CN104318226B - Car license recognition equipment parameter setting method and Car license recognition device - Google Patents
Car license recognition equipment parameter setting method and Car license recognition device Download PDFInfo
- Publication number
- CN104318226B CN104318226B CN201410664528.9A CN201410664528A CN104318226B CN 104318226 B CN104318226 B CN 104318226B CN 201410664528 A CN201410664528 A CN 201410664528A CN 104318226 B CN104318226 B CN 104318226B
- Authority
- CN
- China
- Prior art keywords
- car
- parameter
- result
- license recognition
- parameters
- 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.)
- Active
Links
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of car license recognition equipment parameter setting method to include：Obtain effective license plate image detection and recognition result；Gather data related to predefined parameter in the result；The related data of parameters in the predefined parameter are subjected to statistical analysis, and according to the results modification car license recognition equipment parameter of statistical analysis；Revision to the parameter of car license recognition equipment can be automatically performed by this method so that the performance of car license recognition equipment is improved.
Description
Technical field
The present invention relates to image processing field, knows more particularly to a kind of car license recognition equipment parameter setting method and car plate
Other device.
Background technology
With increasing for vehicle, car license recognition equipment has been widely used in parking lot gateway, mall gateway
Deng place；Wherein, due to being limited by hardware resource during actual use, algorithm limitation limits car license recognition equipment
System etc., its performance can only meet it is some under the conditions of can be only achieved pre-provisioning request.
Therefore in order to ensure the performance of car license recognition equipment, when installation at the scene, it typically may require that installation people
Member follows installation rules.The installation rules usually obtains by test for a long time in the lab, then again to installation personnel
Give training, approached with angle when ensuring the angle and development in laboratory of video camera installation.Car license recognition device is in reality simultaneously
Some Mating parameters, such as the full-size of car plate, minimum dimension, Character segmentation template, acquiescence area etc. are had in use.
These parameters typically support the use with algorithm, to improve algorithm performance.
But in actual applications, site environment and application scenarios are ever-changing, and project installation personnel's is horizontal in addition
Uneven, the installation of mistake can cause the verification and measurement ratio of car license recognition equipment and discrimination to decline.More serious situation even goes out
Now the verification and measurement ratio of the equipment of each installation personnel installation and discrimination are different.Project installation personnel because the training time is few,
Or Car license recognition principle is not known about, normally only arrange parameter by rule of thumb, therefore the setting of parameter is not necessarily accurate.It is incorrect
Parameter setting can cause Car license recognition device hydraulic performance decline.
Therefore, the parameter of car license recognition equipment how is revised so that the performance of car license recognition equipment is improved, and is ability
Field technique personnel's technical issues that need to address.
The content of the invention
It is an object of the invention to provide a kind of car license recognition equipment parameter setting method, this method can be automatically performed to car
The revision of the parameter of board identification equipment so that the performance of car license recognition equipment is improved.
Include in order to solve the above technical problems, the present invention provides a kind of car license recognition equipment parameter setting method：
Obtain effective license plate image detection and recognition result；
Gather data related to predefined parameter in the result；
The related data of parameters in the predefined parameter are subjected to statistical analysis, and according to the result of statistical analysis
Change car license recognition equipment parameter.
Wherein, effective license plate image detection is obtained with also including after recognition result：
Count effective license plate image detection and the number of recognition result；
When the number reaches predetermined threshold, data related to predefined parameter in all results are gathered.
Wherein, the whether effective standard of result that the car plate is detected and identified includes：
The number of the character recognized is as character number in car plate；
And/or the confidence level of the character in car plate on each correspondence position meets predetermined value；
And/or the summation after the confidence level superposition of the character in car plate on each correspondence position reaches threshold value.
Wherein, the related data by parameters in predefined parameter, which carry out statistical analysis, includes：
The related data of parameters in predefined parameter are counted；
It is determined that the registration and scope of the data after statistics；
Analyzed using the registration and scope of the related data of parameters by the analysis rule of parameters,
Obtain statistic analysis result.
Wherein, it is described to obtain effective license plate image detection with also including before recognition result：
License plate image is gathered according to pre-defined rule；
The license plate image collected is detected and identified.
Wherein, the results modification car license recognition equipment parameter according to statistical analysis includes：
The numerical value of parameters in predefined parameter is determined according to the result of statistical analysis；
By the numerical value compared with the numerical value of the parameters before statistical analysis；
When comparative result is different, the numerical value of the parameter is changed.
