CN111815726B - Ellipse angle coding and decoding method based on computer vision recognition system - Google Patents
Ellipse angle coding and decoding method based on computer vision recognition system Download PDFInfo
- Publication number
- CN111815726B CN111815726B CN202010655501.9A CN202010655501A CN111815726B CN 111815726 B CN111815726 B CN 111815726B CN 202010655501 A CN202010655501 A CN 202010655501A CN 111815726 B CN111815726 B CN 111815726B
- Authority
- CN
- China
- Prior art keywords
- ellipse
- angle
- coding
- value
- computer vision
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T9/00—Image coding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
- G06F17/13—Differential equations
-
- 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
Abstract
The invention discloses an ellipse angle coding and decoding method based on a computer vision recognition system, which comprises the following steps: a mapping rule construction step: constructing an ellipse angle information capacity and corresponding parameter table, wherein the ellipse angle information capacity and corresponding parameter table comprises a plurality of single ellipse angle data capacity values, a plurality of ellipse angle numerical values and a plurality of highest total capacity values, and the single ellipse angle data capacity values, the ellipse angle numerical values and the highest total capacity values are in one-to-one correspondence; ellipse angle coding step: confirming the total data capacity required by the current encoding, calculating the numerical value of the ellipse angle, constructing an ellipse angle encoding table and generating an ellipse angle encoding image; ellipse angle decoding step: identifying all ellipse figures and the angle value of each ellipse, looking up a table to obtain a binary number mapping value, and obtaining coding information according to the binary number mapping value. The invention can improve the anti-attack performance of the computer vision coding image, and has simple, stable and reliable realization process.
Description
Technical Field
The invention relates to a data coding and decoding method, in particular to an ellipse angle coding and decoding method based on a computer vision recognition system.
Background
With the rapid development of Computer vision (Computer vision) technology in recent years, images themselves have become an information exchange medium. For example, some industrial systems can map complex system instructions into corresponding graphics through a coding table, and the system can automatically execute the instructions after reading the graphics. However, the current computer vision codec technology still faces serious challenges, and the anti-attack property is one of the biggest challenges. Where "encoding" refers to the process of converting information from one form or format to another; "decoding" is the inverse of encoding and refers to the process of restoring the encoded content to the original information. At present, the information coding and decoding technology is mainly applied to two aspects, on one hand, information encryption is adopted, and original information is difficult to identify under the condition that the coding standard is not known; another aspect is the exchange of information such as common character codecs, HTML codecs, audio video codecs, etc.
The anti-attack of the coded image means that when the coded image is damaged or is subjected to external attack (such as smearing, noise, clipping and the like), the coded image can still be identified by a computer vision algorithm. Currently, there are two main common computer vision coding techniques:
the first is a two-dimensional Code (QR Code). As the most popular computer visual coding technology in the market at present, the two-dimensional code has the advantages of high identification speed, large information capacity, strong fault-tolerant capability, self-contained error correction and the like. However, it should be noted that the functional boundaries of error tolerance and correction of the two-dimensional code are limited to data and cannot be extended to the level of graphics. If image attacks, such as smearing, clipping, noise and the like, are performed on the two-dimensional code, the identification of the two-dimensional code is directly failed.
The second is image coding based on deep learning. The deep learning algorithm can generally extract key features from the image and use the key features as codes, but the weakness of the method is still the problem of attack resistance of the image. It is known that attacks on coded images tend to be "sudden" and "uncertain", where deep learning algorithms are not given any opportunity to "learn". Attacks on the original image can directly result in changes in the key features and thus in the encoded information.
Disclosure of Invention
The invention aims to solve the technical problem of providing an elliptical angle coding and decoding method based on a computer vision identification system, which can improve the anti-attack performance of a computer vision coding image, has simple realization process, is stable and reliable and is easy to detect and identify.
In order to solve the technical problems, the invention adopts the following technical scheme.
