CN109085179A - A kind of board surface flaw detection device and detection method - Google Patents
A kind of board surface flaw detection device and detection method Download PDFInfo
- Publication number
- CN109085179A CN109085179A CN201811079391.5A CN201811079391A CN109085179A CN 109085179 A CN109085179 A CN 109085179A CN 201811079391 A CN201811079391 A CN 201811079391A CN 109085179 A CN109085179 A CN 109085179A
- Authority
- CN
- China
- Prior art keywords
- axis
- defect
- rack
- screw rod
- guide rail
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 38
- 230000007547 defect Effects 0.000 claims abstract description 46
- 230000007812 deficiency Effects 0.000 claims description 12
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 230000008878 coupling Effects 0.000 claims description 4
- 238000010168 coupling process Methods 0.000 claims description 4
- 238000005859 coupling reaction Methods 0.000 claims description 4
- 238000000034 method Methods 0.000 claims description 4
- 208000037656 Respiratory Sounds Diseases 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 2
- 210000004218 nerve net Anatomy 0.000 claims 1
- 238000000638 solvent extraction Methods 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 abstract description 7
- 230000008901 benefit Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 4
- 239000002023 wood Substances 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- 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
-
- 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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
Landscapes
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a kind of board surface flaw detection device and its detection methods, it is related to intelligence manufacture equipment technical field, including rack one and rack two, the one top fixed frame two of rack, X-axis is set above the rack two, and both ends are fixedly connected with Y-axis above the X-axis, place plank below the Y-axis, be slidably connected Z axis in the Y-axis, and the adjustable mounting rack of light source is installed on the Z axis.The present invention can be from X-axis, Y-axis and the multi-faceted adjustment camera of Z axis, camera is set completely to take board surface from multi-angle, anti- leak-stopping, which is clapped, generates miss detection, improve production efficiency, simultaneously, using camera realization the defect of board surface is used for quickly detecting automatically, have many advantages, such as it is multiple functional, using simple, efficiency is higher, safe and reliable.
Description
Technical field
The present invention relates to intelligence manufacture equipment technical field, in particular to a kind of board surface flaw detection device and detection
Method.
Background technique
Currently in order to guarantee that wood furniture, the quality of the used plank such as desk product are good, need in advance to being made
Plank, wood surface defect detected, see its whether meet demand.
By practical investigation, the board surface flaw detection of current most of Furniture manufacturing factories is carried out by manual type,
Which efficiency is relatively low, time-consuming, and is easy to happen miss detection, and then be easy to produce waste product, influences production efficiency, so
With regard to needing a kind of board surface flaw detection device.
Summary of the invention
The embodiment of the invention provides a kind of board surface flaw detection device and detection methods, to solve the prior art
The problem of.
A kind of board surface flaw detection device, including rack one and rack two, the one top fixed frame two of rack,
X-axis is set above the rack two, and both ends are fixedly connected with Y-axis above the X-axis, place plank, the Y-axis below the Y-axis
On be slidably connected Z axis, light source adjustable mounting rack is installed on the Z axis.
Preferably, the X-axis includes X-axis guide rail, the X-axis guide rail is fixed on the upper surface two sides of the rack two, institute
The X-axis guide rail sliding block that is slidably connected in X-axis guide rail is stated, the X-axis guide rail sliding block below feed screw nut's connection frame by being fixedly connected
Feed screw nut one, and the feed screw nut one is threadedly coupled screw rod one, and one both ends of screw rod are threadedly coupled across travel switch one
Bearing block one, the side end of the screw rod one are fixedly connected with the rotating part of servo motor one, the servo motor one and row
Cheng Kaiguan mono- is electrically connected, and the screw rod one is fixed on the lower section of the rack two.
Preferably, the upper surface of the rack two is workbench, the workbench two sides are slidably connected the X-axis,
The X-axis upper end is fixedly connected with Y-axis guide rail, screw rod two is arranged inside the Y-axis guide rail, two both ends of screw rod are opened across stroke
It closes two and is threadedly coupled bearing seat two, the bearing block two is fixed on the both ends of the Y-axis guide rail, and two side end of screw rod is solid
Surely the rotating part of servo motor two is connected；
Be slidably connected Z axis track on the Y-axis track, and screw rod three, spiral shell on the screw rod three is arranged in the Z axis track interior
Line connection wire rod nut two, feed screw nut's seat is fixed on the feed screw nut two, and the screw rod three is threadedly coupled bearing seat three, institute
The top that bearing block three is fixed on the Z axis track is stated, three end of the screw rod connects turning for servo motor three by shaft coupling
Dynamic part.
