CN109214380A - License plate sloped correcting method - Google Patents
License plate sloped correcting method Download PDFInfo
- Publication number
- CN109214380A CN109214380A CN201811062278.6A CN201811062278A CN109214380A CN 109214380 A CN109214380 A CN 109214380A CN 201811062278 A CN201811062278 A CN 201811062278A CN 109214380 A CN109214380 A CN 109214380A
- Authority
- CN
- China
- Prior art keywords
- angle point
- license plate
- pixel
- pixel value
- image
- 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
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
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/243—Aligning, centring, orientation detection or correction of the image by compensating for image skew or non-uniform image deformations
Abstract
The invention proposes a kind of license plate sloped correcting method, including the following steps: S1 obtains license plate rgb format image, and the rgb format image is converted to HSI format-pattern, extracts the S component map in HSI format-pattern；S2 detects the angular coordinate of S component map；S3, the angular coordinate deposit two-dimensional matrix L that will test；S4 finds lower-left angle point, upper left angle point, bottom right angle point and upper right angle point；S5, according to upper left angle point, upper right angle point, lower-left angle point and bottom right angle point coordinate, find out two horizontal slopes and two vertical slopes respectively, and find out the mean value of two horizontal slopes and the mean value of two vertical slopes；S6 finds out inclination alpha according to formula tan α=k of slope and inclination angle: S7, completes license plate sloped correction according to inclination alpha.This method calculates simply, converts picture into HSI format, and calculate the S component map under the format, effectively eliminates influence of the brightness to product slant correction, can quickly realize license plate sloped correction.
Description
Technical field
The present invention relates to computer fields, and in particular to a kind of license plate sloped correcting method.
Background technique
With the development of national economy, for automobile at the walking-replacing tool of most family's indispensabilities, the quantity of automobile gives traffic pipe
Reason causes immense pressure.Intelligent transportation system can well solve the pressure of traffic administration, and Car license recognition is handed over as intelligence
The nucleus module of way system, has great importance.License plate sloped correction is the one of committed step of Vehicle License Plate Recognition System, directly
Connect the result for influencing Car license recognition.
Ideally, the license plate image of acquisition is the rectangle of one with horizontal direction parallel.Since video camera is shot
The factors such as angle, vehicle heading and speed, camera lens and license plate distance cause the image of acquisition to there is certain inclination, therefore need
Slant correction is carried out to license plate image, provides good basis for subsequent License Plate Segmentation and Car license recognition.Currently, license plate image inclines
The method tiltedly corrected mainly has the methods of straight-line detection, projection most value, Corner Detection and principal component analysis.(1) it is examined based on straight line
The sloped correcting method of survey mainly has least square fitting method, Hough transform and Radon converter technique, these methods pass through detection
The straight line of license plate frame completes correction, and algorithm is simple.(2) it completes to correct by sciagraphy based on the slant correction that projection is most worth,
Strong antijamming capability.(3) slant correction based on Corner Detection utilizes angle point feature --- things can be indicated with minimum information
Main feature, license plate sloped correction can be effectively completed.(4) slant correction based on principal component analysis passes through analysis license plate
Main feature completes slant correction, can simplify calculation amount, the real-time of correction is preferable.This 4 kinds of methods can complete license plate
Slant correction, but it is all sensitive to bright and dark light.
Summary of the invention
In order to overcome above-mentioned defect existing in the prior art, the object of the present invention is to provide a kind of license plate sloped correction sides
Method system.
In order to realize above-mentioned purpose of the invention, the present invention provides a kind of license plate sloped correcting methods, which is characterized in that
Including the following steps:
It is same to obtain license plate rgb format image, and the rgb format image is converted to HSI format-pattern by S1, extracts HSI lattice
S component map in formula image；
S2 detects the angular coordinate of S component map；
S3, the angular coordinate deposit two-dimensional matrix L that will test；
S4 finds lower-left angle point, upper left angle point, bottom right angle point and upper right angle point；
Wherein, the abscissa of lower-left angle point is minimum, and ordinate is minimum；The abscissa of upper left angle point is minimum, and ordinate is maximum；
The abscissa of bottom right angle point is maximum, and ordinate is minimum；Upper right angle point abscissa is maximum, the maximum angle point of ordinate；
It is oblique to find out two levels according to the coordinate of upper left angle point and upper right angle point, lower-left angle point and bottom right angle point respectively by S5
Rate and two vertical slopes, and find out the mean value of two horizontal slopes and the mean value of two vertical slopes；
S6 finds out inclination alpha according to formula tan α=k of slope and inclination angle:
S7 completes license plate sloped correction according to inclination alpha.
