CN107679534A - A kind of license plate locating method and device - Google Patents

A kind of license plate locating method and device Download PDF

Info

Publication number
CN107679534A
CN107679534A CN201710942158.4A CN201710942158A CN107679534A CN 107679534 A CN107679534 A CN 107679534A CN 201710942158 A CN201710942158 A CN 201710942158A CN 107679534 A CN107679534 A CN 107679534A
Authority
CN
China
Prior art keywords
license plate
crest
area
projected image
row
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201710942158.4A
Other languages
Chinese (zh)
Inventor
孙伟源
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhengzhou Yunhai Information Technology Co Ltd
Original Assignee
Zhengzhou Yunhai Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhengzhou Yunhai Information Technology Co Ltd filed Critical Zhengzhou Yunhai Information Technology Co Ltd
Priority to CN201710942158.4A priority Critical patent/CN107679534A/en
Publication of CN107679534A publication Critical patent/CN107679534A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
    • G06V20/63—Scene text, e.g. street names
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
    • G06V20/625—License plates

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Vehicle Waterproofing, Decoration, And Sanitation Devices (AREA)
  • Traffic Control Systems (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses a kind of license plate locating method and device.It is related to intelligent image identification technology；Solves the problems, such as plate location recognition difficulty.This method includes：Enter line scans to pretreatment image, choose license plate candidate area；The projection in vertical direction is done to the license plate candidate area, obtains projected image；Drop shadow curve's Wave pattern based on the projected image, it is determined that accurate license plate area.Technical scheme provided by the invention is applied to car plate certification scene, realizes the license plate image identification of precise and high efficiency.

Description

A kind of license plate locating method and device
Technical field
The present invention relates to intelligent image identification technology, espespecially a kind of license plate locating method and device.
Background technology
Automobile has been indispensable a kind of important vehicles in people's daily life, with user vehicle rapidly Increase, highway, urban road, park construction is more and more, control of traffic and road and parking lot management is become more next More troublesome, control to traffic and safety management requirement also increasingly improve, these all inevitable requirement have one it is more efficient more convenient Simpler way to manage.
Intelligent transportation system (ITS) has become the Main way of Current traffic management development, automatic as traffic administration Vehicle license plate identification (License Plate Recognition, LPR) technology of the important means of change is exactly to be given birth to for this, its Task is that automobile monitoring image is analyzed and handled, and then automatically identifies each mark of car that image includes, goes forward side by side Row related data library management.LPR systems can be widely used in the various important events for needing car plate certification, such as electronic charging Stand, parking lot vehicle management etc..
The general electronic eyes all in freeway toll station or city of collection of vehicle image, due to outdoor environment not Stability so that vehicle scene is influenceed in imaging process by many factors, and picture quality can decline, and have a strong impact on car The positioning and identification of board information.
The content of the invention
In order to solve the above-mentioned technical problem, the invention provides a kind of license plate locating method and device.Spy based on image Sign calculates with upright projection and realizes License Plate, solves the problems, such as plate location recognition difficulty, has reached pinpoint effect Fruit.
In order to reach the object of the invention, the invention provides a kind of license plate locating method, including：
Enter line scans to pretreatment image, choose license plate candidate area；
The projection in vertical direction is done to the license plate candidate area, obtains projected image；
Drop shadow curve's Wave pattern based on the projected image, it is determined that accurate license plate area.
Preferably, the step of line scans are entered to pretreatment image, choose license plate candidate area includes：
The pretreatment picture is progressively scanned, two neighboring pixel occurs by black in vain or by white to black in a row Change a Gray Level Jump, the Gray Level Jump that adds up number；
Judge that transition times belong to suspicious row more than the row of preset saltus step threshold value；
Reach preset car plate height doors in the region height that continuous suspicious row is formed to prescribe a time limit, judge the region for car Board candidate region.
Preferably, drop shadow curve's Wave pattern based on the projected image, it is determined that the step of accurate license plate area includes：
Intercept the Part I of the projected image；
Determine the crest that the Part I passes through；
After width is rejected in the crest passed through from the Part I more than the crest of candidate region height, first wave is obtained Peak set；
The crest that the distance between described primary peak set medium wave peak is met to character pitch merges, it is determined that accurately License plate area.
Preferably, the crest that the distance between described primary peak set medium wave peak is met to character pitch merges, It is determined that after the step of accurate license plate area, in addition to：
The Part II of the projected image is intercepted, the Part II is different from the Part I；
Determine the crest that the Part II passes through；
After width is rejected in the crest passed through from the Part II more than the crest of candidate region height, the second ripple is obtained Peak set；
The crest that the distance between described secondary peak set medium wave peak is met to character pitch merges, in acquisition When second accurate license plate area is identical with the accurate license plate area, judge that the spiritual license plate area is effective.
Present invention also offers a kind of license plate positioning device, including：
Coarse positioning module, for entering line scans to pretreatment image, choose license plate candidate area；
Computing module is projected, for doing the projection in vertical direction to the license plate candidate area, obtains projected image；
Pinpoint module, for drop shadow curve's Wave pattern based on the projected image, it is determined that accurate license plate area.
Preferably, the coarse positioning module includes：
Row scanning element, for the pretreatment picture progressive scan, two neighboring pixel appearance to be by black in a row To Gray Level Jump of change white or by white to black, the Gray Level Jump that adds up number；
Suspicious line flag unit, for judging that transition times belong to suspicious row more than the row of preset saltus step threshold value；
Candidate region identifying unit, the region height for being formed in continuous suspicious row reach preset car plate height doors In limited time, judge the region for license plate candidate area.
Preferably, the pinpoint module includes：
First interception unit, for intercepting the Part I of the projected image；
Primary peak determining unit, the crest passed through for determining the Part I；
Primary peak screening unit, for rejecting width in the crest that is passed through from the Part I, to be more than candidate region high After the crest of degree, primary peak set is obtained；
