CN104318226A - License plate recognition device parameter setting method and license plate recognizer - Google Patents
License plate recognition device parameter setting method and license plate recognizer Download PDFInfo
- Publication number
- CN104318226A CN104318226A CN201410664528.9A CN201410664528A CN104318226A CN 104318226 A CN104318226 A CN 104318226A CN 201410664528 A CN201410664528 A CN 201410664528A CN 104318226 A CN104318226 A CN 104318226A
- Authority
- CN
- China
- Prior art keywords
- car
- result
- parameter
- 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.)
- Granted
Links
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a license plate recognition device parameter setting method. The method includes the steps that an effective license plate image detection and recognition result is acquired; data relevant to preset parameters in the result are acquired; relevant data of various parameters in the preset parameters are subjected to statistics analysis, and license plate recognition device parameters are modified according to the statistics analysis result; through the method, the license plate recognition device parameters can be automatically revised, and the performance of a license plate recognition device is improved.
Description
Technical field
The present invention relates to image processing field, particularly relate to a kind of Car license recognition apparatus parameter setting method and Car license recognition device.
Background technology
Along with increasing of vehicle, the places such as Car license recognition equipment has been widely used in gateway, parking lot, mall gateway; Wherein, owing to being subject to the restriction of hardware resource in the process that Car license recognition equipment uses in reality, algorithm limitation restriction etc., its performance just can only can reach pre-provisioning request meeting under some condition.
Therefore, in order to ensure the performance of Car license recognition equipment, when carrying out at the scene installing, generally can require that installation personnel follows installation rules.This installation rules is generally obtain through long-time test, and then give training installation personnel in the lab, close with angle when guaranteeing the angle that video camera is installed and development in laboratory.Car license recognition device has some Mating parameters, the full-size of such as car plate, minimum dimension, Character segmentation template in actual use simultaneously, acquiescence area etc.General and the algorithm of these parameters supports the use, to improve algorithm performance.
But in actual applications, site environment and application scenarios ever-changing, the level of project installation personnel is also uneven in addition, and the installation of mistake can cause the verification and measurement ratio of Car license recognition equipment and discrimination to decline.More serious situation even occur the verification and measurement ratio of the equipment that each installation personnel is installed and discrimination different.Project installation personnel are few due to the training time, or do not understand Car license recognition principle, generally only parameters by rule of thumb, and therefore the setting of parameter is not necessarily accurate.Incorrect optimum configurations can cause Car license recognition device hydraulic performance decline.
Therefore, how revising the parameter of Car license recognition equipment, the performance of Car license recognition equipment is improved, is those skilled in the art's technical issues that need to address.
Summary of the invention
The object of this invention is to provide a kind of Car license recognition apparatus parameter setting method, the method can complete the revision of the parameter to Car license recognition equipment automatically, and the performance of Car license recognition equipment is improved.
For solving the problems of the technologies described above, the invention provides a kind of Car license recognition apparatus parameter setting method and comprising:
Obtain effective license plate image detection and indentification result;
Gather data relevant to preset parameter in described result;
The relevant data of parameters in described preset parameter are carried out statistical study, and according to the results modification Car license recognition device parameter of statistical study.
Wherein, also comprise after obtaining effective license plate image detection and indentification result:
Add up the number of effective license plate image detection and indentification result;
When described number reaches predetermined threshold, gather data relevant to preset parameter in all results.
Wherein, described car plate carry out detection and indentification result whether effective standard comprise:
The number of the character recognized is the same with character number in car plate;
And/or the degree of confidence of character in car plate on each correspondence position meets predetermined value;
And/or the summation after the degree of confidence superposition of character in car plate on each correspondence position reaches threshold value.
Wherein, the described relevant data by parameters in preset parameter are carried out statistical study and are comprised:
The relevant data of parameters in preset parameter are added up;
Determine registration and the scope of the data after adding up;
Utilize the registration of the relevant data of parameters and scope to be analyzed by the analysis rule of parameters, obtain statistic analysis result.
Wherein, also comprise before described acquisition effective license plate image detection and indentification result:
License plate image is gathered according to pre-defined rule;
Detection and indentification is carried out to the license plate image collected.
