CN105447831B - License plate image processing method and processing device - Google Patents
License plate image processing method and processing device Download PDFInfo
- Publication number
- CN105447831B CN105447831B CN201510924361.XA CN201510924361A CN105447831B CN 105447831 B CN105447831 B CN 105447831B CN 201510924361 A CN201510924361 A CN 201510924361A CN 105447831 B CN105447831 B CN 105447831B
- Authority
- CN
- China
- Prior art keywords
- license plate
- characters
- processed
- character
- 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.)
- Active
Links
- 238000012545 processing Methods 0.000 title claims abstract description 17
- 238000003672 processing method Methods 0.000 title claims abstract description 9
- 238000000034 method Methods 0.000 claims abstract description 15
- 238000006243 chemical reaction Methods 0.000 claims abstract description 14
- 230000035772 mutation Effects 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 5
- 238000005530 etching Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000015654 memory Effects 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 3
- 238000007670 refining Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 239000012535 impurity Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012544 monitoring process Methods 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)
- Traffic Control Systems (AREA)
- Character Input (AREA)
Abstract
The present invention provides license plate image processing method and processing device, this method comprises: calculating the stroke width value of characters on license plate to be processed in license plate image to be processed；Compare the stroke width value of the characters on license plate to be processed and the stroke width value of normal characters on license plate, if the stroke width value of the characters on license plate to be processed is greater than the stroke width value of the normal characters on license plate, determines the license plate image overexposure to be processed；Character edge is successively cut down by pixel wide to the characters on license plate to be processed, refines the characters on license plate to be processed.After carrying out binary conversion treatment to overexposure image, coarse character, loss in detail can be solved the problem of using the present invention and is easy adhesion, improves the accuracy of Recognition of License Plate Characters.
Description
Technical field
The present invention relates to field of intelligent transportation technology more particularly to a kind of license plate image processing method and processing devices.
Background technique
Currently, the quantity of motor vehicles is more and more, it is increasing to the management difficulty of motor vehicles, and Car license recognition
Management difficulty to motor vehicles will be effectively reduced in intelligence.But there is Car license recognition shadow to interfere more, the spies such as environment complexity
Point, such as in actual bayonet monitoring system, electronic police system application, influence of the illumination to Car license recognition is maximum, wherein
License plate overexposure problem caused by environmental factor (sun light direct beam) or light filling factor is commonplace, brings to Car license recognition
Very big challenge.
In the prior art, due to coarse to the characters on license plate after overexposure license plate image progress binary conversion treatment, details is lost
It loses, and is easy adhesion, therefore etching operation can be carried out to the image after binary conversion treatment, so that the image after binary conversion treatment
Reduce a circle.But etching operation is it needs to be determined that corrode filter window, and the edge of characters on license plate is variation, and is mellow and full
Variation, corrode the contour structures that can destroy character to characters on license plate with the corrosion window for determining shape, to character recognition
It interferes.
Summary of the invention
The present invention provides a kind of license plate image processing method and processing device, with solve in the prior art to overexposure license plate image into
Character is coarse after row binary conversion treatment, loss in detail, and the problem of be easy adhesion, and avoid the prior art to character into
The contour structures of character are destroyed caused by row etching operation and are interfered caused by character recognition.
According to a first aspect of the embodiments of the present invention, a kind of license plate image processing method is provided, which comprises
Calculate the stroke width value of characters on license plate to be processed in license plate image to be processed；
Compare the stroke width value of the characters on license plate to be processed and the stroke width value of normal characters on license plate, if it is described to
The stroke width value for handling characters on license plate is greater than the stroke width value of the normal characters on license plate, then determines the license plate to be processed
Image overexposure；
Character edge is successively cut down by pixel wide to the characters on license plate to be processed, refines the license plate word to be processed
Symbol.
According to a second aspect of the embodiments of the present invention, a kind of license plate image processing unit is provided, described device includes:
Computing unit, for calculating the stroke width value of characters on license plate to be processed in license plate image to be processed；
Judging unit, it is wide for the stroke width value of the characters on license plate to be processed and the stroke of normal characters on license plate
Angle value determines if the stroke width value of the characters on license plate to be processed is greater than the stroke width value of the normal characters on license plate
The license plate image overexposure to be processed；
Unit is refined, for successively cutting down character edge by pixel wide to the characters on license plate to be processed, described in refinement
Characters on license plate to be processed.
