not be using a certain or a variety of specific features
Effective position is carried out to car plate under generic scenario;Character is extracted, in the feelings that camera pixel is relatively low or picture noise is excessive
Under condition, cause to be affected to the character feature extracted;For character recognition, to the more demanding of vehicle local environment, or
Person needs to extract specific feature for specific scene, therefore, hinders its popularization under generic scenario larger.
Against the above deficiency/and it is based on this, the embodiment of the present application is proposed according to the image got, utilizes Multiple detection skill
Art obtains license plate image and its boundary information, is corrected processing to license plate image according to boundary information, and extract correction process
Multiple character pictures in license plate image afterwards, and using trained multiple identification models to multiple character pictures of extraction
It is identified, exports the recognition result of car plate, high inclination-angle car plate is accurately identified to realize, and under different scenes
The robustness of Car license recognition is promoted, while meeting the needs of being accurately identified to car plate under generic scenario.
For the ease of the implementation of the application, following Examples illustrates.
Embodiment 1
Fig. 1 shows the method schematic of Car license recognition in the embodiment of the present application one, as shown in Figure 1, this method includes:
Step 101:The image information got is detected, license plate image and its boundary information are obtained.
Step 102:Processing is corrected to the license plate image according to the boundary information, the car plate figure after being corrected
Picture.
Step 103:Multiple character pictures in license plate image after extraction correction, and utilize multiple preset identification models
The multiple character picture is identified, the recognition result of car plate is obtained.
In a step 101, rough license plate image is obtained using the rough detection based on deep learning, and to rough car plate
Marginal information and colouring information in image carry out car plate examining survey, obtain license plate image and its boundary information, i.e., by multiple
Detection technique ensures the accurate positionin to high inclination-angle car plate boundary, and the car plate detection based on characteristic informations such as edge, colors
So that the robustness of car plate detection of the application when for different scenes is stronger, to be suitable for generic scenario without limitation
In special scenes such as bayonets.
In a step 102, it is different from the prior art, when carrying out correction for direction to license plate image, generally use is directly revolved
To car plate into line tilt correction, the application handles to obtain rule using affine transformation the mode turned for inclination, deflection car plate
Car plate rectangular image, to extract the accurate of multiple character pictures in the license plate image after correction in effective lifting step 103
Degree.
In the present embodiment, the image information got is detected, obtains license plate image and its boundary information, wrapped
It includes:
Using preset neural network model, license plate image to be determined is obtained according to the image information got;
According in the license plate image to be determined marginal information and colouring information obtain license plate image and its boundary information.
In implementation, preset neural network model is the advance trained detection model based on deep learning, i.e., to adopting
The image information collected carries out correct classification annotation, by forward direction transmission and reverse conduction, to the depth of the initialization of structure
Network parameter in learning network is trained, and obtains the trained detection model based on deep learning.
In implementation, using the detection model based on deep learning, car plate rough detection is carried out to the image information got, is obtained
To the boundary rectangle information (e.g., the boundary coordinate of boundary rectangle) of car plate, rough license plate image is oriented, rough vehicle is extracted
The marginal information and colouring information of board image, using Sobel operators and method for color matching to the marginal information and face extracted
Color information carries out car plate examining survey, orients accurate license plate image and its boundary information.
In the present embodiment, processing is corrected to the license plate image according to the boundary information, after being corrected
License plate image, including:
Inclination angle and the angle of deviation of car plate are calculated according to the boundary information;
According to the inclination angle of the car plate and angle of deviation, affine transformation is carried out to the license plate image, after being corrected
License plate image.
In implementation, Fig. 2 shows the car plate angle schematic diagrames of Car license recognition in the embodiment of the present application one, as shown in Fig. 2, vehicle
The boundary information of board image includes that the shape and boundary coordinate of car plate calculate car plate according to the shape and boundary coordinate of car plate
Tiltangleθ and angle of deviation, and according to tiltangleθ and angle of deviation, affine transformation is carried out to license plate image, after obtaining correction
License plate image.
In the present embodiment, multiple character pictures in the license plate image after extraction correction, including:
To the license plate image progress binaryzation and Morphological scale-space after correction, multiple words in the license plate image after being corrected
The location information of symbol;And
Gray proces are carried out to the license plate image after correction, obtain license plate grey level image;
According to the location information of the multiple character, the license plate grey level image is extracted into line character, after obtaining correction
License plate image in multiple character pictures.