An ellipse angle coding and decoding method based on a computer vision recognition system, the method comprises the following steps: a mapping rule construction step: constructing an ellipse angle information capacity and corresponding parameter table, wherein the ellipse angle information capacity and corresponding parameter table comprises a plurality of single ellipse angle data capacity values, a plurality of ellipse angle numerical values and a plurality of highest total capacity values, and the single ellipse angle data capacity values, the ellipse angle numerical values and the highest total capacity values are in one-to-one correspondence; ellipse angle coding step: step S10, confirming the total data capacity needed by the current coding; step S11, looking up the ellipse angle information capacity and the corresponding parameter table, determining the single ellipse angle data capacity value according to the total data capacity, and calculating the ellipse angle number value according to the single ellipse angle data capacity value; step S12, determining a selection angle value of a single ellipse and a fault tolerance range corresponding to the selection angle value, simultaneously allocating a binary number mapping value uniquely corresponding to the selection angle value to the single ellipse, representing information to be coded by utilizing a plurality of binary number mapping values, and constructing an ellipse angle coding table according to the selection angle value, the fault tolerance range and the binary number mapping value of the plurality of ellipses; step S13, drawing a single ellipse graph according to the selected angle value, generating an ellipse angle coding image by all the ellipse graphs, and finishing the coding step; ellipse angle decoding step: step S20, the computer vision recognition system recognizes the ellipse angle coding image to obtain all ellipse graphs and the angle value of each ellipse; step S21, according to the angle value of each ellipse, looking up the ellipse angle coding table to obtain the binary number mapping value corresponding to the ellipse; and step S22, sorting the binary number mapping values corresponding to all the ellipses, and obtaining the coding information according to all the binary number mapping values.
Preferably, in step S13, all the elliptical figures are printed or embedded into a preset image, so as to generate an elliptical angle encoded image.
Preferably, in the step S12, the selection angle value of the single ellipse is a rotation angle value of the major axis of the ellipse with respect to the cartesian coordinate system.
Preferably, in step S12, the fault tolerance range is an angle interval range with a fixed angle difference, and the selected angle value is located in the angle interval range.
Preferably, in step S20, the computer vision recognition system recognizes the ellipse angle coded image by using a preset ellipse angle figure girth integral detection algorithm, and further obtains all ellipse figures and an angle value of each ellipse.
The invention discloses an ellipse angle coding and decoding method based on a computer vision recognition system, which establishes a mapping relation between an ellipse angle figure and binary digits, and based on the mapping relation, the computer vision recognition system can map the corresponding binary digits according to the matching relation between the angle numerical value detected in the ellipse angle figure and an ellipse angle coding table. Compared with the prior art, the invention utilizes the geometric stability of the ellipse to map different ellipse angle graphs into binary digits, is assisted by a fault-tolerant mechanism, and detects and identifies the change of the ellipse angle graphs through a computer vision identification system so as to obtain corresponding binary mapping values and coding information.
Drawings
FIG. 1 is a flow chart of the ellipse angle encoding step;
FIG. 2 is a flow chart of the ellipse angle decoding step;
FIG. 3 is a schematic view of the elliptical geometry of a first embodiment of the present invention;
FIG. 4 is a diagram of an ellipse angle coding mapping relation according to a first embodiment of the present invention;
FIG. 5 is a table of ellipse angle information capacity and corresponding parameters according to a first embodiment of the present invention;
FIG. 6 is an ellipse angle encoding table according to a first embodiment of the present invention.
Detailed Description
The invention is described in more detail below with reference to the figures and examples.
The invention discloses an ellipse angle coding and decoding method based on a computer vision identification system, which is shown by combining a figure 1 and a figure 2 and comprises the following steps:
a mapping rule construction step: constructing an ellipse angle information capacity and corresponding parameter table, wherein the ellipse angle information capacity and corresponding parameter table comprises a plurality of single ellipse angle data capacity values, a plurality of ellipse angle numerical values and a plurality of highest total capacity values, and the single ellipse angle data capacity values, the ellipse angle numerical values and the highest total capacity values are in one-to-one correspondence;
ellipse angle coding step:
step S10, confirming the total data capacity needed by the current coding;
step S11, looking up the ellipse angle information capacity and the corresponding parameter table, determining the single ellipse angle data capacity value according to the total data capacity, and calculating the ellipse angle number value according to the single ellipse angle data capacity value;
step S12, determining a selection angle value of a single ellipse and a fault tolerance range corresponding to the selection angle value, simultaneously allocating a binary number mapping value uniquely corresponding to the selection angle value to the single ellipse, representing information to be coded by utilizing a plurality of binary number mapping values, and constructing an ellipse angle coding table according to the selection angle value, the fault tolerance range and the binary number mapping value of the plurality of ellipses;
step S13, drawing a single ellipse graph according to the selected angle value, generating an ellipse angle coding image by all the ellipse graphs, and finishing the coding step;
ellipse angle decoding step:
step S20, the computer vision recognition system recognizes the ellipse angle coding image to obtain all ellipse graphs and the angle value of each ellipse;
step S21, according to the angle value of each ellipse, looking up the ellipse angle coding table to obtain the binary number mapping value corresponding to the ellipse;
and step S22, sorting the binary number mapping values corresponding to all the ellipses, and obtaining the coding information according to all the binary number mapping values.
In the method, the mapping relation between the ellipse angle graph and the binary digits is established, and based on the mapping relation, the computer vision recognition system can map the corresponding binary digits according to the matching relation between the angle numerical value detected in the ellipse angle graph and the ellipse angle coding table. Compared with the prior art, the invention utilizes the geometric stability of the ellipse to map different ellipse angle graphs into binary digits, is assisted by a fault-tolerant mechanism, and detects and identifies the change of the ellipse angle graphs through a computer vision identification system so as to obtain corresponding binary mapping values and coding information.
In step S13 of this embodiment, all the elliptical patterns are printed or embedded into a preset image, so as to generate an elliptical angle encoded image.
In a preferable mode, in step S11, the calculation formula of the ellipse angle number n includes:
n＝2v；
wherein v is the data capacity value of a single ellipse angle;
further, in the step S12, the selection angle value of the single ellipse is a rotation angle value of the major axis of the ellipse with respect to the cartesian coordinate system. In step S12, the fault tolerance range is an angle range with a fixed angle difference, and the selected angle value is located in the angle range.
In step S20 of this embodiment, the computer vision recognition system recognizes the ellipse angle encoded image by using a preset ellipse angle figure contour integral detection algorithm, so as to obtain all ellipse figures and an angle value of each ellipse.
Further, the ellipse angle graph circular track integral detection algorithm is implemented by the following formula:
wherein: x and y are Cartesian coordinates of any point P on the circumference of the ellipse, alpha is a major semi-axis of the ellipse, b is a minor semi-axis of the ellipse, and beta is a rotation angle of the major semi-axis of the ellipse relative to the origin of coordinates of the Cartesian coordinate system;
c (x, y) is a binary edge image domain generated after Canny edge detection is carried out on an image to be detected;
2 π b +4(a-b) is the ellipse perimeter;
The above-mentioned elliptical angle encoding and decoding method is described in more detail by a specific embodiment.
Example one
Referring to fig. 3, an ellipse is a more stable two-dimensional geometric figure. Firstly, the area of the pixel is different from that of a straight line, and the area of the pixel required by the ellipse is large and is not easily influenced by external attack. Secondly, the geometrical shape can still be judged as long as the arc line of the ellipse circumference is still in. In addition, the mathematical properties of the "major axis" and "minor axis" in an ellipse give the ellipse the ability to express angular information. With the inclination of the major and minor axes of the ellipse, the ellipse can express angle information.
Regarding the mapping rule of the ellipse angle coding, please refer to fig. 4, the mapping rule of the ellipse angle coding is to establish the mapping relationship between the ellipse angle graph and the binary digits. The computer vision algorithm matches the ellipse code table according to the angle value detected from the ellipse angle graph, and further maps out the corresponding binary digits.
Based on the mathematical property that the major and minor semi-axes of the ellipse are each mirrored equally, an ellipse angle equal to or exceeding 180 will result in a repetition of the angle pattern, e.g., an ellipse angle pattern of 210 deg. is identical to an ellipse angle pattern of 30 deg.. Therefore, the angle encoding range of the present embodiment is limited to the specific range.
All ellipse angles within the interval can be mapped to binary digits according to practical needs. According to the mathematical characteristics of binary system, the calculation formula of the number of the ellipse angles is n-2vWhere v is the data capacity value for a single ellipse angle. For example, if the data capacity of a single ellipse angle needs to be specified to be 2bits, v is 2, and thus n is 22 or 4 ellipse angles are required to participate in encoding.
Referring to fig. 4, for example, 4 evenly distributed beta ellipse angles, i.e., 0 °, 45 °, 90 °, and 135 °, are mapped with binary digits. In practical computer applications, each ellipse angle can hold 2bits of data, and all 4 ellipse angles can hold 2 × 4 ═ 8bits of data.
Referring to fig. 5, if a single ellipse angle is required to accommodate higher data, a larger number of angles can be traded for a larger data capacity for a single ellipse angle. Figure 5 showsThe ellipse angle information capacity and corresponding parameter table of the present invention is shown, for example, if the data contained in a single ellipse angle needs to be increased from 2bits to 3bits, v is 3, n is 23All 8 ellipse angles can accommodate up to 3 × 8 — 24bits of data; if a single ellipse angle needs to accommodate 4bits of data, v is 4 and n is 24All 16 ellipse angles can accommodate up to 4 x 16 to 64bits of data, and so on.
Regarding the fault-tolerant mechanism of the elliptical angle coding, in the embodiment, in consideration of the uncertainty of the external image attack, a proper fault-tolerant mechanism needs to be added to the elliptical angle coding so as to improve the robustness of the computer visual detection algorithm.
The fault-tolerant mechanism is implemented in an ellipse angle coding table and is embodied by two specific parameters of 'selection angle' and 'fault-tolerant range'. The ' fault tolerance range ' is a positive and negative angle fault tolerance space when the computer vision algorithm detects the ellipse angle value, and the image angle ' is the middle angle value of the fault tolerance range.
Fig. 6 is an "ellipse angle coding table" according to the present embodiment, and the data capacity of a single ellipse angle is 2 bits. For example, an ellipse angle pattern with an angle of 23 ° is selected, the fault tolerance range is 20 ° to 25 °, i.e., the ellipse angle values calculated from the computer vision detection algorithm result in a range of 20 ° to 25 °, which can be successfully mapped to a binary number of 00.
The contour integral detection algorithm for an elliptical angular figure according to this embodiment is actually a detection algorithm for an elliptical image, and the elliptical image can be detected by applying Hough Transform (Hough Transform) library in OpenCV or a trained Deep Learning (Deep Learning) framework such as Caffe, tensiflow, and Keras.
However, the above algorithms have a disadvantage that the accuracy at the encoding level is not sufficient. This accuracy problem is mainly reflected in: with the increase of coding capacity, the more similar the ellipse angle graphs, even if a fault-tolerant mechanism exists, the more probable the traditional ellipse detection algorithm is to detect two similar but different ellipse angle graphs as the same angle graph.
In this regard, the present embodiment applies an elliptical image detection algorithm based on a circular track integral to solve the above problem, and the algorithm may bring higher recognition accuracy while the amount of computation may be reduced. The original contour integral ellipse algorithm does not support ellipse angle graphs, and the detection of the ellipse angle graphs can be compatible only by a small amount of modification in the embodiment.
Assuming that the coordinates of the center point of the ellipse are (0, 0), parameterizing the ellipse formula, we can obtain:
x＝a cos(t)
y＝b sin(t)；
wherein, x and y are cartesian coordinates of any point P on the ellipse circumference, α is ellipse major semi-axis, b is ellipse minor semi-axis, t is an angle increasing from the ellipse center, after the ellipse is rotated based on the ellipse center, a new ellipse graph with a rotation angle is generated, x ' and y ' are cartesian coordinates of any point P ' on the ellipse graph circumference after rotation, β is a rotation angle of the ellipse major semi-axis relative to the cartesian coordinate system origin, and then the formula is obtained:
substituting the parameters x and y into the following parameters:
after parameterizing the formula, the cartesian coordinates of P' are obtained as:
x′＝a cos(t)*cos(β)-b sin(t)*sin(β)
y′＝a cos(t)*sin(β)+b sin(t)*cos(β)；
the formula for solving x 'and y' is used for replacing the formula for solving x and y in the original circular track integral algorithm, and after a new ellipse definition parameter beta is added, the ellipse image with the angle can be detected by applying the same process, wherein the beta parameter is the ellipse angle value detected by the invention. The operator of the ellipse angle graph can be expressed as follows:
wherein: x and y are Cartesian coordinates of any point P on the circumference of the ellipse, alpha is a major semi-axis of the ellipse, b is a minor semi-axis of the ellipse, and beta is a rotation angle of the major semi-axis of the ellipse relative to the origin of coordinates of the Cartesian coordinate system;
c (x, y) is a binary edge image domain generated after Canny edge detection is carried out on an image to be detected;
2 π b +4(a-b) is the ellipse perimeter;
Based on the above embodiments, the invention provides a novel ellipse angle coding and decoding method, which fills the blank of computer vision coding technology at home and abroad, compared with the prior art, the invention utilizes the geometric stability of an ellipse, detects the change of an ellipse angle graph by a computer vision algorithm, maps different ellipse angle graphs into binary digits, and is assisted by a fault-tolerant mechanism, thereby not only solving the anti-attack problem of the computer vision coding image, but also having simple, stable and reliable realization process of the whole method, being capable of being applied to computer vision detection scenes of various industries in a large scale, and better meeting the application requirements and market requirements.
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 or improvements made within the technical scope of the present invention should be included in the scope of the present invention.
Claims (7)
1. An ellipse angle coding and decoding method based on a computer vision recognition system is characterized by comprising the following steps:
a mapping rule construction step: constructing an ellipse angle information capacity and corresponding parameter table, wherein the ellipse angle information capacity and corresponding parameter table comprises a plurality of single ellipse angle data capacity values, a plurality of ellipse angle numerical values and a plurality of highest total capacity values, and the single ellipse angle data capacity values, the ellipse angle numerical values and the highest total capacity values are in one-to-one correspondence;
ellipse angle coding step:
step S10, confirming the total data capacity needed by the current coding;
step S11, looking up the ellipse angle information capacity and the corresponding parameter table, determining the single ellipse angle data capacity value according to the total data capacity, and calculating the ellipse angle number value according to the single ellipse angle data capacity value;
step S12, determining a selection angle value of a single ellipse and a fault tolerance range corresponding to the selection angle value, simultaneously allocating a binary number mapping value uniquely corresponding to the selection angle value to the single ellipse, representing information to be coded by utilizing a plurality of binary number mapping values, and constructing an ellipse angle coding table according to the selection angle value, the fault tolerance range and the binary number mapping value of the plurality of ellipses;
step S13, drawing a single ellipse graph according to the selected angle value, generating an ellipse angle coding image by all the ellipse graphs, and finishing the coding step;
ellipse angle decoding step:
step S20, the computer vision recognition system recognizes the ellipse angle coding image to obtain all ellipse graphs and the angle value of each ellipse;
step S21, according to the angle value of each ellipse, looking up the ellipse angle coding table to obtain the binary number mapping value corresponding to the ellipse;
and step S22, sorting the binary number mapping values corresponding to all the ellipses, and obtaining the coding information according to all the binary number mapping values.
2. The elliptical angle coding and decoding method based on computer vision recognition system of claim 1, wherein in step S13, all elliptical patterns are printed or embedded into a preset image, thereby generating an elliptical angle coded image.
3. The ellipse angle coding and decoding method based on computer vision recognition system of claim 1, wherein in said step S11, the calculation formula of said ellipse angle number n comprises:
n＝2v；
where v is the data capacity value for a single ellipse angle.
4. The ellipse angle coding and decoding method of claim 1, wherein in step S12, the selection angle value of the single ellipse is a rotation angle value of the major axis of the ellipse with respect to a cartesian coordinate system.
5. The elliptical angle coding-decoding method based on computer vision recognition system of claim 1, wherein in step S12, the fault tolerance range is an angle interval range with a fixed angle difference value, and the selected angle value is located in the angle interval range.
6. The ellipse angle coding and decoding method of claim 1, wherein in step S20, the computer vision recognition system uses a predetermined ellipse angle figure envelope integral detection algorithm to identify the ellipse angle coded image, so as to obtain the angle values of all ellipse figures and each ellipse.
7. The computer vision recognition system-based ellipse angle coding and decoding method of claim 6, wherein the ellipse angle graph circular track integral detection algorithm is implemented by the following formula:
wherein: x and y are Cartesian coordinates of any point P on the circumference of the ellipse, alpha is a major semi-axis of the ellipse, b is a minor semi-axis of the ellipse, and beta is a rotation angle of the major semi-axis of the ellipse relative to the origin of coordinates of the Cartesian coordinate system;
c (x, y) is a binary edge image domain generated after Canny edge detection is carried out on an image to be detected;
2 π b +4(a-b) is the ellipse perimeter;
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010655501.9A CN111815726B (en) | 2020-07-09 | 2020-07-09 | Ellipse angle coding and decoding method based on computer vision recognition system |
| PCT/CN2020/106035 WO2022007064A1 (en) | 2020-07-09 | 2020-07-31 | Ellipse angle encoding and decoding method based on computer vision recognition system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010655501.9A CN111815726B (en) | 2020-07-09 | 2020-07-09 | Ellipse angle coding and decoding method based on computer vision recognition system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111815726A CN111815726A (en) | 2020-10-23 |
| CN111815726B true CN111815726B (en) | 2021-08-10 |
Family
ID=72843241
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010655501.9A Active CN111815726B (en) | 2020-07-09 | 2020-07-09 | Ellipse angle coding and decoding method based on computer vision recognition system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111815726B (en) |
| WO (1) | WO2022007064A1 (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113643391B (en) * | 2021-10-15 | 2022-04-05 | 深圳纸芯科技有限公司 | Label template generation method and anti-transfer method of anti-counterfeit label |
| CN113965420B (en) * | 2021-12-23 | 2022-03-11 | 西安道法数器信息科技有限公司 | Network security encryption method and system based on artificial intelligence |
| CN115664601A (en) * | 2022-12-28 | 2023-01-31 | 合力（天津）能源科技股份有限公司 | Wireless measurement while drilling information transmission method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299249A (en) * | 2014-08-20 | 2015-01-21 | 深圳大学 | High-robustness mark point decoding method and system |
| CN105678787A (en) * | 2016-02-03 | 2016-06-15 | 西南交通大学 | Heavy-duty lorry driving barrier detection and tracking method based on binocular fisheye camera |
| CN105809700A (en) * | 2016-03-23 | 2016-07-27 | 南京航空航天大学 | Detecting and positioning method of air refueling taper sleeve image blocked by fuel receiving plug |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100287525A1 (en) * | 2009-05-07 | 2010-11-11 | Microsoft Corporation | Extension through visual reflection |
| CN101964045A (en) * | 2010-09-30 | 2011-02-02 | 西北工业大学 | Distortion correction method of data matrix code marked on cylindrical surface product |
| CN103530889A (en) * | 2013-11-04 | 2014-01-22 | 天津工业大学 | Method for decoding coding mark points of measuring stick based on skeleton extraction |
| CN108764004B (en) * | 2018-06-04 | 2021-04-09 | 空气动力学国家重点实验室 | Annular coding mark point decoding and identifying method based on coding ring sampling |
| CN109285198B (en) * | 2018-08-22 | 2020-09-11 | 大连理工大学 | Method for coding and identifying annular coding mark points |
| CN109785349A (en) * | 2019-01-07 | 2019-05-21 | 哈尔滨理工大学 | A kind of polar coordinates edge coding method based on circle model |
-
2020
- 2020-07-09 CN CN202010655501.9A patent/CN111815726B/en active Active
- 2020-07-31 WO PCT/CN2020/106035 patent/WO2022007064A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299249A (en) * | 2014-08-20 | 2015-01-21 | 深圳大学 | High-robustness mark point decoding method and system |
| CN105678787A (en) * | 2016-02-03 | 2016-06-15 | 西南交通大学 | Heavy-duty lorry driving barrier detection and tracking method based on binocular fisheye camera |
| CN105809700A (en) * | 2016-03-23 | 2016-07-27 | 南京航空航天大学 | Detecting and positioning method of air refueling taper sleeve image blocked by fuel receiving plug |
Non-Patent Citations (3)
| Title |
|---|
| Remote sensing ionospheric variations due to total solar eclipse, using GNSS observations;Mohamad MahdiAlizadeh 等;《Geodesy and Geodynamics》;20200531;第202-210页 * |
| 基于椭圆特征区域与重要位平面分解的鲁棒图像水印算法;杨金劳 等;《包装工程》;20181130;第39卷(第21期);第206-305页 * |
| 用最佳椭圆线重建多圆图像;王一多 等;《北京化工大学学报》;20040622;第91-94页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022007064A1 (en) | 2022-01-13 |
| CN111815726A (en) | 2020-10-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111815726B (en) | Ellipse angle coding and decoding method based on computer vision recognition system | |
| Zhang et al. | A robust, real-time ellipse detector | |
| US7580576B2 (en) | Stroke localization and binding to electronic document | |
| US20180165492A1 (en) | Decoding Method and System for QR Code with One Damaged Position Detection Pattern | |
| CN105069394A (en) | Two-dimension code weighted average gray level method decoding method and system | |
| CN109285198B (en) | Method for coding and identifying annular coding mark points | |
| Chiu et al. | A fast randomized Hough transform for circle/circular arc recognition | |
| CN106156684A (en) | A kind of two-dimensional code identification method and device | |
| CN103793735A (en) | Circular two-dimensional bar code and encoding and decoding method thereof | |
| AU2007254626A1 (en) | Data encoding and decoding using circular configurations of marks | |
| CN104992207B (en) | A kind of mobile phone two-dimensional bar code decoding method | |
| EP2954457A1 (en) | System and method for identifying similarities in different images | |
| CN110659709A (en) | Anti-counterfeiting two-dimensional code and generation, detection and identification method thereof | |
| CN115683129B (en) | Long-term repositioning method and device based on high-definition map | |
| CN113763269A (en) | Stereo matching method for binocular images | |
| CN114239780A (en) | Anti-counterfeiting tracing code generation and verification method based on dot matrix | |
| CN113822091A (en) | Method and device for correcting errors of two-dimensional code pattern, electronic equipment and storage medium | |
| CN108256609A (en) | A kind of circle view finding figure Quick Response Code and its generation and decomposition method | |
| CN105741297B (en) | A kind of repeat pattern image matching method with affine-invariant features | |
| CN110599478A (en) | Image area copying and pasting tampering detection method | |
| CN108664940A (en) | A kind of partial fingerprints matching process and system | |
| Cao et al. | Lossless data embedding in electronic inks | |
| CN108734164A (en) | Card, identification card method, paint this reading machine people and storage device | |
| Molaei et al. | Robust and blind 3D mesh watermarking in spatial domain based on faces categorization and sorting | |
| Nurhaida et al. | Determining the Number of Batik Motif Object based on Hierarchical Symmetry Detection Approach |
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 |