CN106600593A - Aluminum ceramic ball surface detect detection method - Google Patents
Aluminum ceramic ball surface detect detection method Download PDFInfo
- Publication number
- CN106600593A CN106600593A CN201611180223.6A CN201611180223A CN106600593A CN 106600593 A CN106600593 A CN 106600593A CN 201611180223 A CN201611180223 A CN 201611180223A CN 106600593 A CN106600593 A CN 106600593A
- Authority
- CN
- China
- Prior art keywords
- image
- porcelain ball
- aluminum porcelain
- carried out
- middle aluminum
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 title claims abstract description 74
- 229910052782 aluminium Inorganic materials 0.000 title claims abstract description 74
- 238000001514 detection method Methods 0.000 title claims abstract description 26
- 239000000919 ceramic Substances 0.000 title abstract 6
- 238000000034 method Methods 0.000 claims abstract description 27
- 238000001914 filtration Methods 0.000 claims abstract description 23
- 230000003287 optical effect Effects 0.000 claims abstract description 23
- 230000007547 defect Effects 0.000 claims abstract description 22
- 238000003709 image segmentation Methods 0.000 claims abstract description 5
- 238000012216 screening Methods 0.000 claims abstract description 4
- 229910052573 porcelain Inorganic materials 0.000 claims description 69
- 238000009499 grossing Methods 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000009795 derivation Methods 0.000 claims description 7
- 230000033001 locomotion Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 238000004321 preservation Methods 0.000 claims description 3
- 238000012876 topography Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 abstract description 2
- 230000014759 maintenance of location Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 4
- 239000000126 substance Substances 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 208000035475 disorder Diseases 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 210000001835 viscera Anatomy 0.000 description 2
- 208000013668 Facial cleft Diseases 0.000 description 1
- 235000008331 Pinus X rigitaeda Nutrition 0.000 description 1
- 235000011613 Pinus brutia Nutrition 0.000 description 1
- 241000018646 Pinus brutia Species 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 239000003513 alkali Substances 0.000 description 1
- 208000003464 asthenopia Diseases 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000003054 catalyst Substances 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 239000003960 organic solvent Substances 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
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
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G06T5/73—
-
- G06T5/90—
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2201/00—Features of devices classified in G01N21/00
- G01N2201/10—Scanning
- G01N2201/102—Video camera
Abstract
The invention relates to an aluminum ceramic ball surface detect detection method. The method comprises steps that optical images of an aluminum ceramic ball surface are acquired; gray transform for the optical images is carried out; a linear smooth filter is constructed to filter the binary images, and high frequency components and sharpening details are removed; a high contrast retention algorithm is employed to enhance filtering images; first image segmentation for the filtering images is carried through employing a threshold edge descriptor to acquire the preliminary defect information of the aluminum ceramic ball surface; statistics classification is carried out through taking areas as characteristics, and screening is carried out; screened regions are expanded and merged into a domain, and independent region segmentation is carried out; linear smooth operation for the local initial images acquired in the previous step is carried out for another time, precise image segmentation is carried out through utilizing a dynamic threshold method, and the precise defect information of the aluminum ceramic ball surface is acquired; area statistics is carried out, pixel points are calculated, if the pixel points are greater than 0, a corresponding aluminum ceramic ball is determined to be disqualified. The method is advantaged in that detection accuracy and an automation degree are improved, and detection efficiency is improved.
Description
Technical field
The present invention relates to a kind of middle aluminum porcelain ball detection method of surface flaw.
Background technology
Porcelain ball is widely used in the industries such as oil, chemical industry, chemical fertilizer, natural gas and environmental protection, covering as catalyst in reactor
Lid backing material and tower packing.It has high temperature high voltage resistant, and water absorption rate is low, the characteristics of stable chemical performance.Be amenable to acid, alkali and
The corrosion of other organic solvents, and it is amenable to the temperature change occurred in production process.For aluminum porcelain ball in each size, in order to protect
Card Product Usability, it is necessary to which micro- defect (such as fine crack, micro- breakage) on its surface is detected.The table of current such part
Face defect detection relies primarily on human eye visual detection, due to examinate person's technology, experience, working environment and asthenopia etc.
