CN105447831A - License plate image processing method and apparatus - Google Patents
License plate image processing method and apparatus Download PDFInfo
- Publication number
- CN105447831A CN105447831A CN201510924361.XA CN201510924361A CN105447831A CN 105447831 A CN105447831 A CN 105447831A CN 201510924361 A CN201510924361 A CN 201510924361A CN 105447831 A CN105447831 A CN 105447831A
- Authority
- CN
- China
- Prior art keywords
- license plate
- characters
- character
- pending
- stroke width
- 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
- 238000003672 processing method Methods 0.000 title abstract 2
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000006243 chemical reaction Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 8
- 238000005530 etching Methods 0.000 description 5
- 238000003384 imaging method Methods 0.000 description 5
- 230000006378 damage Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 239000012535 impurity Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/77—Retouching; Inpainting; Scratch removal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Character Input (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention provides a license plate image processing method and apparatus. The method comprises: calculating a stroke width value of a to-be-processed license plate character in a to-be-processed license plate image; comparing the stroke width value of the to-be-processed license plate character with the stroke width value of the normal license plate character, and if the stroke width value of the to-be-processed license plate character is greater than the stroke width value of the normal license plate character, the to-be-processed license plate image is determined for overexposure; and layer by layer reducing a character edge of the to-be-processed license plate character according to the pixel width, and detailing the to-be-processed license plate character. After binarization processing on the overexposure image, the method disclosed by the present invention can solve problems of thick characters, details loss, and easy adhesion, so that license plate character recognition accuracy is improved.
Description
Technical field
The present invention relates to technical field of intelligent traffic, particularly relate to a kind of license plate image disposal route and device.
Background technology
At present, the quantity of motor vehicles gets more and more, increasing to the management difficulty of motor vehicles, and the management difficulty that the intellectuality of Car license recognition will effectively reduce motor vehicles.But Car license recognition has shadow, and interference is many, the features such as circumstance complication, such as in the bayonet socket supervisory system, electronic police system application of reality, illumination having the greatest impact to Car license recognition, wherein the car plate overexposure problem that causes of environmental factor (sunshine direct projection) or light filling factor is commonplace, brings very large challenge to Car license recognition.
In prior art, because the characters on license plate carried out after binary conversion treatment overexposure license plate image is thick, loss in detail, and easily adhesion, therefore can carry out etching operation to the image after binary conversion treatment, make the image after binary conversion treatment reduce a circle.But etching operation needs to determine to corrode filter window, and the edge of characters on license plate is change, and is mellow and full change, with determining that the corrosion window of shape carries out to characters on license plate the contour structures that corrosion can destroy character, causes interference to character recognition.
Summary of the invention
The invention provides a kind of license plate image disposal route and device, overexposure license plate image is carried out to character after binary conversion treatment is thick, loss in detail to solve in prior art, and the problem of easily adhesion, and avoid the contour structures that prior art carries out the destruction character that etching operation causes to character and the interference that character recognition is caused.
According to the first aspect of the embodiment of the present invention, provide a kind of license plate image disposal route, described method comprises:
Calculate the stroke width value of pending characters on license plate in pending license plate image;
The stroke width value of more described pending characters on license plate and the stroke width value of normal characters on license plate, if the stroke width value of described pending characters on license plate is greater than the stroke width value of described normal characters on license plate, then judge described pending license plate image overexposure;
To described pending characters on license plate according to pixels width successively cut down character edge, pending characters on license plate described in refinement.
According to the second aspect of the embodiment of the present invention, provide a kind of license plate image treating apparatus, described device comprises:
Computing unit, for calculating the stroke width value of pending characters on license plate in pending license plate image;
Judging unit, for the stroke width value of more described pending characters on license plate and the stroke width value of normal characters on license plate, if the stroke width value of described pending characters on license plate is greater than the stroke width value of described normal characters on license plate, then judge described pending license plate image overexposure;
Refinement unit, for described pending characters on license plate according to pixels width successively cut down character edge, pending characters on license plate described in refinement.