In implementation, carries out binaryzation successively to the license plate image after correction, closed operation, contouring, takes minimum enclosed rectangle
Processing, calculate correction after license plate image in connected domain, and according to connected domain to the character in the license plate image after correction into
Row segmentation, obtains character position.Meanwhile gray processing is carried out to the license plate image after correction, obtain license plate grey level image, and according to
Multiple character grey images in obtained character position extraction license plate grey level image.
In the present embodiment, multiple preset identification models include the identification model of word for identification, and for knowing
The identification model of other English alphabet and number.
In implementation, preset identification model is the advance trained identification model based on deep learning, i.e., to collecting
Character picture carry out correct classification annotation, by forward direction transmission and reverse conduction, to the deep learning of the initialization of structure
Network parameter in network is trained, and obtains the first identification mould of the trained word for identification based on deep learning
Type, for identification the second identification model of English alphabet and number, and the third of word, English alphabet and number for identification
Identification model reduces the classification that single character classifier needs classification annotation that is, by the multiple character classifiers of training, to be promoted
The accuracy of Car license recognition.Wherein, the quantity of identification model can be set according to the needs of actual conditions, this implementation is not to identifying mould
The quantity of type is defined.
In implementation, the multiple character grey images extracted are identified using multiple identification models, specifically, by word
Accord with gray level image A1It imported into the first identification model, output obtains corresponding recognition result Z1;By character grey image A2-A6
It is directed respectively into the second identification model, output obtains corresponding recognition result Z2-Z6;By character grey image A7It imported into
In three identification models, output obtains corresponding recognition result Z7, to obtain the recognition result of car plate.
The application is described in detail the embodiment of the present application 1, detailed process is as follows by taking concrete scene as an example:
Step 201:Deep learning network is obtained getting on the bus for line into training under line using the data set pre-established
The deep learning model M of board detection1, and on line character recognition deep learning model M2, M3, M4。
Step 202:Image information is obtained, deep learning model M is utilized1Rough detection is carried out to image information, is obtained rough
License plate image, extract the marginal information and colouring information of rough license plate image, utilize Sobel operators and method for color matching
Car plate examining survey is carried out to the marginal information and colouring information extracted, orients accurate license plate image and its boundary information.
Step 203:According to the boundary information of license plate image, using affine transformation to the inclination detected or the car plate of deflection
Image is corrected processing, by carrying out binaryzation and Morphological scale-space to the license plate image after correction process, obtains at correction
The location information of 7 characters in license plate image after reason, meanwhile, gray processing is carried out to the license plate image after correction, obtains car plate
Gray level image, and according to 7 character grey images in obtained character position extraction license plate grey level image.
Step 204:Utilize advance trained deep learning model M2, M3, M4, 7 character greys to extracting respectively
Image is identified, and exports the recognition result of car plate, and go to step 202 continue to next image information carry out car plate knowledge
Not.
Embodiment 2
Based on same inventive concept, a kind of cloud system of Car license recognition is additionally provided in the embodiment of the present application, due to these
The principle that equipment solves the problems, such as is similar to a kind of method of Car license recognition, therefore the implementation of these equipment may refer to the reality of method
It applies, overlaps will not be repeated.
Fig. 3 shows the cloud system structure chart of Car license recognition in the embodiment of the present application two, as shown in figure 3, Car license recognition
Cloud system 300 may include:Detection module 301, correction module 302 and identification module 303.
Detection module 301 obtains license plate image and its boundary information for being detected to the image information got.
Correction module 302, for being corrected processing to the license plate image according to the boundary information, after obtaining correction
License plate image.
Identification module 303 for extracting multiple character pictures in the license plate image after correcting, and utilizes multiple preset
The multiple character picture is identified in identification model, obtains the recognition result of car plate.
In the present embodiment, detection module 301 includes:
Using preset neural network model, license plate image to be determined is obtained according to the image information got;
According in the license plate image to be determined marginal information and colouring information obtain license plate image and its boundary information.
In the present embodiment, correction module 302 includes:
Inclination angle and the angle of deviation of car plate are calculated according to the boundary information;
According to the inclination angle of the car plate and angle of deviation, affine transformation is carried out to the license plate image, after being corrected
License plate image.
In the present embodiment, multiple character pictures in the license plate image after extraction correction, including:
To the license plate image progress binaryzation and Morphological scale-space after correction, multiple words in the license plate image after being corrected
The location information of symbol;And
Gray proces are carried out to the license plate image after correction, obtain license plate grey level image;
According to the location information of the multiple character, the license plate grey level image is extracted into line character, after obtaining correction
License plate image in multiple character pictures.
In the present embodiment, multiple preset identification models include the identification model of word for identification, and for knowing
The identification model of other English alphabet and number.
Embodiment 3
Based on same inventive concept, a kind of electronic equipment is additionally provided in the embodiment of the present application, due to its principle and one kind
The method of Car license recognition is similar, therefore its implementation may refer to the implementation of method, and overlaps will not be repeated.
Fig. 4 shows the structural schematic diagram of electronic equipment in the embodiment of the present application three, as shown in figure 4, the electronic equipment
Including:Transceiver 401, memory 402, one or more processors 403;And one or more modules, it is one or
Multiple modules are stored in the memory, and are configured to be executed by one or more of processors, it is one or
Multiple modules include the instruction for executing each step in any above method.
Embodiment 4
Based on same inventive concept, the embodiment of the present application also provides a kind of computer journeys being used in combination with electronic equipment
Sequence product implements the implementation that may refer to method since its principle is similar to a kind of method of Car license recognition, repetition
Place repeats no more.The computer program product includes computer-readable storage medium and is embedded in computer program therein
Mechanism, the computer program mechanism include the instruction for executing each step in any above method.
For convenience of description, each section of apparatus described above is divided into various modules with function and describes respectively.Certainly, exist
Implement each module or the function of unit can be realized in same or multiple softwares or hardware when the application.
It should be understood by those skilled in the art that, embodiments herein can be provided as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, the application can be used in one or more wherein include computer usable program code computer
The computer program production implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The application is with reference to method, the flow of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that can be realized by computer program instructions every first-class in flowchart and/or the block diagram
The combination of flow and/or box in journey and/or box and flowchart and/or the block diagram.These computer programs can be provided
Instruct the processor of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine so that the instruction executed by computer or the processor of other programmable data processing devices is generated for real
The device for the function of being specified in present one flow of flow chart or one box of multiple flows and/or block diagram or multiple boxes.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that instruction generation stored in the computer readable memory includes referring to
Enable the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device so that count
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, in computer or
The instruction executed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although the preferred embodiment of the application has been described, created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the application range.
Claims (12)
1. a kind of licence plate recognition method, which is characterized in that including:
The image information got is detected, license plate image and its boundary information are obtained;
Processing is corrected to the license plate image according to the boundary information, the license plate image after being corrected;
Multiple character pictures in license plate image after extraction correction, and using multiple preset identification models to the multiple word
Symbol image is identified, and obtains the recognition result of car plate.
2. the method as described in claim 1, which is characterized in that the described pair of image information got is detected, and obtains vehicle
Board image and its boundary information, including:
Using preset neural network model, license plate image to be determined is obtained according to the image information got;
According in the license plate image to be determined marginal information and colouring information obtain license plate image and its boundary information.
3. the method as described in claim 1, which is characterized in that described to be carried out to the license plate image according to the boundary information
Correction process, the license plate image after being corrected, including:
Inclination angle and the angle of deviation of car plate are calculated according to the boundary information;
According to the inclination angle of the car plate and angle of deviation, affine transformation, the car plate after being corrected are carried out to the license plate image
Image.
4. the method as described in claim 1 or 3, which is characterized in that multiple words in license plate image after the extraction correction
Image is accorded with, including:
To the license plate image progress binaryzation and Morphological scale-space after correction, multiple characters in the license plate image after being corrected
Location information;And
Gray proces are carried out to the license plate image after correction, obtain license plate grey level image;
According to the location information of the multiple character, the license plate grey level image is extracted into line character, the vehicle after being corrected
Multiple character pictures in board image.
5. the method as described in claim 1, which is characterized in that the multiple preset identification model includes word for identification
Identification model, and for identification English alphabet and number identification model.
6. a kind of Car license recognition cloud system, which is characterized in that including:
Detection module obtains license plate image and its boundary information for being detected to the image information got;
Correction module, for being corrected processing to the license plate image according to the boundary information, the car plate after being corrected
Image;
Identification module for extracting multiple character pictures in the license plate image after correcting, and utilizes multiple preset identification moulds
The multiple character picture is identified in type, obtains the recognition result of car plate.
7. cloud system as claimed in claim 6, which is characterized in that the detection module includes:
Using preset neural network model, license plate image to be determined is obtained according to the image information got;
According in the license plate image to be determined marginal information and colouring information obtain license plate image and its boundary information.
8. cloud system as claimed in claim 6, which is characterized in that the correction module includes:
Inclination angle and the angle of deviation of car plate are calculated according to the boundary information;
According to the inclination angle of the car plate and angle of deviation, affine transformation, the car plate after being corrected are carried out to the license plate image
Image.
9. the cloud system as described in claim 6 or 8, which is characterized in that multiple in the license plate image after the extraction correction
Character picture, including:
To the license plate image progress binaryzation and Morphological scale-space after correction, multiple characters in the license plate image after being corrected
Location information;And
Gray proces are carried out to the license plate image after correction, obtain license plate grey level image;
According to the location information of the multiple character, the license plate grey level image is extracted into line character, the vehicle after being corrected
Multiple character pictures in board image.
10. cloud system as claimed in claim 6, which is characterized in that the multiple preset identification model includes for identification
The identification model of word, and the identification model of English alphabet and number for identification.
11. a kind of electronic equipment, which is characterized in that the electronic equipment includes:
Transceiver, memory, one or more processors;And
One or more modules, one or more of modules are stored in the memory, and are configured to by described one
A or multiple processors execute, and one or more of modules include being required in 1-5 in any the method for perform claim
The instruction of each step.
12. a kind of computer program product being used in combination with electronic equipment, the computer program product includes that computer can
The storage medium of reading and it is embedded in computer program mechanism therein, the computer program mechanism includes being wanted for perform claim
Ask the instruction of each step in any the method in 1-5.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2018/078044 WO2019169532A1 (en) | 2018-03-05 | 2018-03-05 | License plate recognition method and cloud system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108701234A true CN108701234A (en) | 2018-10-23 |
Family
ID=63841511
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201880001017.5A Pending CN108701234A (en) | 2018-03-05 | 2018-03-05 | Licence plate recognition method and cloud system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108701234A (en) |
| WO (1) | WO2019169532A1 (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110287793A (en) * | 2019-05-23 | 2019-09-27 | 北京爱诺斯科技有限公司 | A kind of image analysis method of recognizable eyesight prescription |
| CN110427937A (en) * | 2019-07-18 | 2019-11-08 | 浙江大学 | A kind of correction of inclination license plate and random length licence plate recognition method based on deep learning |
| CN111126383A (en) * | 2019-12-06 | 2020-05-08 | 广州烽火众智数字技术有限公司 | License plate detection method, system, device and storage medium |
| CN111339846A (en) * | 2020-02-12 | 2020-06-26 | 深圳市商汤科技有限公司 | Image recognition method and device, electronic equipment and storage medium |
| CN111368816A (en) * | 2020-02-27 | 2020-07-03 | 深圳中兴网信科技有限公司 | License plate recognition method, system, device and computer readable storage medium |
| CN111476109A (en) * | 2020-03-18 | 2020-07-31 | 深圳中兴网信科技有限公司 | Bill processing method, bill processing apparatus, and computer-readable storage medium |
| CN111652208A (en) * | 2020-04-17 | 2020-09-11 | 北京三快在线科技有限公司 | User interface component identification method and device, electronic equipment and storage medium |
| CN112052845A (en) * | 2020-10-14 | 2020-12-08 | 腾讯科技（深圳）有限公司 | Image recognition method, device, equipment and storage medium |
| CN112446375A (en) * | 2019-09-03 | 2021-03-05 | 上海高德威智能交通系统有限公司 | License plate recognition method, device, equipment and storage medium |
| CN112651417A (en) * | 2019-10-12 | 2021-04-13 | 杭州海康威视数字技术股份有限公司 | License plate recognition method, device, equipment and storage medium |
| CN113688658A (en) * | 2020-05-18 | 2021-11-23 | 华为技术有限公司 | Object identification method, device, equipment and medium |
| CN113688658B (en) * | 2020-05-18 | 2024-06-28 | 华为云计算技术有限公司 | Object identification method, device, equipment and medium |
Families Citing this family (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112686246B (en) * | 2019-10-18 | 2024-01-02 | 深圳市优必选科技股份有限公司 | License plate character segmentation method and device, storage medium and terminal equipment |
| CN110969160B (en) * | 2019-11-21 | 2023-04-14 | 合肥工业大学 | License plate image correction and recognition method and system based on deep learning |
| CN118097577A (en) * | 2020-02-10 | 2024-05-28 | 西安艾润物联网技术服务有限责任公司 | License plate correction method, ETC antenna device and computer readable storage medium |
| CN111340045B (en) * | 2020-02-12 | 2023-09-01 | 浙江大华技术股份有限公司 | License plate number recognition method, device and storage medium |
| CN111860512B (en) * | 2020-02-25 | 2023-12-05 | 北京嘀嘀无限科技发展有限公司 | Vehicle identification method, device, electronic equipment and computer readable storage medium |
| CN111476234B (en) * | 2020-03-17 | 2024-05-24 | 平安科技（深圳）有限公司 | License plate character shielding recognition method and device, storage medium and intelligent equipment |
| CN111382722B (en) * | 2020-03-23 | 2023-09-05 | 浙江大华技术股份有限公司 | License plate image optimization method, image processing device and device with storage function |
| CN111507342B (en) * | 2020-04-21 | 2023-10-10 | 浙江大华技术股份有限公司 | Image processing method, device, system and storage medium |
| CN113762233A (en) * | 2020-06-05 | 2021-12-07 | 北京都是科技有限公司 | License plate detection method, system and device and thermal infrared image processor |
| CN112001383A (en) * | 2020-08-10 | 2020-11-27 | 长沙奇巧匠人软件有限公司 | Water meter code intelligent identification method based on convolutional neural network technology |
| CN112016556B (en) * | 2020-08-21 | 2022-07-15 | 中国科学技术大学 | Multi-type license plate recognition method |
| CN112133101B (en) * | 2020-09-22 | 2021-11-26 | 杭州海康威视数字技术股份有限公司 | Method and device for enhancing license plate area, camera device, computing equipment and storage medium |
| CN112215222A (en) * | 2020-10-12 | 2021-01-12 | 上海眼控科技股份有限公司 | License plate recognition method, device, equipment and storage medium |
| CN112232237B (en) * | 2020-10-20 | 2024-03-12 | 城云科技（中国）有限公司 | Method, system, computer device and storage medium for monitoring vehicle flow |
| CN112883973A (en) * | 2021-03-17 | 2021-06-01 | 北京市商汤科技开发有限公司 | License plate recognition method and device, electronic equipment and computer storage medium |
| CN113326843B (en) * | 2021-06-17 | 2022-11-18 | 讯飞智元信息科技有限公司 | License plate recognition method and device, electronic equipment and readable storage medium |
| CN113688649A (en) * | 2021-08-16 | 2021-11-23 | 江苏博赛孚医疗科技有限公司 | Quick QR code positioning method |
| CN115661807B (en) * | 2022-12-28 | 2023-04-07 | 成都西物信安智能系统有限公司 | Method for acquiring license plate information |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006080568A1 (en) * | 2005-01-31 | 2006-08-03 | Nec Corporation | Character reader, character reading method, and character reading control program used for the character reader |
| CN105279512A (en) * | 2015-10-22 | 2016-01-27 | 东方网力科技股份有限公司 | Tilt vehicle license plate recognition method and device |
| CN106203418A (en) * | 2016-07-14 | 2016-12-07 | 北京精英智通科技股份有限公司 | A kind of method and device of car plate detection |
| CN107180230A (en) * | 2017-05-08 | 2017-09-19 | 上海理工大学 | General licence plate recognition method |
| CN107679531A (en) * | 2017-06-23 | 2018-02-09 | 平安科技（深圳）有限公司 | Licence plate recognition method, device, equipment and storage medium based on deep learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101102572B1 (en) * | 2009-01-15 | 2012-01-04 | 주식회사 비츠로씨앤씨 | Number Plate Extraction Method of a Car Image |
-
2018
- 2018-03-05 WO PCT/CN2018/078044 patent/WO2019169532A1/en active Application Filing
- 2018-03-05 CN CN201880001017.5A patent/CN108701234A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006080568A1 (en) * | 2005-01-31 | 2006-08-03 | Nec Corporation | Character reader, character reading method, and character reading control program used for the character reader |
| CN105279512A (en) * | 2015-10-22 | 2016-01-27 | 东方网力科技股份有限公司 | Tilt vehicle license plate recognition method and device |
| CN106203418A (en) * | 2016-07-14 | 2016-12-07 | 北京精英智通科技股份有限公司 | A kind of method and device of car plate detection |
| CN107180230A (en) * | 2017-05-08 | 2017-09-19 | 上海理工大学 | General licence plate recognition method |
| CN107679531A (en) * | 2017-06-23 | 2018-02-09 | 平安科技（深圳）有限公司 | Licence plate recognition method, device, equipment and storage medium based on deep learning |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110287793A (en) * | 2019-05-23 | 2019-09-27 | 北京爱诺斯科技有限公司 | A kind of image analysis method of recognizable eyesight prescription |
