CN110490179A - Licence plate recognition method, device and storage medium - Google Patents
Licence plate recognition method, device and storage medium Download PDFInfo
- Publication number
- CN110490179A CN110490179A CN201810461160.4A CN201810461160A CN110490179A CN 110490179 A CN110490179 A CN 110490179A CN 201810461160 A CN201810461160 A CN 201810461160A CN 110490179 A CN110490179 A CN 110490179A
- Authority
- CN
- China
- Prior art keywords
- license plate
- characteristic sequence
- character
- area
- sequence
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Character Discrimination (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of licence plate recognition method, device and computer readable storage mediums, belong to field of intelligent transportation technology.This method comprises: including the license plate area of license plate in acquisition image, and using the characteristic information in convolutional neural networks CNN model extraction license plate area, characteristic information includes multiple characteristic sequences；The character in license plate area is identified based on multiple characteristic sequences；License plate number is determined based on character identification result.The embodiment of the present invention is by identifying the character in license plate area, and license plate number is determined according to character identification result, it does not need to identify license plate by being split license plate area to obtain multiple character zones, thus also there is no need to adjust Image Processing parameter according to special scenes, interference of the scene factor to Car license recognition is effectively prevented, to improve the versatility and accuracy of licence plate recognition method.
Description
Technical field
The present invention relates to field of intelligent transportation technology, in particular to a kind of licence plate recognition method, device and computer-readable
Storage medium.
Background technique
License plate is vehicle " identity card ", is the important logo information for being different from other vehicles.In current intelligent transportation
Monitoring device can be arranged in many scenes such as bayonet, parking lot or street in field, obtained in scene and wrapped by monitoring device
The image of license plate containing vehicle, and then the license plate in the image is identified.
Car license recognition can mainly be summarized as three steps, respectively license plate area detection, license plate area in the related technology
Segmentation and character recognition.When carrying out Car license recognition by above three step, due to being influenced by scene factor, such as
Weather, illumination, monitoring device inclination, license plate sloped etc., therefore, the accuracy of Character segmentation is difficult to ensure, so as to cause license plate
Identify that accuracy is lower.
Summary of the invention
The embodiment of the invention provides a kind of licence plate recognition method, device and computer readable storage mediums, can be used for
Solve the problems, such as that license plate identification accuracy is lower in the related technology.The technical solution is as follows:
In a first aspect, providing a kind of licence plate recognition method, which comprises
In acquisition image include the license plate area of license plate, and utilizes license plate described in convolutional neural networks CNN model extraction
Characteristic information in region, the characteristic information include multiple characteristic sequences；
The character in the license plate area is identified based on the multiple characteristic sequence；
License plate number is determined based on character identification result.
It is optionally, described that the character in the license plate area is identified based on the multiple characteristic sequence, comprising:
Each characteristic sequence in the multiple characteristic sequence is handled by attention Attention model, is obtained
The corresponding character of each characteristic sequence in the license plate area.
Optionally, it is described by attention Attention model to each characteristic sequence in the multiple characteristic sequence
It is handled, obtains the corresponding character of each characteristic sequence in the license plate area, comprising:
For any feature sequence A in the multiple characteristic sequence, the feature sequence is determined by Attention model
Arrange the weight of A and in addition to the characteristic sequence A remaining each characteristic sequence weight, the weight of the characteristic sequence A is greater than
The weight of remaining each characteristic sequence；
Based on the characteristic sequence A, the weight of the characteristic sequence A, remaining described each characteristic sequence and it is described remaining
The weight of each characteristic sequence determines the semantic information of the characteristic sequence A；
Identification is decoded to the semantic information of the characteristic sequence A, obtains the corresponding character of the characteristic sequence A.
Optionally, after the characteristic information using in license plate area described in convolutional neural networks CNN model extraction, also
Include:
License plate type belonging to the license plate is determined based on the multiple characteristic sequence；
It is correspondingly, described that license plate number is determined based on character identification result, comprising:
The license plate number of the license plate is determined based on the character identification result and the license plate type.
It is optionally, described that license plate type belonging to the license plate is determined based on the multiple characteristic sequence, comprising:
Based on the multiple characteristic sequence, determine that the license plate belongs to each default license plate type using the CNN model
Probability value；
The corresponding default license plate type of most probable value is determined as license plate type belonging to the license plate.
Optionally, the license plate number that the license plate is determined based on the character identification result and the license plate type,
Include:
Obtain the corresponding license plate number sample of the license plate type；
Whether belonged in the license plate number of the license plate type based on license plate type judgement includes subsegment and principal piece,
The subsegment and the principal piece refer both to continuous character string in license plate number, and the number of characters that the principal piece includes is greater than the subsegment packet
The number of characters contained, alternatively, the size in region shared by the character that the principal piece includes is greater than the character institute occupied area that the subsegment includes
The size in domain；
If belonging in the license plate number of the license plate type includes subsegment and principal piece, the character identification result is pressed
Subsegment and principal piece are divided according to the license plate number sample, and the character identification result after division is determined as to the license plate number of the license plate
Code.
Optionally, it is described license plate number is determined based on character identification result after, further includes:
Obtain the corresponding license plate color information of the license plate type and affiliated area information；
Export the license plate number, the license plate color information and the area information of the license plate.
Second aspect, provides a kind of license plate recognition device, and described device includes:
Obtain module, for obtain include in image license plate license plate area, and utilize convolutional neural networks CNN model
The characteristic information in the license plate area is extracted, the characteristic information includes multiple characteristic sequences；
Identification module, for being identified based on the multiple characteristic sequence to the character in the license plate area；
First determining module, for determining license plate number based on character identification result.
Optionally, the identification module is used for:
Each characteristic sequence in the multiple characteristic sequence is handled by attention Attention model, is obtained
The corresponding character of each characteristic sequence in the license plate area.
Optionally, the identification module is specifically used for:
For any feature sequence A in the multiple characteristic sequence, the feature sequence is determined by Attention model
Arrange the weight of A and in addition to the characteristic sequence A remaining each characteristic sequence weight, the weight of the characteristic sequence A is greater than
The weight of remaining each characteristic sequence；
Based on the characteristic sequence A, the weight of the characteristic sequence A, remaining described each characteristic sequence and it is described remaining
The weight of each characteristic sequence determines the semantic information of the characteristic sequence A；
Identification is decoded to the semantic information of the characteristic sequence A, obtains the corresponding character of the characteristic sequence A.
Optionally, described device further include:
Second determining module, for determining license plate type belonging to the license plate based on the multiple characteristic sequence；
Correspondingly, first determining module includes:
Submodule is determined, for determining the license plate number of the license plate based on the character identification result and the license plate type
Code.
Optionally, second determining module is specifically used for:
Based on the multiple characteristic sequence, determine that the license plate belongs to the general of each default license plate type using the CNN
Rate value；
The corresponding default license plate type of most probable value is determined as license plate type belonging to the license plate.
