CN113740364A - Quantitative detection method for layering defects of drilled holes - Google Patents
Quantitative detection method for layering defects of drilled holes Download PDFInfo
- Publication number
- CN113740364A CN113740364A CN202111215052.7A CN202111215052A CN113740364A CN 113740364 A CN113740364 A CN 113740364A CN 202111215052 A CN202111215052 A CN 202111215052A CN 113740364 A CN113740364 A CN 113740364A
- Authority
- CN
- China
- Prior art keywords
- defect
- image
- center
- value
- coordinate
- 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.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 98
- 238000001514 detection method Methods 0.000 title claims abstract description 10
- 238000005070 sampling Methods 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 14
- 238000002591 computed tomography Methods 0.000 claims abstract description 4
- 230000002087 whitening effect Effects 0.000 claims abstract description 3
- 230000032798 delamination Effects 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 7
- 238000003754 machining Methods 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 9
- 238000005259 measurement Methods 0.000 description 8
- 238000005553 drilling Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
- G01N23/02—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material
- G01N23/04—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material and forming images of the material
- G01N23/046—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material and forming images of the material using tomography, e.g. computed tomography [CT]
Abstract
The invention belongs to the technical field of machining defect detection, and particularly relates to a quantitative detection method for a layered defect of a drilled hole, which comprises the following steps: carrying out pure black whitening on the layered defect gray image obtained by CT scanning through software; selecting a certain number of continuous sampling points at the center of the image, ensuring that the distance between the sampling points and the center of the image in the width and height directions does not exceed a fixed span, ensuring that all the sampling points are positioned in the layered defect, finally forming a square by taking the center of the image as the center of all the sampling points, and determining the circle center coordinates (x) of all the sampling pointsc,yc) (ii) a The method comprises the steps that pixel points on paths are traversed one by one along the circle centers of the x axis and the y axis at the four edges of an image, and the positions of the outermost pixel points of the layered defects are determined; and respectively calculating the distance radius and the angle value between each outermost layered defect pixel point and the circle center, thereby determining the area of the actual layered defect region.
Description
Technical Field
The invention belongs to the technical field of machining defect detection, and particularly relates to a quantitative detection method for a layered defect of a drilled hole.
Background
The evaluation of the delamination defect is to evaluate the generation degree and influence of the delamination defect by calculating a delamination defect factor. The basic numerical values for calculating the delamination defect factor are mainly divided into two types: one is a one-dimensional size, and mainly comprises the pore diameter obtained by drilling and the corresponding diameter of a selected point in a layering area; the other is two-dimensional size, which is mainly the area of the drilled hole, the calculated area corresponding to the selected point of the delamination area and the area of the actual delamination defect area, as shown in fig. 1. D in FIG. 1nomFor drilling hole diameters, DmaxIn the region of the layered defect, the converted diameter of the corresponding point located at the outermost position of the hole center is twice the distance between the point and the hole center, AnomThe hole diameter corresponds to the area of the circle, AmaxIs warp DmaxCalculating the area of the resulting circle, AdIs the actual delamination defect area.
The most commonly used formula for calculating the delamination defect factor is as follows:
its advantages are easy measurement and calculation. For each hole, the hole diameter is generally the nominal diameter of the used drill bit, so that the layering defect factor can be calculated by measuring the distance between the outermost corresponding point of the layering defect area and the circle center. The disadvantage is that it is not sensitive to the actual generation area of the delamination defect. And measure DmaxThe most important is the determination of the hole center and the corresponding point at the outermost side of the delamination defect.
The calculation method of the delamination defect factor based on the area of the actual delamination defect area is as follows:
the method has the advantage of better meeting the practical situation of the layering defect. The disadvantages are that the area measurement and calculation of the actual delamination defect area are difficult, and D cannot be evaluated when the delamination defect width is extremely unevenmaxImpact on delamination defect factor.
To evaluate D simultaneouslymaxAnd AdFor the influence of the layered defect factor, the two layered defect factor calculation methods can be combined:
the advantages of the above formula are: when D is presentmaxWhen the influence on the delamination defect factor is dominant, FdaThe value approaches Fd. When A isdHaving an effect on the delamination defect factor greater than DmaxWhen F is presentdaValue closer to Fa. Its disadvantage is similar to formula (2.2), also AdMeasurement and calculation are difficult.
In summary, the calculation of the delamination defect factor is premised on the measurement and determination of the relevant size and area, and the key points of the calculation are the determination of the center of the hole and the corresponding point at the outermost side of the delamination defect area and the measurement and calculation of the actual delamination defect area.