A kind of Car license recognition device provided by the present invention includes：Acquisition module, acquisition module, modified module, wherein,
Acquisition module, for obtaining effective license plate image detection and recognition result；
Acquisition module, for gathering data related to predefined parameter in the result；
Modified module, for the related data of parameters in predefined parameter to be carried out into statistical analysis, and according to statistics
The results modification car license recognition equipment parameter of analysis.
Wherein, Car license recognition device also includes counting module, wherein,
Counting module, for counting effective license plate image detection and the number of recognition result, when the number reaches pre-
When determining threshold value, data related to predefined parameter in all results are gathered.
Wherein, the acquisition module includes：
Collecting unit, for gathering data related to predefined parameter in the result.
Wherein, the modified module includes：Statistic unit, analytic unit, unit is changed, wherein,
Statistic unit, for the related data of parameters in predefined parameter to be counted, it is determined that the number after statistics
According to registration and scope；
Analytic unit, the analysis rule for passing through parameters using the registration and scope of the related data of parameters
Analyzed, obtain statistic analysis result；
Unit is changed, according to the results modification car license recognition equipment parameter of statistical analysis.
Car license recognition equipment parameter setting method provided by the present invention, obtain effective license plate image detection and tied with identification
Fruit；Gather data related to predefined parameter in the result；The related data of parameters in the predefined parameter are entered
Row statistical analysis, and according to the results modification car license recognition equipment parameter of statistical analysis；By car license recognition equipment to collecting
License plate image detected and identified, obtain the detection of effective license plate image and recognition result, and gather in effective result with
The related data of predefined parameter；Statistical analysis is carried out to the related data of parameters in predefined parameter, can be detected
The right setting numerical value of the parameter corresponding with the data that recognition effect is good, is repaiied to the parameter of original car license recognition equipment
Change, to ensure the performance of car license recognition equipment；This method can be automatically performed the revision to the parameter of car license recognition equipment so that
The performance of car license recognition equipment is improved, and can adapt to various actual environments.
Brief description of the drawings
, below will be to embodiment or existing for the clearer explanation embodiment of the present invention or the technical scheme of prior art
The required accompanying drawing used is briefly described in technology description, it should be apparent that, drawings in the following description are only this hair
Some bright embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can be with root
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is the flow chart of car license recognition equipment parameter setting method provided in an embodiment of the present invention；
Fig. 2 is that the related data provided in an embodiment of the present invention by parameters in predefined parameter carry out statistical analysis
The flow chart of method；
Fig. 3 is the flow chart of the method for modification car license recognition equipment parameter provided in an embodiment of the present invention；
Fig. 4 is the structured flowchart of Car license recognition device provided in an embodiment of the present invention；
Fig. 5 is the structured flowchart of another Car license recognition device provided in an embodiment of the present invention；
Fig. 6 is the structured flowchart of acquisition module provided in an embodiment of the present invention；
Fig. 7 is the structured flowchart of modified module provided in an embodiment of the present invention.
Embodiment
It is an object of the invention to provide a kind of car license recognition equipment parameter setting method, this method can be automatically performed to car
The revision of the parameter of board identification equipment so that the performance of car license recognition equipment is improved.
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
Part of the embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
The method of the present invention can the operational mode based on video flowing, the vehicle image that collects is carried out car plate detection with
Identification.
Fig. 1 is refer to, Fig. 1 is the flow chart of car license recognition equipment parameter setting method provided in an embodiment of the present invention；Should
Method can include：
Step s100, effective license plate image detection and recognition result are obtained；
Wherein, car license recognition equipment is detected to the vehicle image of acquisition, identified here, is tied when obtaining detection with identification
During fruit, judge whether the recognition result is effective, because modifying, setting to the parameter of car license recognition equipment according to these results
It is fixed, to improve the performance of car license recognition equipment, therefore effective result can only be acquired.
Step s110, data related to predefined parameter in the result are gathered；
Wherein, the result that car license recognition equipment is detected and identified to license plate image includes many information, is not to need
Information all in the result is extracted, simply before extraction gathers, the pre-set parameter for needing to detect, if
Only need to be acquired the data of predefined parameter after setting, such as the ginseng to car plate size is only needed under the parking lot environment
Number is detected, and whether see needs to be modified it, as long as therefore with regard to extracting the data relevant with car plate size parameter.
Here the difference that the species of predefined parameter can be according to actual conditions or the specific setting of different progress with scene are
Can.