Optionally, the determining submodule is specifically used for:
Obtain the corresponding license plate number sample of the license plate type；
Whether belonged in the license plate number of the license plate type based on license plate type judgement includes subsegment and principal piece,
The subsegment and the principal piece refer both to continuous character string in license plate number, and the number of characters that the principal piece includes is greater than the subsegment packet
The number of characters contained, alternatively, the size in region shared by the character that the principal piece includes is greater than the character institute occupied area that the subsegment includes
The size in domain；
If belonging in the license plate number of the license plate type includes subsegment and principal piece, the character identification result is pressed
Subsegment and principal piece are divided according to the license plate number sample, and the character identification result after division is determined as to the license plate number of the license plate
Code.
Optionally, described device is also used to:
Obtain the corresponding license plate color information of the license plate type and affiliated area information；
Export the license plate number, the license plate color information and the area information of the license plate.
The third aspect, provides a kind of license plate recognition device, and described device includes:
Processor；
Memory for storage processor executable instruction；
Wherein, the processor is configured to executing any one method described in above-mentioned first aspect.
Fourth aspect provides a kind of computer readable storage medium, and computer program, institute are stored in the storage medium
State the method that any one described in above-mentioned first aspect is realized when computer program is executed by processor.
Technical solution provided in an embodiment of the present invention have the benefit that obtain image in include license plate license plate
Region, and using the characteristic information in CNN model extraction license plate area, characteristic information may include multiple characteristic sequences, be based on
Multiple characteristic sequences identify the character in license plate area, and determine license plate number based on character identification result.It that is to say,
In embodiments of the present invention, directly the character in license plate area can be identified, and vehicle is determined according to character identification result
Trade mark code, without identifying license plate by being split to license plate area to obtain multiple character zones, due to need not be again
License plate area segmentation is carried out therefore to avoid interference of the scene factor to Car license recognition, improve the accuracy of Car license recognition.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is a kind of system architecture diagram of licence plate recognition method provided in an embodiment of the present invention；
Fig. 2 is a kind of flow chart of licence plate recognition method provided in an embodiment of the present invention；
Fig. 3 A is a kind of flow chart of licence plate recognition method provided in an embodiment of the present invention；
Fig. 3 B is a kind of schematic diagram of Attention model provided in an embodiment of the present invention；
Fig. 4 is a kind of license plate recognition device structural schematic diagram provided in an embodiment of the present invention；
Fig. 5 is a kind of structural schematic diagram of terminal for Car license recognition provided in an embodiment of the present invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to embodiment party of the present invention
Formula is described in further detail.
Before carrying out detailed explanation to the embodiment of the present invention, first to the present embodiments relate to application scenarios
It is introduced.
Currently, license plate recognition technology has been widely used in intelligent transportation field.In practical applications, Ke Yitong
It crosses and monitoring device progress Image Acquisition is set in many scenes such as bayonet, parking lot and road, and to the license plate in image
It is identified to obtain license board information.Wherein, monitoring device usually requires to work under different complex scenes, therefore, passes through
The quality of monitoring device acquired image also will receive the influence of scene factor.For example, the prison in bayonet or road is arranged in
Control equipment will receive the influence of the factors such as weather, illumination, can be unintelligible so as to cause acquired image, for another example setting is each
Monitoring device in kind scene may be because of external force run-off the straight, in this way, passing through the monitoring device acquired image
In vehicle and license plate may also can run-off the straight.In addition to this, monitoring device can also carry out under many different scenes
Image Acquisition, and the licence plate recognition method provided in the embodiment of the present invention can be used to adopt monitoring device under any scene
The license plate for including in the image collected is identified.
Next to the present embodiments relate to system architecture be introduced.
Fig. 1 is a kind of system architecture diagram of licence plate recognition method provided in an embodiment of the present invention.As shown in Figure 1, the system
In may include monitoring device 101 and terminal 102.
Wherein, monitoring device 101 and the foundation of terminal 102 have communication connection, and by the communication connection, monitoring device 101 can
Acquired image is sent to terminal 102.Terminal 102, can be to image when receiving the image of monitoring device transmission
Middle license plate is identified, and exports final recognition result.
It should be noted that monitoring device 101 can be CCD (Charge Coupled Device, charge-coupled device)
Video camera, or other cameras that can be carried out Image Acquisition and can be communicated with terminal 102.Terminal 102 can
Think the computer equipments such as desktop computer, portable computer, network server.
Next licence plate recognition method provided in an embodiment of the present invention is introduced.
Fig. 2 is a kind of flow chart of licence plate recognition method provided in an embodiment of the present invention.This method can be applied to Fig. 1 institute
In the terminal shown, as shown in Fig. 2, method includes the following steps:
Step 201: including the license plate area of license plate in acquisition image, and using in CNN model extraction license plate area
Characteristic information.
Wherein, the characteristic information in license plate area may include multiple characteristic sequences.
Step 202: the character in license plate area being identified based on multiple characteristic sequences.
It wherein, include license plate number in license plate area, in general, license plate number is made of multiple characters, in license plate area
Multiple characters are identified, multiple characters of available composition license plate number.Wherein, character can be English character, number with
And other spcial characters.
Step 203: license plate number is determined based on character identification result.
In embodiments of the present invention, include the license plate area of license plate in the available image of terminal, and utilize CNN model
The characteristic information in license plate area is extracted, characteristic information may include multiple characteristic sequences, based on multiple characteristic sequences to license plate
Character in region is identified, and determines license plate number based on character identification result.It that is to say, in embodiments of the present invention,
Directly the character in license plate area can be identified, and license plate number is determined according to character identification result, without
License plate is identified to obtain multiple character zones by being split to license plate area, due to that need not carry out license plate area point again
It cuts, therefore, also there is no need to adjust Image Processing parameter according to special scenes, effectively prevents scene factor to Car license recognition
Interference, to improve the versatility and accuracy of licence plate recognition method.
Fig. 3 A is a kind of flow chart of licence plate recognition method provided in an embodiment of the present invention, and this method can be applied to Fig. 1
Shown in terminal, as shown in Figure 3A, method includes the following steps:
Step 301: utilizing the license plate area in FRCNN acquisition image including license plate.
FRCNN model is that (Region-Based Convolutional Neural Networks is based on region in RCNN
Convolutional neural networks) a kind of model for target detection for growing up on model.Target is carried out when passing through FRCNN model
When detection, detection process is broadly divided into 4 candidate region generation, feature extraction, classification and position refine basic steps.In general,
FRCNN model may include multiple convolutional layers and multiple full articulamentums.
When carrying out license plate area detection, terminal can using the image got by monitoring device as input picture,
Wherein, first convolutional layer can carry out convolution algorithm to the pixel value for multiple pixels that the image of input includes, and export
Convolution algorithm is as a result, input value as next convolutional layer.And so on, the output valve of previous convolutional layer is as next
The input value of convolutional layer, to the last a convolutional layer obtains multiple candidate regions based on the output valve determination of previous convolutional layer
Domain.Later, the multiple candidate regions which obtained are as the input value of the first full articulamentum, for multiple candidate region
In each candidate region, full articulamentum can differentiate whether the candidate region is license plate area to be detected, and determine the time
The position coordinates of favored area.Finally, exporting the probability and not that the candidate region is license plate area by the last one full articulamentum
For the probability of license plate area and the position coordinates of the candidate region.
It should be noted that license plate area refers to the region in image where the license plate of vehicle, wrapped in the license plate area
Information, the terminals such as character information and license plate texture containing composition license plate number, can be into one after getting license plate area
Step ground detects the information in the license plate area by step 302-305, to identify to license plate.
In addition, in embodiments of the present invention, FRCNN model is the pre- model for first passing through multiple training sample training and obtaining.
Wherein, may include in multiple training samples monitoring device acquisition country variant different regions vehicle image, in this way, instruction
The FRCNN model got by can the license plate area in the vehicle image to country variant, different regions detect.
Step 302: using the characteristic information in CNN model extraction license plate area, this feature information includes multiple feature sequences
Column.
After getting license plate area, terminal can be using the license plate area as the input of CNN model, and then passes through
Characteristic information in CNN model extraction license plate area.Wherein, this feature information mainly include be used to indicate it is more in license plate area
Multiple characteristic sequences of a character.
Wherein, CNN model can carry out the characteristic information in license plate area according to sequence from left to right from top to bottom
It extracts, to export multiple characteristic sequences according to sequence of extraction.
Wherein, in one possible implementation, the license plate area that terminal can will acquire is normalized to specified ruler
It is very little, the license plate area of the specified size is then input to CNN model again.For example, the specified size can be 180*60, when
So, or other sizes, the embodiment of the present invention are not specifically limited herein.
Step 303: the character in license plate area being identified based on multiple characteristic sequences.
After extracting multiple characteristic sequences out of license plate area by CNN model, terminal can determine multiple features
The semantic information of each characteristic sequence in sequence, and then be decoded using semantic information of the RNN model to each characteristic sequence
Identification, to obtain multiple characters in license plate area.
It should be noted that terminal can be according to the output sequence of multiple characteristic sequences, one by one by Attention algorithm
Determine the semantic information of each characteristic sequence in multiple characteristic sequences.Specifically, in embodiments of the present invention, it will be with multiple spy
The specific implementation process of semantic information is clearly determined for for any feature sequence A in sign sequence.
Wherein, for any feature sequence A in multiple characteristic sequences, terminal can be determined by Attention algorithm
The weight of characteristic sequence A and in addition to characteristic sequence A remaining each characteristic sequence weight, wherein the weight of characteristic sequence A is big
In the weight of remaining each characteristic sequence；Later, based on characteristic sequence A, the weight of characteristic sequence A, remaining each characteristic sequence
The semantic information of characteristic sequence A is determined with the weight of remaining each characteristic sequence.
It should be noted that Attention model is a kind of model that can be used for carrying out semantics recognition.In
It mainly include semantic synthesis module and decoding identification module in Attention model, wherein semantic synthesis module is defeated for seeking
The semantic information of the characteristic sequence entered, decoding identification module are then used to solve the semantic information for each characteristic sequence sought
Code identification, thus output character recognition result.Wherein, above-mentioned two module can be realized by RNN model.
Fig. 3 B is a kind of schematic diagram of Attention model provided in an embodiment of the present invention, wherein Attention model
In semantic synthesis module realized by the first RNN model, decoding identification module realized by the 2nd RNN model.First
RNN model and the 2nd RNN model include input layer, hidden layer and output layer.Assuming that multiple characteristic sequences are according to output sequence
Respectively x1、x2、x3…xn, multiple characteristic sequence can be input to the input layer of the first RNN model by terminal in sequence,
The input layer of first RNN model, can be by the corresponding transmission of multiple characteristic sequence after receiving multiple characteristic sequence
To multiple hidden layer node h1、h2、h3…hn, hidden layer node h1It can be to characteristic sequence x1It is handled, obtains processing result f
(x1), and by processing result f (x1) it is used as hidden layer node h2Input, hidden layer node h2It can be according to f (x1) to feature
Sequence x2It is handled, to obtain processing result f (x2), and so on, hidden layer node hnAccording to f (xn-1) to characteristic sequence
xnIt is handled, to obtain processing result f (xn).When obtaining f (x2)、f(x3)…f(xn), later, output layer can be according to every
The preset weights and f (x of a characteristic sequence1)、f(x2)、f(x3)…f(xn) calculate characteristic sequence x1Semantic information C1,
In, characteristic sequence x1Preset weights be greater than other characteristic sequences preset weights.Later, by C1It is exported by output layer, as
The input value of 2nd RNN model, the input layer of the 2nd RNN model receive semantic information C1Later, by voice messaging C1It passes
Transport to the hidden layer node H of the 2nd RNN model0It is handled, obtains processing result S (C1), and by output layer according to the S
(C1) calculate and export characteristic sequence x1Corresponding character y1。
When obtaining character identification result y1Later, the output layer of the first RNN model is respectively by f (x1)、f(x2)、f(x3)…f
(xn) with the hidden layer node H of the 2nd RNN model1S (the C of output1) be compared, exist so that it is determined that obtaining each characteristic sequence
The weight at current time, wherein characteristic sequence x2It is greater than the weight of other characteristic sequences in the weight at current time, later, the
The output layer of one RNN model obtains characteristic sequence x based on determining weight computing2Semantic information C2, later, by C2By defeated
Layer exports out, and as the input value of the 2nd RNN model, the input layer of the 2nd RNN model receives semantic information C2Later, will
Voice messaging C2It is transmitted to the hidden layer node H of the 2nd RNN model2, the hidden layer node H of the 2nd RNN model2According to second
The hidden layer node H of RNN model1Processing result S (the C of output1) and character identification result y1To semantic information C2Located
Reason, to obtain processing result S (C2), and by output layer according to the S (C2) calculate and export characteristic sequence x2Corresponding character
y2.And so on, terminal can successively obtain characteristic sequence x by the Attention model3…xn-1、xnCorresponding word
Accord with y3…yn-1、yn。
Optionally, after being identified to obtain multiple characters to each characteristic sequence by Attention model, terminal
Multiple character can also be exported according to preset format by the 2nd RNN model.Specifically, the 2nd RNN model can determine respectively
A character corresponding position coordinates in license plate area, and will be multiple according to the difference between the position coordinates of each adjacent two character
Character is divided into different character strings and exports according to sequencing.For example, character y1、y2、y3Distance between any two is respectively less than specified
Threshold value, and y3With y4The distance between be greater than specified threshold, and y4、y5、y6、y7In per adjacent the distance between two characters
Respectively less than specified threshold, at this point, then can be by character y1、y2、y3As a character string, y4、y5、y6、y7As another word
Symbol string, and the less character string of the character either lesser character string in shared region is first exported.
It is the license plate because of the license plate of some areas or country it should be noted why exporting according to the method described above
Number have point of principal piece and subsegment, wherein often there is interval between principal piece and subsegment, also, have can for the number of characters of principal piece
It can be greater than the number of characters of subsegment, alternatively, region shared by the character of principal piece may be greater than region shared by the character of subsegment.