| CN110427937A (en) * | 2019-07-18 | 2019-11-08 | 浙江大学 | A kind of correction of inclination license plate and random length licence plate recognition method based on deep learning |
| CN110427937B (en) * | 2019-07-18 | 2022-03-22 | 浙江大学 | Inclined license plate correction and indefinite-length license plate identification method based on deep learning |
| CN112446375A (en) * | 2019-09-03 | 2021-03-05 | 上海高德威智能交通系统有限公司 | License plate recognition method, device, equipment and storage medium |
| CN112651417A (en) * | 2019-10-12 | 2021-04-13 | 杭州海康威视数字技术股份有限公司 | License plate recognition method, device, equipment and storage medium |
| CN111126383A (en) * | 2019-12-06 | 2020-05-08 | 广州烽火众智数字技术有限公司 | License plate detection method, system, device and storage medium |
| CN111339846A (en) * | 2020-02-12 | 2020-06-26 | 深圳市商汤科技有限公司 | Image recognition method and device, electronic equipment and storage medium |
| CN111339846B (en) * | 2020-02-12 | 2022-08-12 | 深圳市商汤科技有限公司 | Image recognition method and device, electronic equipment and storage medium |
| CN111368816A (en) * | 2020-02-27 | 2020-07-03 | 深圳中兴网信科技有限公司 | License plate recognition method, system, device and computer readable storage medium |
| CN111476109A (en) * | 2020-03-18 | 2020-07-31 | 深圳中兴网信科技有限公司 | Bill processing method, bill processing apparatus, and computer-readable storage medium |
| CN111652208A (en) * | 2020-04-17 | 2020-09-11 | 北京三快在线科技有限公司 | User interface component identification method and device, electronic equipment and storage medium |
| CN113688658A (en) * | 2020-05-18 | 2021-11-23 | 华为技术有限公司 | Object identification method, device, equipment and medium |
| CN113688658B (en) * | 2020-05-18 | 2024-06-28 | 华为云计算技术有限公司 | Object identification method, device, equipment and medium |
| CN112052845A (en) * | 2020-10-14 | 2020-12-08 | 腾讯科技（深圳）有限公司 | Image recognition method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019169532A1 (en) | 2019-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108701234A (en) | Licence plate recognition method and cloud system | |
| CN109145759B (en) | Vehicle attribute identification method, device, server and storage medium | |
| CN109583483B (en) | Target detection method and system based on convolutional neural network | |
| CN107679531A (en) | Licence plate recognition method, device, equipment and storage medium based on deep learning | |
| US10445602B2 (en) | Apparatus and method for recognizing traffic signs | |
| EP2339537B1 (en) | Method of determining reference features for use in an optical object initialization tracking process and object initialization tracking method | |
| CN109934847B (en) | Method and device for estimating posture of weak texture three-dimensional object | |
| CN109871845B (en) | Certificate image extraction method and terminal equipment | |
| WO2019171628A1 (en) | Image processing system and image processing method | |
| CN111709980A (en) | Multi-scale image registration method and device based on deep learning | |
| US10902264B2 (en) | Automatic generation of secondary class annotations | |
| CN109558844A (en) | The method and apparatus of self-defined template discrimination is promoted based on image normalization | |
| CN110827312A (en) | Learning method based on cooperative visual attention neural network | |
| CN111783541A (en) | Text recognition method and device | |
| CN107369086A (en) | A kind of identity card stamp system and method | |
| CN114494773A (en) | Part sorting and identifying system and method based on deep learning | |
| CN113313725B (en) | Bung hole identification method and system for energetic material medicine barrel | |
| CN110414522A (en) | A kind of character identifying method and device | |
| CN113724329A (en) | Object attitude estimation method, system and medium fusing plane and stereo information | |
| Abbas | Recovering homography from camera captured documents using convolutional neural networks | |
| JP2019191973A (en) | Learning image generation apparatus, learning image generation method, image recognition device, and image recognition method | |
| CN106056575B (en) | A kind of image matching method based on like physical property proposed algorithm | |
| CN112434581A (en) | Outdoor target color identification method and system, electronic device and storage medium | |
| Calefati et al. | Reading meter numbers in the wild | |
| CN113283423B (en) | Natural scene distortion text image correction method and system based on generation network |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181023 |
|
| RJ01 | Rejection of invention patent application after publication |