Wherein, the parameter that can be collected here can include：The size of car plate, the ratio of width to height of car plate, the fortune of car plate
Row track, acquiescence province and area etc..
Step s120, the related data of parameters in the predefined parameter are subjected to statistical analysis, and according to statistics
The results modification car license recognition equipment parameter of analysis.
Wherein, the data being collected into parameters in predefined parameter in step s110 are subjected to statistical analysis, wherein
The method that the data being collected into every class predefined parameter are carried out with statistical analysis can be set in advance, be not every kind of parameter
Statistical analysis technique be all consistent, simply general direction can carry out a weight to the corresponding data that collect
Right statistics, the statistics of quantity, the statistics of number range；It is specific how to be analyzed and processed according to obtained data, also need
Advance program setting is carried out according to the meaning and actual conditions of every kind of parameter.Processor can utilize relative under every kind of parameter
The analysis program answered is analyzed according to the data collected；Modified afterwards using statistic analysis result, set Car license recognition
Device parameter.
Such as in the size of car plate car plate width parameter, current car plate grader typically all using draw window search for
Mode, the car plate grader of AdaBoost Algorithm for Training is such as used, is typically scanned for using more sizes, multiple dimensioned window.Such as
Fruit not can determine that the size of car plate size, and system can carry out a large amount of futile searches, and lose time.Can be monitoring in the present invention
Picture is by three regions are highly divided equally into, wherein certain overlapping region be present in three regions, then for these three
Region counts occurring and identifies the minimum widith and Breadth Maximum of successful car plate respectively, and minimum widith is reduced
10% start width as the search in the region, Breadth Maximum is expanded the 10% termination width as the search in the region.
Detection obtains the width of the car plate, the position then occurred by car plate, selects the car plate category with identifying a successfully car plate every time
In which region, with the minimum car plate width in the region compared with maximum car plate width.If smaller than minimum car plate width,
Change minimum car plate width.If bigger than maximum car plate width, maximum car plate width is changed.
Wherein, the other specification such as the ratio of width to height of car plate has the statistics of oneself as the parameter of car plate width in the size of car plate
Analysis rule, such as minimum widith is reduced 10% start width as the search in the region, Breadth Maximum is expanded 10%
Termination width as the search in the region.And the knot of statistical analysis can be utilized according to the statistical analysis rule of corresponding parameter
Fruit carries out the modification of relevant parameter, such as selects which region the car plate belongs to, minimum car plate width and maximum with the region
Car plate width is compared.If smaller than minimum car plate width, minimum car plate width is changed.If bigger than maximum car plate width,
Change maximum car plate width.
Based on above-mentioned technical proposal, the embodiment of the present invention provides a kind of car license recognition equipment parameter setting method, passes through car
Board identification equipment is detected and identified to the license plate image collected, obtains effective license plate image detection and recognition result,
And gather data related to predefined parameter in effective result；The related data of parameters in predefined parameter are counted
Analysis, it can obtain detecting the parameter right setting numerical value corresponding with the data that recognition effect is good, to original Car license recognition
The parameter of equipment is modified, to ensure the performance of car license recognition equipment；This method can be automatically performed to car license recognition equipment
Parameter revision so that the performance of car license recognition equipment is improved, and can adapt to various actual environments.
Optionally, effective license plate image detection is obtained with also including after recognition result：
Count effective license plate image detection and the number of recognition result；
When the number reaches predetermined threshold, data related to predefined parameter in all results are gathered.
Wherein, effective license plate image detection can also obtained with after recognition result, counting effective license plate image inspection
Survey the number with recognition result；License plate image detection is counted with identifying effective number；It can utilize in car license recognition equipment
Processor in counter counted；When occurring effective and counting to predetermined threshold, capture program is called to be acquired
The data related to predefined parameter in all results.
Car license recognition equipment can so be caused when carrying out parameter revision setting, it is more efficient, it is not necessary to every time right
One result is modified, and can also have the problem of too frequent like that, it is preferred that can set a threshold value, work as license plate image
When detection is with identifying that effective number reaches threshold value, then data related to predefined parameter in all results are being acquired,
Effect can be more preferable, namely the accumulation for allowing car license recognition equipment to carry out a period of time, also quite with to preceding once modification, arrange parameter
The checking that effect afterwards is carried out, when sample size reaches certain numerical value, statistical analysis is being carried out, can more may had
The data of meaning, also reduce influence of the deviation data to overall data.