Disclosure of Invention
The invention aims to provide a quantitative detection method for a layering defect of a drilled hole, which overcomes the defects of the prior art, and quickly and accurately determines the center of the hole and the determination of the corresponding point at the outermost side of a layering defect area and measures and calculates the area of the actual layering defect area after a software module of a Python platform is used for processing a layering defect gray image.
In order to solve the problems, the technical scheme adopted by the invention is as follows:
a quantitative detection method for the layered defects of drilled holes is characterized by comprising the following steps: the method comprises the following steps:
s1, carrying out pure black and white on the layered defect gray image obtained by CT scanning through software;
s2, selecting the center of the imageTaking a certain number of continuous sampling points, ensuring that the distance between each sampling point and the center of the image in the width and height directions does not exceed a fixed span, ensuring that all the sampling points are positioned in the layered defect, finally forming a square by taking the center of the image as the center of all the sampling points, and determining the circle center coordinates (x) of all the sampling pointsc,yc)；
S3, gradually traversing pixel points on the path along the x-axis and y-axis circle centers at four edges of the image one by one, and determining the positions of the outermost pixel points of the layered defects;
and S4, respectively calculating the distance radius and the angle value between each outermost layered defect pixel point and the circle center, thereby determining the area of the actual layered defect area.
Further, in S1, the step of performing pure whitening on the layer defect gray image by software includes:
(1) introducing an image module of an image processing standard library PIL in a Python platform;
(2) opening a target image and setting a critical gray value;
(3) and performing logic judgment on each pixel point in the image according to the width and the height of the image, changing the gray value of each pixel point into pure white if the gray value is less than or equal to a critical value, and changing the gray value of each pixel point into pure black if the gray value is greater than the critical value.
Further, the center coordinates (x) of all the sampling points are determined as described in S2c,yc) The method comprises the following specific steps:
(1) taking the width direction of the layered defect image from left to right as the positive direction of an x axis, the leftmost side as 0, the height direction from top to bottom as the positive direction of a y axis and the uppermost side as 0, and selecting the central coordinate of the image as (x)0,y0)；
(2) Starting to extend from x0 along the positive direction and the negative direction of the x axis in the sampling point range to each pixel point, carrying out logic judgment until a first pure white pixel point is found, writing the pixel point coordinate into a list inner _ x, stopping the circulation in the x axis direction, and entering the next y coordinate circulation;
(3) starting to extend from y0 along the positive direction and the negative direction of the y axis in the sampling point range to each pixel point, carrying out logic judgment until the first pure white pixel point is found, writing the pixel point coordinate into a list inner _ y, stopping the circulation of the y axis direction, and entering the next circulation of the x coordinate;
(4) sorting the coordinate elements in the list inner _ x according to the y coordinate value, and sorting the coordinate elements in the list inner _ y according to the x coordinate value;
(5) extracting and adding x coordinate values in adjacent coordinate elements (equal y coordinates) in the inner _ x list to obtain a chord length value x in the x-axis direction in the hole wall circles；
(6) Calculating xsThe average value is integrated to obtain the coordinate value x of the circle center xc；
(7) Extracting and adding y coordinate values in adjacent coordinate elements (equal x coordinates) in the inner _ y list to obtain a chord length value y in the y-axis direction in the hole wall circles；
Calculating ys average value and rounding to obtain circle center y coordinate value yc。
Further, the determining the position of the outermost layered defect pixel point in S4 specifically includes the following steps:
(1) dividing the layered defect gray image into four areas according to 90 degrees through a horizontal line and a vertical line of the circle center, and clockwise increasing the area with the rightmost side as 0 degree;
(2) and (3) pixel points on the path are gradually traversed from the four edges of the gray level image of the layered defect along the x-axis and the y-axis to the circle center, and the coordinate of the first pure white pixel point searched is the position of the outermost side of the layered defect.
Further, the step of calculating the distance radius and the angle value between each outermost layered defect pixel point and the circle center in S5 includes the following steps:
(1) calculating the distance between the outermost pixel point of each hierarchical defect and the center of the circle, and storing the distance into a dictionary dists, wherein the key of each key-value pair in the dictionary is (x)i,yi) Angle relative to the center of the circle, the value being (x)i,yi) Distance from the center of the circle;
(2) and (5) sorting the dictionary dists, and drawing a chart to obtain the average distance radius, the maximum value of the distance radius and the corresponding angle of the distance radius.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the invention, after the software module of the Python platform is adopted to process the gray level image of the layered defect, the determination of the circle center of the hole and the corresponding point at the outermost side of the layered defect area and the measurement and calculation of the actual area of the layered defect area are rapidly and accurately determined.
2. The invention can be closer to the actual condition of the layering defect by determining the area of the actual layering defect area, thereby providing a more accurate measurement and evaluation means for the detection, quality control and parameter optimization of the drilling quality.
Drawings
FIG. 1 is a schematic view of a drilled hole delamination defect area.
FIG. 2 is a flow chart of a method for quantitatively detecting a layer defect of a drilled hole.
FIG. 3 is a black and white image of different layered defect regions.
Fig. 4 is a diagram of determining the hole center of a gray scale image of a layered defect.
FIG. 5 is a search graph of the outermost pixels of the hierarchical defect.
Fig. 6 is a schematic diagram of processing results of different layered defect images.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 2, the method for quantitatively detecting the delamination defect of the drilled hole according to the present invention comprises the following steps:
s1, carrying out pure black and white on the layered defect gray image obtained by CT scanning through software;
s2, selecting a certain number of continuous sampling points in the center of the image, wherein the sampling points are in the width and height directions with the center of the imageThe distance does not exceed a fixed span, all sampling points are ensured to be positioned in the layered defect, finally all sampling points form a square by taking the image center as the center, and the circle center coordinates (x) of all sampling points are determinedc,yc)；
S3, gradually traversing pixel points on the path along the x-axis and y-axis circle centers at four edges of the image one by one, and determining the positions of the outermost pixel points of the layered defects;
and S4, respectively calculating the distance radius and the angle value between each outermost layered defect pixel point and the circle center, thereby determining the area of the actual layered defect area.
As shown in fig. 3, in order to facilitate subsequent processing such as hole center determination, searching for outermost points of the hierarchical regions, and area measurement, pure black and white processing is performed on the hierarchical defect gray image by software in S1, which includes the specific steps of:
(1) introducing an image module of an image processing standard library PIL in a Python platform;
(2) opening a target image and setting a critical gray value;
(3) and performing logic judgment on each pixel point in the image according to the width and the height of the image, changing the gray value of each pixel point into pure white if the gray value is less than or equal to a critical value, and changing the gray value of each pixel point into pure black if the gray value is greater than the critical value.
As shown in fig. 4, to determine the center of the circle, the center coordinates (x) of all the sample points are determined as described in S2c,yc) The method comprises the following specific steps:
(1) taking the width direction of the layered defect image from left to right as the positive direction of an x axis, the leftmost side as 0, the height direction from top to bottom as the positive direction of a y axis and the uppermost side as 0, and selecting the central coordinate of the image as (x)0,y0)；
(2) Starting to extend from x0 along the positive direction and the negative direction of the x axis in the sampling point range to each pixel point, carrying out logic judgment until a first pure white pixel point is found, writing the pixel point coordinate into a list inner _ x, stopping the circulation in the x axis direction, and entering the next y coordinate circulation;
(3) starting to extend from y0 along the positive direction and the negative direction of the y axis in the sampling point range to each pixel point, carrying out logic judgment until the first pure white pixel point is found, writing the pixel point coordinate into a list inner _ y, stopping the circulation of the y axis direction, and entering the next circulation of the x coordinate;
(4) sorting the coordinate elements in the list inner _ x according to the y coordinate value, and sorting the coordinate elements in the list inner _ y according to the x coordinate value;
(5) extracting and adding x coordinate values in adjacent coordinate elements (equal y coordinates) in the inner _ x list to obtain a chord length value x in the x-axis direction in the hole wall circles；
(6) Calculating xsThe average value is integrated to obtain the coordinate value x of the circle center xc；
(7) Extracting and adding y coordinate values in adjacent coordinate elements (equal x coordinates) in the inner _ y list to obtain a chord length value y in the y-axis direction in the hole wall circles；
(8) Calculating ys average value and rounding to obtain circle center y coordinate value yc。
As shown in fig. 5, the determining the position of the outermost pixel point of the hierarchical defect in S4 specifically includes the following steps:
(1) dividing the layered defect gray image into four areas according to 90 degrees through a horizontal line and a vertical line of the circle center, and clockwise increasing the area with the rightmost side as 0 degree;
(2) and (3) pixel points on the path are gradually traversed from the four edges of the gray level image of the layered defect along the x-axis and the y-axis to the circle center, and the coordinate of the first pure white pixel point searched is the position of the outermost side of the layered defect.
In S5, the calculating of the distance radius and the angle value between each outermost layered defect pixel point and the circle center respectively includes the following steps:
(1) calculating the distance between the outermost pixel point of each hierarchical defect and the center of the circle, and storing the distance into a dictionary dists, wherein the key of each key-value pair in the dictionary is (x)i,yi) Angle relative to the center of the circle, the value being (x)i,yi) Distance from the center of the circle;
(2) sorting the dictionaries dists, and drawing a chart to obtain an average distance radius, a maximum distance radius value and a corresponding angle of the maximum distance radius value; in the Python platform, the keys of the dictionary have uniqueness, but the values corresponding to different keys can be the same, so that the corresponding points of each key value pair in the dists dictionary are not repeated;
(3) as shown in fig. 6, graphs are prepared based on the statistical results, and the average distance radius, the maximum distance radius value, and the corresponding angle are read from the graphs.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (5)
1. A quantitative detection method for the layered defects of drilled holes is characterized by comprising the following steps: the method comprises the following steps:
s1, carrying out pure black and white on the layered defect gray image obtained by CT scanning through software;
s2, selecting a certain number of continuous sampling points at the center of the image, ensuring that the distance between the sampling points and the center of the image in the width and height directions does not exceed a fixed span, ensuring that all the sampling points are positioned in the layered defect, finally forming a square by taking the center of the image as the center of all the sampling points, and determining the circle center coordinates (x) of all the sampling pointsc,yc)；
S3, gradually traversing pixel points on the path along the x-axis and y-axis circle centers at four edges of the image one by one, and determining the positions of the outermost pixel points of the layered defects;
and S4, respectively calculating the distance radius and the angle value between each outermost layered defect pixel point and the circle center, thereby determining the area of the actual layered defect area.
2. The method for quantitatively detecting the delamination defect of the drilled hole according to claim 1, wherein: in S1, performing pure black whitening on the hierarchical defect gray image by software, specifically including:
(1) introducing an image module of an image processing standard library PIL in a Python platform;
(2) opening a target image and setting a critical gray value;
(3) and performing logic judgment on each pixel point in the image according to the width and the height of the image, changing the gray value of each pixel point into pure white if the gray value is less than or equal to a critical value, and changing the gray value of each pixel point into pure black if the gray value is greater than the critical value.
3. The method for quantitatively detecting the delamination defect of the drilled hole according to claim 1, wherein: determining the center coordinates (x) of all the sample points as described in S2c,yc) The method comprises the following specific steps:
(1) taking the width direction of the layered defect image from left to right as the positive direction of an x axis, the leftmost side as 0, the height direction from top to bottom as the positive direction of a y axis and the uppermost side as 0, and selecting the central coordinate of the image as (x)0,y0)；
(2) Starting to extend from x0 along the positive direction and the negative direction of the x axis in the sampling point range to each pixel point, carrying out logic judgment until a first pure white pixel point is found, writing the pixel point coordinate into a list inner _ x, stopping the circulation in the x axis direction, and entering the next y coordinate circulation;
(3) starting to extend from y0 along the positive direction and the negative direction of the y axis in the sampling point range to each pixel point, carrying out logic judgment until the first pure white pixel point is found, writing the pixel point coordinate into a list inner _ y, stopping the circulation of the y axis direction, and entering the next circulation of the x coordinate;
(4) sorting the coordinate elements in the list inner _ x according to the y coordinate value, and sorting the coordinate elements in the list inner _ y according to the x coordinate value;
(5) extracting and adding x coordinate values in adjacent coordinate elements (equal y coordinates) in the inner _ x list to obtain a chord length value x in the x-axis direction in the hole wall circles；
(6) Calculating xsThe average value is integrated to obtain the coordinate value x of the circle center xc；
(7) Extracting and adding y coordinate values in adjacent coordinate elements (equal x coordinates) in the inner _ y list to obtain a chord length value y in the y-axis direction in the hole wall circles；
(8) Calculating ys average value and rounding to obtain circle center y coordinate value yc。
4. The method for quantitatively detecting the delamination defect of the drilled hole according to claim 1, wherein: determining the position of the outermost pixel point of the layered defect in S4 specifically comprises the following steps:
(1) dividing the layered defect gray image into four areas according to 90 degrees through a horizontal line and a vertical line of the circle center, and clockwise increasing the area with the rightmost side as 0 degree;
(2) and (3) pixel points on the path are gradually traversed from the four edges of the gray level image of the layered defect along the x-axis and the y-axis to the circle center, and the coordinate of the first pure white pixel point searched is the position of the outermost side of the layered defect.
5. The method for quantitatively detecting the delamination defect of the drilled hole according to claim 1, wherein: in S5, the calculating of the distance radius and the angle value between each outermost layered defect pixel point and the circle center respectively includes the following steps:
(1) calculating the distance between the outermost pixel point of each hierarchical defect and the center of the circle, and storing the distance into a dictionary dists, wherein the key of each key-value pair in the dictionary is (x)i,yi) Angle relative to the center of the circle, the value being (x)i,yi) Distance from the center of the circle;
(2) and (5) sorting the dictionary dists, and drawing a chart to obtain the average distance radius, the maximum value of the distance radius and the corresponding angle of the distance radius.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2021107847964 | 2021-07-12 | ||
| CN202110784796 | 2021-07-12 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113740364A true CN113740364A (en) | 2021-12-03 |
Family
ID=78726831
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111215052.7A Pending CN113740364A (en) | 2021-07-12 | 2021-10-19 | Quantitative detection method for layering defects of drilled holes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113740364A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114152637A (en) * | 2022-02-07 | 2022-03-08 | 东莞市志橙半导体材料有限公司 | Hard silicon carbide material punching detection device and method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110660056A (en) * | 2019-10-10 | 2020-01-07 | 昆山市建设工程质量检测中心 | Building crack width measurement algorithm and method based on image processing |
| CN110794037A (en) * | 2019-11-13 | 2020-02-14 | 上海交通大学 | Quantitative evaluation method for drilling defects of carbon fiber composite material |
| CN112881467A (en) * | 2021-03-15 | 2021-06-01 | 中国空气动力研究与发展中心超高速空气动力研究所 | Large-size composite material damage imaging and quantitative identification method |
-
2021
- 2021-10-19 CN CN202111215052.7A patent/CN113740364A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110660056A (en) * | 2019-10-10 | 2020-01-07 | 昆山市建设工程质量检测中心 | Building crack width measurement algorithm and method based on image processing |
| CN110794037A (en) * | 2019-11-13 | 2020-02-14 | 上海交通大学 | Quantitative evaluation method for drilling defects of carbon fiber composite material |
| CN112881467A (en) * | 2021-03-15 | 2021-06-01 | 中国空气动力研究与发展中心超高速空气动力研究所 | Large-size composite material damage imaging and quantitative identification method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114152637A (en) * | 2022-02-07 | 2022-03-08 | 东莞市志橙半导体材料有限公司 | Hard silicon carbide material punching detection device and method |
| CN114152637B (en) * | 2022-02-07 | 2022-04-26 | 东莞市志橙半导体材料有限公司 | Hard silicon carbide material punching detection device and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR940003829B1 (en) | Position recognizing method | |
| CN113724193B (en) | PCBA part size and clearance high-precision visual measurement method | |
| WO2022088096A1 (en) | Method for measuring actual area of defect, and method and apparatus for testing display panel | |
| CN106643549A (en) | Machine vision-based tile size detection method | |
| CN113740364A (en) | Quantitative detection method for layering defects of drilled holes | |
| CN113340909A (en) | Glue line defect detection method based on machine vision | |
| CN112287977A (en) | Target detection method based on key point distance of bounding box | |
| CN113269049A (en) | Method for detecting handwritten Chinese character area | |
| CN113393447B (en) | Needle tip true position detection method and system based on deep learning | |
| CN117423046B (en) | Visual detection method for cement mortar stirring process based on image processing | |
| CN117173176B (en) | Multi-layer photoetching process hot spot detection method based on image processing | |
| CN113689451A (en) | Carbon plate boundary extraction method and device, storage medium and electronic equipment | |
| CN113947583A (en) | Weld joint nondestructive testing method based on deep learning two-dimensional time sequence image | |
| CN115082444B (en) | Copper pipe weld defect detection method and system based on image processing | |
| CN116452826A (en) | Coal gangue contour estimation method based on machine vision under shielding condition | |
| CN114359276B (en) | Steel die blanking optimization scheme obtaining method based on pockmark defects | |
| CN112857252B (en) | Tunnel image boundary line detection method based on reflectivity intensity | |
| CN110411384B (en) | Method for detecting surface roughness of internal rod piece of three-dimensional printing lattice structure | |
| CN112215240B (en) | Optimization method for improving 2D complex edge detection precision | |
| CN113256571A (en) | Vector graphic feature point extraction method based on direction feature and local uniqueness | |
| CN106446962A (en) | Dynamic girder obstacle clustering recognition method | |
| CN114037705B (en) | Metal fracture fatigue source detection method and system based on moire lines | |
| CN111192264A (en) | Automatic paper defect detection method based on improved non-local mean value fast-RCNN algorithm | |
| Liu et al. | A Double Diagonal Ratio Metric for Tiny Object Detection in Aerial Images | |
| CN112819810B (en) | Sand particle roundness calculation method |
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 |