This method calculates simply, converts picture into HSI format, and calculate the S component map under the format, effectively
Influence of the brightness to product slant correction is eliminated, license plate sloped correction is quickly realized.
Further, the step S2 including the following steps:
S2-1, described with the gray-value variation in horizontal and vertical direction pixel in any direction on grey scale change, retouch
The formula of stating is
Wherein, I (x+u, y+v)=I (x, y)+Ixu+Iyv+O(u2,v2), (x, y) is target pixel points coordinate；(u, v) table
Show offset of other pixels relative to target pixel points；ωu,vFor weighted window function, I is image array, IxAnd IyRespectively
Indicate image array I in the horizontal direction with the first-order partial derivative of vertical direction.
S2-2 obtains the autocorrelation matrix M of pixel (x, y): ignoring the higher-order shear deformation in foregoing description formulaIt obtainsWherein,M is
The autocorrelation matrix of pixel (x, y)；
S2-3 enables autocorrelation matrix M=0, obtains two non-negative eigenvalue λs of matrix M1And λ2If λ1≥λ2；
S2-4 works as λ2When greater than setting first threshold, then target pixel points are angle point；
Work as λ2The λ equal to 01When greater than first threshold, shows that target pixel points are located at edge, execute step S2-5；
Work as λ1Equal to 0, shows that target pixel points are located at flat site, execute step S2-5；
S2-5 calculates the angle point response R of pixel (x, y):
S2-6 traverses all pixels point of whole picture S component map, executes step S2-1 to step S2-6, calculates all pixels
The angle point response R of point；
S2-7, if there is the response of pixel to be less than Th1, which is not angle point, and pixel value is assigned to B；If there is picture
The response of vegetarian refreshments is greater than Th1And it is less than Th2, which is candidate angular, and pixel value is assigned to C；If there is the response of pixel
Value is greater than Th2, which is angle point, pixel value is assigned to D, wherein Th1<Th2, and Th1、Th2, B, C, D be nonnegative number；
S2-8 carries out non-maxima suppression to all candidate angulars in image, inhibits the pseudo- angle point around true angle point,
Obtain the angle point in image.
The angular coordinate confirmation method is simple, and calculating speed is fast, reduces missing inspection angle point and pseudo- angle point.
Further, in the step S2-1,σ is (x+u's) and (y+v)
Variance, this can effectively reduce operand.
Further, angle point response R=det (M)-k × trace2(M), wherein det (M)=λ1λ2For auto-correlation square
The determinant of battle array M, trace (M)=λ1+λ2For the mark of autocorrelation matrix, k is constant, this can effectively reduce operand.
Further, the Th1* 1/3, Th of=(max pixel value-minimum pixel value)2=(max pixel value-minimum image
Element value) * 2/3, wherein max pixel value and minimum pixel value refer to max pixel value and minimum pixel value in the S component map.
Beneficial effects of the present invention:
1, influence of the bright and dark light to license plate sloped correction is mainly solved, inclination is completed using color model and Corner Detection
Correction.
2, color model part can extract each Color Channel respectively, the characteristics of for different channels, targetedly
Using.
3, Corner Detection part uses improved Harris Corner Detection Algorithm, can effectively reduce calculation amount, reduces leakage
Examine angle point and pseudo- angle point.
Additional aspect and advantage of the invention will be set forth in part in the description, and will partially become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect of the invention and advantage will become from the description of the embodiment in conjunction with the following figures
Obviously and it is readily appreciated that, in which:
Fig. 1 is the flow chart of this method；
Fig. 2 is angular coordinate overhaul flow chart.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and for explaining only the invention, and is not considered as limiting the invention.