Using the embodiment of the present invention, characters on license plate to be processed in license plate image to be processed is calculated by image processing equipment
Stroke width value；The stroke width value of characters on license plate more to be processed and the stroke width value of normal characters on license plate, if to be processed
The stroke width value of characters on license plate is greater than the stroke width value of normal characters on license plate, then determines license plate image overexposure to be processed；It is right
Characters on license plate to be processed successively cuts down character edge by pixel wide, refines characters on license plate to be processed.The present invention is to characters on license plate
After carrying out micronization processes, solves overexposure characters on license plate and carry out after binary conversion treatment that character is coarse, loss in detail, and be easy viscous
Even the problem of, and contour structures and the interference caused by character recognition that etching operation destroys character are avoided, improve word
Symbol identification accuracy.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows and meets implementation of the invention
Example, and be used to explain the principle of the present invention together with specification.
Fig. 1 is license plate image processing method flow chart in one embodiment of the present invention；
Fig. 2 be one embodiment of the present invention in judge license plate image whether the flow chart of overexposure；
Fig. 3 is a kind of hardware structure diagram of equipment where license plate image processing unit in one embodiment of the present invention；
Fig. 4 is license plate image processing unit block diagram in one embodiment of the present invention.
Specific embodiment
It is real to be further explained explanation below in conjunction with attached drawing with specific embodiment convenient for the understanding of the present invention
Example is applied to be not intended to limit the scope of the present invention..
Technical solution provided in an embodiment of the present invention can be applied to the Car license recognition field of field of intelligent transportation technology, can answer
For the processing to overexposure license plate image.
It is license plate image processing method flow chart in one embodiment of the present invention referring to Fig. 1:
Step 101: the grayscale image of the license plate image to be processed is obtained, binary conversion treatment is carried out to the grayscale image, point
Separate out characters on license plate to be processed and background.
Preferably, it Da-Jin algorithm can be used to carry out binary conversion treatment to image to be processed, obtain characters on license plate and back to be processed
The separated bianry image of scape.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 can also be 0, and the pixel value of background parts is 1.With characters on license plate part in present specification
Pixel value be 1, the pixel values of background parts describes technical solution of the present invention for being 0.
Step 102: calculating the stroke width value of characters on license plate in license plate image to be processed.
The concrete operation method for calculating the stroke width value of characters on license plate to be processed in license plate image to be processed can be found in Fig. 2
Shown in flow chart.
Step 103: the stroke width value of the characters on license plate to be processed and the stroke width value of normal characters on license plate,
If the stroke width value of the characters on license plate to be processed is greater than the stroke width value of the normal characters on license plate, determine it is described to
Handle license plate image overexposure.
Wherein, the stroke width value of normal characters on license plate is the stroke width of characters on license plate in the normal license plate image of imaging
Value, it is identical as the acquisition scene of license plate image to be processed to be imaged normal license plate image.
Since under different acquisition scene, the characters on license plate stroke width of license plate image collected may be different, therefore are
It is normal can to extract a large amount of imaging in the image acquired under the acquisition scene of image to be processed for the accuracy of calculated result
License plate image, i.e. illumination be normal, not overexposure license plate image.Equally each imaging can be calculated according to method shown in Fig. 2
The character stroke width of the characters on license plate of normal license plate image, to the characters on license plate that normal license plate image is largely imaged
Character stroke width is averaged, and the normal stroke width value of characters on license plate can be obtained.
Step 104: the stroke width value for calculating the characters on license plate to be processed and the stroke of the normal characters on license plate are wide
Refinement threshold value is arranged according to difference in the difference of angle value.
Wherein, refinement threshold value can be refinement number, be also possible to refine stroke width.
