CN108335288A - The crater image method for detecting abnormality of view-based access control model clarity and contours extract - Google Patents
The crater image method for detecting abnormality of view-based access control model clarity and contours extract Download PDFInfo
- Publication number
- CN108335288A CN108335288A CN201810047308.XA CN201810047308A CN108335288A CN 108335288 A CN108335288 A CN 108335288A CN 201810047308 A CN201810047308 A CN 201810047308A CN 108335288 A CN108335288 A CN 108335288A
- Authority
- CN
- China
- Prior art keywords
- clarity
- image
- molten bath
- profile
- intermediate frequency
- 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.)
- Withdrawn
Links
- 239000000284 extract Substances 0.000 title claims abstract description 13
- 238000000034 method Methods 0.000 title claims description 18
- 230000005856 abnormality Effects 0.000 title claims description 5
- 230000004438 eyesight Effects 0.000 claims abstract description 16
- 230000002159 abnormal effect Effects 0.000 claims abstract description 13
- 238000000605 extraction Methods 0.000 claims abstract description 7
- 238000001514 detection method Methods 0.000 claims abstract description 6
- 238000013461 design Methods 0.000 claims description 9
- 230000000007 visual effect Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 5
- 230000008447 perception Effects 0.000 claims description 5
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 2
- ALSKYCOJJPXPFS-BBRMVZONSA-N dihydro-beta-erythroidine Chemical compound C([C@@H](C[C@@]123)OC)C=C1CCN2CCC1=C3CC(=O)OC1 ALSKYCOJJPXPFS-BBRMVZONSA-N 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 claims description 2
- 238000000638 solvent extraction Methods 0.000 claims description 2
- 230000003595 spectral effect Effects 0.000 claims description 2
- 238000001228 spectrum Methods 0.000 claims description 2
- 238000013450 outlier detection Methods 0.000 claims 3
- 239000004744 fabric Substances 0.000 claims 2
- 230000016776 visual perception Effects 0.000 abstract description 2
- 238000003466 welding Methods 0.000 description 11
- 230000000694 effects Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 208000022846 Abnormality of vision Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
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
- G06T7/0006—Industrial image inspection using a design-rule based approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- 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
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30152—Solder
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The present invention proposes a kind of variation of the width of the value and profile according to vision definition to differentiate the detection method of the affiliated abnormal class of the crater image；The present invention is from image vision angle, in conjunction with clarity and the computation performance of contours extract, first with clarity operator just classify, is classified again to weldering speed in conjunction with profile width, reduce operation time to a certain extent.And the used double light path visual perception device of the present invention, it is effective to improve vision profile and clarity extraction accuracy.
Description
Technical field
The invention belongs to molten bath visual fields, and in particular to the double light path vision sensing equipment and one kind of FPGA module triggering
The crater image method for detecting abnormality that clarity and profile collaboration judge.
Background technology
Welding is important one of the processing technology of manufacturing industry, is widely used in material processing and structure manufacture.
Skilled welder can be incorporated experience by observation weld pool surface information and prejudge and control to weldquality, with intelligence machine
People's welding gradually replaces artificial weldering, and the accurate sensing of weld pool resonance is the important prerequisite of welding process intelligentized control method, needs to build
Vertical reliable and stable visual sensing system ensures the crater image information obtained as far as possible comprehensively, accurately.
Molten bath two-dimensional visual sensing mainly carries out image sensing acquisition by vision-sensing method to molten bath, at image
Reason and feature extraction analyze the relationship between characteristics of image and welding quality and establish Controlling model.With the continuous depth of research
Enter, researcher the characteristics of molten bath in different materials, different welding methods in conjunction with rational visual sensing system is established, in molten bath figure
As method for sensing, image processing algorithm, characteristics of image define and extracting method and the control of the welding quality of view-based access control model etc.
Achieve greater advance.The accurate sensing of weld pool resonance is the important prerequisite of welding process intelligentized control method, needs to establish and stablize
Reliable visual sensing system ensures the crater image information obtained as far as possible comprehensively, accurately.If directly utilizing visual sensing
Device absorbs the crater image in welding process, and strong arclight will make the photosensitive primitive of CCD reach light saturation, and weld pool resonance is several
It is fallen into oblivion completely by arclight.
To weaken the influence of arclight, this patent using molten bath vision and technological parameter collaborative perception device, for based on
Clarity and the vision of contours extract calculate demand, are designed like scheme.Stronger boundary is needed due to calculating molten bath profile
Contrast needs band logical height to expose；It calculates weld pool surface vision definition to need to inhibit arc light, needs the low exposure of high pass, therefore this
Molten bath light beam is divided into the double light path vision sensing equipment of 850nm high passes and 650nm band logicals using Amici prism by patent.So may be used
The weld pool surface information on the molten bath boundary for the high contrast that gets both and the interference of low arc light improves follow-up molten bath contours extract and clear
Spend computational accuracy.After obtaining image, influenced to reduce various random noises and pattern distortion, this patent is stretched using intermediate frequency
Method again pre-processes image, inhibits useless noise information, improves picture quality, is carried convenient for the calculating and profile of clarity
It takes.
Invention content
The present invention is based on the crater image method for detecting abnormality of vision definition and contours extract, include the following steps：
Step 1：Determine the abnormal class that crater image is likely to occur；
Step 2：Design technology parameter collaborative perception FPGA module, according to different visions calculate demand, design specific aim at
Image space case；
Step 3：The light path acquisition positive sample design step 2 and all kinds of negative samples；
Step 4：Intermediate frequency stretch processing is carried out to all crater image samples of acquisition and calculates its definition values, according to knot
Fruit is distributed, and setting divides all kinds of threshold values organized extremely, determines current parameters exception, voltage parameter is abnormal and protection gas parameter is different
Normal clarity range；
Step 5：It is special that normal group of the electrical parameter in step 4 acquired results in the case of consistent with protection gas parameter is subjected to profile
The extraction of reference breath carries out data analysis to obtain the classification results of different weldering speed grades, realizes the inspection of molten bath weldering speed exception
It surveys.
Further, demand is calculated according to different visions described in step 2, design specific aim is imaged scheme, specific mistake
Cheng Wei：It such as calculates molten bath profile and needs stronger boundary contrast, the exposure of band logical height can be used；Calculate weld pool surface optical clarity
Degree needs to inhibit arc light, and the low exposure of high pass can be used；Therefore molten bath light beam is divided into two bundles using Amici prism, a branch of use
850nm high passes, a branch of use 650nm band logicals, form double Spectral Visual sensing devices；And ensure that double spectrum samples synchronize.
Further, all crater image samples to acquisition described in step 4 carry out intermediate frequency stretch processing and calculate
Its definition values, includes the following steps：
Step 3-1：The pretreatment of intermediate frequency stretching is carried out to the crater image that is obtained, is extracted more important thin in image
Save component；
It is as follows that intermediate frequency component stretches formula：
In formula, H (x, y) is the image frequency domain after stretching, and D (x, y) is the frequency domain of original input image, dlIt is stretched for intermediate frequency
Initial frequency, dhBe intermediate frequency stretch by frequency, m, n are the exponent number of filter；
Step 3-2：Optional step 3-1 clarity operator calculates the clarity of image；
Step 3-3：Classification results delimited manually, find definition values and play corresponding class relations；
The value for calculating separately above-mentioned clarity operator, manually sets the threshold value of all kinds of abnormal results, show that energy gradient is calculated
The clarity evaluation operator result of the differentiation accuracy rate highest of son, energy gradient is as follows：
The image that image row direction is added with the difference of the gray value of neighbor pixel on column direction it is clear
Clear angle value, in formula, I (x, y) is gray values of the image I at (x, y), and q (I) is the output result definition values of the function.
Further, positive sample and all kinds of negative samples are acquired under the conditions of double light path described in step 3, specifically include electricity
Throat floater, electric voltage exception protect gas exception and weldering speed abnormal.
Further, described in step 5 by electrical parameter in step 4 acquired results with protection gas parameter it is consistent in the case of just
Often group carry out contour feature information extraction the specific steps are：
Step 5-1：The ROI in molten bath is arranged；
First, big ROI is set and removes extra background area；Secondly, according to the overall permanence in molten bath, i.e., head brightness compared with
High and be easy to be interfered by arc light, half resolidified region brightness of tail portion is relatively low and interferes less, can be classified as ROI1 and ROI2；Root
According to the imaging characteristic on head and tail region, small scale gray scale stretching is carried out respectively, and gray scale stretching formula is as follows：
In formula, small scale is stretchedValue it is smaller can remove highlight regions, for large scale stretchValue it is larger, the contrast of tail portion entirety can be enhanced；
Step 5-2：The partitioning pretreatment in molten bath；
Gaussian filtering and opening operation are carried out to weaken the interference of edge arc light to the image that gray scale stretching in ROI1 is crossed, then
Low threshold edge detection is carried out with Canny operators and filters out too small edge contour；Since the interference in the regions ROI2 is smaller, gray scale
Distribution is relatively uniform, therefore directly carries out Da-Jin algorithm Threshold segmentation to the regions ROI2 and carry out high threshold with Canny operators
Edge detection；
Step 5-3：Profile merges and connection；
ROI1 and the ROI2 edge contour detected are merged, and 8 neighborhoods and 16 neighborhoods of image are scanned for,
The fracture of profile Small and Medium Sized is connected, the detection of profile endpoint is carried out for the fracture of large scale later, abutting end point is carried out
Connection finally obtains the profile of molten bath connection.
Beneficial effects of the present invention are：This patent is from image vision angle, in conjunction with clarity and contours extract
Computation performance first with clarity operator just classify, be classified again to weldering speed in conjunction with profile width, to a certain extent
Reduce operation time.And the used double light path visual perception device of this patent, effective raising vision profile and clarity carry
Take precision.
Description of the drawings
Fig. 1 is synchronous 850 high passes of present invention triggering, 650 band logical images；
Fig. 2 is the classification results of clarity of the present invention；
Fig. 3 is the extraction of molten bath profile of the present invention；
Fig. 4 is the classification of molten bath weldering speed of the present invention.
Specific implementation mode
Refering to fig. 1, steps are as follows for the specific implementation of 2,3,4 this patents：
Step 1, design technology parameter collaborative perception FPGA module builds double light path molten bath visual sensor acquisition molten bath figure
Picture；
Step 2, frequency domain is transformed by Fourier transformation to 850 high-pass images acquired, carries out frequency domain details increasing
By force, and using Fourier inversion by image time domain is gone back to from frequency domain again, obtains the result figure after intermediate frequency stretches；
Step 3, various clarity operators are selected to evaluate the image after stretching into line definition, and according to experiment sample institute
Belong to classification to classify, finds and sort out the best clarity operator of effect；
Step 4, energy gradient operator classification effect is best in step 3, as shown in Fig. 2, energy gradient operator can be by Ar
=0 group, too low group of electric current and brownout group these abnormal phenomenon are classified, and are divided according to threshold value is manually set, protection
The definition values q of gas exception>5, current anomaly：q<0.6, low-voltage group：0.6<q<2, and electrical parameter and protection gas parameter it is normal
Group：2<q<5.And the recognition accuracy of each part mentioned above is respectively to protect gas abnormal：90.0%；Current anomaly：98.44%；
Electric voltage exception：91.33%, electrical parameter and protection gas parameter are normal：98.68%.Overall accuracy reaches：95.23%；
Step 5, when carrying out real-time abnormality detection with test image, if the value for clarity q occur is more than 5 or the feelings less than 2
Condition then suspends welding and checks corresponding exception, if definition values 2<q<5, then contours extract is carried out, and further detection is
The counties Fou Chu weldering speed abnormal phenomenon；
Step 6, according to the characteristic information in obtained molten bath contours extract molten bath, such as：Pool width, molten bath length, molten bath
Afterwards towing angle, molten bath length-width ratio.It can be divided by hard -threshold according to the width information extracted, distinguish same welding procedure
And same welding electrical parameters, weldering speed grade under conditions of camera angle is constant.The higher pool width of weldering speed is smaller, molten bath
Length is longer, otherwise the lower pool width of weldering speed is bigger, and molten bath length is smaller.By carrying out respectively obtaining difference to data
The hard segmentation threshold of weldering speed grade, from th1 to th6.It is 2mm/s that its middle grade a pair, which answers weldering speed, grade and correspond to weldering speed and be
4mm/s, it is 6mm/s that grade three, which corresponds to weldering speed, and it is 8mm/s that grade four, which corresponds to weldering speed, and it is 12mm/s, grade that grade five, which corresponds to weldering speed,
Six correspond to the 16mm/s of weldering speed, as shown in Figure 4.
Claims (5)
1. the crater image method for detecting abnormality of view-based access control model clarity and contours extract, which is characterized in that include the following steps：
Step 1：Determine the abnormal class that crater image is likely to occur；
Step 2：Design technology parameter collaborative perception FPGA module calculates demand, design specific aim imaging side according to different visions
Case；
Step 3：The light path acquisition positive sample design step 2 and all kinds of negative samples；
Step 4：Intermediate frequency stretch processing is carried out to all crater image samples of acquisition and calculates its definition values, according to result point
Cloth, setting divide all kinds of threshold values organized extremely, determine current parameters exception, voltage parameter is abnormal and protects gas abnormal parameters
Clarity range；
Step 5：Normal group of the electrical parameter in step 4 acquired results in the case of consistent with protection gas parameter is subjected to contour feature letter
The extraction of breath carries out data analysis to obtain the classification results of different weldering speed grades, realizes the detection of molten bath weldering speed exception.
2. molten bath vision according to claim 1 and technological parameter collaborative perception device, which is characterized in that described in step 2
Calculate demand according to different visions, design specific aim is imaged scheme, and detailed process is：It is stronger such as to calculate molten bath profile needs
The exposure of band logical height can be used in boundary contrast；It calculates weld pool surface vision definition to need to inhibit arc light, the low exposure of high pass can be used
Light；Therefore molten bath light beam is divided into two bundles using Amici prism, it is a branch of to use 850nm high passes, is a branch of using 650nm band logicals, shape
Spectral Visual sensing device in pairs；And ensure that double spectrum samples synchronize.
3. the molten bath Outlier Detection Algorithm of view-based access control model clarity according to claim 1, which is characterized in that step 4 institute
All crater image samples to acquisition stated carry out intermediate frequency stretch processing and calculate its definition values, include the following steps：
Step 3-1：The pretreatment that intermediate frequency stretching is carried out to the crater image obtained, extracts details more important in image point
Amount；
It is as follows that intermediate frequency component stretches formula：
In formula, H (x, y) is the image frequency domain after stretching, and D (x, y) is the frequency domain of original input image, dlThe starting stretched for intermediate frequency
Frequency, dhBe intermediate frequency stretch by frequency, m, n are the exponent number of filter；
Step 3-2：Optional step 3-1 clarity operator calculates the clarity of image；
Step 3-3：Classification results delimited manually, find definition values and play corresponding class relations；
The value for calculating separately above-mentioned clarity operator, manually sets the threshold value of all kinds of abnormal results, obtains energy gradient operator
Differentiate that accuracy rate highest, the clarity evaluation operator result of energy gradient are as follows：
The clarity for the image that image row direction is added with the difference of the gray value of neighbor pixel on column direction
It is worth, in formula, I (x, y) is gray values of the image I at (x, y), and q (I) is the output result definition values of the function.
4. the molten bath Outlier Detection Algorithm according to claim 1 based on clarity and contours extract, which is characterized in that
Positive sample and all kinds of negative samples are acquired under the conditions of double light path described in step 3, specifically includes current anomaly, and electric voltage exception is protected
It protects gas exception and weldering speed is abnormal.
5. the molten bath Outlier Detection Algorithm according to claim 1 based on clarity and contours extract, which is characterized in that
Normal group of the electrical parameter in step 4 acquired results in the case of consistent with protection gas parameter is subjected to contour feature letter described in step 5
The extraction of breath the specific steps are：
Step 5-1：The ROI in molten bath is arranged；
First, big ROI is set and removes extra background area；Secondly, according to the overall permanence in molten bath, i.e., head brightness it is higher and
It is easy to be interfered by arc light, half resolidified region brightness of tail portion is relatively low and interferes less, can be classified as ROI1 and ROI2；According to head
The imaging characteristic in portion and tail region, carries out small scale gray scale stretching respectively, and gray scale stretching formula is as follows：
In formula, small scale is stretchedValue it is smaller can remove highlight regions, for large scale stretch's
It is worth larger, the contrast of tail portion entirety can be enhanced；
Step 5-2：The partitioning pretreatment in molten bath；
Gaussian filtering and opening operation are carried out to weaken the interference of edge arc light to the image that gray scale stretching in ROI1 is crossed, then used
Canny operators carry out Low threshold edge detection and filter out too small edge contour；Since the interference in the regions ROI2 is smaller, gray scale point
Cloth is relatively uniform, therefore directly carries out Da-Jin algorithm Threshold segmentation to the regions ROI2 and carry out high threshold side with Canny operators
Edge detects；
Step 5-3：Profile merges and connection；
ROI1 and the ROI2 edge contour detected are merged, and 8 neighborhoods and 16 neighborhoods of image are scanned for, is connected
The fracture of profile Small and Medium Sized later carries out the fracture of large scale the detection of profile endpoint, abutting end point is attached,
Finally obtain the profile of molten bath connection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810047308.XA CN108335288A (en) | 2018-01-18 | 2018-01-18 | The crater image method for detecting abnormality of view-based access control model clarity and contours extract |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810047308.XA CN108335288A (en) | 2018-01-18 | 2018-01-18 | The crater image method for detecting abnormality of view-based access control model clarity and contours extract |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108335288A true CN108335288A (en) | 2018-07-27 |
Family
ID=62925194
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810047308.XA Withdrawn CN108335288A (en) | 2018-01-18 | 2018-01-18 | The crater image method for detecting abnormality of view-based access control model clarity and contours extract |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108335288A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111257348A (en) * | 2020-03-27 | 2020-06-09 | 河海大学常州校区 | LED light guide plate defect detection method based on machine vision |
| CN111932572A (en) * | 2020-10-12 | 2020-11-13 | 南京知谱光电科技有限公司 | Aluminum alloy molten pool contour extraction method |
| CN112756783A (en) * | 2021-01-06 | 2021-05-07 | 广东工业大学 | Method for determining welding keyhole offset in laser welding tracking process |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106112318A (en) * | 2016-07-13 | 2016-11-16 | 桂林航天工业学院 | The online welding seam tracking method of a kind of view-based access control model and system |
| CN107363403A (en) * | 2017-09-09 | 2017-11-21 | 深圳市华天世纪激光科技有限公司 | A kind of laser welding system based on CCD vision monitorings |
| CN108320280A (en) * | 2018-01-16 | 2018-07-24 | 南京理工大学 | The crater image method for detecting abnormality of view-based access control model clarity and contours extract |
-
2018
- 2018-01-18 CN CN201810047308.XA patent/CN108335288A/en not_active Withdrawn
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106112318A (en) * | 2016-07-13 | 2016-11-16 | 桂林航天工业学院 | The online welding seam tracking method of a kind of view-based access control model and system |
| CN107363403A (en) * | 2017-09-09 | 2017-11-21 | 深圳市华天世纪激光科技有限公司 | A kind of laser welding system based on CCD vision monitorings |
| CN108320280A (en) * | 2018-01-16 | 2018-07-24 | 南京理工大学 | The crater image method for detecting abnormality of view-based access control model clarity and contours extract |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111257348A (en) * | 2020-03-27 | 2020-06-09 | 河海大学常州校区 | LED light guide plate defect detection method based on machine vision |
| CN111932572A (en) * | 2020-10-12 | 2020-11-13 | 南京知谱光电科技有限公司 | Aluminum alloy molten pool contour extraction method |
| CN112756783A (en) * | 2021-01-06 | 2021-05-07 | 广东工业大学 | Method for determining welding keyhole offset in laser welding tracking process |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108320280A (en) | The crater image method for detecting abnormality of view-based access control model clarity and contours extract | |
| CN112630222B (en) | Mobile phone cover plate glass defect detection method based on machine vision | |
| CN107808378B (en) | Method for detecting potential defects of complex-structure casting based on vertical longitudinal and transverse line profile features | |
| Putzu et al. | White blood cells identification and counting from microscopic blood images | |
| CN109685766A (en) | A kind of Fabric Defect detection method based on region fusion feature | |
| Patel et al. | Automatic segmentation and yield measurement of fruit using shape analysis | |
| CN104574353B (en) | The surface defect decision method of view-based access control model conspicuousness | |
| CN107220649A (en) | A kind of plain color cloth defects detection and sorting technique | |
| Dima et al. | Automatic segmentation and skeletonization of neurons from confocal microscopy images based on the 3-D wavelet transform | |
| CN109993099A (en) | A kind of lane line drawing recognition methods based on machine vision | |
| CN108022233A (en) | A kind of edge of work extracting method based on modified Canny operators | |
| CN109816644A (en) | A kind of bearing defect automatic checkout system based on multi-angle light source image | |
| CN108961251A (en) | A kind of raw cotton fault and defects inspecting and recognition methods and system | |
| WO2013148566A1 (en) | Image blur detection | |
| CN108335288A (en) | The crater image method for detecting abnormality of view-based access control model clarity and contours extract | |
| CN107610104A (en) | Crack detecting method at a kind of elevator compensation chain R based on machine vision | |
| CN111353993A (en) | Thread angle measuring method based on machine vision | |
| WO2021109011A1 (en) | Intelligent capacitor internal defect detection method based on ultrasound image | |
| Celik et al. | Fabric defect detection using linear filtering and morphological operations | |
| Feng et al. | A separating method of adjacent apples based on machine vision and chain code information | |
| CN113435460A (en) | Method for identifying brilliant particle limestone image | |
| Kiruthika et al. | Matching of different rice grains using digital image processing | |
| CN110096980A (en) | Character machining identifying system | |
| CN109961432A (en) | A kind of detection method and system of filter cloth breakage | |
| CN115345876A (en) | Bolt thread defect detection method based on ultrasonic image |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180727 |
|
| WW01 | Invention patent application withdrawn after publication |