CN101093543A - Method for correcting image in 2D code of quick response matrix - Google Patents
Method for correcting image in 2D code of quick response matrix Download PDFInfo
- Publication number
- CN101093543A CN101093543A CN200710074943.9A CN200710074943A CN101093543A CN 101093543 A CN101093543 A CN 101093543A CN 200710074943 A CN200710074943 A CN 200710074943A CN 101093543 A CN101093543 A CN 101093543A
- Authority
- CN
- China
- Prior art keywords
- view finding
- graphical dots
- code
- quick response
- finding graphical
- 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
Images
Abstract
A method for calibrating 2-D code image of quick response matrix includes scanning and confirming three FP points of QR code image according to reference decoding algorithm, confirming distribution point set of four side edges according to three FP points, obtaining fitted linear of four side edges by utilizing RANSAC algorithm to separately fit distribution set of four side edges, crossing obtained fitted-linears to obtain four top points of QR code image under image coordinate system, using SVD means to obtain perspective transform parameter of four said top points, carrying out re-sampling on QR code image based on obtained transform parameter for obtaining calibrated QR code image.
Description
Technical field
The present invention relates to a kind of bearing calibration of image, especially a kind of bearing calibration of image in 2 D code of quick response matrix.
Background technology
At present, the reference decoding algorithm that " quick response matrix code QR Code " (State Standard of the People's Republic of China GB/T18284-2000) provides is at first determined FP (Finder Pattern according to horizontal and vertical scanning, the view finding figure), determine AP (AlignmentPattern according to FP, correction graph), set up sampling grid according to FP and AP then, obtain the preceding information of decoding.In practice, for the image of QR Code (Quickly Response Code, quick response matrix code) image, in order accurately to obtain the position of FP through obtaining after the rotational transform, general except horizontal and vertical scanning, also increase the crisscross scanning of 45 degree.
Yet, because the restriction of image-forming condition, QR Code image tends to produce perspective transform, and above method promptly allows to successfully find FP, also can't obtain correct AP position and sampling grid according to the reference decoding algorithm, promptly existing algorithm can't robust ground identification perspective QR Code image.
Summary of the invention
The technical problem to be solved in the present invention provides the bearing calibration that a kind of parameter by robust ground estimation perspective matrix realizes the QR Code image of QR Code picture decoding purpose.
The technical solution adopted for the present invention to solve the technical problems is:
A kind of bearing calibration of image in 2 D code of quick response matrix may further comprise the steps:
1.1 according to the reference decoding algorithm, three view finding graphical dots of described image in 2 D code of quick response matrix are determined in scanning;
1.2 determine the distribution point set of four sides of described image in 2 D code of quick response matrix respectively according to described three view finding graphical dots;
1.3 the distribution point set of described four sides adopts the match of random sampling consistency algorithm to obtain the fitting a straight line of four sides respectively, the fitting a straight line of described four sides intersects four summits that obtain described image in 2 D code of quick response matrix under the image coordinate system in twos;
Estimate that the perspective transform relation of described four summits in image coordinate system and world coordinate system obtains the perspective transform parameter 1.4 adopt singular value decomposition method;
1.5 according to described perspective transform parameter, to described image in 2 D code of quick response matrix resampling, the image in 2 D code of quick response matrix after obtaining proofreading and correct.
In the such scheme, definite method of the distribution point set of four sides is as follows in the step 1.2, wherein, view finding graphical dots all adjacent with all the other two view finding graphical dots in described three view finding graphical dots is designated as the second view finding graphical dots, the view finding graphical dots adjacent clockwise with the described second view finding graphical dots is designated as the 3rd view finding graphical dots, and the view finding graphical dots adjacent counterclockwise with the described second view finding graphical dots is designated as the first view finding graphical dots:
With the second view finding graphical dots is starting point, scan to the direction of the second view finding graphical dots and inverse direction thereof according to the first view finding graphical dots and to obtain the sweep starting point collection, the every bit of concentrating with described sweep starting point is a starting point, scans the distribution point set that obtains described image in 2 D code of quick response matrix one side according to the 3rd view finding graphical dots to the direction of the second view finding graphical dots; With the second view finding graphical dots is starting point, scan to the direction of the second view finding graphical dots and inverse direction thereof according to the 3rd view finding graphical dots and to obtain the sweep starting point collection, the every bit of concentrating with described sweep starting point is a starting point, scans the distribution point set that obtains described image in 2 D code of quick response matrix one side according to the first view finding graphical dots to the direction of the second view finding graphical dots; With the 3rd view finding graphical dots is starting point, scan to the direction of the second view finding graphical dots and inverse direction thereof according to the first view finding graphical dots and to obtain the sweep starting point collection, the every bit of concentrating with described sweep starting point is a starting point, and the direction of complying with the second view finding graphical dots to the, three view finding graphical dots scans the distribution point set that obtains described image in 2 D code of quick response matrix one side; With the first view finding graphical dots is starting point, scan according to the direction of the second view finding graphical dots to the, three view finding graphical dots and inverse direction thereof and to obtain the sweep starting point collection, the every bit of concentrating with described sweep starting point is a starting point, scans the distribution point set that obtains described image in 2 D code of quick response matrix one side according to the second view finding graphical dots to the direction of the first view finding graphical dots.
In the such scheme, the digital differential analysis method is adopted in described scanning, carries out according to the conversion of the uneven color in the scanning process, and after promptly scanning the color dark color and transferring twice of light color to, described scanning stops.
In the such scheme, the match step of step 1.3 cathetus comprises:
4.1 the threshold value of threshold value that preset matching is counted and match number of times;
4.2 the selected one distribution point set without the side of match, 2 to 4 points selecting described distributed points to concentrate form a sub-point set;
4.3 described sub-point set is carried out match, obtain the fitting a straight line of a described side, and write down described distributed points and concentrate and to match the quantity of the point on the described fitting a straight line and the parameter of described fitting a straight line;
4.4, then be the final fitting result of described side, if also there is distribution point set, get back to step 4.2, otherwise finish the match step without the side of match with described fitting a straight line if the quantity of the point of coupling meets or exceeds the threshold value that described coupling is counted; If the quantity of the point of coupling does not reach the threshold value that described coupling is counted, judge whether the match number of times exceeds the threshold value of described match number of times, if do not surpass, get back to step 4.3, otherwise the fitting a straight line with the quantity maximum of the point of coupling in the record is the final fitting result of described side, if also there is distribution point set, gets back to step 4.2, otherwise finish the match step without the side of match.
In the such scheme, described perspective transform parameter is that the system of linear equations that adopts described singular value decomposition method to separate by the perspective transform pass series structure of described four summits in image coordinate system and world coordinate system obtains.
In the such scheme, three view finding graphical dots are utilized laterally, are vertically reached the described image in 2 D code of quick response matrix of 45 degree cross scans and obtain.
Beneficial effect of the present invention mainly shows: technical scheme provided by the invention adopts RANSAC (random sample consensus, the random sampling consistance) algorithm accurately obtains the image coordinate on four summits of QR Code image, adopt SVD (Singular ValueDecomposition then, svd) method comes robust ground to estimate the parameter of perspective matrix, thereby realizes the purpose of QR Code picture decoding; Because the point set element that the RANSAC algorithm is found the solution is less, therefore calculate relatively simply fast, committed memory is less, particularly under the condition that the internal memory restriction is arranged, can utilize this method to realize the identification of QR Code image.
Description of drawings
Fig. 1 is the bearing calibration of image in 2 D code of quick response matrix of the present invention;
Fig. 2 is the synoptic diagram of three view finding graphical dots of one embodiment of the invention;
Fig. 3 is the synoptic diagram of four distribution point sets of one embodiment of the invention;
Fig. 4 is the synoptic diagram of four fitting a straight lines of one embodiment of the invention;
Fig. 5 is the synoptic diagram of the image in 2 D code of quick response matrix of one embodiment of the invention after overcorrect.
Embodiment
The invention will be further described below in conjunction with accompanying drawing.
With reference to Fig. 1, a kind of bearing calibration of image in 2 D code of quick response matrix may further comprise the steps:
Step 1:, utilize laterally, vertically to reach three FP points that 45 degree cross scans are determined QR Code image, as the P1 among Fig. 2, P2, P3 according to the reference decoding algorithm;
Step 2: determine the distribution point set of four direction respectively according to three FP points, as the L1 among Fig. 3, L2, L3, L4, concrete determining step is as described below:
1, with P1 is starting point, scans to the direction of P1 and inverse direction thereof according to P3 and obtain the sweep starting point collection that the every bit of concentrating with described sweep starting point is a starting point, scan the distribution point set L1 that obtains described QR Code image one side to the direction of P1 according to P2;
2, with P1 be starting point, scan to the direction of P1 and inverse direction thereof according to P2 and to obtain the sweep starting point collection, the every bit of concentrating with described sweep starting point is a starting point, scans the distribution point set L2 that obtains described image in 2 D code of quick response matrix one side according to P3 to the direction of P1;
3, with P2 be starting point, scan to the direction of P1 and inverse direction thereof according to P3 and to obtain the sweep starting point collection, the every bit of concentrating with described sweep starting point is a starting point, scans the distribution point set L3 that obtains described image in 2 D code of quick response matrix one side according to P1 to the direction of P2;
4, with P3 be starting point, scan to the direction of P2 and inverse direction thereof according to P1 and to obtain the sweep starting point collection, the every bit of concentrating with described sweep starting point is a starting point, scans the distribution point set L4 that obtains described image in 2 D code of quick response matrix one side according to P1 to the direction of P3;
The digital differential analysis method is all adopted in scanning in the above steps, carries out according to the conversion of the uneven color in the scanning process, promptly scan the color dark color transfer to light color twice after, described scanning stops.
Step 3: four distribution point set L1, L2, L3, L4 adopt the match of RANSAC algorithm to obtain the fitting a straight line of four sides respectively, and as 11 among Fig. 4,12,13,14, concrete match step is as described below:
1, the preset matching threshold value of counting and the threshold value of match number of times;
2, selected one distribution point set without the side of match, 2 to 4 points selecting described distributed points to concentrate form a sub-point set;
3, described sub-point set is carried out match, obtain the fitting a straight line of a described side, and write down described distributed points and concentrate and to match the quantity of the point on the described fitting a straight line and the parameter of described fitting a straight line;
4, if the quantity of the point of coupling meets or exceeds the threshold value that described coupling is counted, then be the final fitting result of described side,, get back to step 2, otherwise finish the match step if also there is distribution point set without the side of match with described fitting a straight line; If the quantity of the point of coupling does not reach the threshold value that described coupling is counted, judge whether the match number of times exceeds the threshold value of described match number of times, if do not surpass, get back to step 3, otherwise the fitting a straight line with the quantity maximum of the point of coupling in the record is the final fitting result of described side, if also there is distribution point set, gets back to step 2, otherwise finish the match step without the side of match.
After fitting a straight line was finished, the fitting a straight line 11,12,13,14 of four sides intersected four summits that obtain QR Code image under the image coordinate system in twos, be designated as respectively (x0, y0), (x1, y1), (x2, y2), (x3, y3);
Step 4: because (u0, v0), (u1, v1), (u2, v2), (u3 is known v3) to four summits of QR Code image in the world coordinates, therefore, can use perspective transformation matrix
Set up the corresponding relation of the point between image coordinate system and the world coordinate system, i=0 wherein, 1,2,3:
ui=(c00*xi+c01*yi+c02)/(c20*xi+c21*yi+c22)
vi=(c10*xi+c11*yi+c12)/(c20*xi+c21*yi+c22)
And obtain system of linear equations:
Wherein, c22=1;
Adopt the SVD method to separate above-mentioned system of linear equations and obtain separating of perspective transformation matrix, promptly obtained the perspective transform parameter;
Step 5: according to described perspective transform parameter, to QR Code image resampling, the QR Code image after obtaining proofreading and correct.So far, the trimming process of QR Code image finishes, and the result who obtains as shown in Figure 5.Thereby subsequent can the decoding to QR Code image according to the reference decoding algorithm realized the identification of QR Code image.
Claims (6)
1, a kind of bearing calibration of image in 2 D code of quick response matrix is characterized in that, may further comprise the steps:
1.1 according to the reference decoding algorithm, three view finding graphical dots of described image in 2 D code of quick response matrix are determined in scanning;
1.2 determine the distribution point set of four sides of described image in 2 D code of quick response matrix respectively according to described three view finding graphical dots;
1.3 the distribution point set of described four sides adopts the match of random sampling consistency algorithm to obtain the fitting a straight line of four sides respectively, the fitting a straight line of described four sides intersects four summits that obtain described image in 2 D code of quick response matrix under the image coordinate system in twos;
Estimate that the perspective transform relation of described four summits in image coordinate system and world coordinate system obtains the perspective transform parameter 1.4 adopt singular value decomposition method;
1.5 according to described perspective transform parameter, to described image in 2 D code of quick response matrix resampling, the image in 2 D code of quick response matrix after obtaining proofreading and correct.
2, the recognition methods of 2 D code of quick response matrix as claimed in claim 1, it is characterized in that: definite method of the distribution point set of four sides is as follows in the step 1.2, wherein, view finding graphical dots all adjacent with all the other two view finding graphical dots in described three view finding graphical dots is designated as the second view finding graphical dots, the view finding graphical dots adjacent clockwise with the described second view finding graphical dots is designated as the 3rd view finding graphical dots, and the view finding graphical dots adjacent counterclockwise with the described second view finding graphical dots is designated as the first view finding graphical dots:
With the second view finding graphical dots is starting point, scan to the direction of the second view finding graphical dots and inverse direction thereof according to the first view finding graphical dots and to obtain the sweep starting point collection, the every bit of concentrating with described sweep starting point is a starting point, scans the distribution point set that obtains described image in 2 D code of quick response matrix one side according to the 3rd view finding graphical dots to the direction of the second view finding graphical dots; With the second view finding graphical dots is starting point, scan to the direction of the second view finding graphical dots and inverse direction thereof according to the 3rd view finding graphical dots and to obtain the sweep starting point collection, the every bit of concentrating with described sweep starting point is a starting point, scans the distribution point set that obtains described image in 2 D code of quick response matrix one side according to the first view finding graphical dots to the direction of the second view finding graphical dots; With the 3rd view finding graphical dots is starting point, scan to the direction of the second view finding graphical dots and inverse direction thereof according to the first view finding graphical dots and to obtain the sweep starting point collection, the every bit of concentrating with described sweep starting point is a starting point, and the direction of complying with the second view finding graphical dots to the, three view finding graphical dots scans the distribution point set that obtains described image in 2 D code of quick response matrix one side; With the first view finding graphical dots is starting point, scan according to the direction of the second view finding graphical dots to the, three view finding graphical dots and inverse direction thereof and to obtain the sweep starting point collection, the every bit of concentrating with described sweep starting point is a starting point, scans the distribution point set that obtains described image in 2 D code of quick response matrix one side according to the second view finding graphical dots to the direction of the first view finding graphical dots.
3, the recognition methods of 2 D code of quick response matrix as claimed in claim 2, it is characterized in that: the digital differential analysis method is adopted in described scanning, conversion according to the uneven color in the scanning process is carried out, promptly scan the color dark color transfer to light color twice after, described scanning stops.
4, as the recognition methods of one of them described 2 D code of quick response matrix of claim 1 to 3, it is characterized in that: the match step of step 1.3 cathetus comprises:
4.1 the threshold value of threshold value that preset matching is counted and match number of times;
4.2 the selected one distribution point set without the side of match, 2 to 4 points selecting described distributed points to concentrate form a sub-point set;
4.3 described sub-point set is carried out match, obtain the fitting a straight line of a described side, and write down described distributed points and concentrate and to match the quantity of the point on the described fitting a straight line and the parameter of described fitting a straight line;
4.4, then be the final fitting result of described side, if also there is distribution point set, get back to step 4.2, otherwise finish the match step without the side of match with described fitting a straight line if the quantity of the point of coupling meets or exceeds the threshold value that described coupling is counted; If the quantity of the point of coupling does not reach the threshold value that described coupling is counted, judge whether the match number of times exceeds the threshold value of described match number of times, if do not surpass, get back to step 4.3, otherwise the fitting a straight line with the quantity maximum of the point of coupling in the record is the final fitting result of described side, if also there is distribution point set, gets back to step 4.2, otherwise finish the match step without the side of match.
5, the recognition methods of 2 D code of quick response matrix as claimed in claim 4 is characterized in that: described perspective transform parameter is that the system of linear equations that adopts described singular value decomposition method to separate by the perspective transform pass series structure of described four summits in image coordinate system and world coordinate system obtains.
6, the recognition methods of 2 D code of quick response matrix as claimed in claim 1 is characterized in that: three view finding graphical dots are utilized laterally, are vertically reached the described image in 2 D code of quick response matrix of 45 degree cross scans and obtain.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN200710074943A CN101093543B (en) | 2007-06-13 | 2007-06-13 | Method for correcting image in 2D code of quick response matrix |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN200710074943A CN101093543B (en) | 2007-06-13 | 2007-06-13 | Method for correcting image in 2D code of quick response matrix |
Publications (2)
Publication Number | Publication Date |
---|---|
CN101093543A true CN101093543A (en) | 2007-12-26 |
CN101093543B CN101093543B (en) | 2010-05-26 |
Family
ID=38991793
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN200710074943A Expired - Fee Related CN101093543B (en) | 2007-06-13 | 2007-06-13 | Method for correcting image in 2D code of quick response matrix |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101093543B (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101882207A (en) * | 2010-06-01 | 2010-11-10 | 福建新大陆电脑股份有限公司 | Bar code decoding chip of Data Matrix codes and decoding method thereof |
CN102096795A (en) * | 2010-11-25 | 2011-06-15 | 西北工业大学 | Method for recognizing worn two-dimensional barcode image |
CN102254204A (en) * | 2011-06-03 | 2011-11-23 | 吴林 | Coding and decoding method for graphemic code |
CN101576871B (en) * | 2008-05-09 | 2012-02-15 | 永驰科技有限公司 | Operating method for recommending system for accelerating computer arithmetics and image identification system |
CN101807297B (en) * | 2009-02-16 | 2012-07-25 | 海信集团有限公司 | Medical ultrasonic image line detection method |
CN103400131A (en) * | 2013-08-16 | 2013-11-20 | 徐宁 | Correction device and method for image identification |
CN104463291A (en) * | 2013-09-16 | 2015-03-25 | 深圳市同盛绿色科技有限公司 | Anti-counterfeiting method and mobile device |
CN104517089A (en) * | 2013-09-29 | 2015-04-15 | 北大方正集团有限公司 | Two-dimensional code decoding system and method |
CN104517109A (en) * | 2013-09-29 | 2015-04-15 | 北大方正集团有限公司 | QR code image correction method and system |
CN104751099A (en) * | 2015-04-14 | 2015-07-01 | 华中科技大学 | Method for preprocessing before recognizing and reading color three-dimensional-code image |
CN107066919A (en) * | 2016-12-21 | 2017-08-18 | 网易(杭州)网络有限公司 | Pen tip position method for solving, equipment and computer-readable recording medium |
CN113483664A (en) * | 2021-07-20 | 2021-10-08 | 科派股份有限公司 | Screen plate automatic feeding system and method based on line structured light vision |
-
2007
- 2007-06-13 CN CN200710074943A patent/CN101093543B/en not_active Expired - Fee Related
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101576871B (en) * | 2008-05-09 | 2012-02-15 | 永驰科技有限公司 | Operating method for recommending system for accelerating computer arithmetics and image identification system |
CN101807297B (en) * | 2009-02-16 | 2012-07-25 | 海信集团有限公司 | Medical ultrasonic image line detection method |
CN101882207B (en) * | 2010-06-01 | 2012-06-20 | 福建新大陆电脑股份有限公司 | Bar code decoding chip of Data Matrix codes and decoding method thereof |
CN101882207A (en) * | 2010-06-01 | 2010-11-10 | 福建新大陆电脑股份有限公司 | Bar code decoding chip of Data Matrix codes and decoding method thereof |
CN102096795B (en) * | 2010-11-25 | 2014-09-10 | 西北工业大学 | Method for recognizing worn two-dimensional barcode image |
CN102096795A (en) * | 2010-11-25 | 2011-06-15 | 西北工业大学 | Method for recognizing worn two-dimensional barcode image |
CN102254204A (en) * | 2011-06-03 | 2011-11-23 | 吴林 | Coding and decoding method for graphemic code |
CN103400131B (en) * | 2013-08-16 | 2016-12-28 | 徐宁 | Correcting unit in a kind of image recognition and method thereof |
CN103400131A (en) * | 2013-08-16 | 2013-11-20 | 徐宁 | Correction device and method for image identification |
CN104463291A (en) * | 2013-09-16 | 2015-03-25 | 深圳市同盛绿色科技有限公司 | Anti-counterfeiting method and mobile device |
CN104463291B (en) * | 2013-09-16 | 2018-06-05 | 深圳市同盛绿色科技有限公司 | Method for anti-counterfeit and mobile equipment |
CN104517089A (en) * | 2013-09-29 | 2015-04-15 | 北大方正集团有限公司 | Two-dimensional code decoding system and method |
CN104517109A (en) * | 2013-09-29 | 2015-04-15 | 北大方正集团有限公司 | QR code image correction method and system |
CN104517089B (en) * | 2013-09-29 | 2017-09-26 | 北大方正集团有限公司 | A kind of Quick Response Code decodes system and method |
CN104517109B (en) * | 2013-09-29 | 2018-03-06 | 北大方正集团有限公司 | A kind of bearing calibration of QR codes image and system |
CN104751099A (en) * | 2015-04-14 | 2015-07-01 | 华中科技大学 | Method for preprocessing before recognizing and reading color three-dimensional-code image |
CN107066919A (en) * | 2016-12-21 | 2017-08-18 | 网易(杭州)网络有限公司 | Pen tip position method for solving, equipment and computer-readable recording medium |
CN113483664A (en) * | 2021-07-20 | 2021-10-08 | 科派股份有限公司 | Screen plate automatic feeding system and method based on line structured light vision |
CN113483664B (en) * | 2021-07-20 | 2022-10-21 | 科派股份有限公司 | Screen plate automatic feeding system and method based on line structured light vision |
Also Published As
Publication number | Publication date |
---|---|
CN101093543B (en) | 2010-05-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101093543B (en) | Method for correcting image in 2D code of quick response matrix | |
CN101814185B (en) | Line structured light vision sensor calibration method for micro-size measurement | |
CN101936761B (en) | Visual measuring method of stockpile in large-scale stock ground | |
CN103411553B (en) | The quick calibrating method of multi-linear structured light vision sensors | |
CN108389233B (en) | Laser scanner and camera calibration method based on boundary constraint and mean value approximation | |
CN101915573B (en) | Positioning measurement method based on key point detection of marker | |
CN101303768B (en) | Method for correcting circle center error of circular index point when translating camera perspective projection | |
CN103759671B (en) | A kind of dental model three-dimensional surface data non-contact scanning method | |
CN100586200C (en) | Camera calibration method based on laser radar | |
CN107609451A (en) | A kind of high-precision vision localization method and system based on Quick Response Code | |
CN103295239A (en) | Laser-point cloud data automatic registration method based on plane base images | |
CN106097348A (en) | A kind of three-dimensional laser point cloud and the fusion method of two dimensional image | |
CN101661162B (en) | Distortion compensation method based on wide-angle lens | |
CN103177442A (en) | Calibrating method for two-dimensional laser and camera without overlapped viewing fields | |
CN102436652A (en) | Automatic registering method of multisource remote sensing images | |
CN102938142A (en) | Method for filling indoor light detection and ranging (LiDAR) missing data based on Kinect | |
CN100589116C (en) | Method for correcting pattern in 2D code of perspective quick response matrix | |
CN102982551B (en) | Method for solving intrinsic parameters of parabolic catadioptric camera linearly by utilizing three unparallel straight lines in space | |
CN102930548B (en) | Utilize the intersecting elliptical linear solution camera intrinsic parameter that two identical | |
CN102194225A (en) | Automatic registering method for coarse-to-fine space-borne synthetic aperture radar image | |
CN103745221A (en) | Two-dimensional code image correction method | |
CN101799996A (en) | Click-reading method of click-reading machine based on video image | |
CN102930518A (en) | Improved sparse representation based image super-resolution method | |
CN105139401A (en) | Depth credibility assessment method for depth map | |
CN102999895B (en) | Method for linearly solving intrinsic parameters of camera by aid of two concentric circles |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20100526 Termination date: 20190613 |