CN118014886A - Ultrasonic pipeline crack image enhancement method - Google Patents
Ultrasonic pipeline crack image enhancement method Download PDFInfo
- Publication number
- CN118014886A CN118014886A CN202410423930.1A CN202410423930A CN118014886A CN 118014886 A CN118014886 A CN 118014886A CN 202410423930 A CN202410423930 A CN 202410423930A CN 118014886 A CN118014886 A CN 118014886A
- Authority
- CN
- China
- Prior art keywords
- filtering
- point
- window
- rectangular window
- search
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000001914 filtration Methods 0.000 claims abstract description 173
- 230000008859 change Effects 0.000 claims abstract description 26
- 238000012216 screening Methods 0.000 claims abstract description 5
- 230000002708 enhancing effect Effects 0.000 claims abstract 7
- 230000008569 process Effects 0.000 claims description 9
- 238000002604 ultrasonography Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 4
- 230000007547 defect Effects 0.000 abstract description 10
- 238000012545 processing Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 description 7
- 238000001514 detection method Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to an ultrasonic pipeline crack image enhancement method, which comprises the following steps: obtaining filtering points in an ultrasonic image, constructing a rectangular window of each filtering point, setting a plurality of search windows, obtaining the change consistency of the rectangular window of the filtering point and the gray scale of each search window, further obtaining a consistency sequence of the rectangular window of the filtering point, obtaining the possibility degree of each search window serving as a neighborhood block of the filtering point according to the gray scale change consistency of the rectangular window of the filtering point and each search window of the filtering point and the consistency sequence of the search windows of the filtering point, screening the neighborhood blocks of the filtering point according to the possibility degree, obtaining the filtering weight of the filtering point according to all the neighborhood blocks of the filtering point, denoising the ultrasonic image according to the filtering weight of the filtering point, and enhancing the ultrasonic image. The invention can remove the noise of the ultrasonic image more thoroughly, thereby improving the accuracy of identifying the crack defect in the pipeline.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to an ultrasonic pipeline crack image enhancement method.
Background
Pipelines for transporting liquids, gases or other substances in industry and manufacturing industry, in which defects or cracks possibly existing on the wall surface of the pipeline are detected by ultrasonic detection technology, can be used for transporting water, petroleum, natural gas, chemicals and the like, and are widely applied to the fields of energy sources, chemical industry, pharmacy, food processing and the like. Ultrasonic pipeline detection utilizes an ultrasonic sensor to emit ultrasonic waves on the pipeline surface and receives reflected signals. When an ultrasonic wave encounters a defect, crack or other non-uniformity inside the pipe, its propagation path changes, which changes are detected by the transducer. Through analyzing the received ultrasonic signals, engineers or technicians can evaluate the health state of the pipeline and detect the problems of cracks and the like on the wall surface of the pipeline, so that necessary maintenance and repair measures are timely taken, and the safe operation of the pipeline is ensured. However, due to factors such as noise of the sensor, heterogeneity of materials, and complexity of the medium in the pipeline, the ultrasonic image may have a degree of blurring or noise, which may affect accurate detection and analysis of cracks, and thus enhanced denoising of the obtained ultrasonic pipeline crack image is required.
In the prior art, more methods are used for denoising the image, wherein a non-local mean value filtering algorithm has a better denoising effect, and the algorithm obtains the filtering weight of the current filtering point by calculating the similarity between a neighborhood block of the current filtering point and neighborhood blocks of other points in a rectangular window. However, because the ultrasonic image of the pipeline has small gray level difference and has textures with insignificant gray level difference, if the image block adjacent to the current filtering point is directly selected as a neighborhood block to perform noise estimation, the denoising effect on the image is poor, and the identification of cracks possibly existing in the pipeline is inaccurate.