Affect, it is easy to flase drop and missing inspection occur, and manually estimate low efficiency, shortage accuracy and standardization, stability and reliability
Property is poor.In order to solve manually to estimate, work difficulty is big, efficiency is low, the difficult problem that loss is high, needs to introduce a kind of inspection automatically
Survey technology, had not only reduced human cost but also can realize the strict control to product quality.
Current computer vision technique relative maturity, with noncontact, speed fast, high precision, strong antijamming capability etc.
Plurality of advantages, if computer vision technique is introduced in small size in aluminum porcelain ball end face defect detection, is possible to full well
It is to reliability and the requirement of sensitivity and easy to maintenance for foot.
The content of the invention
In view of this, it is an object of the invention to provide a kind of middle aluminum porcelain ball detection method of surface flaw, improves detection
Accuracy and automaticity, improve detection efficiency.
For achieving the above object, the present invention is adopted the following technical scheme that：A kind of middle aluminum porcelain ball detection method of surface flaw, its
It is characterised by, comprises the following steps：
Step S1：The optical imagery on aluminum porcelain ball surface in collection；
Step S2：Greyscale transformation is carried out to the optical imagery, bianry image is obtained；
Step S3：Construction linear smoothing filter is filtered to the bianry image, removes radio-frequency component and sharpens thin
Section, obtains filtering image；
Step S4：Retaining algorithm using high contrast strengthens the filtering image, highlights middle aluminum porcelain ball surface and splits
Contrast between seam and background；
Step S5：Image segmentation first is carried out to the filtering image using threshold skirt descriptive method and obtains some regions,
With reference to morphological image computing wiping out background, the defect information on preliminary middle aluminum porcelain ball surface is obtained；
Step S6：Statistical classification is carried out for some regions are characterized with area, area value M1 and M2, screening is set
Go out region of the area value between M1 and M2；
Step S7：The region setting coefficient of expansion to filtering out expands to corresponding image, to the image after expansion
Domain is merged into, using to being compared to differ from method, region is individually split, obtained with the characteristics of image identical local after expansion just
Beginning image；
Step S8：The local and initial image that step S7 is obtained carries out again linear smoothing computing and is filtered, will again
Filtered imagery exploitation dynamic thresholding method carries out image and precisely splits, and obtains the defect information on accurately middle aluminum porcelain ball surface；
Step S9：Area statistics are carried out to the defect information on the accurate middle aluminum porcelain ball surface, its pixel is calculated, if
Pixel is more than 0, then judge that aluminum porcelain ball is unqualified in correspondence.
Further, in step S1, gathering the device of the optical imagery includes conveyer belt and for aluminum in rotation
The grabbing device of porcelain ball, the grabbing device is square with transmission Tape movement on a moving belt；It is additionally provided with directly over the conveyer belt
Some camera bellows with light source and the industrial camera for obtaining camera bellows internal image, the camera bellows is on the direction of transmission tape travel
Offer the opening passed through for middle aluminum porcelain ball；Unqualified collection frame is provided with immediately below the camera bellows with light source, it is described
Competent collection frame is provided with below conveyer belt tail end；Also include controller, the controller and the industrial camera, crawl dress
The motor connection of conveyer belt is put and controls, for receiving optical imagery, the control grabbing device pine that industrial camera is collected
Aluminum porcelain ball and the motion of conveyer belt is controlled in opening or clamping；The controller is connected with host computer, by optical image transmission to upper
Position machine simultaneously receives the control command of host computer.
Further, the light source is combination strip source, the week side of boss being arranged at the top of camera bellows；The inwall of the camera bellows sets
Diffusing panel is equipped with, it is provided with camera opening at the top of camera bellows, the camera opening is arranged above industrial camera.
Further, in step S3, the linear smoothing filter adopts local mean value computing, each pixel grey scale
It is worth the weights displacement with all values in its local neighborhood, computing formula is：
Wherein, M is the pixel sum in neighborhood N, and h [i, j] is the gray value of Filtered Picture vegetarian refreshments [i, j], f [k, l]
It is the gray value of the neighborhood territory pixel point for filtering preceding pixel point [k, l].
