CN117079284B - Character and image oriented inclination detection and correction method and system - Google Patents
Character and image oriented inclination detection and correction method and system Download PDFInfo
- Publication number
- CN117079284B CN117079284B CN202310924998.3A CN202310924998A CN117079284B CN 117079284 B CN117079284 B CN 117079284B CN 202310924998 A CN202310924998 A CN 202310924998A CN 117079284 B CN117079284 B CN 117079284B
- Authority
- CN
- China
- Prior art keywords
- angle
- image
- integral
- maximum
- value
- 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 39
- 238000012937 correction Methods 0.000 title claims abstract description 38
- 238000001514 detection method Methods 0.000 title claims abstract description 34
- 238000003466 welding Methods 0.000 claims abstract description 41
- 239000011159 matrix material Substances 0.000 claims abstract description 22
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 7
- 229910052704 radon Inorganic materials 0.000 claims description 5
- SYUHGPGVQRZVTB-UHFFFAOYSA-N radon atom Chemical compound [Rn] SYUHGPGVQRZVTB-UHFFFAOYSA-N 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/146—Aligning or centring of the image pick-up or image-field
- G06V30/1475—Inclination or skew detection or correction of characters or of image to be recognised
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/06—Recognition of objects for industrial automation
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention provides a character and image oriented inclination detection and correction method and a system, which relate to the technical field of Chinese character recognition in weld joint images, and the method comprises the steps of acquiring weld joint ray images by using weld joint ray scanning equipment; rotating the coordinate axis of the weld joint ray image by an angle theta (-90 degrees to 89 degrees), calculating the integral of each column of the image matrix at each angle, and finding out the angle integral value corresponding to the maximum value; the integral value of the maximum t% of each angle is obtained, t is a set threshold value, and all the integral values of the maximum t% are summed to obtain a quantity S 1 The method comprises the steps of carrying out a first treatment on the surface of the Different S within + -2 DEG around each angle 1 Summing to obtain another quantity S 2 In S form 2 For the value of this angle, a vector a is generated; and correcting characters and images in the welding line ray image according to the inclination angle by taking the angle corresponding to the maximum value in the vector A as the inclination angle. The invention improves the character recognition accuracy in the weld joint radiographic image and improves the efficiency of digital scanning and archiving of radiographic films.
Description
Technical Field
The invention relates to the technical field of Chinese character recognition in weld images, in particular to a character and image oriented inclination detection and correction method and system.
Background
The application of the ray detection (Radiographic Testing, RT for short) as an effective welding defect detection means in the fields of shipbuilding, nuclear power, electric power and the like is increasing. The quality of the weld determines to a large extent the quality of the parts and the safe operation of the equipment. RT plays an increasingly important role in controlling and improving weld quality. In this process, a large amount of radiographic films are produced, and the storage of these radiographic films consumes a large amount of manpower and material resources.
At present, most researches focus on how to automatically determine weld defects in a weld joint radiographic image, and progress is made, but information of the most basic text in the weld joint radiographic image is often ignored. In digitizing these RT films, operators are currently required to manually enter attribute information such as welding date, item number, and part number. This consumes a lot of manpower. In addition, because the gray value and contrast of the weld joint radiographic image are low, the human eyes are difficult to distinguish different weld joint images and are easy to make mistakes, the automatic identification of the text information of the weld joint radiographic image is a problem to be solved urgently. However, since the character is inclined to different degrees in the image due to the characteristic of welding ray detection, the character recognition accuracy is extremely challenged, as shown in fig. 1, the inclination of three characters, namely T, 7 and 1, has great influence on the recognition accuracy, and under the condition of no inclination, all 3 characters can be well recognized, but the inclined characters can be hardly recognized correctly. Thus, the inclination correction of the character is an effective factor for improving recognition efficiency. As shown in fig. 2, tilt correction of text in a weld joint radiographic image involves a number of challenges, including in particular: (1) The font and the size of each character in the RT weld radiographic image are different; (2) Characters in the RT weld joint ray image are not arranged in regular rows or columns, and the directions of the characters are different; (3) The character string in the RT-beam image is not fixed in position in the RT-beam image.
Based on the above analysis, a highly accurate character inclination correction method for a weld joint radiographic image is highly demanded.
Disclosure of Invention
Therefore, the embodiment of the invention provides a character and image oriented inclination detection and correction method and system, which are used for solving the problems of low character recognition accuracy, low efficiency of digital scanning archiving of radiographic films and the like caused by the inclination of characters in a welding seam radiographic image in the prior art.
In order to solve the above problems, an embodiment of the present invention provides a character and image oriented tilt detection and correction method, including:
s1: acquiring a welding seam ray image by using welding seam ray scanning equipment;
s2: in a two-dimensional space, rotating a welding seam ray image coordinate axis by an angle theta, wherein the rotation angle theta is-90 degrees to 89 degrees, calculating the integral of each column of an image matrix in each angle, and finding out an angle integral value corresponding to the maximum value of the integral;
s3: the integral value of the maximum t% of each angle is obtained, t is a set threshold value, and all the integral values of the maximum t% are summed to obtain a quantity S 1 ；
S4: different S within + -2 DEG around each angle 1 Summing to obtain another quantity S 2 In S form 2 For the value of the angle, a vector A is generated containing 180 elements;
s5: and taking the angle corresponding to the maximum value in the vector A as the inclination angle of the characters and the images in the welding line radial image, and correcting the characters and the images in the welding line radial image according to the inclination angle.
Preferably, in the two-dimensional space, the welding seam ray image coordinate axis is rotated by an angle θ, the rotation angle θ is-90 ° to 89 °, the integral of each column of the image matrix at each angle is calculated, and the angle integral corresponding to the maximum value is found, and the mathematical calculation expression is:
g(s，θ)＝∫∫f(x，y)δ(xcosθ+ysinθ-s)dxdy
where g (s, θ) is the integral of each column of the image matrix at each angle, f (x, y) is the binary image matrix in plane D, δ (·) represents the Dirac delta function, s is the origin to ray distance, and θ is the angle of the x-axis with the ray normal.
Preferably, the integral value of the maximum t% of each angle is calculated, t is a set threshold value, and all the integral values of the maximum t% are summed to obtain the quantity S 1 The mathematical calculation expression is:
S 1 (θ)＝∑R θ [f(x，y)]
wherein R is θ [f(x，y)]Is the maximum t% integrated value at the rotation angle θ after the image f (x, y) is Raton transformed.
Preferably, the different S will be within + -2 DEG around each angle 1 Summing to obtain another quantity S 2 The mathematical calculation expression is:
wherein S is 1 The integrated values for all the largest t% are summed and θ is the angle of the x-axis from the ray normal.
The embodiment of the invention also provides a character and image oriented inclination detection and correction system, which comprises:
the acquisition module is used for acquiring a welding seam ray image by using welding seam ray scanning equipment;
the angle integral calculation module is used for rotating the welding seam ray image coordinate axis by an angle theta in a two-dimensional space, wherein the rotation angle theta is-90 degrees to 89 degrees, calculating the integral of each column of the image matrix at each angle, and finding out an angle integral value corresponding to the maximum value of the integral;
a summation module for obtaining the maximum t% integral value of each angle, t being a set threshold value, and summing all the maximum t% integral values to obtain an amount S 1 ；
A vector generation module for generating different S within + -2 DEG around each angle 1 Summing to obtain another quantity S 2 In S form 2 For the value of this angle, a vector a is formed containing 180 elements;
and the inclination correction module is used for taking the angle corresponding to the maximum value in the vector A as the inclination angle of the characters and the images in the welding line radial image, and correcting the characters and the images in the welding line radial image according to the inclination angle.
Preferably, the angle integral calculating module is configured to rotate, in a two-dimensional space, a welding seam radiation image coordinate axis by an angle θ, where the rotation angle θ is-90 ° to 89 °, calculate an integral of each column of the image matrix at each angle, and find an angle integral value corresponding to a maximum value thereof, and include:
g(s，θ)＝∫∫f(x，y)δ(xcosθ+ysinθ-s)dxdy
where g (s, θ) is the integral of each column of the image matrix at each angle, f (x, y) is the binary image matrix in plane D, δ (·) represents the Dirac delta function, s is the origin to ray distance, and θ is the angle of the x-axis with the ray normal.
Preferably, the summation module is configured to calculate the maximum integrated value of t% for each angle, t is a set threshold value, and sum all the maximum integrated values of t% to obtain the quantity S 1 Comprising:
S 1 (θ)＝∑R θ [f(x，y)]
wherein R is θ [f(x，y)]Is the maximum t% integrated value at which the image f (x, y) passes through the rotation angle θ.
Preferably, the vector generation module is used for generating different S within + -2 DEG around each angle 1 Summing to obtain another quantity S 2 Comprising:
wherein S is 1 The integrated values for all the largest t% are summed and θ is the angle of the x-axis from the ray normal.
The embodiment of the invention also provides an electronic device, which comprises a processor, a memory and a bus system, wherein the processor and the memory are connected through the bus system, the memory is used for storing instructions, and the processor is used for executing the instructions stored by the memory so as to realize the character and image oriented tilt detection and correction method.
The embodiment of the invention also provides a computer storage medium which stores a computer software product, wherein the computer software product comprises a plurality of instructions for enabling a piece of computer equipment to execute the character and image oriented tilt detection and correction method.
From the above technical scheme, the invention has the following advantages:
the invention provides a character and image oriented inclination detection and correction method and system, which comprises the steps of acquiring weld joint ray images by using weld joint ray scanning equipment, firstly solving the integral value of the maximum t% of each angle, and summing the values to obtain a quantity S 1 The method comprises the steps of carrying out a first treatment on the surface of the Then to eliminate the influence of a single large peak on adjacent angles, different S' S within + -2 DEG around each angle 1 Summing to obtain another quantity S 2 In S form 2 For the value of the angle, a vector A is generated containing 180 elements; and finally, taking the angle corresponding to the maximum value in the vector A as the inclination angle of the characters and the images in the welding seam ray image, and correcting the characters and the images in the welding seam ray image according to the inclination angle. Compared with the traditional Radon transformation, the method has higher accuracy. The invention improves the character recognition accuracy in the weld joint radiographic image and improves the efficiency of digital scanning and archiving of radiographic films.
Drawings
For a clearer description of embodiments of the invention or of solutions in the prior art, reference will be made to the accompanying drawings, which are intended to be used in the examples, for a clearer understanding of the characteristics and advantages of the invention, by way of illustration and not to be interpreted as limiting the invention in any way, and from which, without any inventive effort, a person skilled in the art can obtain other figures. Wherein:
FIG. 1 is a weld joint radiographic image;
FIG. 2 is a weld joint radiographic image;
FIG. 3 is a flow chart of a character and image oriented tilt detection and correction method according to one embodiment;
FIG. 4 is a schematic view of calculation of an angular integral value of a weld joint radiographic image in an embodiment;
FIG. 5 is a schematic diagram of the result of inclination detection and correction of characters in a weld radiographic image in an embodiment;
FIG. 6 is a schematic diagram of the results of inclination detection and correction of faces and buildings in a weld joint radiographic image in an embodiment;
FIG. 7 is a block diagram of a character and image oriented tilt detection and correction system according to one embodiment.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 3, an embodiment of the present invention provides a character and image oriented tilt detection and correction method, which includes:
s1: acquiring a welding seam ray image by using welding seam ray scanning equipment;
s2: in a two-dimensional space, rotating a welding seam ray image coordinate axis by an angle theta, wherein the rotation angle theta is-90 degrees to 89 degrees, calculating the integral of each column of an image matrix in each angle, and finding out an angle integral value corresponding to the maximum value of the integral;
s3: the integral value of the maximum t% of each angle is obtained, t is a set threshold value, and all the integral values of the maximum t% are summed to obtain a quantity S 1 ；
S4: different S within + -2 DEG around each angle 1 Summing to obtain another quantity S 2 In S form 2 For the value of the angle, a vector A is generated containing 180 elements;
s5: and taking the angle corresponding to the maximum value in the vector A as the inclination angle of the characters and the images in the welding line radial image, and correcting the characters and the images in the welding line radial image according to the inclination angle.
The embodiment of the invention provides a character and image oriented inclination detection and correction method, which comprises the steps of acquiring a weld joint ray image by using a weld joint ray scanning device, firstly solving an integral value of the maximum t% of each angle, and summing the values to obtain a quantity S 1 The method comprises the steps of carrying out a first treatment on the surface of the Then to eliminate the influence of a single large peak on adjacent angles, different S' S within + -2 DEG around each angle 1 Summing to obtain another quantity S 2 In S form 2 For the value of the angle, a vector A is generated containing 180 elements; finally vector AThe angle corresponding to the maximum value in the welding line ray image is used as the inclination angle of the characters and the images in the welding line ray image, and the characters and the images in the welding line ray image are corrected according to the inclination angle. Compared with the traditional Radon transformation, the method has higher accuracy. The invention improves the character recognition accuracy in the weld joint radiographic image and improves the efficiency of digital scanning and archiving of radiographic films.
Further, in step S1, the present invention acquires a weld ray image using a weld ray scanning apparatus.
Further, in step S2, the objects analyzed by the present invention are two-dimensional character images, and therefore, they are considered in only two-dimensional space, as shown in fig. 4, rotated in a two-dimensional plane, the integral of each column of the image matrix at each angle is calculated, and the angle integral corresponding to the maximum value thereof is found, and the mathematical expression is as follows:
g(s，θ)＝∫∫f(x，y)δ(xcosθ+ysinθ-s)dxdy
where g (s, θ) is the integral of each column of the image matrix at each angle, f (x, y) is the binary image matrix in plane D, δ (·) represents the Dirac delta function, s is the origin to ray distance, and θ is the angle of the x-axis with the ray normal.
Further, in step S3, the integral value of the maximum t% (t is the set threshold value) for each angle is obtained, the present invention sets t=20, and the integral values of all the maximum t% are summed to obtain the amount S 1 . Wherein solve S 1 The mathematical computational expression of (a) is:
S 1 (θ)＝∑R θ [f(x，y)]
wherein R is θ [f(x，y)]Is the maximum t% integrated value at the rotation angle θ after the image f (x, y) is Raton transformed.
Further, in step S4, in order to eliminate the influence of a single large peak on adjacent angles, different S within + -2 DEG around each angle 1 Summing to obtain another quantity S 2 In S form 2 For the value of this angle, a vector a is generated (with-90 ° and 89 °, i.e., (-92, -91, -90, -89, -88) ° sum (87, 88, 89,9)0,91) ° corresponds to S 1 Value, etc.). Wherein solve S 2 The mathematical computational expression of (a) is:
wherein S is 1 The integrated values for all the largest t% are summed and θ is the angle of the x-axis from the ray normal.
Further, in step S5, the maximum value in the vector a is found, and the angle corresponding to the maximum value in the vector a is used as the inclination angle of the character and the image in the weld joint radiographic image, and the character and the image in the weld joint radiographic image are corrected according to the inclination angle.
Compared with the traditional Radon transformation, the method has higher accuracy, and in the traditional Radon transformation, the angle with the maximum peak value is regarded as the angle of the whole inclined image, but the angle is often different from the actual situation, so that any unexpected peak value, such as noise generated by image processing, the special structure of the image and the like, can lead to erroneous results of the method, thereby influencing the result of the whole method.
Based on the analysis, the invention provides a character and image oriented tilt detection and correction method, which uses characters in a welding seam ray image for verification. As a result, 26 letters, 10 numbers and 2 Chinese characters contained in the weld line radiographic image can be well corrected. Some characters with serious noise interference can be well corrected, which shows that the method has robustness (shown in fig. 5). The method is not only suitable for binary images, but also suitable for gray images. Other images are also used to verify methods such as faces and some buildings, which may also be used to good effect (as shown in fig. 6). The third row of the image in fig. 6 is a curve of the vector a, and the angle corresponding to the maximum value is the inclination angle of the image, and the second row is the corrected image.
As shown in fig. 7, the present invention provides a character and image oriented tilt detection and correction system, the system comprising:
an acquisition module 10 for acquiring a weld ray image using a weld ray scanning apparatus;
the angle integral calculation module 20 is configured to rotate the welding seam ray image coordinate axis by an angle θ in a two-dimensional space, where the rotation angle θ is-90 ° to 89 °, calculate the integral of each column of the image matrix at each angle, and find the angle integral corresponding to the maximum value thereof;
a summation module 30 for obtaining the maximum t% integral value of each angle, t being a set threshold value, and summing all the maximum t% integral values to obtain a quantity S 1 ；
A vector generation module 40 for generating a different S within + -2 DEG around each angle 1 Summing to obtain another quantity S 2 In S form 2 For the value of this angle, a vector a is formed containing 180 elements;
the inclination correction module 50 is configured to take an angle corresponding to the maximum value in the vector a as an inclination angle of the character and the image in the weld joint radiographic image, and correct the character and the image in the weld joint radiographic image according to the inclination angle.
The embodiment of the character and image oriented tilt detection and correction system according to the present embodiment is applicable to implementing the foregoing character and image oriented tilt detection and correction method, so that the embodiment of the character and image oriented tilt detection and correction system can be seen in the foregoing embodiment of the character and image oriented tilt detection and correction method, for example, the collecting module 10, the angle integration calculating module 20, the summing module 30, the vector generating module 40, and the tilt correction module 50 are respectively used to implement steps S1, S2, S3, S4, and S5 in the foregoing character and image oriented tilt detection and correction method, so that the detailed description thereof can be referred to corresponding embodiments of each part, and redundancy is avoided.
The embodiment of the invention also provides an electronic device, which comprises a processor, a memory and a bus system, wherein the processor and the memory are connected through the bus system, the memory is used for storing instructions, and the processor is used for executing the instructions stored by the memory so as to realize the character and image oriented tilt detection and correction method.
The embodiment of the invention also provides a computer storage medium which stores a computer software product, wherein the computer software product comprises a plurality of instructions for enabling a piece of computer equipment to execute the character and image oriented tilt detection and correction method.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It is apparent that the above examples are given by way of illustration only and are not limiting of the embodiments. Other variations and modifications of the present invention will be apparent to those of ordinary skill in the art in light of the foregoing description. It is not necessary here nor is it exhaustive of all embodiments. And obvious variations or modifications thereof are contemplated as falling within the scope of the present invention.
Claims (6)
1. A character and image oriented tilt detection and correction method is characterized by comprising the following steps:
s1: acquiring a welding seam ray image by using welding seam ray scanning equipment;
s2: in a two-dimensional space, rotating a welding line ray image coordinate axis by an angle theta, wherein the rotation angle theta is-90 degrees to 89 degrees, and calculating the integral of each column of the image matrix at each angle;
s3: the integral value of the maximum t% of each angle is obtained, t is a set threshold value, and all the integral values of the maximum t% are summed to obtain a quantity S 1 ；
S4: different S within + -2 DEG around each angle 1 Summing to obtain another quantity S 2 In S form 2 For the value of the angle, a vector A is generated containing 180 elements;
s5: the angle corresponding to the maximum value in the vector A is used as the inclination angle of the characters and the images in the welding seam ray image, and the characters and the images in the welding seam ray image are corrected according to the inclination angle;
in the two-dimensional space, the welding line ray image coordinate axis is rotated by an angle theta, the rotation angle theta is-90 degrees to 89 degrees, the integral of each column of the image matrix in each angle is calculated, and the mathematical calculation expression is as follows:
g(s，θ)＝∫∫f(x，y)δ(xcosθ+ysinθ-s)dxdy
wherein g (s, θ) is the integral of each column of the image matrix at each angle, f (x, y) is the binary image matrix in plane D, δ (·) represents the Dirac delta function, s is the origin to ray distance, θ is the angle of the x-axis with the ray normal;
the integral value of the maximum t% of each angle is obtained, t is a set threshold value, and all the integral values of the maximum t% are summed to obtain a quantity S 1 The mathematical calculation expression is:
S 1 (θ)＝∑R θ [f(x，y)]
wherein R is θ [f(x，y)]Is the maximum t% integral value at the rotation angle theta after the image f (x, y) is subjected to Radon transformation.
2. The character and image oriented tilt detection and correction method according to claim 1, wherein the different S is within ±2° around each angle 1 Summing to obtain another quantity S 2 The mathematical calculation expression is:
wherein S is 1 Summing the integrated values for all maximum t%, θ is the x-axis and rayThe angle between the normals.
3. A character and image oriented tilt detection and correction system, comprising:
the acquisition module is used for acquiring a welding seam ray image by using welding seam ray scanning equipment;
the angle integral calculation module is used for rotating the welding line ray image coordinate axis by an angle theta in a two-dimensional space, wherein the rotation angle theta is-90 degrees to 89 degrees, and calculating the integral of each column of the image matrix at each angle;
a summation module for obtaining the maximum t% integral value of each angle, t being a set threshold value, and summing all the maximum t% integral values to obtain an amount S 1 ；
A vector generation module for generating different S within + -2 DEG around each angle 1 Summing to obtain another quantity S 2 In S form 2 For the value of this angle, a vector a is formed containing 180 elements;
the inclination correction module is used for correcting the characters and the images in the welding line ray image according to the inclination angles by taking the angle corresponding to the maximum value in the vector A as the inclination angle of the characters and the images in the welding line ray image;
the angle integral calculation module is configured to rotate a welding seam ray image coordinate axis by an angle θ in a two-dimensional space, where the rotation angle θ is-90 ° to 89 °, and calculate an integral of each column of the image matrix at each angle, and includes:
g(s，θ)＝∫∫f(x，y)δ(xcosθ+ysinθ-s)dxdy
wherein g (s, θ) is the integral of each column of the image matrix at each angle, f (x, y) is the binary image matrix in plane D, δ (·) represents the Dirac delta function, s is the origin to ray distance, θ is the angle of the x-axis with the ray normal;
the summation module is used for solving the maximum integrated value of t% of each angle, t is a set threshold value, and summing all the maximum integrated values of t% to obtain an amount S 1 Comprising:
S 1 (θ)＝∑R θ [f(x，y)]
wherein R is θ [f(x，y)]Is the maximum t% integrated value at which the image f (x, y) passes through the rotation angle θ.
4. The character and image oriented tilt detection and correction system according to claim 3, wherein the vector generation module is configured to generate a different S within ±2° around each angle 1 Summing to obtain another quantity S 2 Comprising:
wherein S is 1 The integrated values for all the largest t% are summed and θ is the angle of the x-axis from the ray normal.
5. An electronic device comprising a processor, a memory and a bus system, the processor and the memory being connected by the bus system, the memory being configured to store instructions, the processor being configured to execute the instructions stored by the memory to implement the character and image oriented tilt detection and correction method of any one of claims 1 to 2.
6. A computer storage medium storing a computer software product comprising instructions for causing a computer device to perform the character and image oriented tilt detection and correction method according to any one of claims 1 to 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310924998.3A CN117079284B (en) | 2023-07-26 | 2023-07-26 | Character and image oriented inclination detection and correction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310924998.3A CN117079284B (en) | 2023-07-26 | 2023-07-26 | Character and image oriented inclination detection and correction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117079284A CN117079284A (en) | 2023-11-17 |
| CN117079284B true CN117079284B (en) | 2024-03-05 |
Family
ID=88712444
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310924998.3A Active CN117079284B (en) | 2023-07-26 | 2023-07-26 | Character and image oriented inclination detection and correction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117079284B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018219054A1 (en) * | 2017-06-02 | 2018-12-06 | 杭州海康威视数字技术股份有限公司 | Method, device, and system for license plate recognition |
| CN109447067A (en) * | 2018-10-24 | 2019-03-08 | 北方民族大学 | A kind of bill angle detecting antidote and automatic ticket checking system |
| CN113516103A (en) * | 2021-08-07 | 2021-10-19 | 山东微明信息技术有限公司 | Table image inclination angle determining method based on support vector machine |
| CN114092941A (en) * | 2020-08-03 | 2022-02-25 | 中移物联网有限公司 | Number identification method and device, electronic equipment and readable storage medium |
| CN114495105A (en) * | 2022-03-11 | 2022-05-13 | 远光软件股份有限公司 | Image tilt correction method, device, storage medium and computer equipment |
| WO2023097931A1 (en) * | 2021-12-03 | 2023-06-08 | 江苏航天大为科技股份有限公司 | Hough transform-based license plate tilt correction method |
-
2023
- 2023-07-26 CN CN202310924998.3A patent/CN117079284B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018219054A1 (en) * | 2017-06-02 | 2018-12-06 | 杭州海康威视数字技术股份有限公司 | Method, device, and system for license plate recognition |
| CN109447067A (en) * | 2018-10-24 | 2019-03-08 | 北方民族大学 | A kind of bill angle detecting antidote and automatic ticket checking system |
| CN114092941A (en) * | 2020-08-03 | 2022-02-25 | 中移物联网有限公司 | Number identification method and device, electronic equipment and readable storage medium |
| CN113516103A (en) * | 2021-08-07 | 2021-10-19 | 山东微明信息技术有限公司 | Table image inclination angle determining method based on support vector machine |
| WO2023097931A1 (en) * | 2021-12-03 | 2023-06-08 | 江苏航天大为科技股份有限公司 | Hough transform-based license plate tilt correction method |
| CN114495105A (en) * | 2022-03-11 | 2022-05-13 | 远光软件股份有限公司 | Image tilt correction method, device, storage medium and computer equipment |
Non-Patent Citations (4)
| Title |
|---|
| Tamper detection in pipeline girth welding based on radiographic images;Yasheng Chang 等;《Measurement》;第167卷;1-12 * |
| 基于边缘检测和Radon变换的运动模糊角度估计的方法;杜青 等;《电子测试》;第19卷;43-44 * |
| 程起敏 著.《遥感图像检索技术》.武汉大学出版社,2011,(第1版),第160-161页. * |
| 谢东洋 等.阵列微焦射线源大视场显微计算机断层成像滤波反投影重建.《光学学报》.2022,第42卷(第11期),第271-280页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117079284A (en) | 2023-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111474184B (en) | AOI character defect detection method and device based on industrial machine vision | |
| US11478214B2 (en) | Geometric calibration for cone beam CT using line fiducials | |
| CN110287854B (en) | Table extraction method and device, computer equipment and storage medium | |
| CN111507908B (en) | Image correction processing method, device, storage medium and computer equipment | |
| JP2009169934A (en) | System and method for recognizing deformable object | |
| CN111860489A (en) | Certificate image correction method, device, equipment and storage medium | |
| CN111797744B (en) | Multimode remote sensing image matching method based on co-occurrence filtering algorithm | |
| CN112396640A (en) | Image registration method and device, electronic equipment and storage medium | |
| US11651604B2 (en) | Word recognition method, apparatus and storage medium | |
| CN117079284B (en) | Character and image oriented inclination detection and correction method and system | |
| CN110132975B (en) | Method and device for detecting surface of cladding of nuclear fuel rod | |
| CN113159103A (en) | Image matching method, image matching device, electronic equipment and storage medium | |
| CN114648611B (en) | Three-dimensional reconstruction method and device for local orbit function | |
| CN107480710B (en) | Feature point matching result processing method and device | |
| CN110598647A (en) | Head posture recognition method based on image recognition | |
| CN115690104A (en) | Wafer crack detection method and device and storage medium | |
| EP3410352A1 (en) | Feature vector generation and encryption | |
| Shao et al. | Grouped outlier removal for robust ellipse fitting | |
| CN109801334B (en) | Workpiece positioning method, standard point determining method, device and equipment | |
| CN108629788B (en) | Image edge detection method, device and equipment and readable storage medium | |
| CN110223373B (en) | Determination method, device and equipment for geometric parameter information of bolt ball | |
| CN116503409B (en) | Weld defect 3D point cloud detection method, equipment and medium | |
| Meng et al. | An automatic calibration method for kerf angle in wafer automated optical inspection | |
| CN117689893B (en) | Laser scanning ultra-wide-angle fundus image semantic segmentation method, system and terminal | |
| CN113673522B (en) | Method, device and equipment for detecting inclination angle of text image and storage medium |
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 |