Disclosure of Invention
In order to solve the above problems, the present invention provides an ultrasonic pipeline crack image enhancement method, comprising the steps of:
collecting an ultrasonic image of a pipeline to be detected by using an ultrasonic detector; obtaining filtering points in an ultrasonic image, and constructing a rectangular window of each filtering point; setting a plurality of search windows;
For each filtering point, acquiring the gray level change consistency of the rectangular window of the filtering point and each searching window according to the gray level distribution of the rectangular window of the filtering point and each searching window; the consistency of the gray level change of the rectangular window of the filtering point and each searching window forms a consistency sequence of the rectangular window of the filtering point;
Obtaining the possible degree of each search window serving as a neighborhood block of the filter point according to the consistency of the gray level change of the rectangular window of the filter point and each search window and the consistency sequence of the search windows of the filter point; screening a plurality of search windows as neighborhood blocks of filter points according to the possible degree; obtaining the filtering weight of the filtering point according to all neighborhood blocks of the filtering point and the gray distribution of the rectangular window of the filtering point;
And denoising the ultrasonic image according to the filtering weight of each filtering point in the ultrasonic image to obtain a denoised ultrasonic image, so as to realize the enhancement of the ultrasonic image.
Preferably, the construction of the rectangular window of each filtering point includes the following specific steps:
building centered on each filtering point A window of size, which is a rectangular window for each filtering point, where/>The side length of the rectangular window is preset.
Preferably, the setting a plurality of search windows includes the following specific steps:
Construction A window with a size, the central point of the window is aligned with the first pixel point of the upper left corner of the ultrasonic image to obtain a first search window, the search window is slid from the first pixel point of the upper left corner of the ultrasonic image from left to right and then from top to bottom with a step length of 1 to obtain a plurality of search windows, wherein/>The side length of the rectangular window is preset.
Preferably, the step of obtaining the consistency of the gray level variation of the rectangular window of the filtering point and each search window according to the gray level distribution of the rectangular window of the filtering point and each search window comprises the following specific steps:
In the method, in the process of the invention, Represents the/>Rectangular window of individual filter points and the/>Gray scale variation consistency of individual search windows, wherein/>Get pass/>Is/are each integer inRepresenting the number of pixels included in an ultrasound image,/>Get pass/>And/>，/>Represents the/>Gray average value of all pixel points in rectangular window of each filtering point,/>Represents the/>Gray average value of all pixel points in each search window,/>Represents the/>Gray variance of all pixel points in rectangular window of each filtering point,/>Represents the/>Gray variance of all pixel points in each search window,/>An exponential function based on a natural constant is represented.
Preferably, the consistency sequence of the rectangular window of the filtering point and the consistency of the gray level change of each searching window comprises the following specific steps:
and arranging the consistency of the gray level change of the rectangular window of the filtering point and each search window in order from large to small to obtain a consistency sequence of the rectangular window of the filtering point.
Preferably, the obtaining the possibility degree of each search window as the neighborhood block of the filtering point includes the following specific steps:
In the method, in the process of the invention, Represents the/>Search Window as the/>The degree of likelihood of a neighborhood block of filter points, where/>Taking the passIs/are each integer inRepresenting the number of pixels contained in an ultrasound image of a pipeline,/>Get pass/>And/>，/>Represents the/>Rectangular window of individual filter points and the/>Gray level variation consistency of individual search windows,/>Represents the/>Center point and the/>, of rectangular window of the filter pointsDistance between center points of search windows,/>Represent the firstThe consistency sequence of the rectangular window of the filtering points and the/>Pearson correlation coefficients for a consistent sequence of rectangular windows of filter points.
Preferably, the filtering the neighborhood blocks with a plurality of search windows as filtering points according to the likelihood includes the following specific steps:
when the probability of the neighborhood block of the filtering point as the search window is larger than the preset probability threshold And taking the search window as a neighborhood block of the filtering point.
Preferably, the step of obtaining the filtering weight of the filtering point according to all the neighborhood blocks of the filtering point and the gray distribution of the rectangular window of the filtering point includes the following specific steps:
In the method, in the process of the invention, Represents the/>Filtering weights of the filtering points/>Represents the/>First/>, of the filtering pointsThe degree of likelihood of a neighborhood block being the neighborhood block for that filter point,/>Represents the/>Number of neighborhood blocks of filter points,/>Representing the side length of a preset rectangular window,/>Represents the/>The first/>, in a rectangular window of individual filter pointsGray value of each pixel/(Represents the/>First/>, of the filtering pointsFirst/>, in a respective neighborhood blockGray values of individual pixels.
Preferably, the denoising processing of the ultrasonic image adopts a non-local mean value filtering algorithm.
Preferably, the step of acquiring the filtering point in the ultrasonic image includes the following specific steps:
each pixel point in the ultrasonic image is used as a filtering point respectively.
The technical scheme of the invention has the beneficial effects that: according to the gray level change of different areas in an ultrasonic image, gray level change consistency of each filtering point rectangular window and a searching window is obtained, then a consistency sequence is obtained, further the possibility degree of the searching window serving as a neighborhood block of the corresponding rectangular window is obtained according to the relevance of the filtering point consistency sequence at different positions, and then the searching window is screened to obtain a plurality of neighborhood blocks corresponding to each filtering point; and then carrying out noise estimation on the local area where the filtering point is positioned according to the gray level changes of the plurality of neighborhood blocks to obtain the filtering weight of the local area. According to the invention, better filtering denoising effect can be obtained by comparing different noise influence degrees of different areas in the image and different textures, the denoising of the ultrasonic image is more thorough, and the crack defects in the ultrasonic image after denoising are clearer, so that the accuracy of identifying the crack defects in the pipeline is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of steps of an ultrasonic pipeline crack image enhancement method of the present invention;
Fig. 2 is an ultrasound image of a pipeline.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given below of the specific implementation, structure, characteristics and effects of the ultrasonic pipeline crack image enhancement method according to the invention in combination with the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the ultrasonic pipeline crack image enhancement method provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of steps of an ultrasonic pipeline crack image enhancement method according to an embodiment of the present invention is shown, the method includes the steps of:
S001: an ultrasound image of the conduit is acquired.
The main purpose of this embodiment is to perform denoising enhancement on an ultrasonic image of a pipeline, so that it is first necessary to acquire an ultrasonic image of a pipeline to be detected. An ultrasonic image of a pipe to be detected is acquired using an ultrasonic probe, and an ultrasonic image of one pipe of the present embodiment is shown in fig. 2.
Thus, an ultrasonic image of the pipeline is acquired.
S002: and acquiring the gray level change consistency of the rectangular window of the filtering point in the ultrasonic image and each search window, and acquiring the consistency sequence of the rectangular window of the filtering point according to the gray level change consistency.
When a crack defect exists in the ultrasonic propagation path, the acoustic path changes, and thus, in the obtained ultrasonic image, a different waveform appears, and the ultrasonic wave is attenuated when propagating in the material, that is, the signal intensity decreases with an increase in the propagation distance. The crack may cause additional attenuation of the signal, which may be used to assess the size and depth of the crack. However, when an image in a pipeline is acquired by ultrasonic waves, there may be a certain degree of blurring or noise in the ultrasonic image due to factors such as noise of a sensor, heterogeneity of materials and complexity of a medium in the pipeline, and when there is a crack defect in the pipeline, a corresponding gray scale change occurs in the ultrasonic image. However, when the image is affected by noise, it affects the recognition of the texture change of the pipeline in the ultrasonic image, and also affects the measurement of the size of the crack defect, which affects the accurate detection and analysis of the crack, so that the obtained ultrasonic image of the pipeline needs to be subjected to enhanced denoising treatment.
It should be further noted that when the non-local mean filtering algorithm is used to denoise the ultrasonic image, because the gray level variation of the ultrasonic image is small, the visual effect presented by the whole is relatively single, and the algorithm measures the noise influence degree of the local area where the current filtering point is located by comparing the similarity between the local area where the current filtering point is located and other neighborhood block areas in the image, but because the gray level variation of the ultrasonic image is small and textures with insignificant gray level variation exist, if the image blocks at the adjacent positions of the current filtering point are directly selected to be used as neighborhood blocks to perform noise estimation, the denoising effect of the image is poor, and the identification of cracks possibly existing in the pipeline is inaccurate. The selection of the neighborhood blocks is therefore critical, which relates to the accuracy of the noise evaluation. The invention obtains a plurality of neighborhood blocks of each filtering point by analyzing the ultrasonic image so as to evaluate the noise influence degree of the filtering point according to the plurality of neighborhood blocks.
Specifically, each pixel point in the ultrasonic image is respectively used as a filtering point, and the side length of a rectangular window is preset firstBuilding/>, centered on each filtering pointA window of size, which is a rectangular window for each filtering point. Then constructing a window with the same size, aligning the central point of the window with the first pixel point of the upper left corner of the ultrasonic image to obtain a first search window, starting the search window from the first pixel point of the upper left corner of the ultrasonic image, and sliding from left to right and then from top to bottom with the step length of 1, so that a plurality of search windows can be obtained. The pair/>, of the present embodimentThe size of (3) is not limited, and the practitioner can set/>, according to the actual implementation situationValues of (e.g./>)。
For each filtering point, acquiring the gray level change consistency of a rectangular window of the filtering point and each searching window:
In the method, in the process of the invention, Represents the/>Rectangular window of individual filter points and the/>Gray scale variation consistency of individual search windows, wherein/>Get pass/>Is/are each integer inRepresenting the number of pixels contained in an ultrasound image of a pipeline,/>Get pass/>And/>. When/>When (1)The search window is the/>Rectangular window of individual filter points, thus the present embodiment sets/>To ensure the/>Rectangular window of individual filter points is not consistent with self-calculated gray level variation,/>Represents the/>Gray average value of all pixel points in rectangular window of each filtering point,/>Represents the/>Gray average value of all pixel points in each search window,/>Represents the/>Gray variance of all pixel points in rectangular window of each filtering point,/>Represents the/>Gray variance of all pixel points in each search window,/>An exponential function that is based on a natural constant; /(I)Represents the/>Rectangular window of individual filter points and the/>The smaller the difference of the gray average values of the pixel points in the search windows, the approximate influence degree of noise on the two windows is indicated, and the included texture features can be approximate; /(I)Represents the/>Rectangular window of individual filter points and the/>The difference of the gray variance of the pixel points in each search window indicates the gray fluctuation of the pixel points in the window, and the larger the variance is, the larger the gray fluctuation of the pixel points in the window is indicated, so that the more similar the gray fluctuation of the rectangular window and the sliding window is, the larger the gray variation consistency of the two windows is.
And for each filtering point, arranging the consistency of the gray level change of the rectangular window of the filtering point and each searching window in order from large to small to obtain a consistency sequence of the rectangular window of the filtering point.
Thus, a consistent sequence of rectangular windows for each filter point is obtained.
S003: and obtaining the possibility degree of each search window serving as a neighborhood block of the filter point according to the consistency sequence of the rectangular windows of the filter point, screening the neighborhood blocks of the filter point according to the possibility degree, and obtaining the filter weight of the filter point according to all the neighborhood blocks of the filter point and the gray distribution of the rectangular windows of the filter point.
It should be noted that, the consistency sequence of the rectangular window of the filtering point is obtained according to the gray scale in different search windows and the gray scale variation in the rectangular window, when the difference of noise influence of the rectangular window of the filtering point is larger or the difference of texture is larger, the consistency of the rectangular window of the filtering point and the gray scale variation of the search window is smaller, otherwise, when the difference of noise influence degree of the rectangular window of the filtering point and the difference of texture is smaller, the consistency of the rectangular window of the filtering point and the gray scale variation of the search window is larger. Therefore, the embodiment obtains the possibility degree of the search window as the neighborhood block of the filter point according to the consistency of the gray value variation of the rectangular window and the search window of the filter point.
Specifically, for each filtering point, according to the consistency of the gray level variation of the rectangular window of the filtering point and each searching window and the consistency sequence of the searching windows of the filtering point, the possible degree of each searching window as a neighborhood block of the filtering point is obtained:
In the method, in the process of the invention, Represents the/>Search Window as the/>The degree of likelihood of a neighborhood block of filter points, where/>Taking the passIs/are each integer inRepresenting the number of pixels contained in an ultrasound image of a pipeline,/>Get pass/>And/>。/>Represents the/>Rectangular window of individual filter points and the/>Gray level variation consistency of individual search windows,/>Represents the/>Center point and the/>, of rectangular window of the filter pointsDistance between center points of search windows,/>Represent the firstThe consistency sequence of the rectangular window of the filtering points and the/>Pearson correlation coefficient of the consistent sequence of rectangular windows of individual filter points, due to the/>Rectangular window of individual filter points and the/>The search windows coincide, thus/>Also represents the/>The consistency sequence of the rectangular window of the filtering points and the/>Pearson correlation coefficients for a consistent sequence of search windows; when the gray level change consistency of the rectangular window of the filtering point and the search window is larger, the gray level change degree of the pixel point in the corresponding search window is closer to the rectangular window of the filtering point, and the possible degree of the search window serving as a neighborhood block of the filtering point is larger; since different areas of the ultrasonic image may be affected by noise to different degrees, when the distance between the rectangular window of the filtering point and the search window is closer, the rectangular window of the filtering point and the search window are more likely to be affected by noise, and at the moment, the more likely the search window is used as a neighborhood block of the filtering point; pearson correlation coefficient/>Represents the/>The consistency sequence of the rectangular window of the filtering points and the/>Correlation of the consistent sequence of search windows, the greater the correlation, illustrating all search windows and the/>Gray scale change relation between rectangular windows of each filtering point and all search windows and/>The closer the gray scale change relationship between the search windows is, the more/>Search Window as the/>The greater the likelihood of a neighborhood block of filter points, the greater the likelihood of a neighborhood block of filter pointsSearch Window with respect to the/>The rectangular window of each filtering point is a search window, but the firstThe position of each search window is the/>When the rectangular window of each filtering point is also provided with a corresponding search window to slide, a consistency sequence of the rectangular window at the position is obtained, because the search windows are all slid from the upper left of the ultrasonic image, the positions of the search windows corresponding to the consistency sequence are basically the same, the bigger the correlation of the consistency sequences of the two windows is, the more similar the change characteristics of the two windows are, thus the/>Search Window as the/>The greater the likelihood of a neighborhood block of filter points.
Thus, the degree of possibility that each search window is used as a neighborhood block of each filtering point is obtained.
In the present embodiment, a threshold of the degree of possibility is presetWithout limitation, the practitioner may set a threshold of likelihood according to the actual implementation, e.g./>. For each filtering point, when the likelihood of the search window as a neighborhood block of the filtering point is greater than the likelihood threshold/>And when the search window is used as a neighborhood block of the filtering point, a plurality of neighborhood blocks of each filtering point can be obtained.
It should be noted that, since the detail changes of the images in the multiple neighborhood blocks of the filtering point may be different, in order to be able to more accurately denoise the images, the filtering weights of the filtering points are obtained according to the gray scale difference of the corresponding pixel points between each neighborhood block and the rectangular window of the filtering point.
Specifically, for each filtering point, the filtering weight of the filtering point is obtained according to all neighborhood blocks of the filtering point:
In the method, in the process of the invention, Represents the/>Filtering weights of the filtering points/>Represents the/>First/>, of the filtering pointsThe degree of likelihood of a neighborhood block being the neighborhood block for that filter point,/>Represents the/>Number of neighborhood blocks of filter points,/>Representing the side length of a preset rectangular window,/>Represents the/>The first/>, in a rectangular window of individual filter pointsGray value of each pixel/(Represents the/>First/>, of the filtering pointsFirst/>, in a respective neighborhood blockGray value of each pixel/(Represents the/>Rectangular window of individual filter points and the/>First/>, of the filtering pointsGray level difference of pixel points at corresponding positions of each neighborhood block,/>Represents the/>Rectangular window of individual filter points and the/>First/>, of the filtering pointsAnd the average value of gray differences of pixel points at corresponding positions of the neighborhood blocks. When the rectangular window of the filtering point or the neighborhood block of the filtering point exceeds the boundary of the ultrasonic image, the corresponding pixel point in the rectangular window or the neighborhood block does not exist, and the gray value of the pixel point closest to the rectangular window or the neighborhood block is given to the pixel point exceeding the boundary of the ultrasonic image, so that the calculation of the filtering weight is realized.
Thus, the filter weight of each filter point is obtained.
S004: and denoising the ultrasonic image according to the filtering weight of each filtering point in the ultrasonic image to obtain a denoised ultrasonic image, so as to realize the enhancement of the ultrasonic image.
And denoising the ultrasonic image through a non-local mean value filtering algorithm according to the filtering weight of each filtering point in the ultrasonic image of the pipeline to obtain a denoised ultrasonic image, thereby realizing the enhancement of the ultrasonic image of the pipeline.
Through the above steps, the enhancement of the ultrasonic image of the pipeline is completed.
According to the embodiment of the invention, the gray level change consistency of each filtering point rectangular window and the search window is obtained through the gray level change of different areas in an ultrasonic image, then a consistency sequence is obtained, the search window is obtained according to the relevance of the consistency sequence of the filtering points at different positions as the possible degree of the neighborhood blocks of the corresponding rectangular window, and then the search window is screened to obtain a plurality of neighborhood blocks corresponding to each filtering point; and then carrying out noise estimation on the local area where the filtering point is positioned according to the gray level changes of the plurality of neighborhood blocks to obtain the filtering weight of the local area. According to the invention, better filtering denoising effect can be obtained by comparing different noise influence degrees of different areas in the image and different textures, the denoising of the ultrasonic image is more thorough, and the crack defects in the ultrasonic image after denoising are clearer, so that the accuracy of identifying the crack defects in the pipeline is improved.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. An ultrasonic pipeline crack image enhancement method is characterized by comprising the following steps:
collecting an ultrasonic image of a pipeline to be detected by using an ultrasonic detector; obtaining filtering points in an ultrasonic image, and constructing a rectangular window of each filtering point; setting a plurality of search windows;
For each filtering point, acquiring the gray level change consistency of the rectangular window of the filtering point and each searching window according to the gray level distribution of the rectangular window of the filtering point and each searching window; the consistency of the gray level change of the rectangular window of the filtering point and each searching window forms a consistency sequence of the rectangular window of the filtering point;
Obtaining the possible degree of each search window serving as a neighborhood block of the filter point according to the consistency of the gray level change of the rectangular window of the filter point and each search window and the consistency sequence of the search windows of the filter point; screening a plurality of search windows as neighborhood blocks of filter points according to the possible degree; obtaining the filtering weight of the filtering point according to all neighborhood blocks of the filtering point and the gray distribution of the rectangular window of the filtering point;
And denoising the ultrasonic image according to the filtering weight of each filtering point in the ultrasonic image to obtain a denoised ultrasonic image, so as to realize the enhancement of the ultrasonic image.
2. The method for enhancing the image of the crack of the ultrasonic pipeline according to claim 1, wherein the construction of the rectangular window of each filtering point comprises the following specific steps:
building centered on each filtering point A window of size, which is a rectangular window for each filtering point, where/>The side length of the rectangular window is preset.
3. The ultrasonic pipeline crack image enhancement method according to claim 1, wherein the setting of a plurality of search windows comprises the following specific steps:
Construction A window with a size, the central point of the window is aligned with the first pixel point of the upper left corner of the ultrasonic image to obtain a first search window, the search window is slid from the first pixel point of the upper left corner of the ultrasonic image from left to right and then from top to bottom with a step length of 1 to obtain a plurality of search windows, wherein/>The side length of the rectangular window is preset.
4. The method for enhancing an ultrasonic pipeline crack image according to claim 1, wherein the step of obtaining the consistency of the gray scale variation of the rectangular window of the filter point and each search window according to the gray scale distribution of the rectangular window of the filter point and each search window comprises the following specific steps:
In the method, in the process of the invention, Represents the/>Rectangular window of individual filter points and the/>Gray scale variation consistency of individual search windows, wherein/>Get pass/>Is/are each integer inRepresenting the number of pixels included in an ultrasound image,/>Get pass/>And each integer of (a)，/>Represents the/>Gray average value of all pixel points in rectangular window of each filtering point,/>Represents the/>Gray average value of all pixel points in each search window,/>Represents the/>Gray variance of all pixel points in rectangular window of each filtering point,/>Represent the firstGray variance of all pixel points in each search window,/>An exponential function based on a natural constant is represented.
5. The ultrasonic pipeline crack image enhancement method according to claim 1, wherein the consistency sequence of the rectangular window of the filtering point and the gray level variation consistency of each searching window comprises the following specific steps:
and arranging the consistency of the gray level change of the rectangular window of the filtering point and each search window in order from large to small to obtain a consistency sequence of the rectangular window of the filtering point.
6. The method for enhancing an ultrasonic pipeline crack image according to claim 1, wherein the step of obtaining the probability of each search window as a neighborhood block of the filtering point comprises the following specific steps:
In the method, in the process of the invention, Represents the/>Search Window as the/>The degree of likelihood of a neighborhood block of filter points, where/>Get pass/>Is/are each integer inRepresenting the number of pixels contained in an ultrasound image of a pipeline,/>Get pass/>And each integer of (a)，/>Represents the/>Rectangular window of individual filter points and the/>Gray level variation consistency of individual search windows,/>Represent the firstCenter point and the/>, of rectangular window of the filter pointsDistance between center points of search windows,/>Represents the/>The consistency sequence of the rectangular window of the filtering points and the/>Pearson correlation coefficients for a consistent sequence of rectangular windows of filter points.
7. The method for enhancing an ultrasonic pipeline crack image according to claim 1, wherein the step of screening a plurality of search windows as neighborhood blocks of filter points according to the degree of possibility comprises the following specific steps:
when the probability of the neighborhood block of the filtering point as the search window is larger than the preset probability threshold And taking the search window as a neighborhood block of the filtering point.
8. The method for enhancing an ultrasonic pipeline crack image according to claim 1, wherein the step of obtaining the filtering weight of the filtering point according to all neighborhood blocks of the filtering point and the gray level distribution of the rectangular window of the filtering point comprises the following specific steps:
In the method, in the process of the invention, Represents the/>Filtering weights of the filtering points/>Represents the/>First/>, of the filtering pointsThe degree of likelihood of a neighborhood block being the neighborhood block for that filter point,/>Represents the/>Number of neighborhood blocks of filter points,/>Representing the side length of a preset rectangular window,/>Represents the/>The first/>, in a rectangular window of individual filter pointsGray value of each pixel/(Represents the/>First/>, of the filtering pointsFirst/>, in a respective neighborhood blockGray values of individual pixels.
9. The method of claim 1, wherein the denoising of the ultrasound image uses a non-local mean filtering algorithm.
10. The method for enhancing an ultrasonic pipeline crack image according to claim 1, wherein the step of acquiring the filtering point in the ultrasonic image comprises the following specific steps:
each pixel point in the ultrasonic image is used as a filtering point respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410423930.1A CN118014886B (en) | 2024-04-10 | 2024-04-10 | Ultrasonic pipeline crack image enhancement method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410423930.1A CN118014886B (en) | 2024-04-10 | 2024-04-10 | Ultrasonic pipeline crack image enhancement method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118014886A true CN118014886A (en) | 2024-05-10 |
| CN118014886B CN118014886B (en) | 2024-06-21 |
Family
ID=90943621
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410423930.1A Active CN118014886B (en) | 2024-04-10 | 2024-04-10 | Ultrasonic pipeline crack image enhancement method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118014886B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014036950A1 (en) * | 2012-09-05 | 2014-03-13 | 北京大学 | Non-local mean-based video denoising method and apparatus |
| CN108921800A (en) * | 2018-06-26 | 2018-11-30 | 成都信息工程大学 | Non-local mean denoising method based on form adaptive search window |
| CN109064418A (en) * | 2018-07-11 | 2018-12-21 | 成都信息工程大学 | A kind of Images Corrupted by Non-uniform Noise denoising method based on non-local mean |
| CN117393116A (en) * | 2023-12-12 | 2024-01-12 | 中国人民解放军空军军医大学 | Medical image data transmission system and method of portable DR equipment |
| CN117557571A (en) * | 2024-01-12 | 2024-02-13 | 普森美微电子技术(苏州)有限公司 | Visual detection method and system for alloy resistance welding defects based on image enhancement |
| CN117764864A (en) * | 2024-02-22 | 2024-03-26 | 济南科汛智能科技有限公司 | nuclear magnetic resonance tumor visual detection method based on image denoising |
-
2024
- 2024-04-10 CN CN202410423930.1A patent/CN118014886B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014036950A1 (en) * | 2012-09-05 | 2014-03-13 | 北京大学 | Non-local mean-based video denoising method and apparatus |
| CN108921800A (en) * | 2018-06-26 | 2018-11-30 | 成都信息工程大学 | Non-local mean denoising method based on form adaptive search window |
| CN109064418A (en) * | 2018-07-11 | 2018-12-21 | 成都信息工程大学 | A kind of Images Corrupted by Non-uniform Noise denoising method based on non-local mean |
| CN117393116A (en) * | 2023-12-12 | 2024-01-12 | 中国人民解放军空军军医大学 | Medical image data transmission system and method of portable DR equipment |
| CN117557571A (en) * | 2024-01-12 | 2024-02-13 | 普森美微电子技术(苏州)有限公司 | Visual detection method and system for alloy resistance welding defects based on image enhancement |
| CN117764864A (en) * | 2024-02-22 | 2024-03-26 | 济南科汛智能科技有限公司 | nuclear magnetic resonance tumor visual detection method based on image denoising |
Non-Patent Citations (1)
| Title |
|---|
| 陈醉: "基于计算机视觉的沥青路面裂缝图像处理算法研究", 中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑, 15 March 2024 (2024-03-15), pages 034 - 309 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118014886B (en) | 2024-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Merazi-Meksen et al. | Mathematical morphology for TOFD image analysis and automatic crack detection | |
| CN110146521B (en) | Pipeline surface corrosion defect detection method and device based on microwave nondestructive detection | |
| JP5639078B2 (en) | Method and apparatus for measuring liquid level in a container using imaging | |
| Song et al. | Wavelet based noise suppression technique and its application to ultrasonic flaw detection | |
| CN107620868B (en) | pipeline leakage detection method and device | |
| US20030098697A1 (en) | Apparatus and method for non-destructive inspection | |
| Shahrokhinasab et al. | Performance of image-based crack detection systems in concrete structures | |
| CN112184693A (en) | Intelligent detection method for weld defects of ray industrial negative | |
| CN114445386B (en) | PVC pipe quality detection and evaluation method and system based on artificial intelligence | |
| TWI708940B (en) | Ultrasonic inspection method and ultrasonic inspection device | |
| Choi et al. | Integrated visualization for reinforced concrete using ultrasonic tomography and image-based 3-D reconstruction | |
| CN111325738A (en) | Intelligent detection method and system for peripheral cracks of transverse hole | |
| CN114264724A (en) | Ultrasonic signal processing method based on CEEMDAN combined wavelet packet threshold | |
| Li et al. | Ultrasound intima‐media thickness measurement of the carotid artery using ant colony optimization combined with a curvelet‐based orientation‐selective filter | |
| CN113899349B (en) | Sea wave parameter detection method, equipment and storage medium | |
| CN109030634B (en) | Ultrasonic imaging and insulation evaluation method and device for internal defects of cable rubber joint | |
| CN118014886B (en) | Ultrasonic pipeline crack image enhancement method | |
| Febrianti et al. | Analysis of non-destructive testing ultrasonic signal for detection of defective materials based on the Simulink Matlab Mathematica computation method | |
| CN112816557B (en) | Defect detection method, device, equipment and storage medium | |
| Forbes et al. | Estimating fruit volume from digital images | |
| CN116681701A (en) | Children lung ultrasonic image processing method | |
| CN112014471A (en) | Plate structure multi-mode lamb wave topological gradient imaging method based on virtual sensor | |
| Grandin et al. | Implementation of automated 3D defect detection for low signal-to noise features in NDE data | |
| Sun et al. | Automated quality characterization for composites using hybrid ultrasonic imaging techniques | |
| Kieckhoefer et al. | Image processing techniques for ultrasonic inspection |
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 |