Further, the particular content of step S4 is as follows：
Step S41：Filtering image is obscured using gaussian kernel, the fuzzy close template of the 3*3 of selection is：
The formula of wherein gaussian kernel approximation computation is：
Step S42：Convolution is carried out to optical imagery using weight matrix, broad image is obtained；
Step S43：Original image is subtracted each other with broad image, high-pass image is obtained；
Step S44：Original image and high-pass image are carried out into Dynamic Weights to be added, expression formula is：
AdImg=BlurImg+Amount* (RawImg-BlurImg+127)
Wherein：To strengthen image, BlurImg is broad image to AdImg, and RawImg-BlurImg+127 is high-pass image,
RawImg is original image, and Amount is weights, and the span of weights is [0,1].
Further, in step S5, the particular content of threshold skirt descriptive method is as follows：
Step S51：The estimated value T1 and T2 of an initial approximation threshold value are selected, wherein, T1 is less than T2；
Step S52：Using estimated value T1 and T2 image according to gray value whether less than T1, more than T2 and between T1 and
It is divided into three groups of region R between T21、R2And R3；
Step S53：Combined region R1And R2, image is divided into region L1 and L2 again；
Step S54：Using method of derivation to the secondary derivation of region L1 and L2 region intersection, as a result preserve in the matrix form；
Step S55：T1 ' and T2 ' are once again set up for the image after above-mentioned preservation, all areas of above-mentioned condition are met
The boundary information in domain is preserved in the matrix form.
Further, in step S8, the particular content of dynamic thresholding method is as follows：
Step S81：Filtered image point set threshold value g { e } will be denoted as again, the threshold value of the point set of topography will be denoted as
G { o }, and set reference difference t；
Step S82：Numerical value in g { e } is individually subtracted into reference difference t, and is compared with g { o }, if meeting g { o }<g{e}-
T, then leave the point set on the image, otherwise rejects, and finally obtains the middle aluminum porcelain ball surface defect information after accurate filtering, and
It is marked.
The present invention has the advantages that compared with prior art：The present invention is unrestrained using computer vision and combined light source
The mode that light technology combines is penetrated, the defects detection on aluminum porcelain ball surface and screening in each size is realized, in particularly solving
Aluminum porcelain ball surface fine cracks detection difficult, in addition the present invention can realize Optimum Design and solve algorithms most in use calculating
The problems such as amount is big, detection speed is slow, the surface defect information of aluminum porcelain ball in can truly reflecting, and can accurately judge detection object
It is whether qualified, and data volume is little, detection efficiency is high, with very strong practicality and wide application prospect.
Description of the drawings
Fig. 1 is method of the present invention flow chart.
Fig. 2 is the schematic device that one embodiment of the invention gathers optical imagery.
Fig. 3 is the camera bellows of one embodiment of the invention and industrial camera partial schematic diagram.
Fig. 4 is the A-A sectional views of Fig. 3.
Fig. 5 is the B-B sectional views of Fig. 3.
Fig. 6 is the C-C sectional views of Fig. 3.
In figure：1- conveyer belts；2- grabbing devices；Aluminum porcelain ball in 3-；4- camera bellows；5- industrial cameras；6- controllers；7- is upper
Machine；8- casings；The unqualified collection frames of 9-；10- competent collection frames；41- combines strip source；42- diffusing panels；43- camera openings；
44- is open.
Specific embodiment
Below in conjunction with the accompanying drawings and embodiment the present invention will be further described.
Fig. 1 is refer to, the present invention provides a kind of middle aluminum porcelain ball detection method of surface flaw, it is characterised in that including following
Step：
Step S1：The optical imagery on aluminum porcelain ball surface in collection；
Fig. 2 to Fig. 6 is refer to, gathering the device of the optical imagery includes conveyer belt 1 and for aluminum porcelain ball 3 in rotation
Grabbing device 2, the grabbing device 2 is moved in the top of conveyer belt 1 with conveyer belt 1；If being additionally provided with directly over the conveyer belt
The dry camera bellows 4 with light source and the industrial camera 5 for obtaining the internal image of camera bellows 4, the side that the camera bellows 4 advances in conveyer belt 1
The opening 44 passed through for middle aluminum porcelain ball 3 is offered upwards；While conveyer belt 1 is moved, middle aluminum porcelain ball 3 is with grabbing device
2 sequentially enter in camera bellows, the optical imagery on the surface of aluminum porcelain ball 3 in being obtained by industrial camera 5；Before often entering next camera bellows, grab
Take device 2 to turn an angle with disorder of internal organs aluminum porcelain ball 3, the angle for rotating every time is determined by the number of camera bellows, if guarantee after
After all of camera bellows, middle aluminum porcelain ball have rotated in the same plane 360 °, such as, in the present embodiment, be provided with 6 secretly
Case, then every time middle aluminum porcelain ball rotates 60 °.