Optionally, the whether effective standard of result that the car plate is detected and identified can include：
The number of the character recognized is as character number in car plate；
And/or the confidence level of the character in car plate on each correspondence position meets predetermined value；
And/or the summation after the confidence level superposition of the character in car plate on each correspondence position reaches threshold value.
Wherein, according to the needs of actual conditions, i.e., actual conditions are detected and identified to the height of parameter request, car plate
The whether effective standard of the result number of character that can include recognizing as character number in car plate, i.e., in China just
The number of normal characters on license plate should be 7, therefore when the number of the character recognized is 7, can calculate car plate detection with knowing
Other result is effective；
The confidence level of character either in car plate on each correspondence position meets predetermined value, because the word in Chinese car plate
Symbol is typically all that English alphabet and numeral form by Chinese character, because their complexity and number species are all different, because
This, their confidence level can also have differences, and due to carrying out character recognition using characters on license plate grader, be used in training process
The training method of support vector machines, therefore the result of each character recognition has a confidence level；The Chinese character in the case of
Confidence level is lower with the confidence level of numeral than English alphabet, therefore when the confidence level of the character in car plate on each correspondence position expires
During sufficient predetermined value, car plate detection can be calculated and the result of identification is effective；
Summation after the confidence level superposition of character either in car plate on each correspondence position reaches threshold value, when in car plate
When summation after the confidence level superposition of character on each correspondence position reaches threshold value, car plate detection and the result of identification can be calculated
Effectively；
Wherein, car plate detection here can also be each of above-mentioned several situations with the whether effective standard of result identified
Kind combination, it is possibility to have other standards, these can be determined according to actual conditions.
Optionally, refer to Fig. 2, Fig. 2 be it is provided in an embodiment of the present invention by predefined parameter parameters it is related
Data carry out the flow chart of the method for statistical analysis；This method can include：
Step s200, the related data of parameters in predefined parameter are counted；
Wherein, the related data of parameters are counted in predefined parameter, and statistics here can be concluded
Statistics, namely integrated.
Step s210, the registration and scope of the data after statistics are determined；
Wherein, some numerical value, such as a data area occupied by all data after data statistics, will can be obtained,
It can be the registration of each data, can be the percentage of each data, can be the confidential interval of data, wait and pass through statistics
The overlapping interval and range intervals that each data obtain.
Step s220, using parameters related data registration and the scope analysis rule that passes through parameters
Analyzed, obtain statistic analysis result.
Wherein, using gained parameters related data registration and scope, pass through the analysis of parameters
To the use of these registrations and scope in rule, statistic analysis result namely modification result are obtained, utilizes the statistical analysis knot
Fruit can carry out the modification of car license recognition equipment parameter.
Such as the size (the mainly width of car plate) of car plate：What current car plate grader was typically all searched for using stroke window
Mode, such as the car plate grader using cascade calculation AdaBoost Algorithm for Training, are typically entered using more sizes, multiple dimensioned window
Row search.If uncertain car plate size, system can carry out a large amount of futile searches, and lose time.The present invention is proposed monitoring
Picture is by three regions are highly divided equally into, wherein three regions can have certain overlapping region, then for these three
Region counts occurring and identifies the minimum widith and Breadth Maximum of successful car plate respectively, and minimum widith is reduced
10% start width as the search in the region, Breadth Maximum is expanded the 10% termination width as the search in the region.
Detect every time and identify a successfully car plate, obtain the width of the car plate, the position then occurred by car plate, select the car plate category
In which region, with the minimum car plate width in the region compared with maximum car plate width.If smaller than minimum car plate width,
Change minimum car plate width.If bigger than maximum car plate width, maximum car plate width is changed.
Wherein, overlapping region is found here with the registration in statistics, car plate is found according to the scope of data
Minimum widith and Breadth Maximum, reduce 10% by the analysis rule of these data and this parameter namely minimum widith
As the start width of the search in the region, Breadth Maximum is expanded the 10% termination width as the search in the region；Can be with
Utilize the modification of the width of these progress car plates.