The application embodiment of the present invention, calculates the stroke width value of pending characters on license plate in pending license plate image by image processing equipment; The stroke width value of more pending characters on license plate and the stroke width value of normal characters on license plate, if the stroke width value of pending characters on license plate is greater than the stroke width value of normal characters on license plate, then judge pending license plate image overexposure; To pending characters on license plate according to pixels width successively cut down character edge, the pending characters on license plate of refinement.After the present invention carries out thinning processing to characters on license plate, solve overexposure characters on license plate and carry out that character after binary conversion treatment is thick, loss in detail, and the problem of easily adhesion, and avoid the contour structures of etching operation destruction character and to the interference that character recognition causes, improve character recognition accuracy.
Accompanying drawing explanation
Accompanying drawing to be herein merged in instructions and to form the part of this instructions, shows embodiment according to the invention, and is used from instructions one and explains principle of the present invention.
Fig. 1 is license plate image process flow figure in one embodiment of the present invention;
Fig. 2 is the process flow diagram judging license plate image whether overexposure in one embodiment of the present invention;
Fig. 3 is a kind of hardware structure diagram of license plate image treating apparatus place equipment in one embodiment of the present invention;
Fig. 4 is license plate image treating apparatus block diagram in one embodiment of the present invention.
Embodiment
For ease of the understanding of the present invention, be further explained explanation below in conjunction with accompanying drawing with specific embodiment, embodiment does not form limiting the scope of the present invention.
The technical scheme that the embodiment of the present invention provides can be applicable to the Car license recognition field of technical field of intelligent traffic, can be applicable to the process to overexposure license plate image.
See Fig. 1, be license plate image process flow figure in one embodiment of the present invention:
Step 101: the gray-scale map obtaining described pending license plate image, carries out binary conversion treatment to described gray-scale map, isolates pending characters on license plate and background.
Preferably, Da-Jin algorithm can be used to carry out binary conversion treatment to pending image, obtain the bianry image that pending characters on license plate and background are separated.Optionally, in bianry image, the pixel value of characters on license plate part is 1, and the pixel value of background parts is 0; The pixel value of characters on license plate part also can be 0, and the pixel value of background parts is 1.In present specification with the pixel value of characters on license plate part for 1, the pixel value of background parts is 0 describe technical solution of the present invention for example.
Step 102: the stroke width value calculating characters on license plate in pending license plate image.
The concrete operation method calculating the stroke width value of pending characters on license plate in pending license plate image can be shown in Figure 2 process flow diagram.
Step 103: the stroke width value of more described pending characters on license plate and the stroke width value of normal characters on license plate, if the stroke width value of described pending characters on license plate is greater than the stroke width value of described normal characters on license plate, then judge described pending license plate image overexposure.
Wherein, the stroke width value of normal characters on license plate is the stroke width value of characters on license plate in the normal license plate image of imaging, and the normal license plate image of imaging is identical with the collection scene of pending license plate image.
Due under different acquisition scene, the characters on license plate stroke width of the license plate image gathered may be different, therefore in order to the accuracy of result of calculation, the normal license plate image of a large amount of imagings is extracted, i.e. normal, the license plate image that do not have overexposure of illumination in the image that can gather under the collection scene of pending image.The character stroke width of the characters on license plate of the normal license plate image of each imaging can be calculated equally according to the method shown in Fig. 2, the character stroke width of the characters on license plate of the normal license plate image of a large amount of imagings is averaged, the normal stroke width value of characters on license plate can be obtained.
Step 104: the difference calculating the stroke width value of described pending characters on license plate and the stroke width value of described normal characters on license plate, arranges refinement threshold value according to difference.
Wherein, refinement threshold value can be refinement number of times, also can be refinement stroke width.
When refinement threshold value is refinement number of times, refinement threshold value is the half of the difference between the stroke width value of pending characters on license plate and the stroke width value of normal car plate; When refinement threshold value is refinement stroke width, refinement threshold value is the difference between the stroke width value of pending characters on license plate and the stroke width value of normal car plate.This is because each Refinement operation, the both sides of stroke all can refinement pixel.Such as, if the normal stroke width value of characters on license plate is 6 pixels, and the current stroke width value of pending image is 10 pixels, difference then between current stroke width value and normal stroke width value is 4 pixels, need refinement 4 pixels, the value of each refinement is 2 pixels, therefore only needs refinement 2 times.Other modes of certain employing arrange threshold value.
Because thinning is set to 0 by the pixel value of the edge pixel by each character to realize, therefore degree of refinement determines and is set to 0 by the pixel value of which floor edge pixel of each character.
Step 105: the coordinate obtaining each character connected component, and the Grad of each character connected component.
Form the criterion of a character connected component according to a character, each Character segmentation of characters on license plate can be opened.The coordinate form of each character connected component can be recorded as the form of (X1, X2, Y1, Y2), namely records the rectangular area on the car plate occupied by each character.Optionally, due to car plate may have some stains, on license plate image, these stains are also shown as independent impurity connected component, before each character connected component of acquisition, can first be removed by impurity connected component.
If but two Characters Stucks together, then these two characters cannot be divided, and two adhesion characters are a character connected component.The follow-up character separating adhesion by thinning.
Step 106: the character edge obtaining each character connected component, and the coordinate figure of all edge pixels of each character connected component.
Concrete, calculate the Grad of each character connected component, Grad sudden change be the edge pixel of character connected component, the character edge of all edge pixels formation characters of each character connected component.Record the coordinate figure of all edge pixels of each character connected component.
Step 107: to described pending characters on license plate according to pixels width successively cut down character edge, when refinement reaches described refinement threshold value, stop refinement.
If the characters on license plate pixel value of bianry image is 1, then after the pixel value of all edge pixels of each character being set to 0, namely achieve abatement one deck character edge.When refinement reaches refinement threshold value, stop refinement.
The definition of successively cutting down character edge in the present embodiment is the outline of according to pixels width delete character, and pixel wide is determined according to setting, such as, can be a pixel wide.
Step 108: if after according to pixels width successively cuts down character edge to the alphabet of described pending characters on license plate, the residue stroke width of characters on license plate is had to be greater than the stroke width of normal character, then judge described pending license plate image inclined position, correct the license plate image after described refinement characters on license plate.
If the license plate image rake ratio gathered is comparatively serious, then after may occurring carrying out thinning processing to characters on license plate, the situation that two or more character is still sticked together, this can carry out correction process to characters on license plate.
Embodiment shown in composition graphs 1 is known, is calculated the stroke width value of pending characters on license plate in pending license plate image by image processing equipment; The stroke width value of more pending characters on license plate and the stroke width value of normal characters on license plate, if the stroke width value of pending characters on license plate is greater than the stroke width value of normal characters on license plate, then judge pending license plate image overexposure; To pending characters on license plate according to pixels width successively cut down character edge, the pending characters on license plate of refinement.After the present invention carries out thinning processing to characters on license plate, solve overexposure characters on license plate and carry out that character after binary conversion treatment is thick, loss in detail, and the problem of easily adhesion, and avoid the contour structures of etching operation destruction character and to the interference that character recognition causes, improve character recognition accuracy.
See Fig. 2, for judging the process flow diagram of license plate image whether overexposure in one embodiment of the present invention:
Step 201: the criterion forming a character connected component according to same character, splits pending characters on license plate.
In the optional implementation of one, due in practical application scene, if the thickness width of any two characters and normal thickness width value are more or less the same in car plate, then the thickness width of all characters on license plate is all little with normal thickness different widths, namely determines license plate image whether overexposure by the thickness width value of any two characters.When splitting characters on license plate, any two characters in characters on license plate can be partitioned into.Preferably, in order to prevent license plate image one edge exposure, divisible go out two characters in the middle of characters on license plate, if general middle two characters do not expose, then whole license plate image does not just expose.
In the optional implementation of another kind, in order to calculate the thickness width value of characters on license plate accurately, also all characters in characters on license plate all can be separated, calculate the thickness width value of each character, and calculate the current thickness width value of mean value as characters on license plate of the thickness width value of each character.If in order to reduce amount of calculation, only can also calculate the thickness width value of certain characters on license plate, but effect may be not ideal.
Specifically can form the criterion of a character connected component to split characters on license plate according to a character, but if two Characters Stucks together, then these two characters cannot be divided, and two adhesion characters are a character connected component.
Step 202: the Grad of calculating character connected component.
Step 203: according to the Grad of character connected component, determines the character edge of character connected component, and records the coordinate figure of all edge pixels of character connected component.
Step 204: according to the coordinate figure of the edge pixel of all character edges, to described pending characters on license plate according to pixels width successively cut down character edge.
Step 205: whether the residue stroke width value judging character connected component is a pixel.
By calculating the Grad of each character connected component after refinement pixel, whether the residue stroke width value determining character connected component is a pixel, if the Grad of character both sides is all sudden change, then the residue stroke width value of description character connected component is a pixel, otherwise is not a pixel.
Wherein, the stroke width value of a character connected component regional may not be identical, in order to avoid certain character Charactes Display after refinement is imperfect, if there is the region that residue stroke width value is a pixel in character connected component, then judge that the residue stroke width value of described character connected component is as a pixel, otherwise judge that the residue stroke width value of described character connected component is not as a pixel.
If so, then perform step 206, otherwise perform step 203.
Step 206: according to the abatement number of times at the described pending characters on license plate edge of abatement, calculate the stroke width value of described pending characters on license plate.
When according to each character connected component, when the thickness width value of the character determined is not identical, to the thickness width value calculating mean value of each character, the stroke width value calculating characters on license plate in pending license plate image can be obtained.
The embodiment of composition graphs 2 is known, by the Grad of calculating character connected component, successively can cut down character edge, and then calculate the thickness width value of each character, follow-uply can carry out refinement according to the difference of the thickness width value of the thickness width value of pending characters on license plate and normal car plate to character.
See Fig. 3, a kind of hardware structure diagram of license plate image treating apparatus place equipment in one embodiment of the present invention:
The embodiment of license plate image treating apparatus of the present invention can be applied on hardware device.Device embodiment can pass through software simulating, also can be realized by the mode of hardware or software and hardware combining.For software simulating, as the device on a logical meaning, be by the CPU of its place equipment, computer program instructions corresponding in nonvolatile memory is read operation in internal memory to be formed.Say from hardware view; as shown in Figure 3; for a kind of hardware structure diagram of license plate image treating apparatus place equipment in one embodiment of the present invention; except the CPU shown in Fig. 3, internal memory, network interface and nonvolatile memory, in embodiment, the equipment at device place can also comprise other hardware usually.
See Fig. 4, be license plate image treating apparatus block diagram in one embodiment of the present invention:
Described device comprises: computing unit 410, judging unit 420, refinement unit 430.
Computing unit, for calculating the stroke width value of pending characters on license plate in pending license plate image;
Judging unit, for the stroke width value of more described pending characters on license plate and the stroke width value of normal characters on license plate, if the stroke width value of described pending characters on license plate is greater than the stroke width value of described normal characters on license plate, then judge described pending license plate image overexposure;
Refinement unit, for described pending characters on license plate according to pixels width successively cut down character edge, pending characters on license plate described in refinement.
Preferably, described computing unit 410 comprises: gray proces subelement 411 (not shown in Fig. 4), for obtaining the gray-scale map of described pending license plate image; Binary conversion treatment subelement 412 (not shown in Fig. 4), for carrying out binary conversion treatment to described gray-scale map, isolates pending characters on license plate and background; Abatement subelement 413, for described pending characters on license plate according to pixels width successively cut down character edge, until abatement is to a surplus pixel wide; Computation subunit 414 (not shown in Fig. 4), for the abatement number of times according to the described pending characters on license plate edge of abatement, calculates the stroke width value of described pending characters on license plate.
Optionally, described computing unit 410, also for the coordinate of the character UNICOM component and character UNICOM component that calculate described pending characters on license plate; Calculate the Grad of described character UNICOM component, the pixel of described Grad sudden change is edge pixel, and all edge pixels of each character UNICOM component form the character edge of character.
Preferably, described refinement unit 430 comprises: arrange subelement 431 (not shown in Fig. 4), for the difference of the stroke width value of the stroke width value and described normal characters on license plate that calculate described pending characters on license plate, refinement threshold value is set according to difference; Refinement subelement 432 (not shown in Fig. 4), for described pending characters on license plate according to pixels width successively cut down character edge, when refinement reaches described refinement threshold value, stop refinement.
Preferably, described device also comprises: described device also comprises: correcting unit 440 (not shown in Fig. 4), if after to the alphabet of described pending characters on license plate, according to pixels width successively cuts down character edge, the residue stroke width of characters on license plate is had to be greater than the stroke width of normal character, then judge described pending license plate image inclined position, correct the license plate image after described refinement characters on license plate.
In said apparatus, the implementation procedure of the function and efficacy of unit specifically refers to the implementation procedure of corresponding step in said method, does not repeat them here.
Those skilled in the art, at consideration instructions and after putting into practice invention disclosed herein, will easily expect other embodiment of the present invention.The application is intended to contain any modification of the present invention, purposes or adaptations, and these modification, purposes or adaptations are followed general principle of the present invention and comprised the undocumented common practise in the art of the present invention or conventional techniques means.Instructions and embodiment are only regarded as exemplary, and true scope of the present invention and spirit are pointed out by claim below.
Should be understood that, the present invention is not limited to precision architecture described above and illustrated in the accompanying drawings, and can carry out various amendment and change not departing from its scope.Scope of the present invention is only limited by appended claim.
Claims (10)
1. a license plate image disposal route, is characterized in that, described method comprises:
Calculate the stroke width value of pending characters on license plate in pending license plate image;
The stroke width value of more described pending characters on license plate and the stroke width value of normal characters on license plate, if the stroke width value of described pending characters on license plate is greater than the stroke width value of described normal characters on license plate, then judge described pending license plate image overexposure;
To described pending characters on license plate according to pixels width successively cut down character edge, pending characters on license plate described in refinement.
2. method according to claim 1, is characterized in that, the stroke width value of pending characters on license plate in the pending license plate image of described calculating, comprising:
Obtain the gray-scale map of described pending license plate image;
Binary conversion treatment is carried out to described gray-scale map, isolates pending characters on license plate and background;
To described pending characters on license plate according to pixels width successively cut down character edge, until abatement is to a surplus pixel wide;
According to the abatement number of times at the described pending characters on license plate edge of abatement, calculate the stroke width value of described pending characters on license plate.
3. method according to claim 1 and 2, is characterized in that, described method also comprises:
Calculate the character UNICOM component of described pending characters on license plate and the coordinate of character UNICOM component;
Calculate the Grad of described character UNICOM component, the pixel of described Grad sudden change is edge pixel, and all edge pixels of each character UNICOM component form the character edge of character.
4. method according to claim 3, is characterized in that, pending characters on license plate described in described refinement, comprising:
Calculate the difference of the stroke width value of described pending characters on license plate and the stroke width value of described normal characters on license plate, refinement threshold value is set according to difference;
To described pending characters on license plate according to pixels width successively cut down character edge, when refinement reaches described refinement threshold value, stop refinement.
5. method according to claim 1, it is characterized in that, described method also comprises: if after to the alphabet of described pending characters on license plate, according to pixels width successively cuts down character edge, the residue stroke width of characters on license plate is had to be greater than the stroke width of normal character, then judge described pending license plate image inclined position, correct the license plate image after described refinement characters on license plate.
6. a license plate image treating apparatus, is characterized in that, described device comprises:
Computing unit, for calculating the stroke width value of pending characters on license plate in pending license plate image;
Judging unit, for the stroke width value of more described pending characters on license plate and the stroke width value of normal characters on license plate, if the stroke width value of described pending characters on license plate is greater than the stroke width value of described normal characters on license plate, then judge described pending license plate image overexposure;
Refinement unit, for described pending characters on license plate according to pixels width successively cut down character edge, pending characters on license plate described in refinement.
7. device according to claim 6, is characterized in that, described computing unit comprises:
Gray proces subelement, for obtaining the gray-scale map of described pending license plate image;
Binary conversion treatment subelement, for carrying out binary conversion treatment to described gray-scale map, isolates pending characters on license plate and background;
Abatement subelement, for described pending characters on license plate according to pixels width successively cut down character edge, until abatement is to a surplus pixel wide;
Computation subunit, for the abatement number of times according to the described pending characters on license plate edge of abatement, calculates the stroke width value of described pending characters on license plate.
8. the device according to claim 6 or 7, is characterized in that, described computing unit, also for the coordinate of the character UNICOM component and character UNICOM component that calculate described pending characters on license plate; Calculate the Grad of described character UNICOM component, the pixel of described Grad sudden change is edge pixel, and all edge pixels of each character UNICOM component form the character edge of character.
9. device according to claim 8, is characterized in that, described refinement unit comprises:
Subelement is set, for the difference of the stroke width value of the stroke width value and described normal characters on license plate that calculate described pending characters on license plate, refinement threshold value is set according to difference;
Refinement subelement, for described pending characters on license plate according to pixels width successively cut down character edge, when refinement reaches described refinement threshold value, stop refinement.
10. device according to claim 6, it is characterized in that, described device also comprises: correcting unit, if after to the alphabet of described pending characters on license plate, according to pixels width successively cuts down character edge, the residue stroke width of characters on license plate is had to be greater than the stroke width of normal character, then judge described pending license plate image inclined position, correct the license plate image after described refinement characters on license plate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510924361.XA CN105447831B (en) | 2015-12-14 | 2015-12-14 | License plate image processing method and processing device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510924361.XA CN105447831B (en) | 2015-12-14 | 2015-12-14 | License plate image processing method and processing device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105447831A true CN105447831A (en) | 2016-03-30 |
| CN105447831B CN105447831B (en) | 2019-02-15 |
Family
ID=55557965
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510924361.XA Active CN105447831B (en) | 2015-12-14 | 2015-12-14 | License plate image processing method and processing device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105447831B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780351A (en) * | 2016-12-09 | 2017-05-31 | 浙江浩腾电子科技股份有限公司 | A kind of license plate sloped antidote |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116751A (en) * | 2013-01-24 | 2013-05-22 | 河海大学 | Automatic license plate character recognition method |
-
2015
- 2015-12-14 CN CN201510924361.XA patent/CN105447831B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116751A (en) * | 2013-01-24 | 2013-05-22 | 河海大学 | Automatic license plate character recognition method |
Non-Patent Citations (1)
| Title |
|---|
| 王飞: "在车牌自动识别系统中对字符的分割与识别的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780351A (en) * | 2016-12-09 | 2017-05-31 | 浙江浩腾电子科技股份有限公司 | A kind of license plate sloped antidote |
| CN106780351B (en) * | 2016-12-09 | 2019-11-29 | 浙江浩腾电子科技股份有限公司 | A kind of license plate sloped antidote |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105447831B (en) | 2019-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5521164B2 (en) | Image processing system and method for identifying consecutive alphanumeric characters | |
| US12175770B2 (en) | Lane extraction method using projection transformation of three-dimensional point cloud map | |
| CN109492642B (en) | License plate recognition method, license plate recognition device, computer equipment and storage medium | |
| US11164012B2 (en) | Advanced driver assistance system and method | |
| CN108154149B (en) | License plate recognition method based on deep learning network sharing | |
| CN108256445B (en) | Lane line detection method and system | |
| KR101483742B1 (en) | Lane Detection method for Advanced Vehicle | |
| CN114463286B (en) | A method for road surface point cloud smoothing and crack information processing based on moving window | |
| CN109886122B (en) | Lane line detection method, lane line detection device, computer device, and storage medium | |
| CN103136528A (en) | Double-edge detection based vehicle license plate identification method | |
| CN107909571A (en) | A kind of weld beam shape method, system, equipment and computer-readable storage medium | |
| CN104598905A (en) | License plate positioning method and device | |
| CN101436300B (en) | Method and apparatus for dividing barrier | |
| CN109377515A (en) | A moving target detection method and system based on improved ViBe algorithm | |
| CN106650732B (en) | License plate recognition method and device | |
| CN113628202A (en) | Determination method, cleaning robot and computer storage medium | |
| CN111159150A (en) | Data expansion method and device | |
| CN107274673B (en) | Vehicle Queue Length Measurement Method and Measurement System Based on Modified Local Variance | |
| CN112990207A (en) | License plate image extraction method, device and system, storage medium and computer equipment | |
| CN111488762A (en) | Lane-level positioning method and device and positioning equipment | |
| CN117315406B (en) | Sample image processing method, device and equipment | |
| CN105447831A (en) | License plate image processing method and apparatus | |
| Chen et al. | Algorithm design of lane departure warning system based on image processing | |
| CN101408977A (en) | Method and apparatus for dividing candidate barrier region | |
| CN114581890B (en) | Method and device for determining lane line, electronic equipment and 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 |