In the description of the present invention, unless otherwise specified and limited, it should be noted that term " installation ", " connected ",
" connection " shall be understood in a broad sense, for example, it may be mechanical connection or electrical connection, the connection being also possible to inside two elements can
, can also indirectly connected through an intermediary, for the ordinary skill in the art to be to be connected directly, it can basis
Concrete condition understands the concrete meaning of above-mentioned term.
As shown in Figure 1, the present invention provides a kind of license plate sloped correcting method, including the following steps:
S1 obtains license plate rgb format image, and the rgb format image is converted to HSI format-pattern, extracts HSI format
S component map in image.
S2 detects the angular coordinate of S component map.
Here the determination of angular coordinate can be detected using tradition Harris angular-point detection method, and the present invention can also adopt
It is detected with improved Harris angular-point detection method, is realized by following steps, as shown in Figure 2:
S2-1, described with the gray-value variation in horizontal and vertical direction pixel in any direction on grey scale change, retouch
The formula of stating is
Wherein, I (x+u, y+v)=I (x, y)+Ixu+Iyv+O(u2,v2), (x, y) is target pixel points coordinate；(u, v) table
Show offset of other pixels relative to target pixel points；ωu,vFor weighted window function,σ is the variance of (x+u) and (y+v).I is image array, IxAnd IyRespectively indicate figure
As matrix I in the horizontal direction with the first-order partial derivative of vertical direction；Since image is discrete series, partial derivative IxAnd IyIt can
To be obtained by difference method, i.e. IxAcquisition, I can be subtracted each other by adjacent rows pixel valueyAdjacent two column pixel value can be passed through
Subtract each other acquisition.
S2-2 obtains the autocorrelation matrix M of pixel (x, y): ignoring the higher-order shear deformation in foregoing description formulaIt obtainsWherein,M is
The autocorrelation matrix of pixel (x, y)；
S2-3 knows that M there are two non-negative characteristic values, is denoted as λ by the symmetry of matrix1And λ2, enable autocorrelation matrix M=
0, obtain two non-negative eigenvalue λs of matrix M1And λ2If λ1≥λ2。
S2-4 works as λ2When greater than setting first threshold, then target pixel points are angle point.
Work as λ2The λ equal to 01When greater than first threshold, shows that target pixel points are located at edge, execute step S2-5.
Work as λ1Equal to 0, shows that target pixel points are located at flat site, execute step S2-5.
Here λ2It include λ equal to 02The case where being similar to 0, while λ1λ is also included equal to 01The case where being similar to 0.The
One threshold value is arranged as the case may be, and first threshold is not less than 150.
S2-5 calculates the angle point response R of pixel (x, y).
Angle point response R=det (M)-k × trace2(M), wherein det (M)=λ1λ2For the ranks of autocorrelation matrix M
Formula, trace (M)=λ1+λ2For the mark of autocorrelation matrix, k is constant, for convenient for operation, k value range be usually 0.04≤k≤
0.06。
S2-6 traverses all pixels point of whole picture S component map, executes step S2-1 to step S2-6, calculates all pixels
The angle point response R of point.
S2-7, if there is the response of pixel to be less than Th1, which is not angle point, and pixel value is assigned to B；If there is picture
The response of vegetarian refreshments is greater than Th1And it is less than Th2, which is candidate angular, and pixel value is assigned to C；If there is the response of pixel
Value is greater than Th2, which is angle point, pixel value is assigned to D, wherein Th1<Th2, and Th1、Th2, B, C, D be nonnegative number.This
In B be usually 0, C be usually 128, D be usually 255.
Preferably, the Th1* 1/3, Th of=(max pixel value-minimum pixel value)2=(max pixel value-minimum
Pixel value) * 2/3, wherein max pixel value and minimum pixel value refer to max pixel value and minimum pixel in the S component map
Value.
S2-7 carries out non-maxima suppression to all candidate angulars in image, inhibits the pseudo- angle point around true angle point,
Obtain all angle points in image.Non-maxima suppression is to inhibit non-maximum, finds the maximum candidate angle of local pixel value
Point is mainly used for eliminating pseudo- angle point, inhibits the pseudo- angle point around true angle point, obtains the angle point in image.
S3 obtains the coordinate of the angle point when because obtaining angle point, the angular coordinate deposit two-dimensional matrix L that will test.
S4 finds lower-left angle point, upper left angle point, bottom right angle point and upper right angle point.
Wherein, the abscissa of lower-left angle point is minimum, and ordinate is minimum；The abscissa of upper left angle point is minimum, and ordinate is maximum；
The abscissa of bottom right angle point is maximum, and ordinate is minimum；Upper right angle point abscissa is maximum, the maximum angle point of ordinate.
S5, according to upper left angle point, upper right angle point, lower-left angle point and bottom right angle point coordinate, it is oblique to find out two levels respectively
Rate and two vertical slopes, and find out the mean value of two horizontal slopes and the mean value of two vertical slopes.
S6 finds out inclination alpha according to formula tan α=k of slope and inclination angle.
S7 completes license plate sloped correction according to inclination alpha.
After the completion of license plate sloped correction, the binary map of the license plate image after output calibration, for subsequent image processing.
Since license plate is affected by environment, salt-pepper noise is more in the image that takes, is obtaining obtaining license plate rgb format figure
As after, the noise in median filtering removal image is carried out to the image.Median filtering belongs to non-linear filtering method, i.e., with entire
The intermediate value of window replaces the pixel value of the position.Median filtering is highly effective in terms of smooth impulsive noise, while it can be protected
The sharp edge of image is protected, selects median point to substitute the value of points of contamination, high treating effect shows salt-pepper noise preferable.
Noise in image significantly reduces after denoising, carries out edge detection to the image after denoising.Since characters on license plate is vertical
To texture, background is cross grain.The effect of Canny edge detection is more detailed, and the detection of transverse and longitudinal edge indifference may be implemented.
For prominent characters on license plate region, Canny edge detection algorithm is improved, allows to preferably detect longitudinal texture, reduce laterally
Texture.Improved model is as follows:
Improved Canny edge detection can preferably detect vertical edges, reduce the interference of transverse edge, prominent word
Symbol, while reducing algorithm amount.
Since part license plate area has the case where fracture or adhesion after edge detection, shape need to be carried out to filtered image
State processing, reduces fracture and adhesion.If filtered license plate retains preferably, Morphological scale-space can not be carried out to license plate, otherwise
It is handled.
Morphological images processing is a kind of neighborhood operation form, using the method for neighbour structure element in each location of pixels
Upper neighbour structure element and bianry image corresponding domain carry out specific logical operation, and the result of logical operation is to export the phase of image
Answer pixel.The basic operation of morphological image process includes: corrosion and expansion, opening and closing operation.Most basic operation be corrosion and
Expansion, other operations are all defined on the basis of both operations.
Using structural element B to the expansion process of image A is defined as:
X=A ⊕ B={ x:B (x) ∩ A ≠ Φ }；
Corrosion treatment using structural element B to image A is defined as:
Wherein, image A be rgb format image, each of x representative image A pixel, B (x) representative structure element,
Φ is empty set, and X is result of the image A after expansion or corrosion.It is exactly structural element with the result that B (x) corrodes A
B is set to be contained in the set that all the points of A are constituted after B translation.It is exactly that structural element B is put down with the result that B (x) expands A
The set for constituting the point of the intersection non-empty of B and A after shifting.
It is as follows to carry out out operation formula,
Indicate that set A opens operation by structural element B；
It is as follows to carry out closed operation formula,
Indicate set A by structural element B closed operation.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiment or examples in can be combined in any suitable manner.
Although an embodiment of the present invention has been shown and described, it will be understood by those skilled in the art that: not
A variety of change, modification, replacement and modification can be carried out to these embodiments in the case where being detached from the principle of the present invention and objective, this
The range of invention is defined by the claims and their equivalents.