Also include controller 6, the controller 6 and the industrial camera 5, grabbing device 2 and the control motion of conveyer belt 1
Motor connection, for receiving during the optical imagery, control grabbing device 2 that industrial camera 5 collects unclamps or clamp aluminum porcelain ball simultaneously
The motion of control conveyer belt 1；The controller 6 is connected with host computer 7, by optical image transmission is to host computer 7 and receives upper
The control command of machine.The underface of the camera bellows 4 with light source is provided with unqualified collection frame 9, under the tail end of the conveyer belt 1
Side is provided with competent collection frame 10；In the initiating terminal of conveyer belt 1, the lower section for aluminum porcelain ball in storage is additionally provided with opening
Casing 8.
In the present embodiment, host computer is computer, after computer receives the optical imagery that controller is transmitted,
The Qualification of corresponding middle aluminum porcelain ball is judged according to following step S2 to step S9, if aluminum porcelain ball is unqualified in judging, is calculated
Machine sends the control command for unclamping corresponding grabbing device to controller, then middle aluminum porcelain ball falls to the unqualified collection frame of lower section,
If aluminum porcelain ball is qualified in judging, computer sends what the order of conveyer belt and grabbing device rotated with disorder of internal organs aluminum porcelain ball
Order, aluminum porcelain ball enters next camera bellows in order, after middle aluminum porcelain ball is after all camera bellows, middle aluminum porcelain ball overall acceptability, control
Device control grabbing device aluminum porcelain ball in transmission end of tape unclamps is set up another and is fallen in competent collection frame.
In the present embodiment, the light source is combination strip source 41, is arranged at the week side of boss at the top of camera bellows 4；The camera bellows 4
Inwall be provided with diffusing panel 42, the top of camera bellows 4 is provided with camera opening 43, and the camera opening 43 is arranged above work
Industry camera 5；Preferably, in order to avoid direct light forms strong reflective, combination strip source 41 according to aluminum porcelain ball surface in irradiation
Incline certain angle laterally when mounted, light irradiation on diffusing panel, Jing diffuse-reflectance direct irradiation on middle aluminum porcelain ball surface,
The shade that can not only be prevented effectively from during illumination, while strong reflection can be prevented effectively from, so as to obtain clearly middle aluminum porcelain ball surface
The image of rift defect.
Step S2：Greyscale transformation is carried out to the optical imagery, bianry image is obtained；
Step S3：Construction linear smoothing filter is filtered to the bianry image, removes radio-frequency component and sharpens thin
Section, obtains filtering image；The linear smoothing filter adopts local mean value computing, each grey scale pixel value its local neighborhood
The weights of interior all values are replaced, and computing formula is：
Wherein, M is the pixel sum in neighborhood N, and h [i, j] is the gray value of Filtered Picture vegetarian refreshments [i, j], f [k, l]
It is the gray value of the neighborhood territory pixel point for filtering preceding pixel point [k, l]；For example 3 × 3 neighborhoods are taken at pixel [i, j] place, obtained
Linear smoothing filter can remove the sharpening details in radio-frequency component and image, and the present invention adopts 9 × 9 smooth filter
Ripple device, its Weight template is as follows：
Step S4：Retaining algorithm using high contrast strengthens the filtering image, to highlight middle aluminum porcelain ball table
Facial cleft is stitched and the contrast between background, is easy to follow-up dividing processing, and specific method is as follows；
Step S41：Filtering image is obscured using gaussian kernel, according to existing situation, selects the weight of 3*3
(blur radius) can obtain good effect, and the fuzzy close template of the 3*3 of selection is：
The formula of wherein gaussian kernel approximation computation is：
Step S42：Convolution is carried out to optical imagery using weight matrix, broad image is obtained；
Step S43：Original image is subtracted each other with broad image, high-pass image is obtained, that is, retains perfect edge, in this example
As exist where surface defect；
Step S44：Original image and high-pass image are carried out into Dynamic Weights to be added, expression formula is：
AdImg=BlurI mg+Amount* (RawImg-BlurImg+127)
Wherein：To strengthen image, BlurImg is broad image to AdImg, and RawImg-BlurImg+127 is high-pass image,
RawImg is original image, and Amount is weights, and the span of weights is [0,1].
Step S5：Image segmentation first is carried out to the filtering image using threshold skirt descriptive method and obtains some regions,
With reference to morphological image computing wiping out background, the defect information on preliminary middle aluminum porcelain ball surface is obtained；Threshold skirt descriptive method
Particular content is as follows：
Step S51：The estimated value T1 and T2 of an initial approximation threshold value are selected, wherein, T1 is less than T2；
Step S52：Using estimated value T1 and T2 image according to gray value whether less than T1, more than T2 and between T1 and
It is divided into three groups of region R between T21、R2And R3；
Step S53：Combined region R1And R2, image is divided into region L1 and L2 again；
Step S54：Using method of derivation to the secondary derivation of region L1 and L2 region intersection, due to region L1 and L2 intersection
Edge feature conversion is obvious, and the extreme value of change is obtained to its secondary derivation can accurately determine the position on border, as a result with square
Formation formula is preserved；
Step S55：T1 ' and T2 ' are once again set up for the image after above-mentioned preservation, all areas of above-mentioned condition are met
The boundary information in domain, and display is distinguished in border with particular color and original image, its result is preserved in the matrix form.
Step S6：Statistical classification is carried out for qualified some regions are characterized with area, by calculating institute
There is the size of the region area for filtering out, set area value M1 and M2, filter out region of the area value between M1 and M2, can
To remove the interference noise occurred due to middle aluminum porcelain ball surface unique characteristics.
Step S7：The region setting coefficient of expansion to filtering out expands to corresponding image, to the image after expansion
Domain is merged into, using to being compared to differ from method, region is individually split, obtained with the characteristics of image identical local after expansion just
Beginning image；Described pair be compared to differ from method it is as follows：
Image after initial gray is converted with merge after above-mentioned expansion process after point set carry out logic and operation, obtain
With characteristics of image identical after the recovery local and initial image after expansion, the image after segmentation as comprising middle aluminum porcelain ball defect.
Step S8：The local and initial image that step S7 is obtained carries out again linear smoothing computing and is filtered, will again
Filtered imagery exploitation dynamic thresholding method carries out image and precisely splits, and obtains the defect information on accurately middle aluminum porcelain ball surface；
The particular content of dynamic thresholding method is as follows：
Step S81：Filtered image point set threshold value g { e } will be denoted as again, the threshold value of the point set of topography will be denoted as
G { o }, and set reference difference t；
Step S82：Numerical value in g { e } is individually subtracted into reference difference t, and is compared with g { o }, if meeting g { o }<g{e}-
T, then leave the point set on the image, otherwise rejects, and finally obtains the middle aluminum porcelain ball surface defect information after accurate filtering, and
It is marked.
Step S9：Area statistics are carried out to the defect information on the accurate middle aluminum porcelain ball surface, its pixel is calculated, if
Pixel is more than 0, then judge that aluminum porcelain ball is unqualified in correspondence.
The foregoing is only presently preferred embodiments of the present invention, all impartial changes done according to scope of the present invention patent with
Modification, should all belong to the covering scope of the present invention.
Claims (7)
1. a kind of middle aluminum porcelain ball detection method of surface flaw, it is characterised in that comprise the following steps：
Step S1：The optical imagery on aluminum porcelain ball surface in collection；
Step S2：Greyscale transformation is carried out to the optical imagery, bianry image is obtained；
Step S3：Construction linear smoothing filter is filtered to the bianry image, removes radio-frequency component and sharpens details, obtains
To filtering image；
Step S4：Using high contrast retain algorithm the filtering image is strengthened, highlight middle aluminum porcelain ball surface crack with
Contrast between background；
Step S5：Image segmentation first is carried out to the filtering image using threshold skirt descriptive method and obtains some regions, with reference to
Morphological image computing wiping out background, obtains the defect information on preliminary middle aluminum porcelain ball surface；
Step S6：Statistical classification is carried out for some regions are characterized with area, area value M1 and M2 is set, screening is appeared
Region of the product value between M1 and M2；
Step S7：The region setting coefficient of expansion to filtering out expands to corresponding image, and the image after expansion is merged
For domain, using to being compared to differ from method, region is individually split, obtained and the characteristics of image identical local and initial figure after expansion
Picture；
Step S8：The local and initial image that step S7 is obtained carries out again linear smoothing computing and is filtered, and will filter again
Imagery exploitation dynamic thresholding method afterwards carries out image and precisely splits, and obtains the defect information on accurately middle aluminum porcelain ball surface；
Step S9：Area statistics are carried out to the defect information on the accurate middle aluminum porcelain ball surface, its pixel is calculated, if pixel
Point is more than 0, then judge that aluminum porcelain ball is unqualified in correspondence.
2. middle aluminum porcelain ball detection method of surface flaw according to claim 1, it is characterised in that：In step S1, adopt
Collecting the device of the optical imagery includes conveyer belt and the grabbing device for aluminum porcelain ball in rotation, and the grabbing device is in transmission
Band top is with transmission Tape movement；Some camera bellows with light source are additionally provided with directly over the conveyer belt and for obtaining inside camera bellows
The industrial camera of image, the camera bellows offers the opening passed through for middle aluminum porcelain ball on the direction of transmission tape travel；It is described
Unqualified collection frame is provided with immediately below camera bellows with light source, below the conveyer belt tail end competent collection frame is provided with；
Also include controller, the controller and the motor connection of the industrial camera, grabbing device and control conveyer belt, be used for
Receive during the optical imagery, control grabbing device that industrial camera collects unclamps or clamp aluminum porcelain ball and control the fortune of conveyer belt
It is dynamic；The controller is connected with host computer, by optical image transmission is to host computer and receives the control command of host computer.
3. middle aluminum porcelain ball detection method of surface flaw according to claim 2, it is characterised in that：The light source is combobar
Shape light source, the week side of boss being arranged at the top of camera bellows；The inwall of the camera bellows is provided with diffusing panel, camera is provided with the top of camera bellows and is opened
Mouthful, the camera opening is arranged above industrial camera.
4. middle aluminum porcelain ball detection method of surface flaw according to claim 1, it is characterised in that：In step S3, institute
Linear smoothing filter is stated using local mean value computing, each grey scale pixel value is put with the weights of all values in its local neighborhood
Change, computing formula is：
Wherein, M is the pixel sum in neighborhood N, and h [i, j] is the gray value of Filtered Picture vegetarian refreshments [i, j], and f [k, l] is filter
The gray value of the neighborhood territory pixel point of wavefront pixel [k, l].
5. middle aluminum porcelain ball detection method of surface flaw according to claim 1, it is characterised in that：Step S4 it is concrete
Content is as follows：
Step S41：Filtering image is obscured using gaussian kernel, the fuzzy close template of the 3*3 of selection is：
The formula of wherein gaussian kernel approximation computation is：
Step S42：Convolution is carried out to optical imagery using weight matrix, broad image is obtained；
Step S43：Original image is subtracted each other with broad image, high-pass image is obtained；
Step S44：Original image and high-pass image are carried out into Dynamic Weights to be added, expression formula is：
AdImg=BlurImg+Amount* (RawImg-BlurImg+127)
Wherein：To strengthen image, BlurImg is broad image to AdImg, and RawImg-BlurImg+127 is high-pass image,
RawImg is original image, and Amount is weights, and the span of weights is [0,1].
6. middle aluminum porcelain ball detection method of surface flaw according to claim 1, it is characterised in that：In step S5, threshold
The particular content of value edge-description method is as follows：
Step S51：The estimated value T1 and T2 of an initial approximation threshold value are selected, wherein, T1 is less than T2；
Step S52：Using estimated value T1 and T2 image according to gray value whether less than T1, more than T2 and between T1 and T2 it
Between be divided into three groups of region R1、R2And R3；
Step S53：Combined region R1And R2, image is divided into region L1 and L2 again；
Step S54：Using method of derivation to the secondary derivation of region L1 and L2 region intersection, as a result preserve in the matrix form；
Step S55：T1 ' and T2 ' are once again set up for the image after above-mentioned preservation, all regions of above-mentioned condition are met
Boundary information is preserved in the matrix form.
7. middle aluminum porcelain ball detection method of surface flaw according to claim 1, it is characterised in that：In step S8, move
The particular content of state threshold method is as follows：
Step S81：Filtered image point set threshold value g { e } will be denoted as again, the threshold value of the point set of topography will be denoted as into g
{ o }, and set reference difference t；
Step S82：Numerical value in g { e } is individually subtracted into reference difference t, and is compared with g { o }, if meeting g { o }<G { e }-t, then
Point set on the image is stayed, is otherwise rejected, finally obtain the middle aluminum porcelain ball surface defect information after accurate filtering, and to it
It is marked.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611180223.6A CN106600593B (en) | 2016-12-19 | 2016-12-19 | A kind of middle aluminium porcelain ball surface defect inspection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611180223.6A CN106600593B (en) | 2016-12-19 | 2016-12-19 | A kind of middle aluminium porcelain ball surface defect inspection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106600593A true CN106600593A (en) | 2017-04-26 |
| CN106600593B CN106600593B (en) | 2019-08-09 |
Family
ID=58601864
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611180223.6A Active CN106600593B (en) | 2016-12-19 | 2016-12-19 | A kind of middle aluminium porcelain ball surface defect inspection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106600593B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107862693A (en) * | 2017-12-08 | 2018-03-30 | 湖南文理学院 | Detection method and device for nickel foam surface defect |
| CN108230324A (en) * | 2018-01-31 | 2018-06-29 | 浙江理工大学 | Magnetic shoe surface microdefect visible detection method |
| CN108318491A (en) * | 2017-12-04 | 2018-07-24 | 华南理工大学 | A kind of fabric defect detection method based on frequency spectrum curvature analysis |
| CN109146871A (en) * | 2018-08-31 | 2019-01-04 | 珠海格力智能装备有限公司 | The recognition methods of crackle and device |
| CN109584239A (en) * | 2018-12-13 | 2019-04-05 | 华南理工大学 | A kind of bloom body surface defect detecting system and method based on reflected light |
| CN112354964A (en) * | 2020-10-14 | 2021-02-12 | 宁波格劳博智能工业有限公司 | Full-automatic cleaning and detecting equipment and method for lithium battery gravure printing roller |
| CN113008897A (en) * | 2021-02-24 | 2021-06-22 | 江苏阿瑞斯智能设备有限公司 | Method, device and equipment for detecting defects of ceramic catalyst carrier |
| CN113066046A (en) * | 2020-12-04 | 2021-07-02 | 泰州可以信息科技有限公司 | Cross section area qualified grade analysis platform and method |
| WO2022007125A1 (en) * | 2020-07-07 | 2022-01-13 | 蒋梦兰 | Porcelain surface crack repairing and identifying system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6028948A (en) * | 1997-12-29 | 2000-02-22 | Lockheed Martin Corporation | Surface anomaly-detection and analysis method |
| JP4012366B2 (en) * | 2000-12-26 | 2007-11-21 | 新日本製鐵株式会社 | Surface flaw detector |
| CN102393397A (en) * | 2011-08-30 | 2012-03-28 | 成都四星液压制造有限公司 | System and method for detecting surface defects of magnetic shoe |
| CN105447851A (en) * | 2015-11-12 | 2016-03-30 | 刘新辉 | Glass panel sound hole defect detection method and system |
| CN106093066A (en) * | 2016-06-24 | 2016-11-09 | 安徽工业大学 | A kind of magnetic tile surface defect detection method based on the machine vision attention mechanism improved |
-
2016
- 2016-12-19 CN CN201611180223.6A patent/CN106600593B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6028948A (en) * | 1997-12-29 | 2000-02-22 | Lockheed Martin Corporation | Surface anomaly-detection and analysis method |
| JP4012366B2 (en) * | 2000-12-26 | 2007-11-21 | 新日本製鐵株式会社 | Surface flaw detector |
| CN102393397A (en) * | 2011-08-30 | 2012-03-28 | 成都四星液压制造有限公司 | System and method for detecting surface defects of magnetic shoe |
| CN105447851A (en) * | 2015-11-12 | 2016-03-30 | 刘新辉 | Glass panel sound hole defect detection method and system |
| CN106093066A (en) * | 2016-06-24 | 2016-11-09 | 安徽工业大学 | A kind of magnetic tile surface defect detection method based on the machine vision attention mechanism improved |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108318491A (en) * | 2017-12-04 | 2018-07-24 | 华南理工大学 | A kind of fabric defect detection method based on frequency spectrum curvature analysis |
| CN108318491B (en) * | 2017-12-04 | 2020-07-28 | 华南理工大学 | Fabric defect detection method based on frequency spectrum curvature analysis |
| CN107862693B (en) * | 2017-12-08 | 2021-10-08 | 湖南文理学院 | Method and device for detecting surface defects of foamed nickel |
| CN107862693A (en) * | 2017-12-08 | 2018-03-30 | 湖南文理学院 | Detection method and device for nickel foam surface defect |
| CN108230324A (en) * | 2018-01-31 | 2018-06-29 | 浙江理工大学 | Magnetic shoe surface microdefect visible detection method |
| CN108230324B (en) * | 2018-01-31 | 2023-10-20 | 浙江理工大学 | Visual detection method for microdefect on surface of magnetic shoe |
| CN109146871A (en) * | 2018-08-31 | 2019-01-04 | 珠海格力智能装备有限公司 | The recognition methods of crackle and device |
| CN109584239A (en) * | 2018-12-13 | 2019-04-05 | 华南理工大学 | A kind of bloom body surface defect detecting system and method based on reflected light |
| CN109584239B (en) * | 2018-12-13 | 2024-02-06 | 华南理工大学 | High-light object surface defect detection system and method based on reflected light |
| WO2022007125A1 (en) * | 2020-07-07 | 2022-01-13 | 蒋梦兰 | Porcelain surface crack repairing and identifying system |
| CN112354964A (en) * | 2020-10-14 | 2021-02-12 | 宁波格劳博智能工业有限公司 | Full-automatic cleaning and detecting equipment and method for lithium battery gravure printing roller |
| CN113066046A (en) * | 2020-12-04 | 2021-07-02 | 泰州可以信息科技有限公司 | Cross section area qualified grade analysis platform and method |
| CN113008897A (en) * | 2021-02-24 | 2021-06-22 | 江苏阿瑞斯智能设备有限公司 | Method, device and equipment for detecting defects of ceramic catalyst carrier |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106600593B (en) | 2019-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106600593A (en) | Aluminum ceramic ball surface detect detection method | |
| Ren et al. | State of the art in defect detection based on machine vision | |
| Luo et al. | Automated visual defect detection for flat steel surface: A survey | |
| WO2018107939A1 (en) | Edge completeness-based optimal identification method for image segmentation | |
| CN109636772A (en) | The defect inspection method on the irregular shape intermetallic composite coating surface based on deep learning | |
| CN102636490B (en) | Method for detecting surface defects of dustproof cover of bearing based on machine vision | |
| Xiao et al. | Surface defect detection using image pyramid | |
| CN113592845A (en) | Defect detection method and device for battery coating and storage medium | |
| CN105913415A (en) | Image sub-pixel edge extraction method having extensive adaptability | |
| CN101576958B (en) | Extraction method of rectangle seal graphics with border based on form feature | |
| Dubey et al. | Maximally stable extremal region marking-based railway track surface defect sensing | |
| CN109544522A (en) | A kind of Surface Defects in Steel Plate detection method and system | |
| CN108090494B (en) | Textile defect identification method based on Gabor filter and support vector machine | |
| CN107122737A (en) | A kind of road signs automatic detection recognition methods | |
| CN109658376A (en) | A kind of surface defect recognition method based on image recognition | |
| CN109410228A (en) | Internal wave of ocean detection algorithm based on Method Based on Multi-Scale Mathematical Morphology Fusion Features | |
| Zhou et al. | Exploring faster RCNN for fabric defect detection | |
| CN108665458A (en) | Transparent body surface defect is extracted and recognition methods | |
| CN110443791B (en) | Workpiece detection method and device based on deep learning network | |
| Pahwa et al. | FaultNet: Faulty rail-valves detection using deep learning and computer vision | |
| CN109118471A (en) | A kind of polishing workpiece, defect detection method suitable under complex environment | |
| CN104880389A (en) | Mixed crystal degree automatic measurement and fine classification method for steel crystal grains, and system thereof | |
| CN103914827A (en) | Method for visual inspection of shortages of automobile sealing strip profile | |
| CN108647593A (en) | Unmanned plane road surface breakage classification and Detection method based on image procossing and SVM | |
| CN107480585A (en) | Object detection method based on DPM algorithms |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |