CN112215030B - Restoration and identification method based on cylindrical surface two-dimensional code - Google Patents
Restoration and identification method based on cylindrical surface two-dimensional code Download PDFInfo
- Publication number
- CN112215030B CN112215030B CN202011174973.9A CN202011174973A CN112215030B CN 112215030 B CN112215030 B CN 112215030B CN 202011174973 A CN202011174973 A CN 202011174973A CN 112215030 B CN112215030 B CN 112215030B
- Authority
- CN
- China
- Prior art keywords
- dimensional code
- coordinate system
- coordinate
- image
- pixel
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/146—Methods for optical code recognition the method including quality enhancement steps
- G06K7/1469—Methods for optical code recognition the method including quality enhancement steps using sub-pixel interpolation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Electromagnetism (AREA)
- General Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Artificial Intelligence (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a restoration and identification method based on a cylindrical surface two-dimensional code, which comprises the following steps: selecting a region where three 'return' type position detection graphs of the two-dimensional code are located according to the distance from the coordinates of the corner points of the connected domain to the image boundary and the rectangular area surrounded by the three corner points; the positions and the intervals of the three position detection graphs are utilized to calculate the hyper-parameters required by coordinate transformation, the camera coordinate system is converted into a world coordinate system according to the hyper-parameters, and the actual position of the two-dimensional code under the world coordinate system is obtained; mapping from a cylindrical surface to a plane of the two-dimensional code is realized by utilizing the corresponding relation between the arc length and the angle in a world coordinate system; converting a world coordinate system into a two-dimensional code image coordinate system according to the hyper-parameters, and acquiring pixel coordinates; the problem that the pixel coordinate is not adjusted and increased gradually is solved by using mirror image transposition, and the pixel coordinate range after mirror image transposition is compressed in the size range of the input image again by adopting normalization, so that the mapping position of the input image coordinate in the restoration image is obtained; and filling the pixel by interpolation for the coordinate which does not have the mapping relation with the input image coordinate in the repair map.
Description
Technical Field
The invention relates to the field of restoration and identification, in particular to a restoration and identification method based on a cylindrical surface two-dimensional code.
Background
In real life, a two-dimensional code may be subjected to many kinds of distortions including image noise due to illumination, equipment, and the like, pattern contamination due to dust, stain, oil stain, and the like, and rigid deformation that maintains a shape and non-rigid deformation that loses an inherent shape.
Some distortions can be eliminated in a simple way. In the case of noise-induced image impairments, simple filtering or transformation methods can generally be used. For example, when lighting is performed, the brightness is too high, or the two-dimensional code is attached with stickers such as transparent adhesive tape and the like to cause abnormal reflection of light, the abnormal reflection may be reflected as a piece of connected white noise on an image, and the noise can be eliminated by using Gaussian filtering; the problem that the boundary blurring is caused by the fact that dark pixels at the boundary of the two-dimensional code image are difficult to distinguish from a dark background when the brightness is too low can be solved through Gamma change. In addition, the problem caused by different distortions can be dealt with by the ground. For example: a Hough transformation method is adopted for the geometric distortion problem; the Otsu method is used for the case of uneven illumination and complex background; an algorithm based on edge detection is adopted when the edge is fuzzy; scanning boundary points to determine variable control points to realize an algorithm of curved surface deformation correction; adopting a two-dimensional code preprocessing method under the condition of uneven radial illumination; for the adaptive illumination balancing method and the perspective transformation algorithm adopted under the complex background; for the bar code boundary generated black and white aliasing and bar code abrasion caused by uneven illumination, an algorithm of block threshold processing after positioning and segmentation can be adopted; meanwhile, the method also comprises a corner detection algorithm and an image restoration algorithm based on the sparse representation theory.
For the problem of non-rigid deformation of the two-dimensional code, a better solution is not provided at present, and the detection and identification of equipment are greatly influenced. Cylindrical distortion of a two-dimensional code is a common non-rigid deformation, and the distortion is visible everywhere in life. Under the condition of improper storage or external force interference, the two-dimensional code is often distorted and bent in some shapes and is distorted in lamination. Particularly, the two-dimensional code can be attached or pasted on a non-plane (can or street lamp), and some curved surface distortion can be generated passively. Although the device can recognize the two-dimensional code when the degree of bending is small, it takes longer, and in severe cases, reading the two-dimensional code data often fails. Because the curved surface distortion of the two-dimensional code is very common, and the distortion is difficult to eliminate on the premise of not damaging the two-dimensional code, the influence is caused to the life and production of people, and the two-dimensional code has practical significance and practical value by taking the distortion as background research.
Disclosure of Invention
The invention provides a restoration and identification method based on a cylindrical surface two-dimensional code, which calculates the corner points of a connected domain and detects the region of a position detection graph, then calculates the parameters required by the change of a coordinate system by using the position detection graph, and finally converts and restores by using the coordinate system, and is described in detail as follows:
a restoration and identification method based on a cylindrical surface two-dimensional code comprises the following steps:
acquiring coordinates of corner points at the upper left position, the upper right position and the lower left position of all connected domains of the preprocessed binary image;
selecting a region where three 'return' type position detection graphs of the two-dimensional code are located according to the distance from the coordinates of the corner points of the connected domain to the image boundary and the rectangular area surrounded by the three corner points;
the positions and the intervals of the three position detection graphs are utilized to calculate the hyper-parameters required by coordinate transformation, the camera coordinate system is converted into a world coordinate system according to the hyper-parameters, and the actual position of the two-dimensional code in the world coordinate system is obtained;
mapping from a cylindrical surface to a plane of the two-dimensional code is realized by utilizing the corresponding relation between the arc length and the angle in a world coordinate system; converting a world coordinate system into a two-dimensional code image coordinate system according to the hyper-parameters to obtain pixel coordinates;
the problem that the pixel coordinate is not monotonously increased is solved by using mirror image transposition, and the pixel coordinate range after mirror image transposition is compressed again in the size range of the input image by adopting normalization to obtain the mapping position of the input image coordinate in the restoration image; and filling the pixel by interpolation for the coordinate which does not have the mapping relation with the input image coordinate in the repair map.
Wherein, the areas where the three 'return' type position detection patterns are located are as follows:
the distance from the upper left corner point of the upper left position detection graph to the lower left corner point of the lower left position detection graph is the two-dimensional code pixel length l, the distance from the upper left corner point of the upper left position detection graph to the upper right corner point of the upper right position detection graph is the left-right boundary pixel length d of the two-dimensional code on the cylindrical surface, and the distance from the camera to the cylindrical surface is Z;
wherein the opening angle theta0The system is radian, the system needs to be converted into an angle system when the subsequent coordinate changes, and f is the focal length of the camera.
Further, the implementation of the spatial coordinate system transformation according to the hyper-parameters specifically includes:
by taking the camera coordinate system along ZcThe axis is positively translated by Z + R, and the translated coordinate system is along YcThe shaft rotates clockwise
θ0The field angle of the two-dimensional code on the cylindrical surface is defined;
new coordinate system is taken along XcThe shaft rotating counterclockwise
A conversion from camera coordinates to world coordinates is achieved.
The world coordinate system is converted into a two-dimensional code image coordinate system according to the hyper-parameters:
according to the parameter opening angle theta0And the actual length L of the two-dimensional code, and pushing out any coordinate (x) on the two-dimensional codew,yw,zw) Has the following relation:
wherein (x ', y') is (x)w,yw,zw) Mapping to the corresponding coordinates of the plane, R is the actual radius of the cylinder, and theta is the left boundary of the two-dimensional code to (x)w,yw,zw) The covered central angle.
Further, the solving of the problem that the pixel coordinate is not monotonically increased by using the mirror image transposition is specifically:
wherein col represents a pixel coordinate mapping matrix in the vertical direction of the two-dimensional code, and i and j respectively represent the row number and the column number of pixel coordinates in the vertical direction of the cylindrical part; the min (-) and max (-) functions are functions for obtaining the minimum and maximum values of the matrix; index (·) represents a column index in the matrix to obtain the vertical direction pixel coordinate.
The technical scheme provided by the invention has the beneficial effects that:
1. the distorted two-dimensional code can be repaired only by a small amount of camera internal parameters, namely the focal length dx of the camera and the actual physical lengths dy and dy of the pixels;
2. the method has better robustness for different types of two-dimensional codes, can accurately obtain the area of the two-dimensional code position detection graph through judging conditions, and ensures that the repaired two-dimensional code can be quickly and accurately identified through mirror image transposition and interpolation, thereby solving the problem that the two-dimensional code cannot be identified due to cylindrical surface bending.
Drawings
Fig. 1 is a flow chart of a restoration and identification method based on a cylindrical surface two-dimensional code;
FIG. 2 is a schematic view of a "loop" type position detection pattern;
FIG. 3 is a schematic diagram of the transformation of the image coordinate system to the camera coordinate system;
FIG. 4 is an expanded view of world coordinates into an original image;
FIG. 5 is a schematic diagram of a folding phenomenon in two-dimensional code restoration;
fig. 6 is a diagram of an example of two-dimensional code repair.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention are described in further detail below.
The embodiment of the invention considers the condition of two-dimension code bending in non-rigid deformation, establishes a physical model, and improves the influence of adverse conditions on two-dimension code identification through a design algorithm.
Example 1
The embodiment of the invention provides a restoration and identification method based on a cylindrical surface two-dimensional code, and reduces hyper-parameters required by coordinate system change through a geometric relation of a graph, the specific flow is shown in figure 1 in detail, and the method comprises the following steps:
101: preprocessing an input image;
wherein the pre-treatment comprises: image graying, histogram equalization, median filtering and image binarization. The purpose of the median filtering is to reduce the noise of salt and pepper and reduce the appearance of fine connected domains of the binary image at the boundary, which otherwise affects the judgment of the position detection image region. The Otsu method is adopted for image binarization. The embodiments of the present invention will not be described in detail herein.
102: acquiring coordinates of corner points at the upper left position, the upper right position and the lower left position of all connected domains of the preprocessed binary image;
the coordinates of the three positions are obtained to judge whether the connected domain belongs to the three position detection graph areas. The determination of the coordinates of the corner points is determined by calculating the fixed points of the upper left position, the upper right position and the lower left position of the image respectively.
103: selecting areas of three 'return' type position detection graphs of the two-dimensional code according to the distance from coordinates of corner points of a connected domain to the image boundary and the rectangular area surrounded by the three corner points, wherein the structure of the 'return' type position detection graph is shown in FIG. 2, and the black-white interval ratio from left to right and from top to bottom is 1:1:3:1: 1;
104: and detecting the positions and the intervals of the patterns by using the three positions, and calculating the hyper-parameters required by coordinate transformation.
Among these, the hyper-parameters typically include: the field angle of the two-dimensional code on the cylindrical surface, the radius of the cylindrical surface and the actual length and width of the two-dimensional code.
105: the obtained hyper-parameters are utilized to realize space coordinate system transformation, cylindrical pixel coordinates are converted into image coordinates, the image coordinates are converted into camera coordinates, the camera coordinates are converted into actual coordinates, and the actual position of the two-dimensional code in a world coordinate system is obtained;
106: mapping from a cylindrical surface to a plane of the two-dimensional code is realized by utilizing the corresponding relation between the arc length and the angle in a world coordinate system;
107: realizing space coordinate system transformation by using the same hyper-parameters as those in the step 105, converting the actual coordinates of the two-dimensional code of the plane under the world coordinate system into camera coordinates, converting the camera coordinates into image coordinates, and finally converting the image coordinates into pixel coordinates;
108: solving the problem that the pixel coordinate obtained in the step 107 is not monotonously increased by using mirror image transposition, and recompressing the pixel coordinate range after mirror image transposition within the size range of the input image by adopting normalization to obtain the mapping position of the input image coordinate in the repair map;
109: and filling the pixel by interpolation for the coordinate which does not have the mapping relation with the input image coordinate in the repair map.
In summary, the input image in the embodiment of the present invention generates a binary image through preprocessing, the hyper-parameters required by the coordinate change are reduced by using the two-dimensional code pattern detection area, the image is repaired by using the coordinate change, and finally the defect of the restored two-dimensional code is repaired by using the mirror image transposition and the interpolation, so that the restored two-dimensional code has high subjective visual quality and can be quickly and accurately identified.
Example 2
The scheme of example 1 is further described below with reference to specific calculation formulas and examples, which are described in detail below:
201: obtaining all connected domains on the image through the binary image;
in order to obtain the connected component of the pattern detection area, it is not judged by only the shortest distance to the vertex of the image, and it is necessary to set a judgment condition to exclude the disturbed connected component.
The judgment condition set in the embodiment of the invention is that the number of connected domain pixels is more than 200; the vertical distance between the upper left corner and the lower left corner of the connected domain does not exceed half of the image line number; the horizontal distance between the upper left corner and the upper right corner of the connected domain does not exceed half of the number of image columns; the ratio of the vertical distance between the upper left corner and the upper right corner to the horizontal distance between the upper left corner and the upper right corner is between [0.5 and 2.0 ].
In a specific implementation, the above values may also be set according to requirements in practical applications, and the embodiment of the present invention is not limited thereto.
202: obtaining connected domains of three 'loop' type position detection graphs;
wherein, the step is to obtain the distance between the 'square-shaped' position detection patterns, the distance from the upper left corner point of the upper left position detection pattern to the lower left corner point of the lower left position detection pattern is set as the pixel length l of the two-dimensional code, the distance from the upper left corner point of the upper left position detection pattern to the upper right corner point of the upper right position detection pattern is set as the left-right boundary pixel length d of the two-dimensional code on the cylindrical surface, and the distance from the camera to the cylindrical surfaceThe distance is Z. The over-parametric opening angle theta required for the coordinate change0The two-dimension code actual length L and the cylindrical surface radius R are calculated according to the formula:
wherein the opening angle theta0The system is radian, the system needs to be converted into an angle system when the subsequent coordinate changes, and f is the focal length of the camera.
203: the pixel coordinates are coordinates obtained after discretization of image coordinates, are all positioned on an imaging plane, and are different in respective origin and unit;
the origin of the image coordinate system is the center of the imaging plane and the unit is millimeter, and the origin of the pixel coordinate system is the upper left corner of the imaging plane and the unit is pixel. The transformation relationship between the two is 1pixel ═ dx mm, and for the embodiment of the present invention, dx ═ dy and u are set0And v0The physical meaning is half the length and width of the image in pixel units. The pixel coordinate system to image coordinate system transformation formula is as follows:
where (u, v) is an arbitrary point in the pixel coordinate system, and (x, y) is the corresponding coordinate in the image coordinate system.
204: from the image coordinate system to the camera coordinate system, the equation can be derived, as shown in fig. 3:
wherein (x)c,yc,zc) Is the corresponding point of (x, y) in the camera coordinate system.
Solving the system of equations, and deriving a discriminant and an effective solution of a quadratic equation of one element from the first two equations:
wherein the discriminant expression of the equation of formula (3) is replaced with Δ.
In finding zcAfter, xcAnd ycCan also be solved accordingly, the formula is:
the conversion of the image coordinates to the camera coordinates is completed by the above procedure. The practical result of Δ may be less than 0 because the image border region is the background rather than the cylindrical portion and therefore not suitable for using the above-mentioned coordinate system variation. Since the background part has no influence on the restoration of the two-dimensional code, the background part is not considered in the subsequent coordinate changing and adjusting operation.
205: from the camera coordinate system to the world coordinate system, it first needs to be taken along ZcThe axis is positively translated by Z + R, and the translated coordinate system is along YcThe shaft rotates clockwise
θ0The field angle of the two-dimensional code on the cylindrical surface is shown. Finally, the new coordinate system is arranged along XcThe shaft rotating counterclockwise
A conversion from camera coordinates to world coordinates is achieved.
The homogeneous matrix expression in the conversion process is as follows:
wherein (x)w,yw,zw) Is (x)c,yc,zc) And (4) converting the camera coordinates into the world coordinates by the above process according to the corresponding coordinates in the world coordinate system.
206: expansion of the world coordinate system into the original image is shown in FIG. 4, according to the determined parameter opening angle θ0And the actual length L of the two-dimensional code, and can deduce any coordinate (x) on the two-dimensional codew,yw,zw) Has the following relation:
wherein (x ', y') is (x)w,yw,zw) Mapping to the corresponding coordinates of the plane, R is the actual radius of the cylinder, and theta is the left boundary of the two-dimensional code to (x)w,yw,zw) The covered central angle.
Through the process discussed above, the corresponding relationship from any point in the two-dimensional code image to the corresponding point of the real two-dimensional code is established, and then the two-dimensional code image is reconstructed only according to the camera imaging process.
207: reducing the obtained actual coordinates (x ', y') into pixel coordinates, firstly, corresponding the actual coordinates to camera coordinates, and converting a homogeneous matrix into:
where is the coordinates of (x ', y') in the camera coordinate system. Then, according to the perspective projection rule, the following conversion relation exists:
wherein (u)*,v*) Is that(x'c,y'c,z'c) Coordinates in the image coordinate system. Final image to pixel coordinates:
wherein (u)*,v*) Is (x)*,y*) The corresponding pixel coordinates.
After the image coordinates are converted into pixel coordinates, the pixel values of corresponding points in the original two-dimensional code image are assigned to new points, after all the points are operated, the nearest pixel values are filled in the points which are not assigned through nearest neighbor interpolation, and therefore the two-dimensional code image restoration based on the coordinate conversion is completed.
208: in the process of converting the actual coordinates of the two-dimensional code into the pixel coordinates, the pixel coordinates of the cylindrical surface part are not monotonous in the horizontal direction, and may be increased gradually and then decreased gradually or decreased gradually and then increased gradually, and it appears in the restoration image that the cylindrical surface background part is folded at the boundary, and overlaps with the two-dimensional code region, as shown in fig. 5.
Therefore, mirror image processing is adopted to make the pixel coordinate monotonous in the vertical direction, and the processing method comprises the following steps:
wherein col represents a pixel coordinate mapping matrix in the vertical direction of the two-dimensional code, and i and j represent the number of rows and columns of pixel coordinates in the vertical direction of the cylindrical part respectively. The min (-) and max (-) functions are functions that obtain the minimum and maximum values of the matrix. index (·) represents a column index in the matrix to obtain the vertical pixel coordinate. But the transformed coordinate map may be beyond the boundary of the restored image. Therefore, normalization needs to be used, and the formula is:
209: separating the cylindrical background area from the two-dimensional code area, performing interpolation restoration on the inner part of the two-dimensional code area, and distributing pixels to the coordinates which are not distributed to the pixels by adopting nearest neighbor interpolation according to the rule that the pixels are scanned from left to right and the coordinates of the pixels which are not distributed are unified to obtain the pixels of the left adjacent coordinates.
The interpolation restoration and the nearest neighbor interpolation inside the two-dimensional code region in the step are technical terms known to those skilled in the art, and are not described in detail in the embodiment of the present invention.
Example 3
The protocols of examples 1 and 2 were evaluated for efficacy in combination with specific experimental data, as described in detail below:
the experimental data set is 5 download link two-dimensional code pictures corresponding to different apps from different sources, and expiration and invalidation of the download link two-dimensional code pictures are avoided. The pictures are from WeChat, Jingdong, 12306, Mei Tuo, common QR code.
Fig. 6 reflects the effect of the embodiment of the present invention on repairing and recognizing the two-dimensional code located on the cylindrical surface, the left side is the original image of the two-dimensional code distorted by the cylindrical surface, the right side is the two-dimensional code image after the duplication, the restored image is subjectively in a planar state and can be recognized quickly, which illustrates the effectiveness of the embodiment of the present invention.
In the embodiment of the present invention, except for the specific description of the model of each device, the model of other devices is not limited as long as the device can perform the above functions.
Those skilled in the art will appreciate that the drawings are only schematic illustrations of preferred embodiments, and the above-described embodiments of the present invention are merely provided for description and do not represent the merits of the embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (5)
1. A restoration and identification method based on a cylindrical surface two-dimensional code is characterized by comprising the following steps:
acquiring coordinates of corner points at the upper left position, the upper right position and the lower left position of all connected domains of the preprocessed binary image;
selecting a region where three 'return' type position detection graphs of the two-dimensional code are located according to the distance from the coordinates of the corner points of the connected domain to the image boundary and the rectangular area surrounded by the three corner points;
the positions and the intervals of the three position detection graphs are utilized to calculate the hyper-parameters required by coordinate transformation, the camera coordinate system is converted into a world coordinate system according to the hyper-parameters, and the actual position of the two-dimensional code under the world coordinate system is obtained;
mapping from a cylindrical surface to a plane of the two-dimensional code is realized by utilizing the corresponding relation between the arc length and the angle in a world coordinate system; converting a world coordinate system into a two-dimensional code image coordinate system according to the hyper-parameters to obtain pixel coordinates;
the problem that the pixel coordinate is not monotonously increased is solved by using mirror image transposition, and the pixel coordinate range after mirror image transposition is compressed again in the size range of the input image by adopting normalization to obtain the mapping position of the input image coordinate in the restoration image; and filling the pixel by interpolation for the coordinate which does not have the mapping relation with the input image coordinate in the repair map.
2. The restoration and identification method based on the cylindrical two-dimensional code as claimed in claim 1, wherein the three "loop" type position detection patterns are located in the following areas:
the distance from the upper left corner point of the upper left position detection graph to the lower left corner point of the lower left position detection graph is the two-dimensional code pixel length l, the distance from the upper left corner point of the upper left position detection graph to the upper right corner point of the upper right position detection graph is the left-right boundary pixel length d of the two-dimensional code on the cylindrical surface, and the distance from the camera to the cylindrical surface is Z;
wherein the opening angle theta0The radian system is required when the subsequent coordinate changesTo translate to an angle system, f is the camera focal length and dx is the camera focal length.
3. The restoration and identification method based on the cylindrical two-dimensional code as claimed in claim 1, wherein the implementation of the spatial coordinate system transformation according to the hyper-parameter specifically comprises:
by taking the camera coordinate system along ZcThe axis is positively translated by Z + R, and the translated coordinate system is along YcThe shaft rotates clockwise
θ0The field angle of the two-dimensional code on the cylindrical surface is defined;
new coordinate system is taken along XcThe shaft rotating counterclockwise
A conversion from camera coordinates to world coordinates is achieved.
4. The restoration and identification method based on the cylindrical two-dimensional code as claimed in claim 1, wherein the conversion from the world coordinate system to the two-dimensional code image coordinate system is realized according to the hyper-parameter:
according to the parameter opening angle theta0And the actual length L of the two-dimensional code, and pushing out any coordinate (x) on the two-dimensional codew,yw,zw) Has the following relation:
wherein (x ', y') is (x)w,yw,zw) Mapping to the corresponding coordinates of the plane, R is the actual radius of the cylinder, and theta is the left boundary of the two-dimensional code to (x)w,yw,zw) The center of the circle coveredAnd (4) an angle.
5. The restoration and identification method based on the cylindrical two-dimensional code according to claim 1, wherein the solving of the problem that the pixel coordinate is not monotonically increased by using the mirror image transpose specifically comprises:
wherein col represents a pixel coordinate mapping matrix in the vertical direction of the two-dimensional code, and i and j respectively represent the row number and the column number of pixel coordinates in the vertical direction of the cylindrical part; the min (-) and max (-) functions are functions that obtain the minimum and maximum values of the matrix; index (·) represents a column index in the matrix to obtain the vertical pixel coordinate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011174973.9A CN112215030B (en) | 2020-10-28 | 2020-10-28 | Restoration and identification method based on cylindrical surface two-dimensional code |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011174973.9A CN112215030B (en) | 2020-10-28 | 2020-10-28 | Restoration and identification method based on cylindrical surface two-dimensional code |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112215030A CN112215030A (en) | 2021-01-12 |
| CN112215030B true CN112215030B (en) | 2022-06-10 |
Family
ID=74057372
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011174973.9A Active CN112215030B (en) | 2020-10-28 | 2020-10-28 | Restoration and identification method based on cylindrical surface two-dimensional code |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112215030B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112926715B (en) * | 2021-03-23 | 2024-02-02 | 支付宝（中国）网络技术有限公司 | Two-dimensional code generation and decoding method, device and equipment |
| CN117236247B (en) * | 2023-11-16 | 2024-01-23 | 零壹半导体技术(常州)有限公司 | Signal shielding wire generation method for chip test |
| CN118070826B (en) * | 2024-04-19 | 2024-07-23 | 宁波安得智联科技有限公司 | Two-dimensional code repairing method, device, terminal equipment and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104182200B (en) * | 2014-08-29 | 2018-08-03 | 清华大学 | Cylindrical surface two-dimensional code identification method and device |
| CN106023115B (en) * | 2016-05-30 | 2018-11-30 | 南京汇川图像视觉技术有限公司 | A kind of cylinder back project method |
| CN107145929B (en) * | 2017-05-16 | 2019-08-16 | 重庆大学 | A kind of predistortion two-dimensional code generation method for cylindrical surface two dimensional code patch |
| CN109117693B (en) * | 2017-06-22 | 2021-08-27 | 深圳华智融科技股份有限公司 | Scanning identification method based on wide-angle view finding and terminal |
| JP2019144793A (en) * | 2018-02-20 | 2019-08-29 | 富士ゼロックス株式会社 | Information processing device and program |
| CN111681160B (en) * | 2020-05-28 | 2021-07-06 | 深圳市无虚科技有限公司 | Curved image restoration method, device and equipment and readable storage medium |
-
2020
- 2020-10-28 CN CN202011174973.9A patent/CN112215030B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112215030A (en) | 2021-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112215030B (en) | Restoration and identification method based on cylindrical surface two-dimensional code | |
| CN110866924B (en) | Line structured light center line extraction method and storage medium | |
| CN111260731B (en) | Self-adaptive detection method for checkerboard sub-pixel level corner points | |
| CN111968144B (en) | Image edge point acquisition method and device | |
| CN108830832B (en) | Plastic barrel surface defect detection method based on machine vision | |
| CN109840889A (en) | High-precision vision measurement method, device and system based on bionic Algorithm | |
| CN115170669A (en) | Identification and positioning method and system based on edge feature point set registration and storage medium | |
| CN110569857B (en) | Image contour corner detection method based on centroid distance calculation | |
| Rosenfeld | Image pattern recognition | |
| CN107633253B (en) | Accurate extraction and positioning method based on rectangular surrounding frame in noisy image | |
| CN110009615B (en) | Image corner detection method and detection device | |
| Shah et al. | An iterative approach for shadow removal in document images | |
| CN114972575A (en) | Linear fitting algorithm based on contour edge | |
| CN115661110B (en) | Transparent workpiece identification and positioning method | |
| CN115713556A (en) | Two-dimensional code positioning method and device and computer readable storage medium | |
| JP2004362053A (en) | Two-dimensional code reading device | |
| CN113076952B (en) | Text automatic recognition and enhancement method and device | |
| CN112184723B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN111815725B (en) | QR code region positioning method | |
| CN111178111A (en) | Two-dimensional code detection method, electronic device, storage medium and system | |
| CN110930358A (en) | Solar panel image processing method based on self-adaptive algorithm | |
| Rui | Lane line detection technology based on machine vision | |
| CN116052020A (en) | Unmanned aerial vehicle-based image rapid interpretation method | |
| CN114742705A (en) | Image splicing method based on halcon | |
| CN117115799B (en) | Tire character recognition method based on laser line scanning 3D camera |
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 |