Claims (5)
1. a kind of license plate sloped correcting method, which is characterized in that including the following steps:
S1 obtains license plate rgb format image, and the rgb format image is converted to HSI format-pattern, extracts HIS format-pattern
In S component map；
S2 detects the angular coordinate of S component map；
S3, the angular coordinate deposit two-dimensional matrix L that will test；
S4 finds lower-left angle point, upper left angle point, bottom right angle point and upper right angle point；
Wherein, the abscissa of lower-left angle point is minimum, and ordinate is minimum；The abscissa of upper left angle point is minimum, and ordinate is maximum；Bottom right
The abscissa of angle point is maximum, and ordinate is minimum；Upper right angle point abscissa is maximum, the maximum angle point of ordinate；
S5, according to upper left angle point, upper right angle point, lower-left angle point and bottom right angle point coordinate, find out respectively two horizontal slopes and
Two vertical slopes, and find out the mean value of two horizontal slopes and the mean value of two vertical slopes；
S6 finds out inclination alpha according to formula tan α=k of slope and inclination angle:
S7 completes license plate sloped correction according to inclination alpha.
2. license plate sloped correcting method according to claim 1, which is characterized in that the step S2 includes following step
It is rapid:
S2-1, described with the gray-value variation in horizontal and vertical direction pixel in S component map in any direction on gray scale become
Change, description formula is
Wherein, I (x+u, y+v)=I (x, y)+Ixu+Iyv+O(u2,v2), (x, y) is target pixel points coordinate；(u, v) indicates it
His offset of the pixel relative to target pixel points；ωu,vFor weighted window function, I is image array, IxAnd IyIt respectively indicates
Image array I in the horizontal direction with the first-order partial derivative of vertical direction；
S2-2 obtains the autocorrelation matrix M of pixel (x, y): ignoring the higher-order shear deformation in foregoing description formula
It obtainsWherein,M is pixel (x, y)
Autocorrelation matrix；
S2-3 enables autocorrelation matrix M=0, obtains two non-negative eigenvalue λs of matrix M1And λ2If λ1≥λ2；
S2-4 works as λ2When greater than setting first threshold, then target pixel points are angle point；
Work as λ2The λ equal to 01When greater than first threshold, shows that target pixel points are located at edge, execute step S2-5；
Work as λ1Equal to 0, shows that target pixel points are located at flat site, execute step S2-5；
S2-5 calculates the angle point response R of pixel (x, y):
S2-6 traverses all pixels point of whole picture S component map, executes step S2-1 to step S2-6, calculates all pixels point
Angle point response R；
S2-7, if there is the response of pixel to be less than Th1, which is not angle point, and pixel value is assigned to B；If there is pixel
Response is greater than Th1And it is less than Th2, which is candidate angular, and pixel value is assigned to C；If there is the response of pixel to be greater than
Th2, which is angle point, pixel value is assigned to D, wherein Th1<Th2, and Th1、Th2, B, C, D be nonnegative number；
S2-8 carries out non-maxima suppression to all candidate angulars in image, inhibits the pseudo- angle point around true angle point, obtain
Angle point in image.
3. license plate sloped correcting method according to claim 2, which is characterized in that in the step S2-1,σ is the variance of (x+u) and (y+v).
4. license plate sloped correcting method according to claim 2, which is characterized in that angle point response R=det (M)-k ×
trace2(M), wherein det (M)=λ1λ2For the determinant of autocorrelation matrix M, trace (M)=λ1+λ2For autocorrelation matrix
Mark, k are constant.