The ratio of width to height of car plate：At present because video camera installation has certain angle, therefore car plate is in whole monitor area
The ratio of width to height can have certain difference.Such as car plate away from video camera when, car plate the ratio of width to height is larger, car plate close to shooting
When machine, car plate the ratio of width to height is smaller.So if using only the car plate grader of a size, some regions are likely to result in
It is poor to detect car plate effect.Therefore for the aspect ratio parameter of the car plate grader of multiple sizes, in car plate away from shooting
The region of machine uses the car plate grader of normal rates, in car plate using the larger car plate grader of the ratio of width to height in intermediate region
The less car plate grader of the ratio of width to height is used close to the region of video camera.Equipment can be first by mark when just start-up operation
Accurate car plate grader carries out car plate detection, after detecting and identifying a successfully car plate, obtains the ratio of width to height of the car plate.Counting
After a number of effectively license plate recognition result, it is possible to determine the smaller car plate grader of the ratio of width to height, normal car plate grader
And the use range of the larger car plate grader of the ratio of width to height.Such as 1/4 region uses the larger car plate of the ratio of width to height in monitor area
Grader, 1/4 to 3/4 region use high car plate grader of positive constant width etc..According to the ratio of width to height of the car plate of acquisition in follow-up use
Finely tune the use range of car plate grader.
Wherein, here also with the acquisition the ratio of width to height i.e. scope in detecting and identifying successfully car plate, and obtain successfully
Scope be registration, can determine the smaller car plate grader of the ratio of width to height, normal car plate grader and the ratio of width to height by these
The use range of larger car plate grader；Therefore the various high car plates of width point can be obtained according to above range and registration again
The use range of class device.
The running orbit of car plate：The system used at present can typically set car plate detection region to reduce resource.Car plate
Detection zone is usually that staff is determined in client software by setting-out.But in actual use, the position that car plate occurs
A part for defined area may only be accounted for by being equipped with, and it is possible to be appeared in outside defined area.System is by counting each effective
The appearance position of car plate is identified, obtains the running orbit of each car plate, the position then occurred according to car plate determines that car plate may
The region of appearance.Then the region comprising car plate is suitably extended out as car plate detection region.And constantly adjusted in follow-up use
The region that vehicle board is likely to occur, so as to realize more preferable recognition effect.
Wherein, the position occurred here according to car plate determines that the region that car plate is likely to occur is used in effective result
The scope of the running orbit of car plate, use this to change running orbit parameter, i.e., the region that constantly adjustment car plate is likely to occur.
Give tacit consent to province and area：Because the discrimination of the Chinese character on car plate is typically relatively low, in general cell gateway, come from
Ratio shared by the vehicle of this province can typically be up to more than 95%.For the Chinese character that identification is difficult, acquiescence province can be used
Chinese character substitutes.If province is malfunctioned when gateway information matches are carried out, 6 characters below or numeral can be passed through
Matched.Or made a distinction by other additional information.Car license recognition device can be by counting all car plates occurred
Province information, automatic setting acquiescence province.Simultaneously can also be by counting the regional number occurred, setting acquiescence area.
Wherein, here by appearance province data registration come carry out give tacit consent to province and area setting and repair
Change.
Accordingly, it can be seen that by predefined parameter in the effective result of a large amount of car plate detections parameters it is related
Data are counted, and obtain registration and scope, and utilize the analysis rule under parameters and obtained registration and model
Enclose and analyzed, determine the modification of corresponding parameter；Pass through the representative detection performance of each parameter of modification of parameter
It is improved, hence in so that the performance of car license recognition equipment is greatly improved, and because car license recognition equipment has ginseng
Several functions of being automatically analyzed according to actual conditions, changed automatically, it is not necessary to manual intervention, therefore to the adaptability of environment
It is improved, the change of site environment can be rapidly adapted to.
Optionally, it is described to obtain effective license plate image detection with also including before recognition result：
License plate image is gathered according to pre-defined rule；
The license plate image collected is detected and identified.
Wherein, because car license recognition equipment is during Car license recognition is carried out, vehicle can not be static state, Ke Yishi
Vehicle in traveling.Therefore in order to improve efficiency of the car license recognition equipment to Car license recognition, it is not necessary to each frame collected
Image will be detected and identified.Due to may be representated by continuous frame the information such as vehicle location be substantially it is constant, that
Just occur that the corresponding vehicle image to a position is handled many times, so the same image is repeatedly located
Comprehending reduces the efficiency of image procossing.
Therefore, license plate image can be gathered according to pre-defined rule, such as an image can be gathered every a frame, and to adopting
The license plate image collected is detected and identified, can also in the light of actual conditions carry out gathering an image every predetermined frame, and
The license plate image collected is detected and identified.
By the above method, collection image parameter can be flexibly set so that car license recognition equipment operating efficiency is higher.
Optionally, Fig. 3 is refer to, Fig. 3 is the method for modification car license recognition equipment parameter provided in an embodiment of the present invention
Flow chart；This method can include：
Step s300, the numerical value of parameters in predefined parameter is determined according to the result of statistical analysis；
Wherein, such as the registrations of the data in the province that passes through appearance give tacit consent to the setting in province and area and repaiied
Change.Such as the number that Shaanxi Province occurs in the province of appearance is up to 98%, then by the result of statistical analysis, Shaanxi Province occurs
Number account for the 98% of all detection car plates, wherein, and if in all detection car plates or detection and all Shaanxi for recognizing
It is 90% to save the ratio in car plate shared by Xi'an；It can so determine that it should be Xian District, Shanxi Province to give tacit consent to province and give tacit consent to area
City.
Step s310, by the numerical value compared with the numerical value of the parameters before statistical analysis；
Wherein it is possible to the acquiescence province and acquiescence area that are obtained according to statistic analysis result and the acquiescence province set before
It is compared with acquiescence area.
Step s320, when comparative result is different, the numerical value of the parameter is changed.
Wherein, according to this comparative result, when inconsistent, acquiescence province can be set or changed as Shaanxi Province；Can
With Xi'an that the parameter for giving tacit consent to area is modified or is set as.
Based on above-mentioned technical proposal, car license recognition equipment parameter setting method provided in an embodiment of the present invention, pass through car plate
Identification equipment detected and identified to the license plate image collected by pre-defined rule, can improve operating efficiency, during saving
Between；Obtain the detection of effective license plate image and recognition result, when effective recognition result reaches threshold value, gather in effective result with
The related data of predefined parameter；The degree of accuracy of car license recognition equipment parameter revision is so improved, modification number is reduced, to predetermined
The related data of parameters carry out statistical analysis in parameter, and it is corresponding with the data that recognition effect is good can to obtain detection
The right setting numerical value of parameter, modifies to the parameter of original car license recognition equipment, to ensure the performance of car license recognition equipment；
This method can be automatically performed the revision to the parameter of car license recognition equipment so that and the performance of car license recognition equipment is improved,
And it can adapt to various actual environments.
, can be automatically complete by the above method the embodiments of the invention provide car license recognition equipment parameter setting method
The revision of the parameter of paired car license recognition equipment so that the performance of car license recognition equipment is improved.
Car license recognition device provided in an embodiment of the present invention is introduced below, Car license recognition device described below with above
The car license recognition equipment parameter setting method of description can be mutually to should refer to.
Fig. 4 is refer to, Fig. 4 is the structured flowchart of Car license recognition device provided in an embodiment of the present invention；The Car license recognition device can
With including：Acquisition module 100, acquisition module 200, modified module 300, wherein,
Acquisition module 100, for obtaining effective license plate image detection and recognition result；
Acquisition module 200, for gathering data related to predefined parameter in the result；
Modified module 300, for the related data of parameters in predefined parameter to be carried out into statistical analysis, and according to system
Count the results modification car license recognition equipment parameter of analysis.
Optionally, Fig. 5 is refer to, Fig. 5 is the structured flowchart of another Car license recognition device provided in an embodiment of the present invention；The car
Board identifier can also include：Counting module 400, for counting effective license plate image detection and the number of recognition result, when
When the number reaches predetermined threshold, data related to predefined parameter in all results are gathered.
Optionally, Fig. 6 is refer to, Fig. 6 is the structured flowchart of acquisition module provided in an embodiment of the present invention；Acquisition module
200 can include：
Collecting unit 210, for gathering data related to predefined parameter in the result.
Optionally, Fig. 7 is refer to, Fig. 7 is the structured flowchart of modified module provided in an embodiment of the present invention；Modified module
300 can include：Statistic unit 310, analytic unit 320, unit 330 is changed, wherein,
Statistic unit 310, for the related data of parameters in predefined parameter to be counted, it is determined that after statistics
The registration and scope of data；
Analytic unit 320, the analysis for passing through parameters using the registration and scope of the related data of parameters
Rule is analyzed, and obtains statistic analysis result；
Unit 330 is changed, according to the results modification car license recognition equipment parameter of statistical analysis.
The embodiments of the invention provide Car license recognition device, be able to can be automatically performed to car plate by above-mentioned Car license recognition device
The revision of the parameter of identification equipment so that the performance of car license recognition equipment is improved.
Each embodiment is described by the way of progressive in specification, and what each embodiment stressed is and other realities
Apply the difference of example, between each embodiment identical similar portion mutually referring to.For device disclosed in embodiment
Speech, because it is corresponded to the method disclosed in Example, so description is fairly simple, related part is referring to method part illustration
.
Professional further appreciates that, with reference to the unit of each example of the embodiments described herein description
And algorithm steps, can be realized with electronic hardware, computer software or the combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software, the composition and step of each example are generally described according to function in the above description.These
Function is performed with hardware or software mode actually, application-specific and design constraint depending on technical scheme.Specialty
Technical staff can realize described function using distinct methods to each specific application, but this realization should not
Think beyond the scope of this invention.
Directly it can be held with reference to the step of method or algorithm that the embodiments described herein describes with hardware, processor
Capable software module, or the two combination are implemented.Software module can be placed in random access memory (RAM), internal memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
Detailed Jie has been carried out to car license recognition equipment parameter setting method provided by the present invention and Car license recognition device above
Continue.Specific case used herein is set forth to the principle and embodiment of the present invention, and the explanation of above example is only
It is the method and its core concept for being used to help understand the present invention.It should be pointed out that for those skilled in the art
For, under the premise without departing from the principles of the invention, some improvement and modification can also be carried out to the present invention, these improve and repaiied
Decorations are also fallen into the protection domain of the claims in the present invention.
Claims (6)
- A kind of 1. car license recognition equipment parameter setting method, it is characterised in that including：Obtain effective license plate image detection and recognition result；Gather data related to predefined parameter in the result；The related data of parameters in the predefined parameter are subjected to statistical analysis, and according to the results modification of statistical analysis Car license recognition equipment parameter；The related data of parameters in the predefined parameter are carried out into statistical analysis includes：The related data of parameters in predefined parameter are counted；It is determined that the registration and scope of the data after statistics；Analyzed, obtained by the analysis rule of parameters using the registration and scope of the related data of parameters Statistic analysis result；Effective license plate image detection is obtained with also including after recognition result：Count effective license plate image detection and the number of recognition result；When the number reaches predetermined threshold, data related to predefined parameter in all results are gathered.
- 2. car license recognition equipment parameter setting method as claimed in claim 1, it is characterised in that license plate image detection with The whether effective standard of recognition result includes：The number of the character recognized is as character number in car plate；And/or the confidence level of the character in car plate on each correspondence position meets predetermined value；And/or the summation after the confidence level superposition of the character in car plate on each correspondence position reaches threshold value.
- 3. car license recognition equipment parameter setting method as claimed in claim 1, it is characterised in that described to obtain effective car plate Image detection before recognition result with also including：License plate image is gathered according to pre-defined rule；The license plate image collected is detected and identified.
- 4. car license recognition equipment parameter setting method as claimed in claim 1, it is characterised in that described according to statistical analysis Results modification car license recognition equipment parameter includes：The numerical value of parameters in predefined parameter is determined according to the result of statistical analysis；By the numerical value compared with the numerical value of the parameters before statistical analysis；When comparative result is different, the numerical value of the different corresponding parameter of comparative result in car license recognition equipment parameter is changed.
- A kind of 5. Car license recognition device, it is characterised in that including：Acquisition module, acquisition module, modified module, wherein,Acquisition module, for obtaining effective license plate image detection and recognition result；Acquisition module, for gathering data related to predefined parameter in the result；Modified module, for the related data of parameters in predefined parameter to be carried out into statistical analysis, and according to statistical analysis Results modification car license recognition equipment parameter；The modified module includes：Statistic unit, analytic unit, unit is changed, wherein,Statistic unit, for the related data of parameters in predefined parameter to be counted, it is determined that the data after statistics Registration and scope；Analytic unit, carried out using the registration and scope of the related data of parameters by the analysis rule of parameters Analysis, obtains statistic analysis result；Unit is changed, according to the results modification car license recognition equipment parameter of statistical analysis；Also include counting module, wherein,Counting module, for counting effective license plate image detection and the number of recognition result, when the number reaches predetermined threshold During value, data related to predefined parameter in all results are gathered.
- 6. Car license recognition device as claimed in claim 5, it is characterised in that the acquisition module includes：Collecting unit, for gathering data related to predefined parameter in the result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410664528.9A CN104318226B (en) | 2014-11-19 | 2014-11-19 | Car license recognition equipment parameter setting method and Car license recognition device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410664528.9A CN104318226B (en) | 2014-11-19 | 2014-11-19 | Car license recognition equipment parameter setting method and Car license recognition device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104318226A CN104318226A (en) | 2015-01-28 |
| CN104318226B true CN104318226B (en) | 2018-01-09 |
Family
ID=52373455
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410664528.9A Active CN104318226B (en) | 2014-11-19 | 2014-11-19 | Car license recognition equipment parameter setting method and Car license recognition device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104318226B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106991420A (en) * | 2017-03-27 | 2017-07-28 | 新智认知数据服务有限公司 | A kind of detection method of license plate of the license plate area regression technique based on piecemeal |
| CN109559522B (en) * | 2019-01-21 | 2021-09-28 | 熵基科技股份有限公司 | Debugging method, telescopic upright post, camera and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101184168A (en) * | 2007-12-20 | 2008-05-21 | 四川川大智胜软件股份有限公司 | License plate luminance contrast based camera shutter and gain composite control method |
| CN101196989A (en) * | 2007-10-11 | 2008-06-11 | 北京海鑫科金高科技股份有限公司 | Network built-in type multiplex license plate detecting system and method thereof |
| CN202003409U (en) * | 2011-04-19 | 2011-10-05 | 淮阴工学院 | License plate positioning device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102214290B (en) * | 2010-04-12 | 2013-03-20 | 无锡科利德斯科技有限公司 | License plate positioning method and license plate positioning template training method |
| CN103841313A (en) * | 2012-11-27 | 2014-06-04 | 华为技术有限公司 | Pan-tilt camera control method, system and device |
-
2014
- 2014-11-19 CN CN201410664528.9A patent/CN104318226B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101196989A (en) * | 2007-10-11 | 2008-06-11 | 北京海鑫科金高科技股份有限公司 | Network built-in type multiplex license plate detecting system and method thereof |
| CN101184168A (en) * | 2007-12-20 | 2008-05-21 | 四川川大智胜软件股份有限公司 | License plate luminance contrast based camera shutter and gain composite control method |
| CN202003409U (en) * | 2011-04-19 | 2011-10-05 | 淮阴工学院 | License plate positioning device |
Non-Patent Citations (1)
| Title |
|---|
| 汉字图像识别机研究;黄冉;《中国优秀博硕士学位论文全文数据库（硕士）信息科技辑》;20060815(第08期);第20页2.5节、41-42页4.3节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104318226A (en) | 2015-01-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10896349B2 (en) | Text detection method and apparatus, and storage medium | |
| CN107943954B (en) | Method and device for detecting webpage sensitive information and electronic equipment | |
| EP2891990A1 (en) | Method and device for monitoring video digest | |
| CN110458126B (en) | Pantograph state monitoring method and device | |
| CN110879951A (en) | Motion foreground detection method and device | |
| US10271018B2 (en) | Method of detecting critical objects from CCTV video using metadata filtering | |
| CN107016298B (en) | Webpage tampering monitoring method and device | |
| WO2019169760A1 (en) | Test case range determining method, device, and storage medium | |
| US20180349468A1 (en) | Log analysis system, log analysis method, and log analysis program | |
| CN111127508B (en) | Target tracking method and device based on video | |
| CN113343779B (en) | Environment abnormality detection method, device, computer equipment and storage medium | |
| JP6936961B2 (en) | Information providing device, terminal, identity verification system, information providing method and program | |
| CN110866515A (en) | Method and device for identifying object behaviors in plant and electronic equipment | |
| CN105303442A (en) | Online bank account number detection method and apparatus | |
| CN106301979B (en) | Method and system for detecting abnormal channel | |
| CN106778277A (en) | Malware detection methods and device | |
| CN104318226B (en) | Car license recognition equipment parameter setting method and Car license recognition device | |
| CN115830002A (en) | Infrared image quality evaluation method and device | |
| CN111488847A (en) | System, method and terminal for acquiring sports game video goal segment | |
| CN105447863A (en) | Residue detection method based on improved VIBE | |
| CN110808995A (en) | Safety protection method and device | |
| CN110992299B (en) | Method and device for detecting browser compatibility | |
| CN111460198B (en) | Picture timestamp auditing method and device | |
| CN109426826A (en) | User behavior analysis method and apparatus | |
| CN109409091B (en) | Method, device and equipment for detecting Web page and computer storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |