CN113538418A - Tire X-ray image defect extraction model construction method based on morphological analysis - Google Patents
Tire X-ray image defect extraction model construction method based on morphological analysis Download PDFInfo
- Publication number
- CN113538418A CN113538418A CN202110991452.0A CN202110991452A CN113538418A CN 113538418 A CN113538418 A CN 113538418A CN 202110991452 A CN202110991452 A CN 202110991452A CN 113538418 A CN113538418 A CN 113538418A
- Authority
- CN
- China
- Prior art keywords
- tire
- image
- defect
- ray
- black point
- 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 110
- 238000000605 extraction Methods 0.000 title claims abstract description 29
- 230000000877 morphologic effect Effects 0.000 title claims abstract description 23
- 238000004458 analytical method Methods 0.000 title claims abstract description 16
- 238000010276 construction Methods 0.000 title claims abstract description 9
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000003709 image segmentation Methods 0.000 claims abstract description 6
- 238000011156 evaluation Methods 0.000 claims abstract description 5
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000003384 imaging method Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 230000007797 corrosion Effects 0.000 claims description 5
- 238000005260 corrosion Methods 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 3
- 230000002087 whitening effect Effects 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 2
- 230000002787 reinforcement Effects 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 4
- 238000009659 non-destructive testing Methods 0.000 abstract description 4
- 230000008439 repair process Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 16
- 238000012847 principal component analysis method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000010339 dilation Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005530 etching Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray image
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
A tire X-ray image defect extraction model construction method based on morphological analysis belongs to the technical field of tire image nondestructive testing. It comprises the following steps: 1. acquiring a tire X-ray defect image dataset; 2. tire X-ray image segmentation preprocessing; 3. extracting characteristics of tire shoulders and tire sides; 4. performing X-ray enhancement pretreatment on the tire; 5. calculating the maximum edge information to determine the defect position; 6. and (5) performing performance evaluation on the tire defect extraction model. The invention provides a tire X-ray image defect extraction method based on morphological analysis, which improves the accuracy of defect identification and positioning; the method utilizes image segmentation and image enhancement to enhance the boundary of each part of the tire and accurately divide the boundary, and performs defect identification and extraction on tire shoulders and tire side regions; the method well eliminates regular shading and small noise based on a mathematical morphology method, repairs certain fractures of the regular shading and improves the defect extraction effect.
Description
Technical Field
The invention belongs to the technical field of nondestructive testing of tire images, and particularly relates to a tire X-ray image defect extraction model construction method based on morphological analysis.
Background
The tire industry has been greatly developed along with the popularization of automobiles, but the traffic accidents caused by the defects of the tires account for more than 40 percent. Defects generated in the tire production process can be classified into internal impurities, bubbles, line breakage and the like according to different causes, and the defects are inevitable due to technical limitations.
The X-ray detection result is visual and reliable, the imaging is convenient to store for a long time, and the X-ray detection method is widely used for tire nondestructive testing as a data source of image detection. However, the tire X-ray image has the characteristics of complex shading and much noise, and the existing method generally only aims at one defect and is slow in extraction rate.
Disclosure of Invention
In view of the above problems in the prior art, an object of the present invention is to provide a method for extracting defects in an X-ray image of a tire based on morphological analysis, so as to achieve the purpose of automatic detection that can quickly and simultaneously identify most defects of textures and gray scales.
The invention provides the following technical scheme: the tire X-ray image defect extraction model construction method based on morphological analysis comprises the following steps:
(1) acquiring a tire X-ray defect image dataset: operating an X-ray imaging system, imaging the X-ray on the imaging system after the X-ray penetrates through the tire, and importing the digitized image into a computer for storage;
(2) tire X-ray image segmentation preprocessing: adjusting the pixel size of the tire defect image obtained in the step (1), segmenting the adjusted image, standardizing and binarizing the segmented image, reducing the influence of external factors on the image quality during shooting, corroding and expanding firstly by using an opening operation in mathematical morphology, and further reducing noise to smooth edges;
(3) extracting shoulder and sidewall features: carrying out classification marking on the pixels of the image preprocessed in the step (2), and accurately extracting tire shoulders and tire side parts as enhancement objects;
(4) tire X-ray enhancement pretreatment: standardizing and binarizing the image preprocessed in the step (2) by only retaining the information of tire shoulders and tire sidewalls, and eliminating the background reinforcement defect by using closing operation and corrosion operation;
(5) calculating the maximum edge information to determine the defect position: setting a threshold value N, extracting all black points, taking the points one by one, judging whether the taken black point is in an existing defect group, if the taken black point is in the existing defect group, judging the next black point, if the taken black point is in the existing defect group, calculating the distance between the black point and the nearest black point away from the black point, judging whether the distance between the two black points is smaller than the threshold value N, if the distance between the two black points is larger than the threshold value X, abandoning the black point, if the distance between the two black points is smaller than the threshold value X, judging whether the nearest black point is in the existing defect group, if the nearest black point is in the existing defect group, merging the black point into the defect group, if the nearest black point is not in the existing defect group, newly building the two black point defect groups, calculating the defect area of each defect group, sequencing, and taking the edge information of the largest area as the defect position;
(6) and (3) performing performance evaluation on the tire defect extraction model: the intersection ratio IoU is used as a judgment index for the quality of the positioning result.
The tire X-ray image defect extraction model construction method based on morphological analysis is characterized in that the specific process of the step (2) is as follows:
step 2.1: adjusting the size of the tire defect image into a x b pixels, wherein a represents the length value of the image size in pixel unit, and b represents the width value of the image size in pixel unit, then dividing the tire defect image into a x pixel size, detecting for n times, and standardizing the divided image;
step 2.2: performing binarization processing on the image subjected to the standardization processing in the step 2.1, and taking the mean value of pixel values of all pixel points as a threshold value to convert the part of the image, of which the pixel values are greater than the threshold value, into black and convert the part of the image, of which the pixel values are less than the threshold value, into white;
step 2.3: and (3) performing square opening operation on the image subjected to binarization processing in the step 2.32, corroding and expanding the image, and eliminating noise and small objects in the image, wherein the specific formula is as follows:
where B is a kernel function, A is an original set, both are elements of a two-dimensional integer space Z2, $ represents an etch operation,
an expansion operation;
step 2.4: and performing expansion operation to further smooth the edge, reduce edge noise and make the boundary clearer.
The tire X-ray image defect extraction model construction method based on morphological analysis is characterized in that the specific process of the step (3) is as follows:
step 3.1: carrying out classification marking on each pixel of the preprocessed image, marking white as True and black as False, and uniformly storing;
step 3.2: for each column, if the number of pixels marked as True is greater than 5%, the column is judged as a shoulder and sidewall part, the column is marked as 1, otherwise, the column is 0;
step 3.3: the boundary between the row pixel of the mark 0 and the row pixel of the mark 1 is a boundary of different portions of the tire, and the tire is divided.
The tire X-ray image defect extraction model construction method based on morphological analysis is characterized in that the specific process of the step (4) is as follows:
step 4.1: taking the image preprocessed in the step (2), converting all the pixel values of the rows marked as 0 into 255 for whitening by using the mark value of each row, and only reserving the information of the tire shoulder and the tire side for subsequent detection;
step 4.2: standardizing the images, reducing the difference between the images, then carrying out binarization, taking the average value of a single-column image as a threshold value, and additionally generating a color flip graph in order to simultaneously detect various defects;
step 4.3: respectively repairing the fracture of the regular shading by utilizing closing operation and corrosion operation, eliminating the regular shading and small noise and enhancing the defects; and then combining the binarized image and the color reversed image thereof, and performing expansion operation on the combined image to remove small noise.
By adopting the technology, compared with the prior art, the invention has the following beneficial effects:
the invention provides a tire X-ray image defect extraction method based on morphological analysis, which improves the accuracy of defect identification and positioning; the method utilizes image segmentation and image enhancement to enhance the boundary of each part of the tire and accurately divide the boundary, and performs defect identification and extraction on tire shoulders and tire side regions; the method well eliminates regular shading and small noise based on a mathematical morphology method, repairs certain fractures of the regular shading and improves the defect extraction effect.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a schematic diagram of a conventional tire defect, wherein FIG. 2a is a schematic diagram of an open root defect, FIG. 2b is a schematic diagram of a cord sparse defect, FIG. 2c is a schematic diagram of a foreign object defect, FIG. 2d is a schematic diagram of a bubble defect, and FIG. 2e is a schematic diagram of a jump defect;
fig. 3 is a schematic diagram of a tire defect enhancement result of a PCA algorithm and a morphological algorithm of the present invention, wherein fig. 3a, fig. 3b, and fig. 3c are a schematic diagram of a gray-scale type defect original image, a schematic diagram of a PCA defect extraction result, and a schematic diagram of a morphological defect extraction result, respectively, and fig. 3d, fig. 3e, and fig. 3f are a schematic diagram of a texture type defect original image, a schematic diagram of a PCA defect extraction result, and a schematic diagram of a morphological defect extraction result, respectively;
fig. 4 is a schematic diagram of tire defect positioning results of the PCA algorithm and the morphological algorithm of the present invention, wherein fig. 4 (a) and fig. 4 (b) are schematic diagrams of positioning results of the PCA and the morphological method on gray-level defects, and fig. 4 (c) and fig. 4 (d) are schematic diagrams of positioning results of the PCA and the morphological method on texture defects.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
On the contrary, the invention is intended to cover alternatives, modifications, equivalents and alternatives which may be included within the spirit and scope of the invention as defined by the appended claims. Furthermore, in the following detailed description of the present invention, certain specific details are set forth in order to provide a better understanding of the present invention. It will be apparent to one skilled in the art that the present invention may be practiced without these specific details.
Referring to fig. 1 to 4, a method for extracting tire X-ray image defects based on morphological analysis includes the following steps:
(1) acquiring a tire X-ray defect image dataset
Operating an X-ray imaging system, imaging the X-ray on the imaging system after the X-ray penetrates through the tire, and importing the X-ray into a computer for storage after digitization;
(2) tire X-ray image segmentation preprocessing comprises the following steps:
step 2.1: the tire defect image is resized to 2000 × 20000 pixels, the image is divided into 2000 × 2000 pixels, detection is performed 10 times, the image is normalized, and the influence of conditions such as light on the result during shooting is reduced.
Step 2.2: and (3) carrying out binarization processing on the image, and taking the average value of pixel values of all pixel points as a threshold value to convert the part of the image larger than the threshold value into black and convert the part of the image smaller than the threshold value into white.
Step 2.3: performing opening operation with the kernel size of 5 multiplied by 5 and the square shape, corroding and expanding the kernel, and eliminating noise and small objects in the image;
where B is the kernel function and A is the original set, both of which are two-dimensional integer space Z2The element (c), (d) represents an etching operation,
and (4) performing an expansion operation.
Step 2.4: and performing dilation operation with the kernel size of 3 multiplied by 3 to further smooth edges, reduce edge noise and make boundaries clearer.
(3) Shoulder and sidewall features were extracted as follows:
step 3.1: each pixel is classified and labeled, white is marked as True (True), black is marked as False (False), and the color is uniformly stored.
Step 3.2: for each row, if the number of True is greater than 5%, the row is judged as the shoulder and sidewall portion, the row is marked as 1, otherwise 0.
Step 3.3: the boundary between the marks 0 and 1 is the boundary of different parts of the tire, and the tire is divided.
(4) The tire X-ray enhancement pretreatment comprises the following steps:
step 4.1: and (3) taking an original image, converting all the pixel values of the columns marked with 0 into 255 for whitening by using the marking value of each column, and only reserving the information of the tire shoulder and the tire side for subsequent detection.
Step 4.2: and standardizing the images to reduce the difference between the images. And then carrying out binarization, taking the average value of the single-column image as a threshold value, and regarding different defects, such as foreign matter defects and the like, which are displayed black after binarization, and regarding open-line defects and the like, which are displayed white after binarization, so that in order to detect various defects at the same time, an additional color flip graph is generated, and the subsequent steps are respectively processing two images.
Step 4.3: respectively repairing certain fractures of the regular shading by utilizing the closing operation with the kernel size of 8 multiplied by 8 and the corrosion operation with the kernel size of 12 multiplied by 12, eliminating the regular shading and small noise and strengthening the defects; then, the two pictures are merged to be subjected to a dilation operation with a kernel size of 5 × 5 to remove small noise.
(5) Calculating the maximum edge information to determine the defect position, wherein the process comprises the following steps:
extracting all black points, taking the points one by one, judging whether the black points are in the existing group, if so, judging the next point, if not, calculating the closest point to the point, judging whether the distance between the two points is smaller than a threshold value 50, if so, giving up the point, if not, judging whether the closest point is in the group, if so, merging the points into the group, otherwise, newly building a defect group by two points, calculating the area of each group of defects, and sorting and taking the edge information of the largest area as the defect position.
(6) And (3) performing performance evaluation on the tire defect extraction model, wherein the process is as follows:
in the tire defect extraction, the result is mainly determined by the difference between the defect position obtained finally and the label, so the intersection ratio (IoU) is used as an index for positioning the result
In the formula, (c) area (area) represents the area of the label frame, and (g) area (area) represents the area of the prediction frame. In the test, the larger the cross-over ratio is, the better the cross-over ratio is, the most ideal state is complete overlapping, namely, the cross-over ratio is 1, and the best effect is achieved.
The effectiveness of the morphological method was experimentally verified on various tire defects and compared to the principal component analysis method, with the results shown in table 1.
TABLE 1 comparison of morphology with PCA transformation results
From the above comparison results, it can be seen that the present invention is superior to the conventional principal component analysis method in both enhancement and localization results for tire images of different defect types. Moreover, the principal component analysis method is easy to cause error positioning of the defects and is insensitive to extraction of certain defect characteristics. And the morphology method basically extracts relatively complete defects, hardly contains noise and has good defect identification capability. The method is an effective tire X-ray defect image data analysis method, and is beneficial to improving the capability of X-ray nondestructive testing on tire defect evaluation.
The method provided by the invention adopts a mathematical morphology method to segment and enhance the tire defect image, improves the defect identification effect, improves the detection efficiency, and has universality and universality.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (4)
1. The tire X-ray image defect extraction model construction method based on morphological analysis is characterized by comprising the following steps of:
(1) acquiring a tire X-ray defect image dataset: operating an X-ray imaging system, imaging the X-ray on the imaging system after the X-ray penetrates through the tire, and importing the digitized image into a computer for storage;
(2) tire X-ray image segmentation preprocessing: adjusting the pixel size of the tire defect image obtained in the step (1), segmenting the adjusted image, standardizing and binarizing the segmented image, reducing the influence of external factors on the image quality during shooting, corroding and expanding firstly by using an opening operation in mathematical morphology, and further reducing noise to smooth edges;
(3) extracting shoulder and sidewall features: carrying out classification marking on the pixels of the image preprocessed in the step (2), and accurately extracting tire shoulders and tire side parts as enhancement objects;
(4) tire X-ray enhancement pretreatment: standardizing and binarizing the image preprocessed in the step (2) by only retaining the information of tire shoulders and tire sidewalls, and eliminating the background reinforcement defect by using closing operation and corrosion operation;
(5) calculating the maximum edge information to determine the defect position: setting a threshold value N, extracting all black points, taking the points one by one, judging whether the taken black point is in an existing defect group, if the taken black point is in the existing defect group, judging the next black point, if the taken black point is in the existing defect group, calculating the distance between the black point and the nearest black point away from the black point, judging whether the distance between the two black points is smaller than the threshold value N, if the distance between the two black points is larger than the threshold value X, abandoning the black point, if the distance between the two black points is smaller than the threshold value X, judging whether the nearest black point is in the existing defect group, if the nearest black point is in the existing defect group, merging the black point into the defect group, if the nearest black point is not in the existing defect group, newly building the two black point defect groups, calculating the defect area of each defect group, sequencing, and taking the edge information of the largest area as the defect position;
(6) and (3) performing performance evaluation on the tire defect extraction model: the intersection ratio IoU is used as a judgment index for the quality of the positioning result.
2. The method for building the defect extraction model of the X-ray image of the tire based on the morphological analysis as claimed in claim 1, wherein the specific process of the step (2) is as follows:
step 2.1: adjusting the size of the tire defect image into a x b pixels, wherein a represents the length value of the image size in pixel unit, and b represents the width value of the image size in pixel unit, then dividing the tire defect image into a x pixel size, detecting for n times, and standardizing the divided image;
step 2.2: performing binarization processing on the image subjected to the standardization processing in the step 2.1, and taking the mean value of pixel values of all pixel points as a threshold value to convert the part of the image, of which the pixel values are greater than the threshold value, into black and convert the part of the image, of which the pixel values are less than the threshold value, into white;
step 2.3: and (3) performing square opening operation on the image subjected to binarization processing in the step 2.32, corroding and expanding the image, and eliminating noise and small objects in the image, wherein the specific formula is as follows:
where B is a kernel function, A is an original set, both are elements of a two-dimensional integer space Z2, $ represents an etch operation,
an expansion operation;
step 2.4: and performing expansion operation to further smooth the edge, reduce edge noise and make the boundary clearer.
3. The method for building the defect extraction model of the X-ray image of the tire based on the morphological analysis as claimed in claim 1 or 2, wherein the specific process of the step (3) is as follows:
step 3.1: carrying out classification marking on each pixel of the preprocessed image, marking white as True and black as False, and uniformly storing;
step 3.2: for each column, if the number of pixels marked as True is greater than 5%, the column is judged as a shoulder and sidewall part, the column is marked as 1, otherwise, the column is 0;
step 3.3: the boundary between the row pixel of the mark 0 and the row pixel of the mark 1 is a boundary of different portions of the tire, and the tire is divided.
4. The method for building the defect extraction model of the X-ray image of the tire based on the morphological analysis as claimed in claim 1 or 2, wherein the specific process of the step (4) is as follows:
step 4.1: taking the image preprocessed in the step (2), converting all the pixel values of the rows marked as 0 into 255 for whitening by using the mark value of each row, and only reserving the information of the tire shoulder and the tire side for subsequent detection;
step 4.2: standardizing the images, reducing the difference between the images, then carrying out binarization, taking the average value of a single-column image as a threshold value, and additionally generating a color flip graph in order to simultaneously detect various defects;
step 4.3: respectively repairing the fracture of the regular shading by utilizing closing operation and corrosion operation, eliminating the regular shading and small noise and enhancing the defects; and then combining the binarized image and the color reversed image thereof, and performing expansion operation on the combined image to remove small noise.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110991452.0A CN113538418A (en) | 2021-08-27 | 2021-08-27 | Tire X-ray image defect extraction model construction method based on morphological analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110991452.0A CN113538418A (en) | 2021-08-27 | 2021-08-27 | Tire X-ray image defect extraction model construction method based on morphological analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113538418A true CN113538418A (en) | 2021-10-22 |
Family
ID=78093001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110991452.0A Pending CN113538418A (en) | 2021-08-27 | 2021-08-27 | Tire X-ray image defect extraction model construction method based on morphological analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113538418A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114549448A (en) * | 2022-02-17 | 2022-05-27 | 中国空气动力研究与发展中心超高速空气动力研究所 | Complex multi-type defect detection and evaluation method based on infrared thermal imaging data analysis |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107437256A (en) * | 2016-05-27 | 2017-12-05 | 合肥美亚光电技术股份有限公司 | Applied to tire x-ray image passage Automated Partition Method and system |
| CN107437243A (en) * | 2017-06-19 | 2017-12-05 | 中国科学院自动化研究所 | Tire method for detecting impurities and device based on x-ray image |
| WO2018086299A1 (en) * | 2016-11-11 | 2018-05-17 | 广东电网有限责任公司清远供电局 | Image processing-based insulator defect detection method and system |
| CN109030499A (en) * | 2018-07-27 | 2018-12-18 | 江苏理工学院 | A kind of device and method preventing defect counts repeat count suitable for target defect continuous on-line detection |
| CN111523595A (en) * | 2020-04-23 | 2020-08-11 | 国网天津市电力公司 | Cable defect studying and judging method based on outlier detection algorithm |
-
2021
- 2021-08-27 CN CN202110991452.0A patent/CN113538418A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107437256A (en) * | 2016-05-27 | 2017-12-05 | 合肥美亚光电技术股份有限公司 | Applied to tire x-ray image passage Automated Partition Method and system |
| WO2018086299A1 (en) * | 2016-11-11 | 2018-05-17 | 广东电网有限责任公司清远供电局 | Image processing-based insulator defect detection method and system |
| CN107437243A (en) * | 2017-06-19 | 2017-12-05 | 中国科学院自动化研究所 | Tire method for detecting impurities and device based on x-ray image |
| CN109030499A (en) * | 2018-07-27 | 2018-12-18 | 江苏理工学院 | A kind of device and method preventing defect counts repeat count suitable for target defect continuous on-line detection |
| CN111523595A (en) * | 2020-04-23 | 2020-08-11 | 国网天津市电力公司 | Cable defect studying and judging method based on outlier detection algorithm |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114549448A (en) * | 2022-02-17 | 2022-05-27 | 中国空气动力研究与发展中心超高速空气动力研究所 | Complex multi-type defect detection and evaluation method based on infrared thermal imaging data analysis |
| CN114549448B (en) * | 2022-02-17 | 2023-08-11 | 中国空气动力研究与发展中心超高速空气动力研究所 | Complex multi-type defect detection evaluation method based on infrared thermal imaging data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111862064B (en) | Silver wire surface flaw identification method based on deep learning | |
| CN115082419B (en) | Blow-molded luggage production defect detection method | |
| CN109377485B (en) | Machine vision detection method for instant noodle packaging defects | |
| CN106960208B (en) | Method and system for automatically segmenting and identifying instrument liquid crystal number | |
| CN111179243A (en) | Small-size chip crack detection method and system based on computer vision | |
| CN103048329B (en) | A kind of road surface crack detection method based on active contour model | |
| CN109840483B (en) | Landslide crack detection and identification method and device | |
| CN114820625B (en) | Automobile top block defect detection method | |
| CN114972326A (en) | Defective product identification method for heat-shrinkable tube expanding process | |
| CN112734729B (en) | Water gauge water level line image detection method and device suitable for night light supplement condition and storage medium | |
| CN110751619A (en) | Insulator defect detection method | |
| CN115511842A (en) | Cable insulation skin damage detection method based on machine vision | |
| CN114445707A (en) | Intelligent visual fine detection method for defects of bottled water labels | |
| CN116485764A (en) | Structural surface defect identification method, system, terminal and medium | |
| CN104112123A (en) | Defect characteristic extraction and identification method of AOI system used for bullet apparent defect detection | |
| CN112508913A (en) | Cable section edge detection method based on image detection | |
| CN114882010A (en) | Surface defect detection method based on picture recognition | |
| CN113538418A (en) | Tire X-ray image defect extraction model construction method based on morphological analysis | |
| CN112200053B (en) | Form identification method integrating local features | |
| CN116152674A (en) | Dam unmanned aerial vehicle image crack intelligent recognition method based on improved U-Net model | |
| CN112101108B (en) | Left-right pass-through sign recognition method based on graph pole position characteristics | |
| CN102313740B (en) | Solar panel crack detection method | |
| CN116228687A (en) | Chip package defect detection method and device based on deep learning | |
| CN113870299A (en) | 3D printing fault detection method based on edge detection and morphological image processing | |
| CN110689538B (en) | Tunnel lining crack image detection 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 |