Wherein, the described results modification Car license recognition device parameter according to statistical study comprises:
According to the numerical value of parameters in the result determination preset parameter of statistical study;
The numerical value of the parameters before described numerical value and statistical study is compared;
When comparative result is different, revise the numerical value of this parameter.
A kind of Car license recognition device provided by the present invention comprises: acquisition module, acquisition module, modified module, wherein,
Acquisition module, for obtaining effective license plate image detection and indentification result;
Acquisition module, for gathering data relevant to preset parameter in described result;
Modified module, for carrying out statistical study by the relevant data of parameters in preset parameter, and according to the results modification Car license recognition device parameter of statistical study.
Wherein, Car license recognition device also comprises counting module, wherein,
Counting module, for adding up the number of effective license plate image detection and indentification result, when described number reaches predetermined threshold, gathers data relevant to preset parameter in all results.
Wherein, described acquisition module comprises:
Collecting unit, for gathering data relevant to preset parameter in described result.
Wherein, described modified module comprises: statistic unit, analytic unit, amendment unit, wherein,
Statistic unit, for the relevant data of parameters in preset parameter being added up, determines registration and the scope of the data after adding up;
Analytic unit, is utilized the registration of the relevant data of parameters and scope to be analyzed by the analysis rule of parameters, obtains statistic analysis result;
Amendment unit, according to the results modification Car license recognition device parameter of statistical study.
Car license recognition apparatus parameter setting method provided by the present invention, obtains effective license plate image detection and indentification result; Gather data relevant to preset parameter in described result; The relevant data of parameters in described preset parameter are carried out statistical study, and according to the results modification Car license recognition device parameter of statistical study; By Car license recognition equipment, detection and indentification is carried out to the license plate image collected, obtain effective license plate image detection and indentification result, and gather data relevant to preset parameter in effective result; Statistical study is carried out to the relevant data of parameters in preset parameter, can obtain that the corresponding parameter of the effective data of detection and indentification is right arranges numerical value, the parameter of original car plate identification equipment is modified, to ensure the performance of Car license recognition equipment; The method can complete the revision of the parameter to Car license recognition equipment automatically, the performance of Car license recognition equipment is improved, and can adapts to various actual environment.
Accompanying drawing explanation
In order to the technical scheme of the clearer explanation embodiment of the present invention or prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
The process flow diagram of the Car license recognition apparatus parameter setting method that Fig. 1 provides for the embodiment of the present invention;
The process flow diagram relevant data of parameters in preset parameter being carried out the method for statistical study that Fig. 2 provides for the embodiment of the present invention;
The process flow diagram of the method for the amendment Car license recognition device parameter that Fig. 3 provides for the embodiment of the present invention;
The structured flowchart of the Car license recognition device that Fig. 4 provides for the embodiment of the present invention;
The structured flowchart of another Car license recognition device that Fig. 5 provides for the embodiment of the present invention;
The structured flowchart of the acquisition module that Fig. 6 provides for the embodiment of the present invention;
The structured flowchart of the modified module that Fig. 7 provides for the embodiment of the present invention.
Embodiment
The object of this invention is to provide a kind of Car license recognition apparatus parameter setting method, the method can complete the revision of the parameter to Car license recognition equipment automatically, and the performance of Car license recognition equipment is improved.
For making the object of the embodiment of the present invention, technical scheme and advantage clearly, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
Method of the present invention based on the operational mode of video flowing, can carry out car plate detection and indentification to the vehicle image collected.
Please refer to Fig. 1, the process flow diagram of the Car license recognition apparatus parameter setting method that Fig. 1 provides for the embodiment of the present invention; The method can comprise:
Step s100, obtain effective license plate image detection and indentification result;
Wherein, here Car license recognition equipment detects the vehicle image obtained, identifies, when obtaining detection and indentification result, judge that whether this recognition result is effective, because will modify, set according to the parameter of these results to Car license recognition equipment, to improve the performance of Car license recognition equipment, therefore can only gather effective result.
Step s110, gather data relevant to preset parameter in described result;
Wherein, Car license recognition equipment comprises a lot of information to the result that license plate image carries out detection and indentification, be not need information all in this result to extract, just before namely extraction gathers, the pre-set parameter needing to detect, only need after setting to gather the data of preset parameter, such as, only need to detect the parameter of car plate size under this parking lot environment, see and to change the need of to it, as long as therefore just extract the data relevant with car plate size parameter.The kind of preset parameter here or can use the difference of scene specifically to set according to the difference of actual conditions.
Wherein, the parameter can carrying out here collecting can comprise: the running orbit of the size of car plate, the ratio of width to height of car plate, car plate, acquiescence province and area etc.
Step s120, the relevant data of parameters in described preset parameter are carried out statistical study, and according to the results modification Car license recognition device parameter of statistical study.
Wherein, the data collected in step s110 in parameters in preset parameter are carried out statistical study, wherein can set in advance the method that the data collected in every class preset parameter carry out statistical study, be not the statistical analysis technique of often kind of parameter be all consistent, just general direction can be all the statistics of the corresponding data collected being carried out to a registration, number quantitative statistics, the statistics of numerical range; Concrete how according to the data analysis process obtained, also need the program setting carrying out in advance according to the meaning of often kind of parameter and actual conditions.The routine analyzer corresponding under can utilizing often kind of parameter of processor is according to the data analysis collected; After utilize statistic analysis result to modify, set Car license recognition device parameter.
The such as parameter of car plate width in the size of car plate, current car plate sorter generally all uses a mode of drawing window search, and as used the car plate sorter of AdaBoost Algorithm for Training, generally use many sizes, multiple dimensioned window is searched for.If can not determine the size of car plate size, system can carry out a large amount of futile searches, and loses time.Can monitored picture by being highly on average divided into three regions in the present invention, wherein there is certain overlapping region in three regions, then for these three regions add up respectively occurred and identify minimum widith and the breadth extreme of successful car plate, minimum widith is reduced 10% as the start width of the search in this region, breadth extreme is expanded 10% as the termination width of the search in this region.An each detection and indentification success car plate, obtains the width of this car plate, then press the position of car plate appearance, select this car plate to belong to which region, compares with the minimum car plate width in this region and maximum car plate width.If less than minimum car plate width, revise minimum car plate width.If larger than maximum car plate width, revise maximum car plate width.
Wherein, the parameter of other parameters such as the ratio of width to height of car plate car plate width in the size of car plate has the statistical study rule of oneself, such as minimum widith is reduced 10% as the start width of the search in this region, breadth extreme is expanded 10% as the termination width of the search in this region.And the result of statistical study can be utilized to carry out the amendment of relevant parameter according to the statistical study of corresponding parameter rule, such as, select this car plate to belong to which region, compare with the minimum car plate width in this region and maximum car plate width.If less than minimum car plate width, revise minimum car plate width.If larger than maximum car plate width, revise maximum car plate width.
Based on technique scheme, the embodiment of the present invention provides a kind of Car license recognition apparatus parameter setting method, by Car license recognition equipment, detection and indentification is carried out to the license plate image collected, obtain effective license plate image detection and indentification result, and gather data relevant to preset parameter in effective result; Statistical study is carried out to the relevant data of parameters in preset parameter, can obtain that the corresponding parameter of the effective data of detection and indentification is right arranges numerical value, the parameter of original car plate identification equipment is modified, to ensure the performance of Car license recognition equipment; The method can complete the revision of the parameter to Car license recognition equipment automatically, the performance of Car license recognition equipment is improved, and can adapts to various actual environment.
Optionally, also comprise after obtaining effective license plate image detection and indentification result:
Add up the number of effective license plate image detection and indentification result;
When described number reaches predetermined threshold, gather data relevant to preset parameter in all results.
Wherein, after the effective license plate image detection and indentification result of acquisition, the number of effective license plate image detection and indentification result can also be added up; Namely the effective number of license plate image detection and indentification is added up; The counter in the processor in Car license recognition equipment can be utilized to count; When occurring that effective is counted to predetermined threshold, calling capture program and carrying out gathering data relevant to preset parameter in all results.
Car license recognition equipment can be made like this when carrying out parameter revision and arranging, efficiency is higher, do not need all to modify to a result at every turn, also problem too frequently can be there is like that, preferably, a threshold value can be set, when the effective number of license plate image detection and indentification reaches threshold value, so carrying out gathering data relevant to preset parameter in all results, effect can be better, also Car license recognition equipment is namely allowed to carry out the accumulation of a period of time, also quite with once revise front, the checking that effect after parameters is carried out, when sample size reaches certain numerical value, carrying out statistical study, more may can obtain significant data, also reduce a deviation data to the impact of overall data.
Optionally, described car plate carry out detection and indentification result whether effective standard can comprise:
The number of the character recognized is the same with character number in car plate;
And/or the degree of confidence of character in car plate on each correspondence position meets predetermined value;
And/or the summation after the degree of confidence superposition of character in car plate on each correspondence position reaches threshold value.
Wherein, according to the needs of actual conditions, namely actual conditions are to the height of parameter request, the number that the whether effective standard of result that car plate carries out detection and indentification can comprise the character recognized is the same with character number in car plate, namely it should be 7 in the number of the normal characters on license plate of China, therefore, when the number of the character recognized is 7, the result can calculating car plate detection and indentification is effective;
Or the degree of confidence of character in car plate on each correspondence position meets predetermined value, because the character in Chinese car plate is all generally by Chinese character, English alphabet and numeral composition, due to their complexity and number kind all different, therefore, their degree of confidence also can there are differences, and carries out character recognition owing to using characters on license plate sorter, use the training method of support vector machines in training process, the result of therefore each character recognition has a degree of confidence; Lower than the degree of confidence of English alphabet and numeral by the degree of confidence of Chinese character in situation, therefore when the degree of confidence of the character on correspondence position each in car plate meets predetermined value, the result can calculating car plate detection and indentification is effective;
Or the summation after the degree of confidence superposition of character in car plate on each correspondence position reaches threshold value, when the summation after the degree of confidence superposition of the character on correspondence position each in car plate reaches threshold value, the result can calculating car plate detection and indentification is effective;
Wherein, the whether effective standard of result of car plate detection and indentification here can also be the various combinations of above-mentioned several situation, and also can have other standard, these can be determined according to actual conditions.
Optionally, please refer to Fig. 2, the process flow diagram relevant data of parameters in preset parameter being carried out the method for statistical study that Fig. 2 provides for the embodiment of the present invention; The method can comprise:
Step s200, the relevant data of parameters in preset parameter to be added up;
Wherein, in preset parameter, the relevant data of parameters are added up, and statistics here can be carry out inductive statistics, also namely integrates.
Step s210, the registration determining the data after adding up and scope;
Wherein, after data statistics, some numerical value can be obtained, a data area such as occupied by all data can be the registration of each data, can be the number percent of each data, can being the fiducial interval of data, waiting by adding up the overlapping interval and range intervals that each data obtain.
Step s220, utilize the registration of the relevant data of parameters and scope to be analyzed by the analysis rule of parameters, obtain statistic analysis result.
Wherein, utilize registration and the scope of the relevant data of the parameters of gained, by in the analysis rule of parameters to the use of these registrations and scope, obtain statistic analysis result and also namely revise result, utilize this statistic analysis result can carry out the amendment of Car license recognition device parameter.
The size (mainly the width of car plate) of such as car plate: current car plate sorter generally all uses the mode of drawing window search, such as use the car plate sorter of cascade calculation AdaBoost Algorithm for Training, the many sizes of general use, multiple dimensioned window is searched for.If uncertain car plate size, system can carry out a large amount of futile searches, and loses time.The present invention proposes monitored picture by being highly on average divided into three regions, wherein can there is certain overlapping region in three regions, then for these three regions add up respectively occurred and identify minimum widith and the breadth extreme of successful car plate, minimum widith is reduced 10% as the start width of the search in this region, breadth extreme is expanded 10% as the termination width of the search in this region.Each detection also identifies a successfully car plate, obtains the width of this car plate, then presses the position that car plate occurs, selects this car plate to belong to which region, compares with the minimum car plate width in this region and maximum car plate width.If less than minimum car plate width, revise minimum car plate width.If larger than maximum car plate width, revise maximum car plate width.
Wherein, here the registration in statistics is utilized to find overlapping region, minimum widith and the breadth extreme of car plate is found according to the scope of data, also namely minimum widith is reduced 10% as the start width of the search in this region by the analysis rule of these data and this parameter, breadth extreme is expanded 10% as the termination width of the search in this region; These can be utilized to carry out the amendment of the width of car plate.
The ratio of width to height of car plate: install due to video camera at present and there is certain angle, therefore car plate can exist certain difference in the ratio of width to height of whole guarded region.Such as, time car plate is away from video camera, car plate the ratio of width to height is comparatively large, and car plate is near video camera time, and car plate the ratio of width to height is less.If therefore only use the car plate sorter of a size, some region detection car plate effect may be caused poor.Therefore for the aspect ratio parameter of the car plate sorter of multiple size, at the car plate sorter that car plate uses the ratio of width to height larger away from the region of video camera, the car plate sorter of normal rates is used, at the car plate sorter that car plate uses the ratio of width to height less near the region of video camera at zone line.First the car plate sorter of standard can be used time equipment is just started working to carry out car plate detection, detect and identify successfully after a car plate, obtaining the ratio of width to height of this car plate.After having added up effective license plate recognition result of some, just can determine the less car plate sorter of the ratio of width to height, the usable range of normal car plate sorter and the larger car plate sorter of the ratio of width to height.The car plate sorter that such as, on guarded region 1/4 region uses the ratio of width to height larger, 1/4 to 3/4 region uses positive constant width height car plate sorter etc.According to the usable range of the ratio of width to height fine setting car plate sorter of the car plate obtained in follow-up use.
Wherein, here be also utilize to obtain the ratio of width to height and scope in detection and indentification success car plate, and obtain successful scope and registration, the less car plate sorter of the ratio of width to height can be determined by these, the usable range of normal car plate sorter and the larger car plate sorter of the ratio of width to height; Therefore the usable range of various wide high car plate sorter can be obtained again according to above-mentioned scope and registration.
The running orbit of car plate: the system used at present, in order to reduce resource, generally can set car plate surveyed area.Car plate surveyed area is generally that staff is determined by setting-out at client software.But in actual use, the position that car plate occurs likely only accounts for a part for defined area, and likely appears at outside defined area.System, by the appearance position of each effective identification car plate of statistics, obtains the running orbit of each car plate, and the region that car plate may occur is determined in the position then occurred according to car plate.Then the region comprising car plate is suitably extended out as car plate surveyed area.And the region that continuous adjustment car plate may occur in follow-up use, thus realize better recognition effect.
Wherein, the position occurred according to car plate here determines that namely region that car plate may occur uses the scope of the running orbit of car plate in effective result, utilizes this to revise running orbit parameter, namely constantly adjusts the region that car plate may occur.
Acquiescence province and area: because the discrimination of the Chinese character on car plate is general lower, general gateway, community, from this province vehicle shared by ratio generally can up to more than 95%.For the Chinese character identifying difficulty, the Chinese character in acquiescence province can be used to substitute.If made mistakes in province when carrying out gateway information matches, can be mated by the character of 6 below or numeral.Or distinguished by other additional information.The province information of all car plates that Car license recognition device can be occurred by statistics, the province of setting acquiescence automatically.The number of times in the area that simultaneously also can be occurred by statistics, setting acquiescence area.
Wherein, be that the registration of data in province by occurring carries out giving tacit consent to the setting in province and area and amendment here.
Therefore, can see and to add up by detect in effective result the relevant data of parameters in preset parameter to a large amount of car plate, obtain registration and scope, and analysis rule under utilizing parameters and the registration obtained and scope are analyzed, and determine the amendment of corresponding parameter; By the amendment of parameter, the detection perform representated by each parameter is improved, therefore the performance of Car license recognition equipment is made to be greatly improved, and carry out automatic analysis, the automatic function revised because Car license recognition equipment has parameter according to actual conditions, do not need manual intervention, therefore the adaptability of environment is also improved, the change of site environment can be adapted to fast.
Optionally, also comprise before described acquisition effective license plate image detection and indentification result:
License plate image is gathered according to pre-defined rule;
Detection and indentification is carried out to the license plate image collected.
Wherein, because Car license recognition equipment is in the process of carrying out Car license recognition, vehicle can not be static, can be the vehicle in advancing.Therefore in order to improve the efficiency of Car license recognition equipment to Car license recognition, do not need all will carry out detection and indentification to each two field picture collected.The information such as the vehicle location representated by possibility continuous print frame are constant substantially, so processing many times with regard to there will be the corresponding vehicle image to a position, repeatedly processing like this efficiency of image procossing can be made to reduce to the same image.
Therefore, license plate image can be gathered according to pre-defined rule, such as, can gather an image every a frame, and detection and indentification is carried out to the license plate image collected, also in the light of actual conditions can carry out gathering an image every predetermined frame, and detection and indentification is carried out to the license plate image collected.
By said method, collection image parameter can be set flexibly, make Car license recognition equipment work efficiency higher.
Optionally, please refer to Fig. 3, the process flow diagram of the method for the amendment Car license recognition device parameter that Fig. 3 provides for the embodiment of the present invention; The method can comprise:
Step s300, numerical value according to parameters in the result determination preset parameter of statistical study;
Wherein, such as carry out by the registration of the data in the province of appearance setting and the amendment of giving tacit consent to province and area.The number of times that such as, in the province occurred Shaanxi Province occurs is up to 98%, so by the result of statistical study, the number of times that Shaanxi Province occurs accounts for 98% of all detection car plates, wherein, if again in all detection car plates or detection and indentification to all Shaanxi Province car plate in ratio shared by Xi'an be 90%; So can determine that acquiescence province and acquiescence area should be Xi'an City, Shanxi Province.
Step s310, the numerical value of the parameters before described numerical value and statistical study to be compared;
Wherein, the acquiescence province that can obtain according to statistic analysis result compares with giving tacit consent to area and the acquiescence province set before and giving tacit consent to area.
Step s320, when comparative result is different, revise the numerical value of this parameter.
Wherein, according to this comparative result, when inconsistent, can set or revise acquiescence province is Shaanxi Province; Can modify to the parameter in acquiescence area or be set as Xi'an.
Based on technique scheme, the Car license recognition apparatus parameter setting method that the embodiment of the present invention provides, carries out detection and indentification by Car license recognition equipment to the license plate image collected through pre-defined rule, can increase work efficiency, save time; Obtain effective license plate image detection and indentification result, when effective recognition result reaches threshold value, gather data relevant to preset parameter in effective result; Which enhance the accuracy of Car license recognition device parameter revision, reduce amendment number of times, statistical study is carried out to the relevant data of parameters in preset parameter, can obtain that the corresponding parameter of the effective data of detection and indentification is right arranges numerical value, the parameter of original car plate identification equipment is modified, to ensure the performance of Car license recognition equipment; The method can complete the revision of the parameter to Car license recognition equipment automatically, the performance of Car license recognition equipment is improved, and can adapts to various actual environment.
Embodiments provide Car license recognition apparatus parameter setting method, automatically can be completed the revision of the parameter to Car license recognition equipment by said method, the performance of Car license recognition equipment is improved.
Be introduced the Car license recognition device that the embodiment of the present invention provides below, Car license recognition device described below can mutual corresponding reference with above-described Car license recognition apparatus parameter setting method.
Please refer to Fig. 4, the structured flowchart of the Car license recognition device that Fig. 4 provides for the embodiment of the present invention; This Car license recognition device can comprise: acquisition module 100, acquisition module 200, modified module 300, wherein,
Acquisition module 100, for obtaining effective license plate image detection and indentification result;
Acquisition module 200, for gathering data relevant to preset parameter in described result;
Modified module 300, for carrying out statistical study by the relevant data of parameters in preset parameter, and according to the results modification Car license recognition device parameter of statistical study.
Optionally, please refer to Fig. 5, the structured flowchart of another Car license recognition device that Fig. 5 provides for the embodiment of the present invention; This Car license recognition device can also comprise: counting module 400, for adding up the number of effective license plate image detection and indentification result, when described number reaches predetermined threshold, gathers data relevant to preset parameter in all results.
Optionally, please refer to Fig. 6, the structured flowchart of the acquisition module that Fig. 6 provides for the embodiment of the present invention; Acquisition module 200 can comprise:
Collecting unit 210, for gathering data relevant to preset parameter in described result.
Optionally, please refer to Fig. 7, the structured flowchart of the modified module that Fig. 7 provides for the embodiment of the present invention; Modified module 300 can comprise: statistic unit 310, analytic unit 320, amendment unit 330, wherein,
Statistic unit 310, for the relevant data of parameters in preset parameter being added up, determines registration and the scope of the data after adding up;
Analytic unit 320, is utilized the registration of the relevant data of parameters and scope to be analyzed by the analysis rule of parameters, obtains statistic analysis result;
Amendment unit 330, according to the results modification Car license recognition device parameter of statistical study.
Embodiments provide Car license recognition device, automatically can be completed the revision of the parameter to Car license recognition equipment by above-mentioned Car license recognition device, the performance of Car license recognition equipment is improved.
In instructions, each embodiment adopts the mode of going forward one by one to describe, and what each embodiment stressed is the difference with other embodiments, between each embodiment identical similar portion mutually see.For device disclosed in embodiment, because it corresponds to the method disclosed in Example, so description is fairly simple, relevant part illustrates see method part.
Professional can also recognize further, in conjunction with unit and the algorithm steps of each example of embodiment disclosed herein description, can realize with electronic hardware, computer software or the combination of the two, in order to the interchangeability of hardware and software is clearly described, generally describe composition and the step of each example in the above description according to function.These functions perform with hardware or software mode actually, depend on application-specific and the design constraint of technical scheme.Professional and technical personnel can use distinct methods to realize described function to each specifically should being used for, but this realization should not thought and exceeds scope of the present invention.
The software module that the method described in conjunction with embodiment disclosed herein or the step of algorithm can directly use hardware, processor to perform, or the combination of the two is implemented.Software module can be placed in the storage medium of other form any known in random access memory (RAM), internal memory, ROM (read-only memory) (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technical field.
Above Car license recognition apparatus parameter setting method provided by the present invention and Car license recognition device are described in detail.Apply specific case herein to set forth principle of the present invention and embodiment, the explanation of above embodiment just understands method of the present invention and core concept thereof for helping.It should be pointed out that for those skilled in the art, under the premise without departing from the principles of the invention, can also carry out some improvement and modification to the present invention, these improve and modify and also fall in the protection domain of the claims in the present invention.
Claims (10)
1. a Car license recognition apparatus parameter setting method, is characterized in that, comprising:
Obtain effective license plate image detection and indentification result;
Gather data relevant to preset parameter in described result;
The relevant data of parameters in described preset parameter are carried out statistical study, and according to the results modification Car license recognition device parameter of statistical study.
2. Car license recognition apparatus parameter setting method as claimed in claim 1, is characterized in that, also comprise after obtaining effective license plate image detection and indentification result:
Add up the number of effective license plate image detection and indentification result;
When described number reaches predetermined threshold, gather data relevant to preset parameter in all results.
3. Car license recognition apparatus parameter setting method as claimed in claim 1, is characterized in that, the whether effective standard of result that described car plate carries out detection and indentification comprises:
The number of the character recognized is the same with character number in car plate;
And/or the degree of confidence of character in car plate on each correspondence position meets predetermined value;
And/or the summation after the degree of confidence superposition of character in car plate on each correspondence position reaches threshold value.
4. Car license recognition apparatus parameter setting method as claimed in claim 1, is characterized in that, the described relevant data by parameters in preset parameter are carried out statistical study and comprised:
The relevant data of parameters in preset parameter are added up;
Determine registration and the scope of the data after adding up;
Utilize the registration of the relevant data of parameters and scope to be analyzed by the analysis rule of parameters, obtain statistic analysis result.
5. Car license recognition apparatus parameter setting method as claimed in claim 1, is characterized in that, also comprise before described acquisition effective license plate image detection and indentification result:
License plate image is gathered according to pre-defined rule;
Detection and indentification is carried out to the license plate image collected.
6. Car license recognition apparatus parameter setting method as claimed in claim 1, it is characterized in that, the described results modification Car license recognition device parameter according to statistical study comprises:
According to the numerical value of parameters in the result determination preset parameter of statistical study;
The numerical value of the parameters before described numerical value and statistical study is compared;
When comparative result is different, revise the numerical value of this parameter.
7. a Car license recognition device, is characterized in that, comprising: acquisition module, acquisition module, modified module, wherein,
Acquisition module, for obtaining effective license plate image detection and indentification result;
Acquisition module, for gathering data relevant to preset parameter in described result;
Modified module, for carrying out statistical study by the relevant data of parameters in preset parameter, and according to the results modification Car license recognition device parameter of statistical study.
8. Car license recognition device as claimed in claim 7, is characterized in that, also comprise counting module, wherein,
Counting module, for adding up the number of effective license plate image detection and indentification result, when described number reaches predetermined threshold, gathers data relevant to preset parameter in all results.
9. Car license recognition device as claimed in claim 7, it is characterized in that, described acquisition module comprises:
Collecting unit, for gathering data relevant to preset parameter in described result.
10. Car license recognition device as claimed in claim 7, it is characterized in that, described modified module comprises: statistic unit, analytic unit, amendment unit, wherein,
Statistic unit, for the relevant data of parameters in preset parameter being added up, determines registration and the scope of the data after adding up;
Analytic unit, is utilized the registration of the relevant data of parameters and scope to be analyzed by the analysis rule of parameters, obtains statistic analysis result;
Amendment unit, according to the results modification Car license recognition device parameter of statistical study.
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 true CN104318226A (en) | 2015-01-28 |
| CN104318226B 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) |
Cited By (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 |
| CN109559522A (en) * | 2019-01-21 | 2019-04-02 | 中控智慧科技股份有限公司 | A kind of adjustment method, telescopic column, video camera and storage medium |
Citations (5)
| 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 |
| CN102214290A (en) * | 2010-04-12 | 2011-10-12 | 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 (5)
| 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 |
| CN102214290A (en) * | 2010-04-12 | 2011-10-12 | 无锡科利德斯科技有限公司 | License plate positioning method and license plate positioning template training method |
| CN202003409U (en) * | 2011-04-19 | 2011-10-05 | 淮阴工学院 | License plate positioning device |
| CN103841313A (en) * | 2012-11-27 | 2014-06-04 | 华为技术有限公司 | Pan-tilt camera control method, system and device |
Non-Patent Citations (2)
| Title |
|---|
| 董燕 等: "信息融合技术在车牌识别中的应用研究", 《中原工学院报》 * |
| 黄冉: "汉字图像识别机研究", 《中国优秀博硕士学位论文全文数据库（硕士）信息科技辑》 * |
Cited By (3)
| 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 |
| CN109559522A (en) * | 2019-01-21 | 2019-04-02 | 中控智慧科技股份有限公司 | A kind of adjustment method, telescopic column, video camera and storage medium |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104318226B (en) | 2018-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3806064B1 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
| US10896349B2 (en) | Text detection method and apparatus, and storage medium | |
| JP6733397B2 (en) | Leftover object detection device, method and system | |
| CN110879951B (en) | Motion foreground detection method and device | |
| CN109086734B (en) | Method and device for positioning pupil image in human eye image | |
| EP4060491A1 (en) | Intelligent analysis algorithm selection method, apparatus and system, and electronic device | |
| WO2015184899A1 (en) | Method and device for recognizing license plate of vehicle | |
| CN111127508B (en) | Target tracking method and device based on video | |
| CN109102026B (en) | Vehicle image detection method, device and system | |
| CN105320953A (en) | License plate recognition method | |
| CN109657674A (en) | A kind of vehicles identifications determine method and device | |
| CN109102507A (en) | Screw thread detection method and device | |
| CN111223078A (en) | Method for determining defect grade and storage medium | |
| CN106998336B (en) | Method and device for detecting user in channel | |
| CN111369792B (en) | Traffic incident analysis method and device and electronic equipment | |
| CN105447863A (en) | Residue detection method based on improved VIBE | |
| CN104318226A (en) | License plate recognition device parameter setting method and license plate recognizer | |
| CN110660225A (en) | Red light running behavior detection method, device and equipment | |
| CN111460198B (en) | Picture timestamp auditing method and device | |
| CN110874935B (en) | Method, system and device for recognizing license plate of vehicle | |
| CN106991684B (en) | Foreground extracting method and device | |
| CN105825161A (en) | Image skin color detection method and system thereof | |
| CN112597924B (en) | Electric bicycle track tracking method, camera device and server | |
| CN110782439B (en) | Method and device for auxiliary detection of image annotation quality | |
| CN112163471A (en) | Congestion detection method and device |
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 |