Precise region determining unit, for the distance between described primary peak set medium wave peak to be met into character pitch Crest merges, it is determined that accurate license plate area.
Preferably, the pinpoint module also includes：
Second interception unit, for intercepting the Part II of the projected image, the Part II is different from described the A part；
Secondary peak determining unit, the crest passed through for determining the Part II；
Secondary peak screening unit, for rejecting width in the crest that is passed through from the Part II, to be more than candidate region high After the crest of degree, secondary peak set is obtained；
Result verification unit, for the distance between described secondary peak set medium wave peak to be met to the crest of character pitch Merge, when the second accurate license plate area of acquisition is identical with the accurate license plate area, judge the spiritual car plate area Domain is effective.
The invention provides a kind of license plate locating method and device, first to pretreatment picture row scanning, chooses car plate and waits Favored area, the projection in vertical direction is then done to the license plate candidate area, obtains projected image, based on the projected image Drop shadow curve's Wave pattern, it is determined that accurate license plate area.Pass through textural characteristics slightly first license plate area, then pass through upright projection meter It is accurately positioned, realizes the license plate image identification of precise and high efficiency, solve the problems, such as plate location recognition difficulty.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification Obtain it is clear that or being understood by implementing the present invention.The purpose of the present invention and other advantages can be by specification, rights Specifically noted structure is realized and obtained in claim and accompanying drawing.
Brief description of the drawings
Accompanying drawing is used for providing further understanding technical solution of the present invention, and a part for constitution instruction, with this The embodiment of application is used to explain technical scheme together, does not form the limitation to technical solution of the present invention.
Fig. 1 is a kind of schematic flow sheet for license plate locating method that embodiments of the invention one provide；
Fig. 2 is the vehicle image in embodiments of the invention one；
Fig. 3 is the texture curve map of vehicle image in Fig. 2；
Fig. 4 is the license plate candidate area schematic diagram after coarse positioning；
Fig. 5 is the upright projection schematic diagram of license plate candidate area；
Fig. 6 is a kind of structural representation for license plate positioning device that embodiments of the invention two provide；
Fig. 7 is the structural representation of coarse positioning module 601 in Fig. 6；
Fig. 8 is the structural representation of pinpoint module 603 in Fig. 6.
Embodiment
For the object, technical solutions and advantages of the present invention are more clearly understood, below in conjunction with accompanying drawing to the present invention Embodiment be described in detail.It should be noted that in the case where not conflicting, in the embodiment and embodiment in the application Feature can mutually be combined.
Can be in the computer system of such as one group computer executable instructions the flow of accompanying drawing illustrates the step of Perform.Also, although logical order is shown in flow charts, in some cases, can be with suitable different from herein Sequence performs shown or described step.
The general electronic eyes all in freeway toll station or city of collection of vehicle image, due to outdoor environment not Stability so that vehicle scene is influenceed in imaging process by many factors, and picture quality can decline, and have a strong impact on car The positioning and identification of board information.
In order to solve the above problems, embodiments of the invention propose a kind of car plate based on textural characteristics and upright projection Localization method and device, improve the accuracy rate and efficiency of License Plate.
First with reference to accompanying drawing, embodiments of the invention one are illustrated.
The embodiments of the invention provide a kind of license plate locating method, and the intelligence to car plate position in picture is completed using this method Can identification positioning flow as shown in figure 1, including：
Step 101, enter line scans to pretreatment image, choose license plate candidate area；
Referring to vehicle image as shown in Figure 2, texture curve corresponding to region A, B, C that its center is chosen is as shown in Figure 3.
This step specifically includes：
1st, the pretreatment picture is progressively scanned, two neighboring pixel occurs by black in vain or by white to black in a row Gray Level Jump of change, add up Gray Level Jump number；
2nd, judge that transition times belong to suspicious row more than the row of preset saltus step threshold value；
3rd, the region height formed in continuous suspicious row reaches preset car plate height doors and prescribed a time limit, and judges that the region is License plate candidate area.
From the point of view of automobile image grain distribution, texture is car light, radiator and car than the place of comparatively dense in whole image Board.Car light and radiator are largely horizontal textures, but being continuously increased recently as vehicle, and vertical line is presented in radiator Reason also it is enough.License plate area is then formed by Character Filling, shows more uniform vertical texture.Car body then more is in Reveal horizontal texture.From the point of view of the gray scale of automobile image, car plate and the gray value of car body other parts are very different.And On car body in addition to the point, line of minority, most of grey scale change is all than shallower.Interval in car plate between character is more equal Even, there is saltus step in character and licence plate background color, and character has more uniform gray scale with the inside at licence plate bottom in itself on gray value.
It is in above-mentioned analysis, this step, and because license plate area contains abundant vertical edge, the vertical stroke of character is extremely Rare two edges, license plate area horizontal direction is by white to black or black frequent to white Gray Level Jump, therefore this method uses base Carry out coarse localization license plate area in row scanning.If the Gray Level Jump number of certain a line is more than certain saltus step in two-value automobile image Threshold value T, then the row can be marked as line segment, can be with if certain altitude is arrived in neighbouring suspicious line segment accumulation to the row up and down It is license plate candidate area this zone marker, situation as the region beyond the car plate is more rare.
For example, being progressively scanned downwards since two-value automobile image f (x, y) the first row, a line is scanned from left to right Each pixel, the two neighboring pixel per a line are all designated as a Gray Level Jump in vain or by leucismus is black by blacking, and add up saltus step Number.Common car plate contains 7 characters, and saltus step twice at least occurs in each character, it is contemplated that morphological operation may be lost Individual characters, the threshold value that then assume that character saltus step minimum number are 10, and scan line of the transition times more than 10 just belongs to Suspicious license plate area.Because car plate is a fixed-size rectangular area, the height of car plate also will not be too small, can set car Board height thresholding h1, wherein h1 values are 20 (pixels), when meeting that the region height of textural characteristics is between this threshold value i.e. Think that car plate is contained in this region.As shown in figure 4, the result of coarse positioning is related to two regions D, E.
Step 102, projection in vertical direction is done to the license plate candidate area, obtain projected image；
In this step, the projection that vertical direction is done to the rectangular area after coarse positioning calculates.Then projected image is carried out Analyze and then filter out license plate area.Coarse positioning result license plate candidate area upright projection is as shown in Figure 5.
Step 103, drop shadow curve's Wave pattern based on the projected image, it is determined that accurate license plate area；
By Fig. 5, it is seen that, the belt-like zone obtained after coarse positioning forecloses most noise, institute So that on the position of no car plate, the height of drop shadow curve is fluctuated, when and consecutive hours and be broken, without specific rule Speech.And the projected image of license plate area has quite obvious distribution characteristics.From the content in actual license plate region, there is car plate Position on, drop shadow curve can form multiple continuous peak values, and crest sequence has following characteristics：
(1) actual height of the height of most crests close to car plate.
(2) mean breadth of the width of most crests character close in car plate.
(3) arrangement regulation of each character is roughly the same in the regularity of distribution and car plate of each crest on curve.
Obviously, this crest sequence in drop shadow curve is exactly what is formed by the projection of the bianry image in license plate area. Therefore, as long as finding the starting and ending position of this crest sequence in drop shadow curve, it becomes possible to obtain a left side for license plate area The Position Approximate of right margin.
Because the character in candidate license plate region projects, the crest quantity to be formed is more, in addition in car plate each character shape Shape is different, is also not quite similar so as to the projected area of each character, and this to determine that the projection peak value that each character is formed becomes It is more complicated.For the quick and accurate lookup for completing crest sequence and non-license plate area is screened, based on each The regularity of distribution of the individual peak value in the crest sequence, handled by following algorithm in this step：
1st, the Part I of the projected image is intercepted；
2nd, the crest that the Part I passes through is determined；
3rd, after width is rejected in the crest passed through from the Part I more than the crest of candidate region height, first is obtained Crest set；
The 4th, crest that the distance between described primary peak set medium wave peak is met to character pitch merges, it is determined that smart True license plate area.
Preferably, in order to further determine that the accuracy of result, a wheel checking can be carried out, idiographic flow is as follows：
1st, the Part II of the projected image is intercepted, the Part II is different from the Part I；
2nd, the crest that the Part II passes through is determined；
3rd, after width is rejected in the crest passed through from the Part II more than the crest of candidate region height, second is obtained Crest set；
The 4th, crest that the distance between described secondary peak set medium wave peak is met to character pitch merges, and is obtaining The second accurate license plate area it is identical with the accurate license plate area when, judge that the spiritual license plate area is effective.
It is a concrete example of actual treatment below：
Passed through first with straight line at the 1/4 of projected image, and calculate through crest number, sent out by image viewing It is existing, when straight line passes through from the image containing car plate, because the projection of character is intensive and height is close to car plate height, so its The number of crest will not be very few, and the width of each crest will not be wide, and the region not comprising car plate, only less ripple There is features above in peak, when getting the crest that 1/4 passes straight through, the width of each crest is first determined whether, when width is excessive Rejected when (thresholding is candidate region height), then judge the quantity of remaining crest, find to work as threshold value by many experiments Can preferably it be distinguished comprising license plate area and non-license plate area when electing 4 as, because character may be because pollution on car plate Etc. factor may not be it is too complete thus cause to project it is too low, so the threshold value is unsuitable too high.
Only carry out judging that there is certain limitation by quantity, using character pitch, this characteristic gets previous step Crest result carry out single treatment, the crest that distance between crest is met to character pitch merges, if in the region Car plate be present, the right boundary that can obtain license plate area by specifically merging us.
In order to further determine that the region with the presence or absence of car plate again with 1/3 straight line from projected image by then carrying out Operation as above, it is license plate area that the region can be determined if car plate is still suffered from.
Below in conjunction with the accompanying drawings, embodiments of the invention two are illustrated.
The embodiments of the invention provide a kind of license plate positioning device, the structure of the device as shown in fig. 6, including：
Coarse positioning module 601, for entering line scans to pretreatment image, choose license plate candidate area；
Computing module 602 is projected, for doing the projection in vertical direction to the license plate candidate area, obtains perspective view Picture；
Pinpoint module 603, for drop shadow curve's Wave pattern based on the projected image, it is determined that accurate car plate area Domain.
Preferably, the coarse positioning module 601 structure as shown in fig. 7, comprises：
Row scanning element 6011, for the pretreatment picture progressive scan, in a row two neighboring pixel appearance By black to Gray Level Jump of change white or by white to black, the Gray Level Jump that adds up number；
Suspicious line flag unit 6012, for judging that transition times belong to suspicious row more than the row of preset saltus step threshold value；
Candidate region identifying unit 6013, the car plate that the region height for being formed in continuous suspicious row reaches preset are high When spending thresholding, judge the region for license plate candidate area.
Preferably, the pinpoint module 603 structure as shown in figure 8, including：
First interception unit 6031, for intercepting the Part I of the projected image；
Primary peak determining unit 6032, the crest passed through for determining the Part I；
Primary peak screening unit 6033, it is more than candidate regions for rejecting width in the crest that is passed through from the Part I After the crest of domain height, primary peak set is obtained；
Precise region determining unit 6034, for the distance between described primary peak set medium wave peak to be met into intercharacter Away from crest merge, it is determined that accurate license plate area.
Preferably, the pinpoint module 603 also includes：
Second interception unit 6035, for intercepting the Part II of the projected image, the Part II is different from institute State Part I；
Secondary peak determining unit 6036, the crest passed through for determining the Part II；
Secondary peak screening unit 6037, it is more than candidate regions for rejecting width in the crest that is passed through from the Part II After the crest of domain height, secondary peak set is obtained；
Result verification unit 6038, for the distance between described secondary peak set medium wave peak to be met into character pitch Crest merges, and when the second accurate license plate area of acquisition is identical with the accurate license plate area, judges the spiritual car Board region is effective.
The embodiment provides a kind of license plate locating method and device, first to pretreatment picture row scanning, choosing License plate candidate area is taken, the projection in vertical direction is then done to the license plate candidate area, projected image is obtained, based on described Drop shadow curve's Wave pattern of projected image, it is determined that accurate license plate area.Pass through textural characteristics slightly first license plate area, then by hanging down Deliver directly shadow calculating to be accurately positioned, realize the license plate image identification of precise and high efficiency, solve the problems, such as plate location recognition difficulty, Effectively increase the accuracy of License Plate in vehicle image.
Although disclosed herein embodiment as above, described content be only readily appreciate the present invention and use Embodiment, it is not limited to the present invention.Technical staff in any art of the present invention, taken off not departing from the present invention On the premise of the spirit and scope of dew, any modification and change, but the present invention can be carried out in the form and details of implementation Scope of patent protection, still should be subject to the scope of the claims as defined in the appended claims.

Claims (8)

  1. A kind of 1. license plate locating method, it is characterised in that including：
    Enter line scans to pretreatment image, choose license plate candidate area；
    The projection in vertical direction is done to the license plate candidate area, obtains projected image；
    Drop shadow curve's Wave pattern based on the projected image, it is determined that accurate license plate area.
  2. 2. license plate locating method according to claim 1, it is characterised in that enter line scans to pretreatment image, choose The step of license plate candidate area, includes：
    To the pretreatment picture progressive scan, two neighboring pixel appearance is by the black change in vain or by white to black in a row Gray Level Jump, the Gray Level Jump that adds up number；
    Judge that transition times belong to suspicious row more than the row of preset saltus step threshold value；
    Reach preset car plate height doors in the region height that continuous suspicious row is formed to prescribe a time limit, judge that the region is waited for car plate Favored area.
  3. 3. license plate locating method according to claim 2, it is characterised in that drop shadow curve's ripple based on the projected image Type feature, it is determined that the step of accurate license plate area includes：
    Intercept the Part I of the projected image；
    Determine the crest that the Part I passes through；
    After width is rejected in the crest passed through from the Part I more than the crest of candidate region height, primary peak collection is obtained Close；
    The crest that the distance between described primary peak set medium wave peak is met to character pitch merges, it is determined that accurate car plate Region.
  4. 4. license plate locating method according to claim 3, it is characterised in that by between the primary peak set medium wave peak Distance meet the crest of character pitch and merge, it is determined that after the step of accurate license plate area, in addition to：
    The Part II of the projected image is intercepted, the Part II is different from the Part I；
    Determine the crest that the Part II passes through；
    After width is rejected in the crest passed through from the Part II more than the crest of candidate region height, secondary peak collection is obtained Close；
    The crest that the distance between described secondary peak set medium wave peak is met to character pitch merges, the second of acquisition When accurate license plate area is identical with the accurate license plate area, the judgement spiritual license plate area is effective.
  5. A kind of 5. license plate positioning device, it is characterised in that including：
    Coarse positioning module, for entering line scans to pretreatment image, choose license plate candidate area；
    Computing module is projected, for doing the projection in vertical direction to the license plate candidate area, obtains projected image；
    Pinpoint module, for drop shadow curve's Wave pattern based on the projected image, it is determined that accurate license plate area.
  6. 6. license plate positioning device according to claim 5, it is characterised in that the coarse positioning module includes：
    Row scanning element, for being progressively scanned to the pretreatment picture, two neighboring pixel occurs by black to white in a row Or Gray Level Jump of change by white to black, the Gray Level Jump that adds up number；
    Suspicious line flag unit, for judging that transition times belong to suspicious row more than the row of preset saltus step threshold value；
    Candidate region identifying unit, the region height for being formed in continuous suspicious row reach preset car plate height thresholding When, judge the region for license plate candidate area.
  7. 7. license plate positioning device according to claim 6, it is characterised in that the pinpoint module includes：
    First interception unit, for intercepting the Part I of the projected image；
    Primary peak determining unit, the crest passed through for determining the Part I；
    Primary peak screening unit, it is more than candidate region height for rejecting width in the crest that is passed through from the Part I After crest, primary peak set is obtained；
    Precise region determining unit, for the distance between described primary peak set medium wave peak to be met to the crest of character pitch Merge, it is determined that accurate license plate area.
  8. 8. license plate positioning device according to claim 7, it is characterised in that the pinpoint module also includes：
    Second interception unit, for intercepting the Part II of the projected image, the Part II is different from described first Point；
    Secondary peak determining unit, the crest passed through for determining the Part II；
    Secondary peak screening unit, it is more than candidate region height for rejecting width in the crest that is passed through from the Part II After crest, secondary peak set is obtained；
    Result verification unit, the crest for the distance between described secondary peak set medium wave peak to be met to character pitch are carried out Merge, when the second accurate license plate area of acquisition is identical with the accurate license plate area, the judgement spiritual license plate area has Effect.
CN201710942158.4A 2017-10-11 2017-10-11 A kind of license plate locating method and device Pending CN107679534A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710942158.4A CN107679534A (en) 2017-10-11 2017-10-11 A kind of license plate locating method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710942158.4A CN107679534A (en) 2017-10-11 2017-10-11 A kind of license plate locating method and device

Publications (1)

Publication Number Publication Date
CN107679534A true CN107679534A (en) 2018-02-09

Family

ID=61140385

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710942158.4A Pending CN107679534A (en) 2017-10-11 2017-10-11 A kind of license plate locating method and device

Country Status (1)

Country Link
CN (1) CN107679534A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110533019A (en) * 2018-05-23 2019-12-03 杭州海康威视数字技术股份有限公司 License plate locating method, device and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007093949A1 (en) * 2006-02-14 2007-08-23 Koninklijke Philips Electronics N.V. Distributed license tracking using license trail and shadow
CN102375982A (en) * 2011-10-18 2012-03-14 华中科技大学 Multi-character characteristic fused license plate positioning method
CN103488978A (en) * 2013-09-26 2014-01-01 浙江工业大学 License plate positioning method based on gray level jump and character projection interval mode
CN103903018A (en) * 2014-04-02 2014-07-02 浙江师范大学 Method and system for positioning license plate in complex scene
CN104112139A (en) * 2014-06-30 2014-10-22 南京富士通南大软件技术有限公司 Method and system for accurate positioning of LPR license plate

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007093949A1 (en) * 2006-02-14 2007-08-23 Koninklijke Philips Electronics N.V. Distributed license tracking using license trail and shadow
CN102375982A (en) * 2011-10-18 2012-03-14 华中科技大学 Multi-character characteristic fused license plate positioning method
CN103488978A (en) * 2013-09-26 2014-01-01 浙江工业大学 License plate positioning method based on gray level jump and character projection interval mode
CN103903018A (en) * 2014-04-02 2014-07-02 浙江师范大学 Method and system for positioning license plate in complex scene
CN104112139A (en) * 2014-06-30 2014-10-22 南京富士通南大软件技术有限公司 Method and system for accurate positioning of LPR license plate

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110533019A (en) * 2018-05-23 2019-12-03 杭州海康威视数字技术股份有限公司 License plate locating method, device and storage medium
CN110533019B (en) * 2018-05-23 2022-08-12 杭州海康威视数字技术股份有限公司 License plate positioning method and device and storage medium

Similar Documents

Publication Publication Date Title
CN109886896B (en) Blue license plate segmentation and correction method
US11989951B2 (en) Parking detection method, system, processing device and storage medium
CN102722704B (en) Method and system for recognizing vehicle license plate by integrating video dynamic tracking
CN100449579C (en) All-round computer vision-based electronic parking guidance system
CN101783076B (en) Method for quick vehicle type recognition under video monitoring mode
CN102254152B (en) License plate location method based on color change points and color density
CN103279736B (en) A kind of detection method of license plate based on multi-information neighborhood ballot
CN102867417B (en) Taxi anti-forgery system and taxi anti-forgery method
JP2917661B2 (en) Traffic flow measurement processing method and device
CN100414561C (en) Vehicle plate extracting method based on skiagraphy and mathematical morphology
CN110210451B (en) Zebra crossing detection method
CN103824452A (en) Lightweight peccancy parking detection device based on full view vision
CN103235938A (en) Method and system for detecting and identifying license plate
CN101334836A (en) License plate positioning method incorporating color, size and texture characteristic
CN105303189A (en) Method and device for detecting specific identification image in predetermined area
CN104933409A (en) Parking space identification method based on point and line features of panoramic image
CN102364496A (en) Method and system for identifying automobile license plates automatically based on image analysis
CN103268471A (en) Vehicle illegal land occupying detection method and device
CN102915433A (en) Character combination-based license plate positioning and identifying method
CN102902957A (en) Video-stream-based automatic license plate recognition method
CN111783666A (en) Rapid lane line detection method based on continuous video frame corner feature matching
CN109635737A (en) Automobile navigation localization method is assisted based on pavement marker line visual identity
CN112651293B (en) Video detection method for road illegal spreading event
CN103544489A (en) Device and method for locating automobile logo
CN103279755A (en) Vehicle bottom shadow characteristics-based rapid license plate positioning method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20180209