Preferably, the adjustable mounting rack of light source includes mainboard, the mainboard upper end is rotatablely connected vari ramp, it is described can
Lamp source crossbeam is fixed in oblique adjusting plate end, and the lamp source crossbeam other end is fixed on the mainboard bottom, the lamp source below the crossbeam
Fixedly adjustable lamp source mounting plate, the vari ramp top are fixedly connected with digital camera mounting plate by inclined plate.
A kind of board surface flaw detection method, comprising:
Step 1: collecting each 100, picture of 5 kinds of common deficiencies of plank, extract 22 features of every picture: every dimension is big
The small histogram for being 16, the first moment of color moment, second moment and third moment, the first moment of geometric moment, second moment and third moment, benefit
It is trained with 100*22 feature of the three layers of BP neural network to common deficiency, obtains three layers of BP mind corresponding to common deficiency
Through network；
Step 2: computer to controller issue order-driven platform X, Y-axis reach tested point, camera according to plank
Distance, the height of Automatic-searching Focussing Z axis；
Step 3: calibration for cameras, obtains the Intrinsic Matrix and Distortion Vector of camera；
Step 4: taking pictures to tested point region, picture is corrected according to the calibrating parameters of step 3；
Step 5: the photo after correction is successively carried out gray processing, filtering and noise reduction；
Step 6: being split using multiple target level-set segmentation algorithm to photo, which is believed with regional area
Item, the edge item of different target defect and regularization term three parts are ceased as objective energy function, construct multiple target defects detection
Movable contour model, the profile of each defect is then determined using the calculus of variations；
Step 7: obtaining the external quadrangle of each defect profile, the area of the external quadrangle of each defect is solved, is rejected
Area is less than the defect of given threshold；
Step 8: solving the centre coordinate of the external quadrangle of each defect, it is denoted as the position of corresponding defect；
Step 9: extracting 22 features of each defect as described in step 1；
Step 10: the feature of step 9 is carried out identification classification by the obtained BP neural network of step 1, statistics is each
The quantity of kind defect；
Step 11: since plank area is larger, camera fields of view is limited in scope, in advance according to camera fields of view and plank area
It determines the position of each tested point, repeats step 2 to step 10, complete the automatic detection to board surface flaw.
Preferably, 5 kinds of common deficiencies in the step 1 be knot, it is small holes caused by worms, crackle, rotten, damaged.
Preferably, the equal value difference of pixel of the local region information item between different target defect area in the step 6
Different, the edge item of the different target defect is the GAC model promoted.
The invention has the advantages that: the present invention to make camera from multi-angle from X-axis, Y-axis and the multi-faceted adjustment camera of Z axis
Board surface is completely taken, anti-leak-stopping, which is clapped, generates miss detection, production efficiency is improved, meanwhile, it is realized using camera automatic
The defect of board surface is used for quickly detecting, have many advantages, such as it is multiple functional, using simple, efficiency is higher, safe and reliable.
Detailed description of the invention
Fig. 1 is a kind of structural schematic diagram of board surface flaw detection device provided in an embodiment of the present invention；
Fig. 2 is a kind of structural schematic diagram of the X-axis of board surface flaw detection device provided in an embodiment of the present invention；
Fig. 3 is a kind of Y-axis of board surface flaw detection device provided in an embodiment of the present invention and the structural representation of Z axis
Figure；
Fig. 4 is a kind of structure of the adjustable mounting rack of light source of board surface flaw detection device provided in an embodiment of the present invention
Schematic diagram；
Fig. 5 is a kind of algorithm flow schematic diagram of board surface flaw detection device provided in an embodiment of the present invention.
Description of symbols:
1- rack one, 2- rack two, 3-X axis, 4-Y axis, 5- plank, 6-Z axis, 7- light source is adjustable mounting rack, X-axis guide rail cunning
Block, 9- feed screw nut's connection frame, 10- feed screw nut one, 11-X axis rail, 12- screw rod one, 13- travel switch one, 14- bearing
One, 15- of seat servo motor one, 16- workbench, 17-Y axis rail, 18- travel switch two, 19- screw rod two, 20- bearing block
Two, 21- servo motor two, 22- feed screw nut two, 23- feed screw nut's seat, 24-Z axis rail, 25- screw rod three, 26- bearing block
Three, 27- shaft coupling, 28- servo motor three, 29- mainboard, 30- digital camera mounting plate, 31- inclined plate, lamp source that 32- is adjustable installation
Plate, 33- vari ramp, 34- lamp source crossbeam.
Specific embodiment
Below with reference to the attached drawing in inventive embodiments, technical solution in the embodiment of the present invention carries out clear, complete
Description, it is to be understood that the protection scope of the present invention is not limited by the specific implementation manner.
In order to improve the detection efficiency and effect of board surface flaw, reinforce the high-precision detected to board surface flaw certainly
Dynamicization control, while plank quality is improved, the present invention provides a kind of high-efficient, time-consuming board surface flaws short, at low cost
Visual automatic detection device.The identification different types of defect of board surface is gone using computer and high definition camera, passes through computer
Platform is timed, is pinpointed, quantitative exercise control, while the camera in device takes pictures to plank, is compareed by computer
Piece is handled to obtain defect information, and then improves the efficiency of board surface flaw detection, and testing cost is greatly lowered.
Referring to Fig.1, the present invention provides a kind of board surface flaw detection device, including rack 1 and rack 22, institutes
One 1 top fixed frame 22 of rack is stated, X-axis 3 is arranged in 22 top of rack, and the 3 top both ends of X-axis are fixedly connected with Y-axis
4, plank 5 is placed below the Y-axis 4, be slidably connected Z axis 6 in the Y-axis 4, installs the adjustable mounting rack 7 of light source on the Z axis 6.
Servo motor one, servo motor two and servo motor three are connected by controller with computer, are watched by computer to control
Motor one, servo motor two and servo motor three are taken to achieve the purpose that control X-axis, Y-axis and Z axis, computer and send instructions to
Controller, control X, Y-axis are moved to measuring point to be checked from initial point in the form of parabolic path above plank, then camera according to
Height apart from plank realizes camera auto-focusing by controller control Z axis, and then camera claps plank area to be tested
According to being carried out using Digital Image Processing algorithm and neural network algorithm to photo by computer by photo upload to computer
Reason, obtains related defects information, and defect is shown to mark out and is come.
Referring to Fig. 2, the X-axis 3 includes X-axis guide rail 11, and the X-axis guide rail 11 is fixed on the upper surface of the rack 22
Two sides, be slidably connected in the X-axis guide rail 11 X-axis guide rail sliding block 8, and the X-axis guide rail sliding block 8 passes through feed screw nut's connection frame 9
Lower section is fixedly connected with feed screw nut 1, and the feed screw nut 1 is threadedly coupled screw rod 1, and one 12 both ends of screw rod are worn
Overtravel switch 1 is threadedly coupled bearing seat 1, and the side end of the screw rod 1 is fixedly connected with servo motor 1
Rotating part, the servo motor 1 are electrically connected with travel switch 1, and the screw rod 1 is fixed on the rack 22
Lower section.The rotation of screw rod one is controlled by servo motor one, so that Y-axis be made to move horizontally on screw rod one.
Referring to Fig. 3, the upper surface of the rack 22 is workbench 16, and 16 two sides of workbench are slidably connected institute
X-axis 3 is stated, the X-axis upper end is fixedly connected with Y-axis guide rail 17, screw rod 2 19, the screw rod two is arranged inside the Y-axis guide rail 17
19 both ends pass through travel switch 2 18 and are threadedly coupled bearing seat 2 20, and the bearing block 2 20 is fixed on the Y-axis guide rail 17
Both ends, 2 19 side end of screw rod are fixedly connected with the rotating part of servo motor 2 21；It is controlled by servo motor two
The rotation of screw rod two, so that Z axis be made to move horizontally on screw rod two.
Be slidably connected Z axis track 24 in the Y-axis guide rail 17, and screw rod 3 25, the silk are arranged inside the Z axis track 24
It is threadedly coupled feed screw nut 2 22 on bar 3 25, feed screw nut's seat 23, the screw rod 3 25 are fixed on the feed screw nut 2 22
It is threadedly coupled bearing seat 3 26, the bearing block 3 26 is fixed on the top of the Z axis track 24, and 3 25 end of screw rod is logical
The rotating part that shaft coupling 27 connects servo motor 3 28 is crossed, the rotation of screw rod three is controlled by servo motor three, to make
Mounting rack vertical shift that light source is adjustable.
Referring to Fig. 4, the adjustable mounting rack 7 of light source includes mainboard 29, and 29 upper end of mainboard is rotatablely connected vari ramp
33, the fixed lamp source crossbeam 34 in 33 end of vari ramp, 34 other end of lamp source crossbeam is fixed on 29 bottom of mainboard,
The 34 fixedly adjustable lamp source mounting plate 32 in lower section of the lamp source crossbeam is fixedly connected with number by inclined plate 31 above the vari ramp 33
Word camera installing plate 30；The high definition camera is mounted on the lower section of digital camera mounting plate 30, and the light source is mounted on dimmable lamp
The lower section of source mounting plate 32 is installed by four square side modes of 4 rectangle light sources, and tri- axis of X, Y, Z can be by
Controller driving moves back and forth in positive and negative limit, and the adjustable mounting rack of light source is mounted on the sliding block one on Z axis and on Z axis
Body, light source and digital camera height in the adjustable mounting rack of light source can be motor driven carry out up and down adjustment, described
Camera can realize auto-focusing according to the height of real-time range plank, and shown computer is mounted on board edge, according to camera
Captured picture detects all defect of board surface, and is labeled display；According to motion profile, issued to controller
Instruction, controller driving motor control X, Y-axis move to tested point from initial point；It is communicated with controller, receives controller
The X that sends in real time, Y-axis speed, position, and shown；
Referring to Fig. 5, a kind of a kind of pair of Processing Algorithm of the acquired data of board surface flaw detection device, comprising:
Step 1: collecting each 100, picture of 5 kinds of common deficiencies of plank, extract 22 features of every picture: every dimension is big
The small histogram for being 16, the first moment of color moment, second moment and third moment, the first moment of geometric moment, second moment and third moment, benefit
It is trained with 100*22 feature of the three layers of BP neural network to common deficiency, obtains three layers of BP mind corresponding to common deficiency
Through network；5 kinds of common deficiencies in the step 1 are knot, small holes caused by worms, crackle, rotten, damaged.
Step 2: computer to controller issue order-driven platform X, Y-axis reach tested point, camera according to plank
Distance, the height of Automatic-searching Focussing Z axis；
Step 3: calibration for cameras, obtains the Intrinsic Matrix and Distortion Vector of camera；
Step 4: taking pictures to tested point region, picture is corrected according to the calibrating parameters of step 3；
Step 5: the photo after correction is successively carried out gray processing, filtering and noise reduction；
Step 6: being split using multiple target level-set segmentation algorithm to photo, which is believed with regional area
Item, the edge item of different target defect and regularization term three parts are ceased as objective energy function, construct multiple target defects detection
Movable contour model, the profile of each defect is then determined using the calculus of variations；Local region information item in the step 6
Pixel mean value difference between different target defect area, the edge item of the different target defect are the GAC model promoted.
Step 7: obtaining the external quadrangle of each defect profile, the area of the external quadrangle of each defect is solved, is rejected
Area is less than the defect of given threshold；
Step 8: solving the centre coordinate of the external quadrangle of each defect, it is denoted as the position of corresponding defect；
Step 9: extracting 22 features of each defect as described in step 1；
Step 10: the feature of step 9 is carried out identification classification by the obtained BP neural network of step 1, statistics is each
The quantity of kind defect；
Step 11: since plank area is larger, camera fields of view is limited in scope, in advance according to camera fields of view and plank area
It determines the position of each tested point, repeats step 2 to step 10, complete the automatic detection to board surface flaw.
Working principle: a kind of board surface flaw detection device provided by the invention, computer use the processing of X86-based
Device is communicated by RS232 interface with controller；Camera carries out image transmitting by USB interface and computer；According to initial
The coordinate of point and tested point, issues to controller and instructs, and controller driving motor controls X, Y-axis in turn with parabolical track shape
Formula moves to tested point, the camera auto-focusing on Z axis, will be on captured picture to plank regional area to be measured into taking pictures
It is transmitted to computer, picture is handled by computer, obtains the defect information in plank region to be measured；Controller is in control X, Y
While axis moves, X, the speed of Y-axis, position can be uploaded to computer in real time；The controller uses high performance PLC,
Each shifting axle of the X, Y, Z axis is modularized design, can be designed according to the respective motion range of X, Y, Z, Z axis
Mounting height can also be adjusted by profile height.
In conclusion the present invention can from X-axis, Y-axis and the multi-faceted adjustment camera of Z axis, make camera from multi-angle completely
Board surface is taken, anti-leak-stopping, which is clapped, generates miss detection, production efficiency is improved, meanwhile, it is realized using camera automatically to plank
The defect on surface is used for quickly detecting, have many advantages, such as it is multiple functional, using simple, efficiency is higher, safe and reliable.
Disclosed above is only a specific embodiment of the invention, and still, the embodiment of the present invention is not limited to this, is appointed
What what those skilled in the art can think variation should all fall into protection scope of the present invention.
Claims (7)
1. a kind of board surface flaw detection device, which is characterized in that including rack one (1) and rack two (2), the rack one
(1) X-axis (3) are arranged in top fixed frame two (2), rack two (2) top, and both ends are fixedly connected with Y above the X-axis (3)
Axis (4), Y-axis (4) lower section place plank (5), are slidably connected Z axis (6) on the Y-axis (4), install light on the Z axis (6)
Source is adjustable mounting rack (7).
2. device as described in claim 1, which is characterized in that the X-axis (3) includes X-axis guide rail (11), the X-axis guide rail
(11) the upper surface two sides of the rack two (2) are fixed on, are slidably connected on the X-axis guide rail (11) X-axis guide rail sliding block (8),
Feed screw nut one (10), the screw rod spiral shell are fixedly connected with by feed screw nut's connection frame (9) below the X-axis guide rail sliding block (8)
Female one (10) are spirally connected screw rod one (12), and screw rod one (12) both ends are each passed through two travel switches one (13) and are spirally connected two axis
Seat one (14) is held, the side end of the screw rod one (12) is fixedly connected with the rotating part of servo motor one (15), the servo
Motor one (15) is electrically connected with travel switch one (13), and the screw rod one (12) is mounted on the lower section of the rack two (2).
3. device as described in claim 1, which is characterized in that the upper surface of the rack two (2) is workbench (16), institute
It states workbench (16) two sides to be slidably connected the X-axis (3), the X-axis upper end is fixedly connected with Y-axis guide rail (17), and the Y-axis is led
Screw rod two (19) are set inside rail (17), screw rod two (19) both ends are each passed through two travel switches two (18) and are spirally connected two
Bearing block two (20), the bearing block two (20) are fixed on the both ends of the Y-axis guide rail (17), screw rod two (19) the side end
End is fixedly connected with the rotating part of servo motor two (21)；
It is slidably connected on the Y-axis guide rail (17) Z axis track (24), screw rod three (25) is set inside the Z axis track (24), institute
The feed screw nut two (22) that is spirally connected on screw rod three (25) is stated, feed screw nut's seat (23) is fixed on the feed screw nut two (22), it is described
Screw rod three (25) is spirally connected bearing block three (26), and the bearing block three (26) is fixed on the top of the Z axis track (24), the silk
The rotating part that bar three (25) end passes through shaft coupling (27) connection servo motor three (28).
4. device as described in claim 1, which is characterized in that the adjustable mounting rack of light source (7) includes mainboard (29), described
Mainboard (29) upper end is rotatablely connected vari ramp (33), and vari ramp (33) end is fixed lamp source crossbeam (34), the lamp
Source crossbeam (34) other end is fixed on the mainboard (29) bottom, fixedly adjustable lamp source mounting plate below the lamp source crossbeam (34)
(32), digital camera mounting plate (30) are fixedly connected with by inclined plate (31) above the vari ramp (33).
5. a kind of method for carrying out board surface flaw detection using board surface flaw detection device in claim 1, special
Sign is, comprising:
Step 1: collecting each 100, picture of 5 kinds of common deficiencies of plank, extract 22 features of every picture: every dimension size is
16 histogram, first moment, second moment and the third moment of color moment, the first moment of geometric moment, second moment and third moment, utilize three
Layer BP neural network is trained 100*22 feature of common deficiency, obtains three layers of BP nerve net corresponding to common deficiency
Network；
Step 2: computer is to controller issues order-driven platform X, Y-axis reaches tested point, camera according to plank away from
From the height of Automatic-searching Focussing Z axis；
Step 3: calibration for cameras, obtains the Intrinsic Matrix and Distortion Vector of camera；
Step 4: taking pictures to tested point region, photo is corrected according to the calibrating parameters of step 3；
Step 5: the photo after correction is successively carried out gray processing, filtering and noise reduction；
Step 6: be split using multiple target level-set segmentation algorithm to photo, the partitioning algorithm with local region information item,
The edge item and regularization term three parts of different target defect construct the activity of multiple target defects detection as objective energy function
Then skeleton pattern determines the profile of each defect using the calculus of variations；
Step 7: obtaining the external quadrangle of each defect profile, the area of the external quadrangle of each defect is solved, rejects area
Less than the defect of given threshold；
Step 8: solving the centre coordinate of the external quadrangle of each defect, it is denoted as the position of corresponding defect；
Step 9: extracting 22 features of each defect as described in step 1；
Step 10: the feature of step 9 is carried out identification classification by the obtained BP neural network of step 1, counts various and lack
Sunken quantity；
Step 11: repeating step 2 to step 10, the automatic detection to the surface defect of each tested point position of plank is completed.
6. method as claimed in claim 5, which is characterized in that 5 kinds of common deficiencies in the step 1 be knot, small holes caused by worms,
It is crackle, rotten, damaged.
7. method as claimed in claim 5, which is characterized in that the local region information item in the step 6 is different target
Pixel mean value difference between defect area, the edge item of the different target defect are the GAC model promoted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811079391.5A CN109085179A (en) | 2018-09-17 | 2018-09-17 | A kind of board surface flaw detection device and detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811079391.5A CN109085179A (en) | 2018-09-17 | 2018-09-17 | A kind of board surface flaw detection device and detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109085179A true CN109085179A (en) | 2018-12-25 |
Family
ID=64841646
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811079391.5A Pending CN109085179A (en) | 2018-09-17 | 2018-09-17 | A kind of board surface flaw detection device and detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109085179A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109949286A (en) * | 2019-03-12 | 2019-06-28 | 北京百度网讯科技有限公司 | Method and apparatus for output information |
| CN110018179A (en) * | 2019-05-10 | 2019-07-16 | 河北视窗玻璃有限公司 | A kind of glass defect marking arrangement and glass plate producing process |
| CN110514664A (en) * | 2019-08-20 | 2019-11-29 | 北京信息科技大学 | A kind of cheese Sha Gan detection and localization robot and method |
| CN110687126A (en) * | 2019-10-31 | 2020-01-14 | 南宁华数轻量化电动汽车设计院有限公司 | Plank shooting device and defect detection system |
| CN111982909A (en) * | 2020-06-30 | 2020-11-24 | 广州超音速自动化科技股份有限公司 | Wood board visual detection device and detection method |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07219088A (en) * | 1994-01-31 | 1995-08-18 | Hitachi Cable Ltd | X-ray film inspection device and x-ray inspecting method for power cable |
| US5774212A (en) * | 1997-03-19 | 1998-06-30 | General Electric Co. | Method and apparatus for detecting and analyzing directionally reflective surface flaws |
| US20020138481A1 (en) * | 2001-03-23 | 2002-09-26 | International Business Machines Corporation | Searching product catalogs |
| US20030099330A1 (en) * | 2000-02-05 | 2003-05-29 | Domingo Mery | Method for automatically detecting casting defects in a test piece |
| JP2009293999A (en) * | 2008-06-03 | 2009-12-17 | Panasonic Electric Works Co Ltd | Wood defect detector |
| CN102147375A (en) * | 2010-12-23 | 2011-08-10 | 东莞市升力智能科技有限公司 | Dual-working-platform surface fault automatic detector for flexible printed circuit |
| CN102313747A (en) * | 2011-07-27 | 2012-01-11 | 国家林业局北京林业机械研究所 | Image acquisition system for sawn timber surface defects and detection method |
| CN102680478A (en) * | 2012-04-25 | 2012-09-19 | 华南农业大学 | Detection method and device of surface defect of mechanical part based on machine vision |
| JP2014062887A (en) * | 2012-08-27 | 2014-04-10 | Ntn Corp | Defect detection apparatus, defect correction apparatus, defect detection method |
| CN104392242A (en) * | 2014-11-13 | 2015-03-04 | 东北林业大学 | Method for cooperatively classifying perceived solid wood panel surface textures and defects by feature extraction and compressive sensing based on dual-tree complex wavlet |
| CN204203077U (en) * | 2014-10-16 | 2015-03-11 | 铸锐(上海)工业自动化有限公司 | A kind of camera and outer lines mounting structure for light source |
| CN204269533U (en) * | 2014-10-16 | 2015-04-15 | 铸锐(上海)工业自动化有限公司 | The mounting structure of a kind of kind of wood detection equipment vision system and elevating mechanism |
| CN104655648A (en) * | 2015-03-18 | 2015-05-27 | 常州工学院 | Hardware transplanting device and software transplanting method used for defect detection |
| CN204718970U (en) * | 2015-05-28 | 2015-10-21 | 大族激光科技产业集团股份有限公司 | Product appearance inspection device |
| CN105588841A (en) * | 2016-01-28 | 2016-05-18 | 浙江工业大学 | Stitch inclination defect detection device based on machine vision |
| CN205844213U (en) * | 2016-06-28 | 2016-12-28 | 华南理工大学 | A kind of curved surface automatic defect detecting device |
| CN107121093A (en) * | 2017-06-13 | 2017-09-01 | 电子科技大学 | A kind of gear measurement device and measuring method based on active vision |
| WO2018000731A1 (en) * | 2016-06-28 | 2018-01-04 | 华南理工大学 | Method for automatically detecting curved surface defect and device thereof |
| CN208721584U (en) * | 2018-09-17 | 2019-04-09 | 周口师范学院 | A kind of board surface flaw detection device |
-
2018
- 2018-09-17 CN CN201811079391.5A patent/CN109085179A/en active Pending
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07219088A (en) * | 1994-01-31 | 1995-08-18 | Hitachi Cable Ltd | X-ray film inspection device and x-ray inspecting method for power cable |
| US5774212A (en) * | 1997-03-19 | 1998-06-30 | General Electric Co. | Method and apparatus for detecting and analyzing directionally reflective surface flaws |
| US20030099330A1 (en) * | 2000-02-05 | 2003-05-29 | Domingo Mery | Method for automatically detecting casting defects in a test piece |
| US20020138481A1 (en) * | 2001-03-23 | 2002-09-26 | International Business Machines Corporation | Searching product catalogs |
| JP2009293999A (en) * | 2008-06-03 | 2009-12-17 | Panasonic Electric Works Co Ltd | Wood defect detector |
| CN102147375A (en) * | 2010-12-23 | 2011-08-10 | 东莞市升力智能科技有限公司 | Dual-working-platform surface fault automatic detector for flexible printed circuit |
| CN102313747A (en) * | 2011-07-27 | 2012-01-11 | 国家林业局北京林业机械研究所 | Image acquisition system for sawn timber surface defects and detection method |
| CN102680478A (en) * | 2012-04-25 | 2012-09-19 | 华南农业大学 | Detection method and device of surface defect of mechanical part based on machine vision |
| JP2014062887A (en) * | 2012-08-27 | 2014-04-10 | Ntn Corp | Defect detection apparatus, defect correction apparatus, defect detection method |
| CN204203077U (en) * | 2014-10-16 | 2015-03-11 | 铸锐(上海)工业自动化有限公司 | A kind of camera and outer lines mounting structure for light source |
| CN204269533U (en) * | 2014-10-16 | 2015-04-15 | 铸锐(上海)工业自动化有限公司 | The mounting structure of a kind of kind of wood detection equipment vision system and elevating mechanism |
| CN104392242A (en) * | 2014-11-13 | 2015-03-04 | 东北林业大学 | Method for cooperatively classifying perceived solid wood panel surface textures and defects by feature extraction and compressive sensing based on dual-tree complex wavlet |
| CN104655648A (en) * | 2015-03-18 | 2015-05-27 | 常州工学院 | Hardware transplanting device and software transplanting method used for defect detection |
| CN204718970U (en) * | 2015-05-28 | 2015-10-21 | 大族激光科技产业集团股份有限公司 | Product appearance inspection device |
| CN105588841A (en) * | 2016-01-28 | 2016-05-18 | 浙江工业大学 | Stitch inclination defect detection device based on machine vision |
| CN205844213U (en) * | 2016-06-28 | 2016-12-28 | 华南理工大学 | A kind of curved surface automatic defect detecting device |
| WO2018000731A1 (en) * | 2016-06-28 | 2018-01-04 | 华南理工大学 | Method for automatically detecting curved surface defect and device thereof |
| CN107121093A (en) * | 2017-06-13 | 2017-09-01 | 电子科技大学 | A kind of gear measurement device and measuring method based on active vision |
| CN208721584U (en) * | 2018-09-17 | 2019-04-09 | 周口师范学院 | A kind of board surface flaw detection device |
Non-Patent Citations (10)
| Title |
|---|
| 司徒伟明;邹湘军;王成琳;莫宇达;李锦慧;罗少锋;: "基于OpenCV的木材表面缺陷检测系统", 现代电子技术, no. 12 * |
| 张命令: "基于PLC 的三轴十字滑台带钢表面缺陷检测系统设计", 检测技术与数据处理, vol. 33, no. 2, pages 39 - 44 * |
| 方浩;李艾华;王涛;: "基于DM6437的智能视频监控系统设计与实现", 计算机应用与软件, no. 02 * |
| 朱蕾: "木材表面缺陷图像识别的算法研究", 中国优秀硕士学位论文全文数据库, vol. 2012, no. 5, pages 5 - 12 * |
| 王向阳;张贝贝;杨红颖;: "基于伪Zernike色度分布矩的彩色图像检索方法", 辽宁师范大学学报(自然科学版), no. 03 * |
| 程涛;侯榆青;李明俐;常哲;: "一种基于显著兴趣点的图像检索方法", 计算机工程, no. 18 * |
| 肖宾杰;殳伟群;: "基于图像融合的木板表面缺陷特征提取方法研究", 计算机科学, no. 04 * |
| 郑志霞;黄元庆;冯勇建;: "基于机器视觉的板材表面缺陷检测方法", 莆田学院学报, no. 05, pages 43 - 47 * |
| 郑欢斌;刘辉;刘欢;朱亚伦;齐子诚;: "疲劳裂纹扩展试验裂纹图像采集系统", 轻工机械, no. 06 * |
| 钱晶;高月松;: "图像检索系统中的CBIR技术研究", 电脑知识与技术, no. 02 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109949286A (en) * | 2019-03-12 | 2019-06-28 | 北京百度网讯科技有限公司 | Method and apparatus for output information |
| US11341626B2 (en) | 2019-03-12 | 2022-05-24 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for outputting information |
| CN110018179A (en) * | 2019-05-10 | 2019-07-16 | 河北视窗玻璃有限公司 | A kind of glass defect marking arrangement and glass plate producing process |
| CN110514664A (en) * | 2019-08-20 | 2019-11-29 | 北京信息科技大学 | A kind of cheese Sha Gan detection and localization robot and method |
| CN110687126A (en) * | 2019-10-31 | 2020-01-14 | 南宁华数轻量化电动汽车设计院有限公司 | Plank shooting device and defect detection system |
| CN110687126B (en) * | 2019-10-31 | 2024-05-24 | 南宁华数轻量化电动汽车设计院有限公司 | Plank shooting device and defect detection system |
| CN111982909A (en) * | 2020-06-30 | 2020-11-24 | 广州超音速自动化科技股份有限公司 | Wood board visual detection device and detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109085179A (en) | A kind of board surface flaw detection device and detection method | |
| CN110216080A (en) | A kind of Quality Monitoring Control System of the PCB processing producing line based on image comparison | |
| CN109772733B (en) | Defect bamboo block detecting and sorting device and method based on vision | |
| CN203705352U (en) | Magnetic shoe online detecting device based on machine vision | |
| CN105606629B (en) | A kind of eyeglass planar defect automatic detection device and method | |
| CN203124215U (en) | Frame sealant coating machine | |
| CN103743752A (en) | Online detecting equipment for magnetic shoes based on machine vision | |
| CN102601061B (en) | Automatic sorting device for defective products of pole pieces of timers | |
| CN108760747A (en) | A kind of 3D printing model surface defect visible detection method | |
| CN105651782A (en) | Engine cylinder cover defect automatic detection equipment based on machine vision | |
| CN102866166A (en) | Automatic optic detecting system and method | |
| CN207248724U (en) | A kind of visual detection equipment | |
| CN104634791A (en) | Omnidirectional and visual on-line detection system of surface defects of strip-shaped workpiece | |
| CN111157537A (en) | Strip steel defect detection device and system based on bionic machine vision | |
| CN206656692U (en) | A kind of multistation non-destructive detecting device of gas spring bar | |
| CN104034637B (en) | Based on the online quality inspection device of diamond wire particle of machine vision | |
| CN107741425A (en) | A kind of surface defect real-time detection apparatus for increasing material manufacturing | |
| CN106353336A (en) | Lens coating automatic detection system | |
| CN202676612U (en) | Device used for testing LED circuit chip | |
| CN110335239A (en) | Defects detection training machine and its application method based on deep learning | |
| WO2023168984A1 (en) | Area-array camera-based quality inspection method and system for cathode copper | |
| CN109406526A (en) | A kind of resin lens smog defect detecting device | |
| CN112345553A (en) | Hard disk part detection device and detection method | |
| CN208721584U (en) | A kind of board surface flaw detection device | |
| CN209858405U (en) | PCB defect detection system device based on machine optics |
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 |