5. license plate sloped correcting method according to claim 2, which is characterized in that the Th1=(max pixel value-minimum
Pixel value) * 1/3, Th2=(max pixel value-minimum pixel value) * 2/3, wherein max pixel value and minimum pixel value refer to institute
State the max pixel value and minimum pixel value in S component map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811062278.6A CN109214380B (en) | 2018-09-12 | 2018-09-12 | License plate inclination correction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811062278.6A CN109214380B (en) | 2018-09-12 | 2018-09-12 | License plate inclination correction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109214380A true CN109214380A (en) | 2019-01-15 |
| CN109214380B CN109214380B (en) | 2021-10-01 |
Family
ID=64984054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811062278.6A Active CN109214380B (en) | 2018-09-12 | 2018-09-12 | License plate inclination correction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109214380B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110500951A (en) * | 2019-06-04 | 2019-11-26 | 湘潭大学 | A kind of lamp lens shell sizes detection method based on machine vision |
| CN110634222A (en) * | 2019-08-27 | 2019-12-31 | 河海大学 | Bank bill information identification method |
| CN111207659A (en) * | 2020-01-07 | 2020-05-29 | 河北科技大学 | Chip parameter detection method and device based on capacitor array |
| CN112749735A (en) * | 2020-12-30 | 2021-05-04 | 中冶赛迪重庆信息技术有限公司 | Converter tapping steel flow identification method, system, medium and terminal based on deep learning |
| CN113506279A (en) * | 2021-07-22 | 2021-10-15 | 浙江大华技术股份有限公司 | Method and device for determining inclination angle of object, storage medium and electronic device |
| CN113657371A (en) * | 2021-10-20 | 2021-11-16 | 成都宜泊信息科技有限公司 | Camera angle adjusting method and system, storage medium and electronic equipment |
| CN114882489A (en) * | 2022-07-07 | 2022-08-09 | 浙江智慧视频安防创新中心有限公司 | Method, device, equipment and medium for horizontally correcting rotary license plate |
| CN117315664A (en) * | 2023-09-18 | 2023-12-29 | 山东博昂信息科技有限公司 | Scrap steel bucket number identification method based on image sequence |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104298966A (en) * | 2014-09-17 | 2015-01-21 | 电子科技大学 | License plate positioning method |
| CN104598905A (en) * | 2015-02-05 | 2015-05-06 | 广州中国科学院软件应用技术研究所 | License plate positioning method and device |
| CN106203433A (en) * | 2016-07-13 | 2016-12-07 | 西安电子科技大学 | In a kind of vehicle monitoring image, car plate position automatically extracts and the method for perspective correction |
| CN106503709A (en) * | 2016-10-20 | 2017-03-15 | 江苏商贸职业学院 | A kind of slag-soil truck characters on license plate intelligent identification Method |
| CN107909085A (en) * | 2017-12-01 | 2018-04-13 | 中国科学院长春光学精密机械与物理研究所 | A kind of characteristics of image Angular Point Extracting Method based on Harris operators |
| CN108241859A (en) * | 2016-12-26 | 2018-07-03 | 浙江宇视科技有限公司 | The bearing calibration of car plate and device |
-
2018
- 2018-09-12 CN CN201811062278.6A patent/CN109214380B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104298966A (en) * | 2014-09-17 | 2015-01-21 | 电子科技大学 | License plate positioning method |
| CN104598905A (en) * | 2015-02-05 | 2015-05-06 | 广州中国科学院软件应用技术研究所 | License plate positioning method and device |
| CN106203433A (en) * | 2016-07-13 | 2016-12-07 | 西安电子科技大学 | In a kind of vehicle monitoring image, car plate position automatically extracts and the method for perspective correction |
| CN106503709A (en) * | 2016-10-20 | 2017-03-15 | 江苏商贸职业学院 | A kind of slag-soil truck characters on license plate intelligent identification Method |
| CN108241859A (en) * | 2016-12-26 | 2018-07-03 | 浙江宇视科技有限公司 | The bearing calibration of car plate and device |
| CN107909085A (en) * | 2017-12-01 | 2018-04-13 | 中国科学院长春光学精密机械与物理研究所 | A kind of characteristics of image Angular Point Extracting Method based on Harris operators |
Non-Patent Citations (1)
| Title |
|---|
| 吴艳: "Harris角点检测与AP聚类结合的车牌定位方法", 《广西科技大学学报》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110500951B (en) * | 2019-06-04 | 2021-03-09 | 湘潭大学 | Car light glass shell size detection method based on machine vision |
| CN110500951A (en) * | 2019-06-04 | 2019-11-26 | 湘潭大学 | A kind of lamp lens shell sizes detection method based on machine vision |
| CN110634222A (en) * | 2019-08-27 | 2019-12-31 | 河海大学 | Bank bill information identification method |
| CN110634222B (en) * | 2019-08-27 | 2021-07-09 | 河海大学 | Bank bill information identification method |
| CN111207659A (en) * | 2020-01-07 | 2020-05-29 | 河北科技大学 | Chip parameter detection method and device based on capacitor array |
| CN112749735B (en) * | 2020-12-30 | 2023-04-07 | 中冶赛迪信息技术(重庆)有限公司 | Converter tapping steel flow identification method, system, medium and terminal based on deep learning |
| CN112749735A (en) * | 2020-12-30 | 2021-05-04 | 中冶赛迪重庆信息技术有限公司 | Converter tapping steel flow identification method, system, medium and terminal based on deep learning |
| CN113506279A (en) * | 2021-07-22 | 2021-10-15 | 浙江大华技术股份有限公司 | Method and device for determining inclination angle of object, storage medium and electronic device |
| CN113657371B (en) * | 2021-10-20 | 2021-12-21 | 成都宜泊信息科技有限公司 | Camera angle adjusting method and system, storage medium and electronic equipment |
| CN113657371A (en) * | 2021-10-20 | 2021-11-16 | 成都宜泊信息科技有限公司 | Camera angle adjusting method and system, storage medium and electronic equipment |
| CN114882489A (en) * | 2022-07-07 | 2022-08-09 | 浙江智慧视频安防创新中心有限公司 | Method, device, equipment and medium for horizontally correcting rotary license plate |
| CN114882489B (en) * | 2022-07-07 | 2022-12-16 | 浙江智慧视频安防创新中心有限公司 | Method, device, equipment and medium for horizontally correcting rotating license plate |
| CN117315664A (en) * | 2023-09-18 | 2023-12-29 | 山东博昂信息科技有限公司 | Scrap steel bucket number identification method based on image sequence |
| CN117315664B (en) * | 2023-09-18 | 2024-04-02 | 山东博昂信息科技有限公司 | Scrap steel bucket number identification method based on image sequence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109214380B (en) | 2021-10-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109214380A (en) | License plate sloped correcting method | |
| CN110268190B (en) | Underground pipe gallery leakage detection method based on static infrared thermography processing | |
| CN107067389B (en) | A kind of blind evidence collecting method of distorted image | |
| CN110569857B (en) | Image contour corner detection method based on centroid distance calculation | |
| CN107392885A (en) | A kind of method for detecting infrared puniness target of view-based access control model contrast mechanism | |
| CN105913415A (en) | Image sub-pixel edge extraction method having extensive adaptability | |
| CN105117726B (en) | License plate locating method based on multiple features zone-accumulation | |
| CN106815583A (en) | A kind of vehicle at night license plate locating method being combined based on MSER and SWT | |
| CN107122758A (en) | A kind of vehicle cab recognition and traffic flow detecting method | |
| CN103093458B (en) | The detection method of key frame and device | |
| CN110648349A (en) | Weld defect segmentation method based on background subtraction and connected region algorithm | |
| CN104766344B (en) | Vehicle checking method based on movement edge extractor | |
| CN107610164A (en) | A kind of No. four Image registration methods of high score based on multiple features mixing | |
| CN109544464A (en) | A kind of fire video image analysis method based on contours extract | |
| CN107392095A (en) | A kind of small IR targets detection algorithm based on mask image | |
| CN101976436A (en) | Pixel-level multi-focus image fusion method based on correction of differential image | |
| CN109035287B (en) | Foreground image extraction method and device and moving vehicle identification method and device | |
| CN106204617A (en) | Adapting to image binarization method based on residual image rectangular histogram cyclic shift | |
| CN115147418B (en) | Compression training method and device for defect detection model | |
| CN111539980B (en) | Multi-target tracking method based on visible light | |
| CN105678737A (en) | Digital image corner point detection method based on Radon transform | |
| CN101572820B (en) | Preprocessing method of video signal in detection process of moving target | |
| CN107909085A (en) | A kind of characteristics of image Angular Point Extracting Method based on Harris operators | |
| CN103324906B (en) | A kind of method and apparatus of legacy detection | |
| CN114359149A (en) | Dam bank dangerous case video detection method and system based on real-time image edge enhancement |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |