CN112200741B - Out-of-focus two-dimensional code image restoration method based on edge prior - Google Patents
Out-of-focus two-dimensional code image restoration method based on edge prior Download PDFInfo
- Publication number
- CN112200741B CN112200741B CN202011072797.8A CN202011072797A CN112200741B CN 112200741 B CN112200741 B CN 112200741B CN 202011072797 A CN202011072797 A CN 202011072797A CN 112200741 B CN112200741 B CN 112200741B
- Authority
- CN
- China
- Prior art keywords
- dimensional code
- image
- code image
- edge
- restored
- 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
- 238000000034 method Methods 0.000 title claims abstract description 67
- 239000011159 matrix material Substances 0.000 claims abstract description 19
- 230000008859 change Effects 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000009795 derivation Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000003708 edge detection Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 230000015556 catabolic process Effects 0.000 claims description 7
- 238000006731 degradation reaction Methods 0.000 claims description 7
- 238000009792 diffusion process Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 4
- 241001156002 Anthonomus pomorum Species 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000010845 search algorithm Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000006837 decompression Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention provides a defocus two-dimensional code image restoration method based on edge prior, which comprises the following steps: inputting a two-dimensional code image to be restored, and performing graying processing on the two-dimensional code image to be restored to obtain a pixel matrix F of the two-dimensional code image to be restored; scanning the F, positioning a two-dimensional code image area, obtaining a two-dimensional code central point position O, and setting a left boundary straight line as an edge straight line L; calculating an edge prior coordinate E according to a prior distance S in combination with the central point position O, wherein the prior distance S is an average distance from a central point of the same batch of clear two-dimensional code images to a boundary straight line; obtaining an iterative image A according to the position information of the L, and processing the image A to obtain a point Q with the maximum derivative value change rate; calculating the distance between the column coordinates corresponding to the E and the Q to obtain an estimated defocusing radius R; and calculating a point spread function according to the R, restoring the two-dimensional code image to be restored according to the point spread function, and performing binarization processing to obtain the restored two-dimensional code image.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a defocus two-dimensional code image restoration method based on edge prior.
Background
The QR (quick response) code is one of two-dimensional codes, and the application of the QR (quick response) code is more and more extensive along with the rapid development of the technology of the Internet of things. The out-of-focus blurred image is obtained by convolving the sharp QR code image with a point spread function (blur kernel) plus noise, and the image restoration process is an image deconvolution process or is referred to as a deconvolution process. Image restoration can be divided into two categories, depending on whether the point spread function is known or not: one is a non-blind deconvolution technology of the blurred image, and the point spread function of the blurred image is assumed to be known, and the deconvolution operation is directly carried out on the blurred image; the other is a blind deconvolution technology of the blurred image, and under the condition that a point spread function of the blurred image is unknown, the clear image needs to be restored by combining the prior knowledge of the blurred image, which is an uncertainty problem.
Publication No. CN104331871A (published: 2015-02-04) proposes an image deblurring method, which adopts an out-of-focus blur parameter estimation algorithm based on differential image autocorrelation to determine out-of-focus radius when the image blur type is out-of-focus blur, and then brings the estimated parameters into a classic image restoration algorithm to obtain a restored image. However, the accuracy of the estimation algorithm applied to calculating the defocus radius is low at present, so that the finally obtained restored image has the problem of unsatisfactory restoration effect.
Disclosure of Invention
The invention provides an out-of-focus two-dimensional code image restoration method based on edge prior, aiming at overcoming the defects that the out-of-focus radius estimation algorithm in the prior art is low in accuracy rate and the restoration image has an unsatisfactory restoration effect.
In order to solve the technical problems, the technical scheme of the invention is as follows:
an out-of-focus two-dimensional code image restoration method based on edge prior comprises the following steps:
s1: inputting a two-dimensional code image to be restored, and preprocessing the two-dimensional code image to be restored to obtain a pixel matrix F of the two-dimensional code image to be restored;
s2: scanning the pixel matrix F, preliminarily positioning a two-dimensional code image area to be restored, further obtaining a two-dimensional code central point position O, and setting a left boundary straight line as an edge straight line L;
s3, calculating to obtain an edge priori coordinate E according to a priori distance S in combination with the position O of the central point, wherein the priori distance S is the average distance from the central point of the same batch of clear two-dimensional code images to a boundary straight line;
s4: obtaining an iterative image A according to the position information of the edge straight line L, and processing the iterative image A to obtain a point Q with the maximum derivative value change rate;
s5: calculating the distance between the edge prior coordinate E and the row coordinate corresponding to the point Q with the maximum derivative value change rate in the edge image to obtain an estimated defocus radius R;
s6: and calculating according to the defocusing radius to obtain a point diffusion function, restoring the two-dimensional code image to be restored according to the point diffusion function, and performing image binarization processing to obtain the restored two-dimensional code image.
Preferably, in the step S1, the specific step of preprocessing the two-dimensional code image to be restored includes: carrying out graying processing on a two-dimensional code image to be restored to obtain a pixel matrix of the two-dimensional code image; the expression formula of the pixel matrix is as follows:
wherein N represents the width of the two-dimensional code image, M represents the height of the two-dimensional code image, a (i, j) represents the pixel value of which the pixel coordinate position in the two-dimensional code image is (i, j), i is more than or equal to 1 and less than or equal to M, and j is more than or equal to 1 and less than or equal to N.
Preferably, in the step S2, the specific steps include:
s2.1: carrying out edge detection on the edge image by adopting an edge detection operator to obtain an edge matrix;
s2.2: scanning the edge matrix row by row and column by column from left to right and from top to bottom by adopting a classical search algorithm to obtain the position information of all boundary straight lines in the edge image; searching the edge matrix to obtain a row of pixel values with continuous numerical values of 1, namely position information of the edge straight line;
s2.3: preliminarily positioning a two-dimensional code image area to be restored according to a boundary straight line of the image to obtain a two-dimensional code central point position O;
s2.4: and selecting a left boundary straight line of the two-dimensional code image to be restored as an edge straight line L.
Preferably, the edge detection operator used is the Canny operator.
Preferably, in the step S3, the specific step of calculating the edge prior coordinate E includes:
s3.1: inputting the two-dimensional code images of the same batch and then evaluating the image definition of the two-dimensional code images;
s3.2: when the image is evaluated to be clear, respectively detecting the edge of the image and the image center point O of the two-dimensional code;
s3.3: calculating the average distance between the edge of all the detected images and the central point O, namely the prior distance S;
s3.4: and subtracting the prior distance S from the coordinate of the central point O of the two-dimensional code image to be restored to obtain the coordinate E of the edge prior pixel value.
Preferably, in the step S3.1, the image sharpness evaluation may adopt methods such as Tenengrad gradient method, information entropy method, Brenner gradient method, and the like.
Preferably, in the step S4, the specific step of finding the point with the greatest change rate of the derivative value includes: performing first derivation on the iteration image A, wherein the formula of the first derivation is as follows:
dx(i,j)＝I(i+1,j)-I(i,j)
dy(i,j)＝I(i,j+1)-I(i,j)
wherein I (I, j) represents a pixel value at position (I, j) in the iterative image a;
performing secondary derivation on the first derivative to obtain a second derivative of the iterative image A; the calculation formula is as follows:
G(x,y)＝dx(i,j)+dy(i,j)
and searching a point Q with the maximum derivative value change rate by using the second derivative G (x, y) of the iteration image A and the normal direction of the edge straight line L.
Preferably, in the step S5, the specific step of calculating the defocus radius includes: and subtracting the column coordinate of the edge prior coordinate E from the column coordinate of the point Q with the maximum derivative value change rate in the iterative image A to obtain the value of the estimated defocus radius R.
Preferably, in the step S6, the specific step of obtaining the point spread function includes: inputting the defocusing radius into a defocusing degradation model to obtain a point spread function; the expression formula of the defocusing degradation model is as follows:
wherein h (x, y) is a point spread function, and R is a defocus radius.
Preferably, the specific step of restoring the two-dimensional code image to be restored by using the point spread function includes: firstly, restoring a two-dimensional code image to be restored by combining a point spread function with a Wiener filtering algorithm, and then performing image binarization processing on a restoration result to finally obtain a restored two-dimensional code image.
Compared with the prior art, the technical scheme of the invention has the following remarkable advantages: according to the method, the priori knowledge is set through the edge and the center of the priori image to be used for the estimation of the defocusing radius, so that the accuracy of the defocusing radius estimation can be effectively improved, and the image restoration effect is further improved; by acquiring the left edge straight line group of the gray two-dimensional code image, the calculation amount of target image restoration is reduced while the defocusing radius estimation calculation is not influenced.
Drawings
Fig. 1 is a flowchart of a defocus two-dimensional code image restoration method based on edge prior.
FIG. 2 is a flow chart of the prior distance calculation of the present invention.
Fig. 3 is an input out-of-focus blurred QR code image.
Fig. 4 is a QR code image after edge detection.
Fig. 5 is a graph of the relationship after the second derivation.
Fig. 6 is a QR code image with restoration completed.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent;
certain well-known structures in the drawings and possible omissions of description may be apparent to those skilled in the art.
The technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
The present embodiment provides a method for restoring an out-of-focus two-dimensional code image based on edge prior, which is a flowchart of the method for restoring an out-of-focus two-dimensional code image based on edge prior in the present embodiment, as shown in fig. 1.
In the method for restoring an out-of-focus two-dimensional code image based on edge prior, the method specifically includes the following steps:
s1: and inputting the two-dimensional code image to be restored, and performing graying processing on the two-dimensional code image to be restored to obtain a pixel matrix F of the two-dimensional code image to be restored.
The method comprises the following specific steps: the expression formula of the pixel matrix obtained after the graying processing is carried out on the two-dimensional code image to be restored is as follows:
wherein N represents the width of the two-dimensional code image, M represents the height of the two-dimensional code image, a (i, j) represents the pixel value of which the pixel coordinate position in the two-dimensional code image is (i, j), i is more than or equal to 1 and less than or equal to M, and j is more than or equal to 1 and less than or equal to N.
S2: and scanning the whole image of the pixel matrix F to find an area of the two-dimensional code (except for the outer margin), further obtaining the position O of the center point of the two-dimensional code, and setting the left edge straight line as an edge straight line L.
The method comprises the following specific steps: and scanning the pixel matrix F row by row and column by adopting an edge detection operator from left to right and from top to bottom by adopting a classical search algorithm, determining the edge straight line position when finding the pixel coordinate with the same row or the same column which has continuous numerical value and is 1 so as to determine the approximate area of the two-dimensional code, further obtaining the central point position by calculation, and setting the edge straight line on the left as an edge straight line L.
S3: and calculating to obtain an edge prior coordinate E according to the prior distance S and the central point position O.
The method comprises the following specific steps: inputting two-dimensional code images of the same batch, evaluating image definition of the two-dimensional code images, respectively detecting image edges and image center points O of the two-dimensional codes when the images are evaluated to be clear, calculating average distances between the edges of all the detected images and the center points O, and taking the calculated average distance as a priori distance S. And then, subtracting the prior distance S from the coordinate of the central point O of the two-dimensional code image to be restored to obtain the edge prior coordinate E of the edge prior pixel value.
The image definition evaluation can adopt methods such as a Tenengrad gradient method, an information entropy method, a Brenner gradient method and the like. The average distance is calculated by setting the number of clear images, and the obtained average distance is the prior distance S of the batch of the two-dimensional codes. The prior distance calculation flowchart is shown in fig. 2.
S4: and obtaining an iterative image A according to the position information of the edge straight line L, and performing secondary derivation on the iterative image A to obtain a maximum value Q of the derivative value change rate in the image.
The method comprises the following specific steps: the specific steps of performing the second derivation on the iterative image a include:
performing first derivation on the iteration image A, wherein the formula of the first derivation is as follows:
dx(i,j)＝I(i+1,j)-I(i,j)
dy(i,j)＝I(i,j+1)-I(i,j)
wherein I (I, j) represents a pixel value at position (I, j) in the iterative image a;
performing secondary derivation on the first derivative to obtain a second derivative of the iterative image A; the calculation formula is as follows:
G(x,y)＝dx(i,j)+dy(i,j)
and searching a point Q with the maximum value of the change rate of the derivative value according to the second derivative G (x, y) of the iteration image A and the normal direction of the edge straight line.
S5: and obtaining the estimated defocus radius R according to the distance between the pixel points respectively corresponding to the edge prior pixel value and the maximum value Q of the variation rate of the derivative value in the edge image.
The method comprises the following specific steps: and subtracting the pixel points respectively corresponding to the maximum value of the derivative value change rate in the edge image from the pixel points respectively corresponding to the edge prior pixel value and the maximum value of the derivative value change rate in the edge image to obtain the distance between the pixel points respectively corresponding to the edge prior pixel value and the maximum value of the derivative value change rate in the edge image, namely the estimated defocus radius R.
S6: and obtaining a point diffusion function by calculating the defocusing radius R, restoring the two-dimensional code image to be restored by using the point diffusion function, and performing image binarization processing on the restoration result to finally obtain the restored two-dimensional code image.
In this step, the specific step of obtaining the point spread function includes: inputting the defocusing radius into a defocusing degradation model to obtain a point spread function; the expression formula of the defocus degradation model is as follows:
wherein h (x, y) is a point spread function, and R is a defocus radius.
In a specific implementation process, the out-of-focus blurred QR code image is taken as an example for restoration, the out-of-focus blurred QR code image shown in fig. 3 is input, and then graying is performed on the out-of-focus blurred QR code image to ensure a subsequent restoration effect, and then edge detection is performed on the input QR code image to obtain a pixel matrix, which is the QR code image subjected to edge detection, as shown in fig. 4.
The first derivative of the edge-detected image is derived again, as shown in fig. 5, which represents a relationship diagram after second derivation, where the ordinate is a gradient value (i.e., the result after second derivation), and the abscissa is the difference between the edge prior pixel value and the image column position. The ordinate in the figure can be regarded as the position of the edge straight line L, while the abscissa can be regarded as the normal of the edge straight line L, and the position of Q can be determined by searching the point with the largest derivative change rate from the edge prior coordinate E to the normal direction.
As can be seen from fig. 5, the abscissa of the point corresponding to the point with the maximum derivative change rate is 16, that is, the abscissa of the position of the point Q with the maximum derivative change rate can be determined to be 16, and the coordinate of the edge a priori pixel value is 0 because the edge a priori pixel value is set as the starting point, so that the estimated defocus radius can be obtained to be 16, and then the defocus radius is brought into the defocus degradation model to calculate the point spread function
Final utilization of WienerAnd (3) restoring the blurred QR code image by combining a filtering algorithm with a point spread function to obtain a restored QR code image shown in FIG. 6.
As can be seen from comparing fig. 3 and fig. 6, the method for restoring an image of an out-of-focus QR code based on edge prior provided by the embodiment has a good restoration effect, and can effectively ensure the quality of the image while restoring the sharpness of the image.
The restoration method of the present invention was compared with several other methods known so far, and images with resolutions of 200 × 200, 300 × 300, 500 × 500, and 800 × 800 were selected as input, and the time spent in the entire restoration process was compared, and the time spent in each method is shown in table 1.
Table 1 recovery time data of the present invention and other methods
| Image resolution | Method 1 | |
Method 3 | |
Method 5 | The method of the |
| 200*200(s) | 89.109 | 97.525 | 12.788 | 45.306 | 11.532 | 0.257 |
| 300*300(s) | 118.786 | 179.5 | 31.569 | 70.721 | 26.178 | 0.309 |
| 500*500(s) | 372.215 | 464.622 | 114.665 | 173.342 | 54.731 | 0.437 |
| 800*800(s) | 1936.9 | 1202.1 | 349.67 | 390.98 | 121.81 | 0.75 |
Wherein, the method 1 adopts an L0-norm gradient prior method (L.xu, S.ZHEN, and J.Jia.Unnaturral L0 spark presentation for natural image decoding. in CVPR, pages 1107-1114. IEEE,2013.) proposed by L.xu et al;
the method 2 adopts a blind restoration method based on Dark Channel Prior (Pan J, Sun D, Pfister H, et al. Blind Image concealment Using Dark Channel Prior [ C ]//2016IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE,2016.) proposed by PAN, etc.;
an image restoration method based on Extreme channel Prior proposed by YAN and the like (Yan Y, Ren W, Guo Y, et al. image decompression via Extreme Channels Prior [ C ]//2017IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
method 5 is a Simple Local minimum Intensity Prior and An Improved Blind restoration Algorithm proposed by WEN et al (WEN F, Ying R, Liu Y, et al.a Simple Local minimum Intensity price and An Improved Algorithm for Blind Image deblocking [ J ]. 2019.).
As can be seen from the data in Table 1, the image restoration method based on the edge prior out-of-focus QR code provided by the invention and other methods are adopted to restore images with different resolutions, and under the condition of the same image resolution, the restoration method provided by the invention is obviously less in time consumption than the methods in other five documents, so that the restoration efficiency is greatly improved.
The out-of-focus QR code image restoration method based on edge prior obviously can effectively improve the restoration effect and the restoration efficiency of the out-of-focus QR code image and effectively reduce the restoration calculation amount.
It should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (9)
1. An out-of-focus two-dimensional code image restoration method based on edge prior is characterized by comprising the following steps:
s1: inputting a two-dimensional code image to be restored, and preprocessing the two-dimensional code image to be restored to obtain a pixel matrix F of the two-dimensional code image to be restored;
s2: scanning the pixel matrix F, preliminarily positioning a two-dimensional code image area to be restored, further obtaining a two-dimensional code central point position O, and setting a left boundary straight line as an edge straight line L;
s3, calculating to obtain an edge priori coordinate E according to a priori distance S in combination with the position O of the central point, wherein the priori distance S is the average distance from the central point of the same batch of clear two-dimensional code images to a boundary straight line; the calculation step of the edge prior coordinate E comprises the following steps:
s3.1: inputting the two-dimensional code images of the same batch and then evaluating the image definition of the two-dimensional code images;
s3.2: when the image is evaluated to be clear, respectively detecting the edge of the image and the central point of the image of the two-dimensional code;
s3.3: calculating the average distance between the edge and the central point of all the detected images, namely the prior distance S;
s3.4: subtracting the prior distance S from the central point O of the two-dimensional code image to be restored to obtain a coordinate E of an edge prior pixel value;
s4: obtaining an iterative image A according to the position information of the edge straight line L, and processing the iterative image A to obtain a point Q with the maximum derivative value change rate;
s5: calculating the distance between the edge prior coordinate E and the row coordinate corresponding to the point Q with the maximum derivative value change rate in the edge image to obtain an estimated defocus radius R;
s6: and calculating according to the defocusing radius to obtain a point diffusion function, restoring the two-dimensional code image to be restored according to the point diffusion function, and performing image binarization processing to obtain the restored two-dimensional code image.
2. The restoration method for the out-of-focus two-dimensional code image according to claim 1, characterized in that: in the step S1, the specific step of preprocessing the two-dimensional code image to be restored includes: carrying out graying processing on the two-dimensional code image to be restored to obtain a pixel matrix F of the two-dimensional code image; the expression formula of the pixel matrix F is as follows:
wherein N represents the width of the two-dimensional code image, M represents the height of the two-dimensional code image, a (i, j) represents the pixel value of which the pixel coordinate position in the two-dimensional code image is (i, j), i is more than or equal to 1 and less than or equal to M, and j is more than or equal to 1 and less than or equal to N.
3. The restoration method for the out-of-focus two-dimensional code image according to claim 1, characterized in that: in the step S2, the specific steps are as follows:
s2.1: carrying out edge detection on the edge image by adopting an edge detection operator to obtain an edge matrix;
s2.2: scanning the edge matrix row by row and column by column from left to right and from top to bottom by adopting a classical search algorithm to obtain the position information of all boundary straight lines in the edge image;
s2.3: preliminarily positioning a two-dimensional code image area to be restored according to a boundary straight line of the image to obtain a two-dimensional code central point position O;
s2.4: and selecting a left boundary straight line of the two-dimensional code image to be restored as an edge straight line L.
4. The restoration method of the out-of-focus two-dimensional code image according to claim 3, characterized in that: in the step S2, the edge detection operator uses a Canny operator.
5. The out-of-focus two-dimensional code image restoration method according to claim 1, characterized in that: in the step S3.1, the image definition evaluation adopts a Tenengrad gradient method, an information entropy method and a Brenner gradient method.
6. The out-of-focus two-dimensional code image restoration method according to claim 1, characterized in that: in the step S4, a first derivation is performed on the iterative image a, where the formula of the first derivation is as follows:
dx(i,j)＝I(i+1,j)-I(i,j)
dy(i,j)＝I(i,j+1)-I(i,j)
wherein I (I, j) represents a pixel value at position (I, j) in the iterative image a;
and obtaining a second derivative of the iterative image A by carrying out derivation again on the first derivative, wherein a calculation formula is as follows:
G(x,y)＝dx(i,j)-dy(i,j)
and searching a point Q with the maximum derivative value change rate by using the second derivative G (x, y) of the iteration image A and the normal direction of the edge straight line L.
7. The out-of-focus two-dimensional code image restoration method according to claim 1, characterized in that: in the step S5, the specific step of calculating the defocus radius includes: and subtracting the point Q with the maximum derivative value change rate in the iterative image A from the edge prior coordinate E, wherein the calculated distance is the value of the estimated defocus radius R.
8. The out-of-focus two-dimensional code image restoration method according to claim 1, characterized in that: in the step S6, the specific step of obtaining the point spread function includes: inputting the defocusing radius into a defocusing degradation model to obtain a point spread function; wherein the expression formula of the defocus degradation model is as follows:
wherein h (x, y) is a point spread function, and R is a defocus radius.
9. The out-of-focus two-dimensional code image restoration method according to claim 8, characterized in that: in the step S6, the specific step of restoring the two-dimensional code image to be restored by using the point spread function includes: firstly, restoring a two-dimensional code image to be restored by combining a point spread function with a Wiener filtering algorithm, and then performing image binarization processing on a restoration result to finally obtain a restored two-dimensional code image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011072797.8A CN112200741B (en) | 2020-10-09 | 2020-10-09 | Out-of-focus two-dimensional code image restoration method based on edge prior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011072797.8A CN112200741B (en) | 2020-10-09 | 2020-10-09 | Out-of-focus two-dimensional code image restoration method based on edge prior |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112200741A CN112200741A (en) | 2021-01-08 |
| CN112200741B true CN112200741B (en) | 2022-05-17 |
Family
ID=74012630
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011072797.8A Active CN112200741B (en) | 2020-10-09 | 2020-10-09 | Out-of-focus two-dimensional code image restoration method based on edge prior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112200741B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113743147B (en) * | 2021-07-16 | 2023-08-29 | 广东技术师范大学 | Anti-fuzzy two-dimensional code image based on fuzzy imaging mechanism and blind restoration method thereof |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104636701A (en) * | 2014-12-12 | 2015-05-20 | 浙江工业大学 | Laser two-dimension code identification method based on image restoration |
| CN108765305A (en) * | 2018-04-16 | 2018-11-06 | 佛山市顺德区中山大学研究院 | A kind of defocus QR code method for blindly restoring image |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8249357B2 (en) * | 2006-10-23 | 2012-08-21 | Ben Gurion University Of The Negev, Research And Development Authority | Blind restoration of images degraded by isotropic blur |
-
2020
- 2020-10-09 CN CN202011072797.8A patent/CN112200741B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104636701A (en) * | 2014-12-12 | 2015-05-20 | 浙江工业大学 | Laser two-dimension code identification method based on image restoration |
| CN108765305A (en) * | 2018-04-16 | 2018-11-06 | 佛山市顺德区中山大学研究院 | A kind of defocus QR code method for blindly restoring image |
Non-Patent Citations (3)
| Title |
|---|
| 一种离焦模糊遥感图像盲复原方法;姜明勇等;《测绘科学》;20120720(第04期);第139-141页 * |
| 离焦模糊图像的盲复原算法;孙韶杰等;《计算机科学与探索》;20110430(第04期);第324-335页 * |
| 离焦模糊数字图像的Wiener滤波频域复原;郑楚君等;《激光杂志》;20041015(第05期);第58-59页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112200741A (en) | 2021-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110866924B (en) | Line structured light center line extraction method and storage medium | |
| EP3309703B1 (en) | Method and system for decoding qr code based on weighted average grey method | |
| CN102782706B (en) | Text enhancement of a textual image undergoing optical character recognition | |
| Nina et al. | A recursive Otsu thresholding method for scanned document binarization | |
| CN104408707B (en) | Rapid digital imaging fuzzy identification and restored image quality assessment method | |
| CN112819772B (en) | High-precision rapid pattern detection and recognition method | |
| EP2645305A2 (en) | A system and method for processing image for identifying alphanumeric characters present in a series | |
| CN111489337B (en) | Automatic optical detection pseudo defect removal method and system | |
| CN110070548B (en) | Deep learning training sample optimization method | |
| CN114049499A (en) | Target object detection method, apparatus and storage medium for continuous contour | |
| Zhou et al. | Improved estimation of motion blur parameters for restoration from a single image | |
| CN112200741B (en) | Out-of-focus two-dimensional code image restoration method based on edge prior | |
| CN111753572A (en) | Complex background low-quality two-dimensional bar code detection method based on deep learning | |
| CN116310095A (en) | Multi-view three-dimensional reconstruction method based on deep learning | |
| CN113421210B (en) | Surface point Yun Chong construction method based on binocular stereoscopic vision | |
| CN108205678B (en) | Nameplate character recognition processing method containing bright spot interference | |
| CN108765305B (en) | Out-of-focus QR code image blind restoration method | |
| CN117853510A (en) | Canny edge detection method based on bilateral filtering and self-adaptive threshold | |
| Zhu et al. | Optimization of image processing in video-based traffic monitoring | |
| CN116797484A (en) | Image defogging method and system based on improved dark channel prior | |
| CN115797327A (en) | Defect detection method and device, terminal device and storage medium | |
| CN110264417B (en) | Local motion fuzzy area automatic detection and extraction method based on hierarchical model | |
| CN114662519A (en) | QR code blind deblurring method based on position detection graph gradient and strength prior | |
| Junjie et al. | An image defocus deblurring method based on gradient difference of boundary neighborhood | |
| CN113436116A (en) | Night image deblurring method based on multi-standard light stripe selection in bipartite graph |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220824 Address after: 510640 No. 230, Gaotang Road, Tianhe District, Guangzhou City, Guangdong Province (self-edited property building) Patentee after: Guangzhou Radio and Television City Service Group Co.,Ltd. Address before: No. 293, Zhongshan Avenue West, Tianhe District, Guangzhou, Guangdong 510631 Patentee before: GUANGDONG POLYTECHNIC NORMAL University |
|
| TR01 | Transfer of patent right |