When refinement threshold value is refinement number, stroke width value and normal license plate of the refinement threshold value for characters on license plate to be processed
The half of difference between stroke width value；Refining threshold value is when refining stroke width, and refinement threshold value is characters on license plate to be processed
Stroke width value and normal license plate stroke width value between difference.This is because each Refinement operation, the two sides of stroke
A pixel can all be refined.For example, if the normal stroke width value of characters on license plate is 6 pixels, and image to be processed is worked as
Preceding stroke width value is 10 pixels, then the difference between current stroke width value and normal stroke width value is 4 pixels, is needed
4 pixels are refined, the value refined every time is 2 pixels, therefore only needs to refine 2 times.Certainly using other modes come
Threshold value is set.
Because thinning is realized by the way that the pixel value of the edge pixel of each character is set 0, journey is refined
Degree determines that the pixel value by several layers of edge pixels of each character sets 0.
Step 105: obtaining the coordinate of each character connected component and the gradient value of each character connected component.
The criterion that a character connected component is constituted according to a character, can open each Character segmentation of characters on license plate.
The coordinate form of each character connected component can record as the form of (X1, X2, Y1, Y2), that is, record occupied by each character
Rectangular area on license plate.Optionally, due to that may have some stains on license plate, these stains are also displayed as on license plate image
Individual impurity connected component can first remove impurity connected component before obtaining each character connected component.
But if two Characters Stucks together, the two characters will be unable to be divided, and two adhesion characters are one
A character connected component.The subsequent character that adhesion can be separated by thinning.
Step 106: obtaining the character edge of each character connected component and all edges of each character connected component
The coordinate value of pixel.
Specifically, calculating the gradient value of each character connected component, gradient value mutation is the edge of character connected component
Pixel, all edge pixels of each character connected component constitute the character edge of character.Record each character connected component
The coordinate value of all edge pixels.
Step 107: character edge successively being cut down by pixel wide to the characters on license plate to be processed, when refinement reaches described
When refining threshold value, stop refinement.
If the characters on license plate pixel value of bianry image is 1, the pixel value of all edge pixels of each character is set
After 0, that is, realize one layer of character edge of abatement.When refinement reaches refinement threshold value, stop refinement.
The definition for successively cutting down character edge in the present embodiment is the outer profile that character is eliminated by pixel wide, pixel wide
Depending on setting, such as it can be a pixel wide.
Step 108: if successively cutting down character edge by pixel wide to the alphabet of the characters on license plate to be processed
Afterwards, there is the remaining stroke width of characters on license plate to be greater than the stroke width of normal character, then determine the license plate image position to be processed
Inclination is set, the license plate image after correcting the refinement characters on license plate.
If the license plate image rake ratio of acquisition is more serious, it is likely to occur after carrying out micronization processes to characters on license plate, two
The case where a or more than two characters are still sticked together, this is that processing can be corrected to characters on license plate.
Embodiment as shown in connection with fig. 1 is it is found that calculate vehicle to be processed in license plate image to be processed by image processing equipment
The stroke width value of board character；The stroke width value of characters on license plate more to be processed and the stroke width value of normal characters on license plate,
If the stroke width value of characters on license plate to be processed is greater than the stroke width value of normal characters on license plate, license plate image to be processed is determined
Overexposure；Character edge is successively cut down by pixel wide to characters on license plate to be processed, refines characters on license plate to be processed.The present invention is to vehicle
After board character carries out micronization processes, solves overexposure characters on license plate and carry out after binary conversion treatment that character is coarse, loss in detail, and
The problem of being easy adhesion, and contour structures and the interference caused by character recognition that etching operation destroys character are avoided, it mentions
High character recognition accuracy.
Referring to fig. 2, for judge in one embodiment of the present invention license plate image whether the flow chart of overexposure:
Step 201: constituting the criterion of a character connected component according to the same character, characters on license plate to be processed is carried out
Segmentation.
In an optional implementation manner, due in practical application scene, if any two character in license plate
Thickness width is not much different with normal thickness width value, then the thickness width of all characters on license plate all with normal thickness different widths
Less, can be determined by the thickness width value of any two character license plate image whether overexposure.It is carried out to characters on license plate
When segmentation, any two character that can be partitioned into characters on license plate.Preferably, one edge exposure of license plate image in order to prevent, can
Two characters being partitioned among characters on license plate, if two characters in general centre do not expose, entire license plate image does not just have
There is exposure.
In another optional implementation, in order to calculate the thickness width value of accurate characters on license plate, it can also incite somebody to action
All characters in characters on license plate all separate, and calculate the thickness width value of each character, and the thickness for calculating each character is wide
Current thickness width value of the average value of angle value as characters on license plate.If can also only be calculated to reduce amount of calculation
The thickness width value of some characters on license plate, but effect may be not satisfactory.
The criterion of a character connected component can be constituted according to character specifically to divide characters on license plate, but if two
Together, then the two characters will be unable to be divided a Characters Stuck, and two adhesion characters are a character connected component.
Step 202: the gradient value of calculating character connected component.
Step 203: according to the gradient value of character connected component, determining the character edge of character connected component, and record word
Accord with the coordinate value of all edge pixels of connected component.
Step 204: according to the coordinate value of the edge pixel of all character edges, pixel being pressed to the characters on license plate to be processed
Width successively cuts down character edge.
Step 205: whether the remaining stroke width value for judging character connected component is a pixel.
The gradient value of each character connected component after a pixel can be refined, by calculating to determine character connected component
Remaining stroke width value whether be a pixel, if the gradient value of character two sides is all mutation, illustrate character connection point
The remaining stroke width value of amount is a pixel, is not otherwise a pixel.
Wherein, the stroke width value of a character connected component each region may not be identical, in order to avoid some character
Character is shown imperfect after refinement, if there is the region that remaining stroke width value is a pixel in character connected component,
The remaining stroke width value for determining the character connected component is a pixel, otherwise determines the residue of the character connected component
Stroke width value is not a pixel.
If so, 206 are thened follow the steps, it is no to then follow the steps 203.
Step 206: according to the abatement number for cutting down the characters on license plate edge to be processed, calculating the license plate word to be processed
The stroke width value of symbol.
It, can be to each character when the thickness width value of determining character is not identical when according to each character connected component
Thickness width value calculates average value, obtains the stroke width value for calculating characters on license plate in license plate image to be processed.
In conjunction with Fig. 2 embodiment it is found that by the gradient value of calculating character connected component, can successively cut down character edge,
And then calculate the thickness width value of each character, it is subsequent can be according to the thickness width value and normal license plate of characters on license plate to be processed
The difference of thickness width value character is refined.
Referring to Fig. 3, a kind of hardware structure diagram of equipment where license plate image processing unit in one embodiment of the present invention:
The embodiment of license plate image processing unit of the present invention can be applied on hardware device.Installation practice can pass through
Software realization can also be realized by way of hardware or software and hardware combining.Taking software implementation as an example, it anticipates as a logic
Device in justice is to be read computer program instructions corresponding in nonvolatile memory by the CPU of equipment where it
Operation is formed in memory.For hardware view, as shown in figure 3, for license plate image processing in one embodiment of the present invention
A kind of hardware structure diagram of equipment where device, in addition to CPU shown in Fig. 3, memory, network interface and non-volatile memories
Except device, the equipment in embodiment where device usually can also include other hardware.
Referring to fig. 4, it is license plate image processing unit block diagram in one embodiment of the present invention:
Described device includes: computing unit 410, and judging unit 420 refines unit 430.
Computing unit, for calculating the stroke width value of characters on license plate to be processed in license plate image to be processed；
Judging unit, it is wide for the stroke width value of the characters on license plate to be processed and the stroke of normal characters on license plate
Angle value determines if the stroke width value of the characters on license plate to be processed is greater than the stroke width value of the normal characters on license plate
The license plate image overexposure to be processed；
Unit is refined, for successively cutting down character edge by pixel wide to the characters on license plate to be processed, described in refinement
Characters on license plate to be processed.
Preferably, the computing unit 410 includes: gray proces subelement 411 (being not shown in Fig. 4), for obtaining
State the grayscale image of license plate image to be processed；Binary conversion treatment subelement 412 (is not shown) in Fig. 4, for the grayscale image into
Row binary conversion treatment isolates characters on license plate to be processed and background；Cut down subelement 413, for the license plate word to be processed
Symbol successively cuts down character edge by pixel wide, until abatement to a surplus pixel wide；Computation subunit 414 (is not shown in Fig. 4
Out), for calculating the stroke of the characters on license plate to be processed according to the abatement number for cutting down the characters on license plate edge to be processed
Width value.
Optionally, the computing unit 410, be also used to calculate the characters on license plate to be processed character connection component and
The coordinate of character connection component；The gradient value of the character connection component is calculated, the pixel of the gradient value mutation is edge picture
Element, all edge pixels of each character connection component constitute the character edge of character.
Preferably, the refinement unit 430 includes: setting subelement 431 (being not shown in Fig. 4), for calculate it is described to
The difference for handling the stroke width value of characters on license plate and the stroke width value of the normal characters on license plate is arranged according to difference and refines
Threshold value；It refines subelement 432 (being not shown in Fig. 4), for successively cutting down word by pixel wide to the characters on license plate to be processed
Edge is accorded with, when refinement reaches the refinement threshold value, stops refinement.
Preferably, described device further include: described device further include: correction unit 440 (being not shown in Fig. 4), for such as
After fruit successively cuts down character edge by pixel wide to the alphabet of the characters on license plate to be processed, there is the residue of characters on license plate
Stroke width is greater than the stroke width of normal character, then determines the license plate image position inclination to be processed, correct the refinement
License plate image after characters on license plate.
The function of each unit and the realization process of effect are specifically detailed in the above method and correspond to step in above-mentioned apparatus
Realization process, details are not described herein.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to of the invention its
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the invention, these modifications, purposes or
Person's adaptive change follows general principle of the invention and including the undocumented common knowledge in the art of the present invention
Or conventional techniques.The description and examples are only to be considered as illustrative, and true scope and spirit of the invention are by following
Claim is pointed out.
It should be understood that the present invention is not limited to the precise structure already described above and shown in the accompanying drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present invention is limited only by the attached claims.
Claims (8)
1. a kind of license plate image processing method, which is characterized in that the described method includes:
Calculate the stroke width value of characters on license plate to be processed in license plate image to be processed；
Compare the stroke width value of the characters on license plate to be processed and the stroke width value of normal characters on license plate, if described to be processed
The stroke width value of characters on license plate is greater than the stroke width value of the normal characters on license plate, then determines the license plate image to be processed
Overexposure；
Calculate the character connection component of the characters on license plate to be processed and the coordinate of character connection component；
The gradient value of the character connection component is calculated, the pixel of the gradient value mutation is edge pixel, each character connection
All edge pixels of component constitute the character edge of character；
Character edge is successively cut down by pixel wide to the characters on license plate to be processed, refines the characters on license plate to be processed.
2. the method according to claim 1, wherein described calculate license plate word to be processed in license plate image to be processed
The stroke width value of symbol, comprising:
Obtain the grayscale image of the license plate image to be processed；
Binary conversion treatment is carried out to the grayscale image, isolates characters on license plate to be processed and background；
Character edge is successively cut down by pixel wide to the characters on license plate to be processed, until abatement to a surplus pixel wide；
According to the abatement number for cutting down the characters on license plate edge to be processed, the stroke width of the characters on license plate to be processed is calculated
Value.
3. the method according to claim 1, wherein the refinement characters on license plate to be processed, comprising:
Calculate the difference of the stroke width value of the characters on license plate to be processed and the stroke width value of the normal characters on license plate, root
According to difference, refinement threshold value is set；
Character edge is successively cut down by pixel wide to the characters on license plate to be processed, when refinement reaches the refinement threshold value,
Stop refinement.
4. the method according to claim 1, wherein the method also includes: if to the license plate to be processed
After the alphabet of character successively cuts down character edge by pixel wide, there is the remaining stroke width of characters on license plate to be greater than good word
The stroke width of symbol then determines the license plate image position inclination to be processed, the license plate figure after correcting the refinement characters on license plate
Picture.
5. a kind of license plate image processing unit, which is characterized in that described device includes:
Computing unit calculates described wait locate for calculating the stroke width value of characters on license plate to be processed in license plate image to be processed
The character connection component of characters on license plate and the coordinate of character connection component are managed, the gradient value of the character connection component is calculated,
The pixel of the gradient value mutation is edge pixel, and all edge pixels of each character connection component constitute the character side of character
Edge；
Judging unit, for the stroke width value of the characters on license plate to be processed and the stroke width of normal characters on license plate
Value determines institute if the stroke width value of the characters on license plate to be processed is greater than the stroke width value of the normal characters on license plate
State license plate image overexposure to be processed；
Unit is refined, for successively cutting down character edge by pixel wide to the characters on license plate to be processed, refinement is described wait locate
Manage characters on license plate.
6. device according to claim 5, which is characterized in that the computing unit includes:
Gray proces subelement, for obtaining the grayscale image of the license plate image to be processed；
Binary conversion treatment subelement isolates characters on license plate and back to be processed for carrying out binary conversion treatment to the grayscale image
Scape；
Cut down subelement, for successively cutting down character edge by pixel wide to the characters on license plate to be processed, until abatement arrives
Remain a pixel wide；
Computation subunit, for calculating the vehicle to be processed according to the abatement number for cutting down the characters on license plate edge to be processed
The stroke width value of board character.
7. device according to claim 5, which is characterized in that the refinement unit includes:
Subelement is set, for calculating the stroke width value of the characters on license plate to be processed and the stroke of the normal characters on license plate
Refinement threshold value is arranged according to difference in the difference of width value；
Subelement is refined, for successively cutting down character edge by pixel wide to the characters on license plate to be processed, when refinement reaches
When the refinement threshold value, stop refinement.
8. device according to claim 5, which is characterized in that described device further include: correction unit, if for institute
State characters on license plate to be processed alphabet successively cut down character edge by pixel wide after, have the remaining stroke of characters on license plate wide
Degree is greater than the stroke width of normal character, then determines the license plate image position inclination to be processed, correct the refinement license plate word
License plate image after symbol.
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 CN105447831A (en) | 2016-03-30 |
| CN105447831B true 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) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
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 |
|---|
| 在车牌自动识别系统中对字符的分割与识别的研究;王飞;《中国优秀硕士学位论文全文数据库 信息科技辑》;20070515;第I138-1103页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105447831A (en) | 2016-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9811921B2 (en) | Apparatus and method for processing a depth image | |
| CN109492642B (en) | License plate recognition method, license plate recognition device, computer equipment and storage medium | |
| CN107316326B (en) | Edge-based disparity map calculation method and device applied to binocular stereo vision | |
| JP2016513320A (en) | Method and apparatus for image enhancement and edge verification using at least one additional image | |
| KR20150079638A (en) | Image processing method and apparatus for elimination of depth artifacts | |
| CN108154149B (en) | License plate recognition method based on deep learning network sharing | |
| CN108009522B (en) | Road detection method, device and terminal | |
| CN109447117B (en) | Double-layer license plate recognition method and device, computer equipment and storage medium | |
| CN106373128B (en) | Method and system for accurately positioning lips | |
| US20210088441A1 (en) | Deposit detection device and deposit detection method | |
| US20130022236A1 (en) | Apparatus Capable of Detecting Location of Object Contained in Image Data and Detection Method Thereof | |
| CN112154479A (en) | Method for extracting feature points, movable platform and storage medium | |
| CN111382745A (en) | Nail image segmentation method, device, equipment and storage medium | |
| CN111222514B (en) | Local map optimization method based on visual positioning | |
| CN112233049A (en) | Image fusion method for improving image definition | |
| CN106663317B (en) | Morphological processing method and digital image processing device for digital image | |
| CN105447831B (en) | License plate image processing method and processing device | |
| CN112184723B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN110728276B (en) | License plate recognition method and device | |
| CN104408430B (en) | License plate positioning method and device | |
| CN115937825B (en) | Method and device for generating robust lane line under BEV of on-line pitch angle estimation | |
| CN107292840B (en) | Image restoration method and device, computer-readable storage medium and terminal | |
| CN117132503A (en) | Method, system, equipment and storage medium for repairing local highlight region of image | |
| CN117710703A (en) | Image processing method, device, computer equipment and readable storage medium | |
| CN116597421A (en) | Parking space monitoring method, device and equipment based on image recognition |
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 |