Based on this, by the above method can will the obtained multiple characters of identification according to the feature of principal piece and subsegment as different
Character string output.Since the subsegment in license plate number is often to be used to characterize belonging country and area, it can will represent son
The character string of section first exports, and will export after the character string for representing principal piece.Certainly, the license plate number of some areas or country is not deposited
In point of principal piece and subsegment, in this case, then multiple characters can be sequentially output according to character recognition sequence.
Step 304: determining license plate type belonging to license plate based on multiple characteristic sequences.
After terminal extracts multiple characteristic sequences from license plate area by CNN model, terminal is also based on this
Multiple characteristic sequences determine license plate type belonging to license plate.
Wherein, terminal can be based on multiple characteristic sequences, determine that license plate belongs to each default license plate type using CNN model
Probability value, and the corresponding default license plate type of most probable value is determined as license plate type belonging to license plate.
Specifically, CNN model can be according to the model after country variant and the license plate sample training in area, also, instruct
It include multiple labels in the CNN model got, each label is used to indicate a default license plate type.Terminal can will be multiple
Characteristic sequence carries out softmax normalized, and determines that license plate belongs to the probability of each label according to normalization result, it
Afterwards, license plate type indicated by the corresponding label of most probable value can be determined as license plate kind belonging to current license plate by terminal
Class.
It should be noted that in embodiments of the present invention, this step is optional step.Wherein, if terminal executes the step,
Then passing through step 302 after extraction obtains multiple characteristic sequences in license plate area, terminal can be first according to multiple feature
Sequence identifies the character in license plate area, then determines type belonging to license plate based on multiple characteristic sequence again.Or
Person, terminal first can also determine type belonging to license plate based on multiple characteristic sequence, then further according to multiple characteristic sequence
Character in license plate area is identified.Alternatively, terminal may be performed simultaneously above-mentioned two operation.It that is to say, in the present invention
In embodiment, if terminal executes step 304, terminal can first carry out any of step 303 and step 304, can also be with
It is performed simultaneously the two steps.
Step 305: license plate number is determined based on character identification result.
After being identified by step 303 to the character in license plate area, if terminal does not execute step 304, eventually
The character string exported in order in step 303 can be directly determined as the license plate number of the license plate by end.If terminal executes step
304, then terminal can determine license plate number in conjunction with determining license plate type after obtaining character identification result.
Specifically, the corresponding license plate number sample of the available license plate type of terminal；Belong to vehicle based on the judgement of license plate number sample
It whether include subsegment and principal piece in the license plate number of board type, subsegment and principal piece refer both to continuous character string in license plate number, main
The number of characters that section includes is greater than the number of characters that subsegment includes, alternatively, the size in region shared by the character that principal piece includes is greater than subsegment
The size in region shared by the character for including；If belonging to includes subsegment and principal piece in the license plate number of license plate type, by character
Recognition result divides subsegment and principal piece according to license plate number sample, and the character identification result after division is determined as to the license plate of license plate
Number.
Wherein, it can store the corresponding license plate number sample of license plate type in terminal and be used to indicate corresponding license plate kind
In the license plate number of class whether include subsegment and principal piece instruction information.Terminal can obtain determining license plate from the corresponding relationship
The corresponding license plate number sample of type, and the corresponding instruction information of the license plate type is obtained, later, terminal can be believed based on the instruction
Whether cease in the license plate number for judging this type is divided into subsegment and principal piece.If terminal determines in the license plate number of the license plate type not
There are points of subsegment and principal piece, then, the character string exported in order in step 303 directly can be determined as the license plate by terminal
License plate number.If terminal determines point in the license plate number of the license plate type there are subsegment and principal piece, then, terminal can be by step
The character string exported in order in 303 carries out the division of subsegment and principal piece according to license plate number sample, and by the character string after division
It is determined as the license plate number of the license plate.
Step 306: obtaining the corresponding license plate color information of license plate type and affiliated area information, and export the license plate of license plate
Number, license plate color information and area information.
Specifically, after determining license plate type, terminal can also be according to the license plate kind when terminal executes step 304
Class further obtains the other information of license plate.
Wherein, it can store pair between license plate type, license plate color information and license plate affiliated area information in terminal
It should be related to, terminal can obtain the letter of region belonging to the corresponding colouring information of license plate type and the license plate from the corresponding relationship
Breath.Wherein, area information belonging to license plate may include the information such as country belonging to the license plate, city.Later, terminal can incite somebody to action
These information export display together with license plate number.
It optionally, can also include the license plate that can be more confirmed according to license plate type in corresponding relationship above-mentioned
Information, so that terminal can be output it according to license plate type, so that as much as possible meet user demand.
In embodiments of the present invention, terminal can by FRCNN model obtain image in include license plate license plate area,
And using the characteristic information in CNN model extraction license plate area, characteristic information may include multiple characteristic sequences, later, terminal
The character in license plate area can be identified by Attention model based on multiple characteristic sequences, and utilize CNN model
License plate type belonging to license plate is determined based on multiple characteristic sequences, finally, terminal can be based on character identification result and license plate kind
Class determines license board information.It can be seen that in embodiments of the present invention, the modules of Car license recognition are by deep learning
Method is realized, Car license recognition end to end is really realized, and it is dry to Car license recognition bring that natural scene has been effectively relieved
It disturbs.In addition, in embodiments of the present invention, can directly be identified to the character in license plate area, and according to the feature of extraction
Information determines license plate type, in this way, license board information can be determined in conjunction with license plate type after obtaining character identification result, and
It does not need to identify license plate by being split license plate area to obtain multiple character zones, since license plate area need not be carried out again
Therefore regional partition also there is no need to adjust Image Processing parameter according to special scenes, effectively prevents scene factor to license plate
The interference of identification, to improve the versatility and accuracy of licence plate recognition method.
Referring to fig. 4, the embodiment of the invention provides a kind of license plate recognition device 400, which includes:
Obtain module 401, for obtain include in image license plate license plate area, and utilize convolutional neural networks CNN
Characteristic information in model extraction license plate area, characteristic information include multiple characteristic sequences；
Identification module 402, for being identified based on multiple characteristic sequences to the character in license plate area；
First determining module 403, for determining license plate number based on character identification result.
Optionally, identification module 402 is used for:
Each characteristic sequence in the multiple characteristic sequence is handled by attention Attention model, is obtained
The corresponding character of each characteristic sequence in the license plate area.
Optionally, identification module 402 is specifically used for:
For any feature sequence A in multiple characteristic sequences, the power of characteristic sequence A is determined by Attention model
Value and in addition to characteristic sequence A remaining each characteristic sequence weight, the weight of characteristic sequence A is greater than remaining each characteristic sequence
Weight；
Power based on characteristic sequence A, the weight of characteristic sequence A, remaining each characteristic sequence and remaining each characteristic sequence
It is worth the semantic information for determining characteristic sequence A；
Identification is decoded to the semantic information of characteristic sequence A, obtains the corresponding character of characteristic sequence A.
Optionally, the device 400 further include:
Second determining module, for determining license plate type belonging to license plate based on multiple characteristic sequences；
Correspondingly, the first determining module includes:
Submodule is determined, for determining the license plate number of license plate based on character identification result and license plate type.
Optionally, the second determining module is specifically used for:
Based on multiple characteristic sequences, determine that license plate belongs to the probability value of each default license plate type using CNN model；
The corresponding default license plate type of most probable value is determined as license plate type belonging to license plate.
Optionally it is determined that submodule is specifically used for:
Obtain the corresponding license plate number sample of license plate type；
Whether include subsegment and principal piece, subsegment and master if being belonged in the license plate number of license plate type based on the judgement of license plate type
Section refers both to continuous character string in license plate number, and the number of characters that principal piece includes is greater than the number of characters that subsegment includes, alternatively, principal piece includes
Character shared by region size be greater than subsegment include character shared by region size；
If belonging in the license plate number of license plate type includes subsegment and principal piece, by character identification result according to license plate number
Sample divides subsegment and principal piece, and the character identification result after division is determined as to the license plate number of license plate.
Optionally, which is also used to:
Obtain the corresponding license plate color information of license plate type and affiliated area information；
Export license plate number, license plate color information and the area information of license plate.
In conclusion in embodiments of the present invention, in the available image of terminal including the license plate area of license plate, and benefit
With the characteristic information in CNN model extraction license plate area, characteristic information may include multiple characteristic sequences, be based on multiple feature sequences
Column identify the character in license plate area, and determine license plate number based on character identification result.It that is to say, of the invention real
It applies in example, directly the character in license plate area can be identified, and license plate number is determined according to character identification result, and
It does not need to identify license plate by being split license plate area to obtain multiple character zones, since license plate area need not be carried out again
Therefore regional partition also there is no need to adjust Image Processing parameter according to special scenes, effectively prevents scene factor to license plate
The interference of identification, to improve the versatility and accuracy of licence plate recognition method.
It should be understood that license plate recognition device provided by the above embodiment is when carrying out Car license recognition, only with above-mentioned each
The division progress of functional module can according to need and for example, in practical application by above-mentioned function distribution by different function
Energy module is completed, i.e., the internal structure of equipment is divided into different functional modules, to complete whole described above or portion
Divide function.In addition, license plate recognition device provided by the above embodiment and licence plate recognition method embodiment belong to same design, have
Body realizes that process is detailed in embodiment of the method, and which is not described herein again.
Fig. 5 shows the structural block diagram of the terminal 500 of an illustrative embodiment of the invention offer.The terminal can be figure
Terminal in 1 system architecture.Wherein, which may is that industrial computer, industrial personal computer, laptop, desktop
Brain, smart phone or tablet computer etc..Terminal 500 is also possible to referred to as user equipment, portable terminal, laptop terminal, platform
Other titles such as formula terminal.
In general, terminal 500 includes: processor 501 and memory 502.
Processor 501 may include one or more processing cores, such as 4 core processors, 8 core processors etc..Place
Reason device 501 can use DSP (Digital Signal Processing, Digital Signal Processing), FPGA (Field-
Programmable Gate Array, field programmable gate array), PLA (Programmable Logic Array, may be programmed
Logic array) at least one of example, in hardware realize.Processor 501 also may include primary processor and coprocessor, master
Processor is the processor for being handled data in the awake state, also referred to as CPU (Central Processing
Unit, central processing unit)；Coprocessor is the low power processor for being handled data in the standby state.In
In some embodiments, processor 501 can be integrated with GPU (Graphics Processing Unit, image processor),
GPU is used to be responsible for the rendering and drafting of content to be shown needed for display screen.In some embodiments, processor 501 can also be wrapped
AI (Artificial Intelligence, artificial intelligence) processor is included, the AI processor is for handling related machine learning
Calculating operation.
Memory 502 may include one or more computer readable storage mediums, which can
To be non-transient.Memory 502 may also include high-speed random access memory and nonvolatile memory, such as one
Or multiple disk storage equipments, flash memory device.In some embodiments, the non-transient computer in memory 502 can
Storage medium is read for storing at least one instruction, at least one instruction performed by processor 501 for realizing this Shen
Please in embodiment of the method provide planning flight equipment flight path method.
In some embodiments, terminal 500 is also optional includes: peripheral device interface 503 and at least one peripheral equipment.
It can be connected by bus or signal wire between processor 501, memory 502 and peripheral device interface 503.Each peripheral equipment
It can be connected by bus, signal wire or circuit board with peripheral device interface 503.Specifically, peripheral equipment includes: radio circuit
504, at least one of touch display screen 505, camera 506, voicefrequency circuit 507, positioning component 508 and power supply 509.
Peripheral device interface 503 can be used for I/O (Input/Output, input/output) is relevant outside at least one
Peripheral equipment is connected to processor 501 and memory 502.In some embodiments, processor 501, memory 502 and peripheral equipment
Interface 503 is integrated on same chip or circuit board；In some other embodiments, processor 501, memory 502 and outer
Any one or two in peripheral equipment interface 503 can realize on individual chip or circuit board, the present embodiment to this not
It is limited.
Radio circuit 504 is for receiving and emitting RF (Radio Frequency, radio frequency) signal, also referred to as electromagnetic signal.It penetrates
Frequency circuit 504 is communicated by electromagnetic signal with communication network and other communication equipments.Radio circuit 504 turns electric signal
It is changed to electromagnetic signal to be sent, alternatively, the electromagnetic signal received is converted to electric signal.Optionally, radio circuit 504 wraps
It includes: antenna system, RF transceiver, one or more amplifiers, tuner, oscillator, digital signal processor, codec chip
Group, user identity module card etc..Radio circuit 504 can be carried out by least one wireless communication protocol with other terminals
Communication.The wireless communication protocol includes but is not limited to: WWW, Metropolitan Area Network (MAN), Intranet, each third generation mobile communication network (2G, 3G,
4G and 5G), WLAN and/or WiFi (Wireless Fidelity, Wireless Fidelity) network.In some embodiments, it penetrates
Frequency circuit 504 can also include NFC (Near Field Communication, wireless near field communication) related circuit, this
Application is not limited this.
Display screen 505 is for showing UI (User Interface, user interface).The UI may include figure, text, figure
Mark, video and its their any combination.When display screen 505 is touch display screen, display screen 505 also there is acquisition to show
The ability of the touch signal on the surface or surface of screen 505.The touch signal can be used as control signal and be input to processor
501 are handled.At this point, display screen 505 can be also used for providing virtual push button and/or dummy keyboard, also referred to as soft button and/or
Soft keyboard.In some embodiments, display screen 505 can be one, and the front panel of terminal 500 is arranged；In other embodiments
In, display screen 505 can be at least two, be separately positioned on the different surfaces of terminal 500 or in foldover design；In still other reality
It applies in example, display screen 505 can be flexible display screen, be arranged on the curved surface of terminal 500 or on fold plane.Even, it shows
Display screen 505 can also be arranged to non-rectangle irregular figure, namely abnormity screen.Display screen 505 can use LCD (Liquid
Crystal Display, liquid crystal display), OLED (Organic Light-Emitting Diode, Organic Light Emitting Diode)
Etc. materials preparation.
CCD camera assembly 506 is for acquiring image or video.Optionally, CCD camera assembly 506 include front camera and
Rear camera.In general, the front panel of terminal is arranged in front camera, the back side of terminal is arranged in rear camera.One
In a little embodiments, rear camera at least two is main camera, depth of field camera, wide-angle camera, focal length camera shooting respectively
Any one in head, to realize that main camera and the fusion of depth of field camera realize background blurring function, main camera and wide-angle
Camera fusion realizes that pan-shot and VR (Virtual Reality, virtual reality) shooting function or other fusions are clapped
Camera shooting function.In some embodiments, CCD camera assembly 506 can also include flash lamp.Flash lamp can be monochromatic warm flash lamp,
It is also possible to double-colored temperature flash lamp.Double-colored temperature flash lamp refers to the combination of warm light flash lamp and cold light flash lamp, can be used for not
With the light compensation under colour temperature.
Voicefrequency circuit 507 may include microphone and loudspeaker.Microphone is used to acquire the sound wave of user and environment, and will
Sound wave, which is converted to electric signal and is input to processor 501, to be handled, or is input to radio circuit 504 to realize voice communication.
For stereo acquisition or the purpose of noise reduction, microphone can be separately positioned on the different parts of terminal 500 to be multiple.Mike
Wind can also be array microphone or omnidirectional's acquisition type microphone.Loudspeaker is then used to that processor 501 or radio circuit will to be come from
504 electric signal is converted to sound wave.Loudspeaker can be traditional wafer speaker, be also possible to piezoelectric ceramic loudspeaker.When
When loudspeaker is piezoelectric ceramic loudspeaker, the audible sound wave of the mankind can be not only converted electrical signals to, it can also be by telecommunications
Number the sound wave that the mankind do not hear is converted to carry out the purposes such as ranging.In some embodiments, voicefrequency circuit 507 can also include
Earphone jack.
Positioning component 508 is used for the current geographic position of positioning terminal 500, to realize navigation or LBS (Location
Based Service, location based service).Positioning component 508 can be the GPS (Global based on the U.S.
Positioning System, global positioning system), China dipper system or European Union Galileo system positioning component.
Power supply 509 is used to be powered for the various components in terminal 500.Power supply 509 can be alternating current, direct current,
Disposable battery or rechargeable battery.When power supply 509 includes rechargeable battery, which can be wired charging electricity
Pond or wireless charging battery.Wired charging battery is the battery to be charged by Wireline, and wireless charging battery is by wireless
The battery of coil charges.The rechargeable battery can be also used for supporting fast charge technology.
In some embodiments, terminal 500 further includes having one or more sensors 510.The one or more sensors
510 include but is not limited to: acceleration transducer 511, gyro sensor 512, pressure sensor 513, fingerprint sensor 514,
Optical sensor 515 and proximity sensor 516.
The acceleration that acceleration transducer 511 can detecte in three reference axis of the coordinate system established with terminal 500 is big
It is small.For example, acceleration transducer 511 can be used for detecting component of the acceleration of gravity in three reference axis.Processor 501 can
With the acceleration of gravity signal acquired according to acceleration transducer 511, touch display screen 505 is controlled with transverse views or longitudinal view
Figure carries out the display of user interface.Acceleration transducer 511 can be also used for the acquisition of game or the exercise data of user.
Gyro sensor 512 can detecte body direction and the rotational angle of terminal 500, and gyro sensor 512 can
To cooperate with acquisition user to act the 3D of terminal 500 with acceleration transducer 511.Processor 501 is according to gyro sensor 512
Following function may be implemented in the data of acquisition: when action induction (for example changing UI according to the tilt operation of user), shooting
Image stabilization, game control and inertial navigation.
The lower layer of side frame and/or touch display screen 505 in terminal 500 can be set in pressure sensor 513.Work as pressure
When the side frame of terminal 500 is arranged in sensor 513, user can detecte to the gripping signal of terminal 500, by processor 501
Right-hand man's identification or prompt operation are carried out according to the gripping signal that pressure sensor 513 acquires.When the setting of pressure sensor 513 exists
When the lower layer of touch display screen 505, the pressure operation of touch display screen 505 is realized to UI circle according to user by processor 501
Operability control on face is controlled.Operability control includes button control, scroll bar control, icon control, menu
At least one of control.
Fingerprint sensor 514 is used to acquire the fingerprint of user, collected according to fingerprint sensor 514 by processor 501
The identity of fingerprint recognition user, alternatively, by fingerprint sensor 514 according to the identity of collected fingerprint recognition user.It is identifying
When the identity of user is trusted identity out, the user is authorized to execute relevant sensitive operation, the sensitive operation packet by processor 501
Include solution lock screen, check encryption information, downloading software, payment and change setting etc..Terminal can be set in fingerprint sensor 514
500 front, the back side or side.When being provided with physical button or manufacturer Logo in terminal 500, fingerprint sensor 514 can be with
It is integrated with physical button or manufacturer Logo.
Optical sensor 515 is for acquiring ambient light intensity.In one embodiment, processor 501 can be according to optics
The ambient light intensity that sensor 515 acquires controls the display brightness of touch display screen 505.Specifically, when ambient light intensity is higher
When, the display brightness of touch display screen 505 is turned up；When ambient light intensity is lower, the display for turning down touch display screen 505 is bright
Degree.In another embodiment, the ambient light intensity that processor 501 can also be acquired according to optical sensor 515, dynamic adjust
The acquisition parameters of CCD camera assembly 506.
Proximity sensor 516, also referred to as range sensor are generally arranged at the front panel of terminal 500.Proximity sensor 516
For acquiring the distance between the front of user Yu terminal 500.In one embodiment, when proximity sensor 516 detects use
When family and the distance between the front of terminal 500 gradually become smaller, touch display screen 505 is controlled from bright screen state by processor 501
It is switched to breath screen state；When proximity sensor 516 detects user and the distance between the front of terminal 500 becomes larger,
Touch display screen 505 is controlled by processor 501 and is switched to bright screen state from breath screen state.
It that is to say, the embodiment of the present invention provides not only a kind of device of flight path for planning flight equipment, the device
It can be applied in above-mentioned terminal 500, including processor and for the memory of storage processor executable instruction, wherein place
Reason device is configured as executing the method in embodiment shown in Fig. 2 and Fig. 3 A, moreover, the embodiment of the invention also provides a kind of meters
Calculation machine readable storage medium storing program for executing is stored with computer program in the storage medium, can be with when which is executed by processor
Realize the method in embodiment shown in Fig. 2 and Fig. 3 A.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, the program can store in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (16)
1. a kind of licence plate recognition method, which is characterized in that the described method includes:
In acquisition image include the license plate area of license plate, and utilizes license plate area described in convolutional neural networks CNN model extraction
Interior characteristic information, the characteristic information include multiple characteristic sequences；
The character in the license plate area is identified based on the multiple characteristic sequence；
License plate number is determined based on character identification result.
2. the method according to claim 1, wherein described be based on the multiple characteristic sequence to the license plate area
Character in domain is identified, comprising:
Each characteristic sequence in the multiple characteristic sequence is handled by attention Attention model, obtains institute
State the corresponding character of each characteristic sequence in license plate area.
3. according to the method described in claim 2, it is characterized in that, it is described by attention Attention model to described more
Each characteristic sequence in a characteristic sequence is handled, and multiple characters in the license plate area are obtained, comprising:
For any feature sequence A in the multiple characteristic sequence, the weight of the characteristic sequence A is determined and except the feature
The weight of remaining each characteristic sequence except sequence A, the weight of the characteristic sequence A are greater than remaining each characteristic sequence
Weight；
Based on the characteristic sequence A, the weight of the characteristic sequence A, remaining described each characteristic sequence and described remaining is each
The weight of characteristic sequence determines the semantic information of the characteristic sequence A；
Identification is decoded to the semantic information of the characteristic sequence A, obtains the corresponding character of the characteristic sequence A.
4. method according to claim 1 to 3, which is characterized in that described to be mentioned using convolutional neural networks CNN model
After taking the characteristic information in the license plate area, further includes:
License plate type belonging to the license plate is determined based on the multiple characteristic sequence；
It is correspondingly, described that license plate number is determined based on character identification result, comprising:
The license plate number of the license plate is determined based on the character identification result and the license plate type.
5. according to the method described in claim 4, it is characterized in that, described determine the license plate based on the multiple characteristic sequence
Affiliated license plate type, comprising:
Based on the multiple characteristic sequence, determine that the license plate belongs to the general of each default license plate type using the CNN model
Rate value；
The corresponding default license plate type of most probable value is determined as license plate type belonging to the license plate.
6. according to the method described in claim 4, it is characterized in that, described be based on the character identification result and the license plate kind
Class determines the license plate number of the license plate, comprising:
Obtain the corresponding license plate number sample of the license plate type；
Whether include subsegment and principal piece, described if being belonged in the license plate number of the license plate type based on license plate type judgement
Subsegment and the principal piece refer both to continuous character string in license plate number, and the number of characters that the principal piece includes is greater than the subsegment and includes
Number of characters, alternatively, the size in region shared by the character that the principal piece includes is greater than region shared by the character that the subsegment includes
Size；
If belonging in the license plate number of the license plate type includes subsegment and principal piece, by the character identification result according to institute
It states license plate number sample and divides subsegment and principal piece, and the character identification result after division is determined as to the license plate number of the license plate.
7. according to any method of claim 4-6, which is characterized in that described to determine license plate number based on character identification result
After code, further includes:
Obtain the corresponding license plate color information of the license plate type and affiliated area information；
Export the license plate number, the license plate color information and the area information of the license plate.
8. a kind of license plate recognition device, which is characterized in that described device includes:
Obtain module, for obtain include in image license plate license plate area, and utilize convolutional neural networks CNN model extraction
Characteristic information in the license plate area, the characteristic information include multiple characteristic sequences；
Identification module, for being identified based on the multiple characteristic sequence to the character in the license plate area；
First determining module, for determining license plate number based on character identification result.
9. device according to claim 8, which is characterized in that the identification module is used for:
Each characteristic sequence in the multiple characteristic sequence is handled by attention Attention model, obtains institute
State the corresponding character of each characteristic sequence in license plate area.
10. device according to claim 9, which is characterized in that the identification module is specifically used for:
For any feature sequence A in the multiple characteristic sequence, the feature is determined by attention Attention model
The weight of sequence A and in addition to the characteristic sequence A remaining each characteristic sequence weight, the weight of the characteristic sequence A is big
In the weight of remaining each characteristic sequence；
Based on the characteristic sequence A, the weight of the characteristic sequence A, remaining described each characteristic sequence and described remaining is each
The weight of characteristic sequence determines the semantic information of the characteristic sequence A；
Identification is decoded to the semantic information of the characteristic sequence A, obtains the corresponding character of the characteristic sequence A.
11. according to any device of claim 8-10, which is characterized in that described device further include:
Second determining module, for determining license plate type belonging to the license plate based on the multiple characteristic sequence；
Correspondingly, first determining module includes:
Submodule is determined, for determining the license plate number of the license plate based on the character identification result and the license plate type.
12. device according to claim 11, which is characterized in that second determining module is specifically used for:
Based on the multiple characteristic sequence, determine that the license plate belongs to the general of each default license plate type using the CNN model
Rate value；
The corresponding default license plate type of most probable value is determined as license plate type belonging to the license plate.
13. device according to claim 11, which is characterized in that the determining submodule is specifically used for:
Obtain the corresponding license plate number sample of the license plate type；
Whether include subsegment and principal piece, described if being belonged in the license plate number of the license plate type based on license plate type judgement
Subsegment and the principal piece refer both to continuous character string in license plate number, and the number of characters that the principal piece includes is greater than the subsegment and includes
Number of characters, alternatively, the size in region shared by the character that the principal piece includes is greater than region shared by the character that the subsegment includes
Size；
If belonging in the license plate number of the license plate type includes subsegment and principal piece, by the character identification result according to institute
It states license plate number sample and divides subsegment and principal piece, and the character identification result after division is determined as to the license plate number of the license plate.
14. any device of 1-13 according to claim 1, which is characterized in that described device is also used to:
Obtain the corresponding license plate color information of the license plate type and affiliated area information；
Export the license plate number, the license plate color information and the area information of the license plate.
15. a kind of license plate recognition device, which is characterized in that described device includes
Processor；
Memory for storage processor executable instruction；
Wherein, the processor is configured to perform claim requires any one method described in 1-7.
16. a kind of computer readable storage medium, which is characterized in that computer program is stored in the storage medium, it is described
The method of any one described in claim 1-7 is realized when computer program is executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810461160.4A CN110490179B (en) | 2018-05-15 | 2018-05-15 | License plate recognition method and device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810461160.4A CN110490179B (en) | 2018-05-15 | 2018-05-15 | License plate recognition method and device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110490179A true CN110490179A (en) | 2019-11-22 |
| CN110490179B CN110490179B (en) | 2022-08-05 |
Family
ID=68545110
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810461160.4A Active CN110490179B (en) | 2018-05-15 | 2018-05-15 | License plate recognition method and device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110490179B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111310766A (en) * | 2020-03-13 | 2020-06-19 | 西北工业大学 | License plate identification method based on coding and decoding and two-dimensional attention mechanism |
| CN111368645A (en) * | 2020-02-14 | 2020-07-03 | 北京澎思科技有限公司 | Method and device for identifying multi-label license plate, electronic equipment and readable medium |
| CN111444911A (en) * | 2019-12-13 | 2020-07-24 | 珠海大横琴科技发展有限公司 | Training method and device of license plate recognition model and license plate recognition method and device |
| CN111563504A (en) * | 2020-07-16 | 2020-08-21 | 平安国际智慧城市科技股份有限公司 | License plate recognition method and related equipment |
| CN111832568A (en) * | 2020-06-12 | 2020-10-27 | 北京百度网讯科技有限公司 | License plate recognition method, and training method and device of license plate recognition model |
| CN112381129A (en) * | 2020-11-10 | 2021-02-19 | 浙江大华技术股份有限公司 | License plate classification method and device, storage medium and electronic equipment |
| CN112418234A (en) * | 2020-11-19 | 2021-02-26 | 北京软通智慧城市科技有限公司 | Method and device for identifying license plate number, electronic equipment and storage medium |
| CN113486885A (en) * | 2021-06-17 | 2021-10-08 | 杭州鸿泉物联网技术股份有限公司 | License plate recognition method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106407981A (en) * | 2016-11-24 | 2017-02-15 | 北京文安智能技术股份有限公司 | License plate recognition method, device and system |
| EP3182334A1 (en) * | 2015-12-17 | 2017-06-21 | Xerox Corporation | License plate recognition using coarse-to-fine cascade adaptations of convolutional neural networks |
| CN106960206A (en) * | 2017-02-08 | 2017-07-18 | 北京捷通华声科技股份有限公司 | Character identifying method and character recognition system |
| CN107704860A (en) * | 2017-12-06 | 2018-02-16 | 四川知创空间孵化器管理有限公司 | A kind of number-plate number recognition methods |
| CN107944450A (en) * | 2017-11-16 | 2018-04-20 | 深圳市华尊科技股份有限公司 | A kind of licence plate recognition method and device |
| CN108009543A (en) * | 2017-11-29 | 2018-05-08 | 深圳市华尊科技股份有限公司 | A kind of licence plate recognition method and device |
-
2018
- 2018-05-15 CN CN201810461160.4A patent/CN110490179B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3182334A1 (en) * | 2015-12-17 | 2017-06-21 | Xerox Corporation | License plate recognition using coarse-to-fine cascade adaptations of convolutional neural networks |
| CN106407981A (en) * | 2016-11-24 | 2017-02-15 | 北京文安智能技术股份有限公司 | License plate recognition method, device and system |
| CN106960206A (en) * | 2017-02-08 | 2017-07-18 | 北京捷通华声科技股份有限公司 | Character identifying method and character recognition system |
| CN107944450A (en) * | 2017-11-16 | 2018-04-20 | 深圳市华尊科技股份有限公司 | A kind of licence plate recognition method and device |
| CN108009543A (en) * | 2017-11-29 | 2018-05-08 | 深圳市华尊科技股份有限公司 | A kind of licence plate recognition method and device |
| CN107704860A (en) * | 2017-12-06 | 2018-02-16 | 四川知创空间孵化器管理有限公司 | A kind of number-plate number recognition methods |
Non-Patent Citations (2)
| Title |
|---|
| BAOGUANG SHI等: "An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition", 《IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE》 * |
| 贺赛娜: "复杂场景下的中国车牌识别研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111444911A (en) * | 2019-12-13 | 2020-07-24 | 珠海大横琴科技发展有限公司 | Training method and device of license plate recognition model and license plate recognition method and device |
| CN111368645A (en) * | 2020-02-14 | 2020-07-03 | 北京澎思科技有限公司 | Method and device for identifying multi-label license plate, electronic equipment and readable medium |
| CN111310766A (en) * | 2020-03-13 | 2020-06-19 | 西北工业大学 | License plate identification method based on coding and decoding and two-dimensional attention mechanism |
| CN111832568A (en) * | 2020-06-12 | 2020-10-27 | 北京百度网讯科技有限公司 | License plate recognition method, and training method and device of license plate recognition model |
| JP2021119506A (en) * | 2020-06-12 | 2021-08-12 | ベイジン バイドゥ ネットコム サイエンス アンド テクノロジー カンパニー リミテッド | License-number plate recognition method, license-number plate recognition model training method and device |
| JP7166388B2 (en) | 2020-06-12 | 2022-11-07 | ベイジン バイドゥ ネットコム サイエンス テクノロジー カンパニー リミテッド | License plate recognition method, license plate recognition model training method and apparatus |
| CN111832568B (en) * | 2020-06-12 | 2024-01-12 | 北京百度网讯科技有限公司 | License plate recognition method, training method and device of license plate recognition model |
| CN111563504A (en) * | 2020-07-16 | 2020-08-21 | 平安国际智慧城市科技股份有限公司 | License plate recognition method and related equipment |
| CN111563504B (en) * | 2020-07-16 | 2020-10-30 | 平安国际智慧城市科技股份有限公司 | License plate recognition method and related equipment |
| CN112381129A (en) * | 2020-11-10 | 2021-02-19 | 浙江大华技术股份有限公司 | License plate classification method and device, storage medium and electronic equipment |
| CN112418234A (en) * | 2020-11-19 | 2021-02-26 | 北京软通智慧城市科技有限公司 | Method and device for identifying license plate number, electronic equipment and storage medium |
| CN113486885A (en) * | 2021-06-17 | 2021-10-08 | 杭州鸿泉物联网技术股份有限公司 | License plate recognition method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110490179B (en) | 2022-08-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110490179A (en) | Licence plate recognition method, device and storage medium | |
| CN109829456A (en) | Image-recognizing method, device and terminal | |
| CN109086709A (en) | Feature Selection Model training method, device and storage medium | |
| CN110750992B (en) | Named entity recognition method, named entity recognition device, electronic equipment and named entity recognition medium | |
| CN108681729A (en) | Text image antidote, device, storage medium and equipment | |
| CN110490186A (en) | Licence plate recognition method, device and storage medium | |
| CN110377365A (en) | The method and apparatus for showing small routine | |
| CN110807361A (en) | Human body recognition method and device, computer equipment and storage medium | |
| CN110135336A (en) | Training method, device and the storage medium of pedestrian's generation model | |
| CN108304506A (en) | Search method, device and equipment | |
| CN111105788B (en) | Sensitive word score detection method and device, electronic equipment and storage medium | |
| CN108363982A (en) | Determine the method and device of number of objects | |
| CN108806670B (en) | Audio recognition method, device and storage medium | |
| CN109992685A (en) | A kind of method and device of retrieving image | |
| CN109886208A (en) | Method, apparatus, computer equipment and the storage medium of object detection | |
| CN110503159A (en) | Character recognition method, device, equipment and medium | |
| CN110348318A (en) | Image-recognizing method, device, electronic equipment and medium | |
| CN109547847A (en) | Add the method, apparatus and computer readable storage medium of video information | |
| CN113763931A (en) | Waveform feature extraction method and device, computer equipment and storage medium | |
| CN110147796A (en) | Image matching method and device | |
| CN110166275A (en) | Information processing method, device and storage medium | |
| CN110675473B (en) | Method, device, electronic equipment and medium for generating GIF dynamic diagram | |
| CN114691860A (en) | Training method and device of text classification model, electronic equipment and storage medium | |
| CN110377914A (en) | Character identifying method, device and storage medium | |
| CN113591514B (en) | Fingerprint living body detection method, fingerprint living body detection 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |