CN209707395U - A kind of mask defect detecting device - Google Patents
A kind of mask defect detecting device Download PDFInfo
- Publication number
- CN209707395U CN209707395U CN201821928918.2U CN201821928918U CN209707395U CN 209707395 U CN209707395 U CN 209707395U CN 201821928918 U CN201821928918 U CN 201821928918U CN 209707395 U CN209707395 U CN 209707395U
- Authority
- CN
- China
- Prior art keywords
- mask
- detected
- detecting device
- conveying mechanism
- conveyor belt
- 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.)
- Expired - Fee Related
Links
- 230000007547 defect Effects 0.000 title claims abstract description 35
- 230000007246 mechanism Effects 0.000 claims abstract description 117
- 230000002950 deficient Effects 0.000 claims abstract description 82
- 239000000835 fiber Substances 0.000 claims description 25
- 230000003287 optical effect Effects 0.000 claims description 24
- 230000006698 induction Effects 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 22
- 238000004519 manufacturing process Methods 0.000 abstract description 9
- 230000008901 benefit Effects 0.000 abstract description 4
- 238000000034 method Methods 0.000 description 12
- 238000007689 inspection Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000006073 displacement reaction Methods 0.000 description 5
- 239000000284 extract Substances 0.000 description 5
- 238000003915 air pollution Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 210000000959 ear middle Anatomy 0.000 description 2
- 210000003128 head Anatomy 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 208000003464 asthenopia Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 210000005069 ears Anatomy 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 229910000679 solder Inorganic materials 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The utility model relates to mask production technical fields, provide a kind of mask defect detecting device, comprising: cabinet;Feed mechanism provides mask to be detected;Conveying mechanism conveys the mask to be detected;Image acquisition mechanism acquires the product image of the mask to be detected;Image processing software carries out the product image to be judged as non-defective unit or defective products according to preset mask standard;Sorting mechanism distinguishes collection to the defective products and the non-defective unit;And it is electrically connected the PLC control system of the feed mechanism, the conveying mechanism, described image collecting mechanism, described image processing software, the sorting mechanism.So that mask defect detecting device provided by the utility model has save the cost, detection efficiency is high, and detection accuracy is high, the secure advantage of product quality.
Description
Technical field
The utility model relates to mask production technical fields, especially provide a kind of mask defect detecting device.
Background technique
With industrialization and urbanization process, air pollution increasingly aggravates, and mask product is that people resist air pollution
Regular supplies, in northern haze and the serious region of sandstorm, at essential life dependence product, mask exists mask
In high volume production process, due to many reasons such as raw material, production machine and personnel operations, the mouth of a variety of defects can be generated
Cover product, such as mask dimensional error, ear band is different in size, nose item is not installed, have on mask it is dirty etc., if this defective flows
To market links, many inconvenience can be brought to user, but will bring economic loss to mask manufacturer.
Since mask production is intended to automate comprehensively, production requirement and quality requirement are higher and higher, general mask
Manufacturer differentiates one by one by human eye, and efficiency is extremely low, time-consuming and laborious during leading to current mask Quality Detection, and is easy
Visual fatigue is caused to testing staff, makes product there are hidden danger of quality, large-tonnage product is caused to do over again and waste of raw materials.
Utility model content
The purpose of this utility model is to provide a kind of mask defect detecting devices, it is intended to it is logical to solve mask in the prior art
Cross the technical issues of manual detection efficiency is low, at high cost, quality cannot ensure.
A kind of in order to achieve the above purposes, the technical solution adopted by the utility model is: mask defect detecting device, comprising:
Cabinet;Feed mechanism provides mask to be detected;Conveying mechanism conveys the mask to be detected;Image acquisition mechanism acquires institute
State the product image of mask to be detected;Image processing software judges the product image according to preset mask standard
For non-defective unit or defective products;Sorting mechanism distinguishes collection to the defective products and the non-defective unit;And described in electric connection
The PLC control of feed mechanism, the conveying mechanism, described image collecting mechanism, described image processing software, the sorting mechanism
System.
Further: described image collecting mechanism includes: the bracket being set on the cabinet;It is arranged on the bracket
, with described image processing software be electrically connected camera;Be set to it is on the camera, to be directed at the mask to be detected
Camera lens;And the induction mask to be detected is located at the first fibre optical sensor below the camera lens;The camera and described
One fibre optical sensor and the PCL control system are electrically connected.
Further: described image collecting mechanism further include: light source is set on the cabinet to the mouth to be detected
Cover light filling, the light source and the PLC control system are electrically connected.
Further: the light source is direct LED backlight.
Further: the feed mechanism includes: the first pallet, carries the mask to be detected;First cylinder, will be described
The mask to be detected in first pallet is pushed on the conveying mechanism;Second fibre optical sensor incudes first support
The mask to be detected in disk;First cylinder and second fibre optical sensor electrically connect with the PLC control system
It connects.
Further: the conveying mechanism includes: two group of first roll shaft;On first roll shaft described in being respectively arranged at one group
First conveyor belt and the second conveyor belt;And for driving the first roll shaft rotation so that first conveyor belt
With the first motor of second conveyor belt operating;The mask to be detected is in first conveyor belt and described second defeated
It send and is conveyed between belt.
Further: the sorting mechanism includes: the defective products separating mechanism for being set to the conveying mechanism discharge end;If
The defective products collecting box being placed in below the defective products separating mechanism;It is set to the non-defective unit conveying of the conveying mechanism discharge end
Mechanism;And it is set to the non-defective unit collecting mechanism of the non-defective unit conveying mechanism discharge end.
Further: the defective products separating mechanism includes: movable to be set to the conveying mechanism and the non-defective unit is defeated
Send the second pallet between mechanism;And it is set to below second pallet, driving second pallet and rises or falls
The second cylinder;The defective products collecting box is located at below second pallet, second cylinder and the PLC control system
Electrical connection.
Further: the non-defective unit conveying mechanism includes: two group of second roll shaft;Two be respectively arranged at two groups described in second
Third conveyor belt on roll shaft;And for driving second roll shaft to rotate so that two third conveyor belt fortune
The second motor turned;The non-defective unit is conveyed between two third conveyor belts.
Further: the non-defective unit conveying mechanism further include: be set to the third light of the third conveyor belt discharge end
The pushing direction of fiber sensor and third cylinder, the third cylinder is down-set, the third fibre optical sensor and described
Three cylinders and the PLC control system are electrically connected;The non-defective unit collecting mechanism includes: to be set to the third conveyor belt to go out
Expect the 4th conveyor belt below end, and, drive the third motor of the 4th conveyor belt operating.
The utility model has the beneficial effects that
A kind of mask defect detecting device provided by the utility model is sent automatically by feed mechanism, conveying mechanism realization
Mask to be detected is delivered to below image acquisition mechanism by material, and the product image that image acquisition mechanism acquires mask to be detected passes
It is handed in image processing software and carries out automatic comparison processing, processing information feeds back to PLC control system, then is controlled by PLC and be
System sorts to control sorting mechanism to non-defective unit and defective products, realizes that the automatic detection of mask to be detected, automatic distinguishing are collected,
So that mask defect detecting device provided by the utility model has save the cost, detection efficiency is high, and detection accuracy is high, product matter
Measure secure advantage.
Detailed description of the invention
It, below will be to embodiment or the prior art in order to illustrate more clearly of the technical scheme in the embodiment of the utility model
Attached drawing needed in description is briefly described, it should be apparent that, the accompanying drawings in the following description is only that this is practical new
Some embodiments of type for those of ordinary skill in the art without any creative labor, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the structural schematic diagram of mask defect detecting device provided by the embodiment of the utility model;
Fig. 2 is background image schematic diagram in mask defect inspection method provided by the embodiment of the utility model;
Fig. 3 is product image schematic diagram in mask defect inspection method provided by the embodiment of the utility model;
Fig. 4 is residual image schematic diagram in mask defect inspection method provided by the embodiment of the utility model;
Fig. 5 is gray scale displacement images schematic diagram in mask defect inspection method provided by the embodiment of the utility model;
Fig. 6 is that gray scale rotates image schematic diagram in mask defect inspection method provided by the embodiment of the utility model;
Fig. 7 is mask defect inspection method middle ear band detected rule frame provided by the embodiment of the utility model, the detection of nose item
Regular frame and dirty detected rule frame schematic diagram.
Appended drawing reference: 1, feed mechanism;11, the first cylinder;12, the first pallet;13, the second fibre optical sensor;2, it conveys
Mechanism;21, first motor;22, the first conveyor belt;23, the second conveyor belt;24, the first roll shaft;3, image acquisition mechanism;
31, the first fibre optical sensor;32, camera;33, camera lens;34, light source;35, bracket;4, sorting mechanism;41, defective products seperator
Structure;411, the second cylinder;412, the second pallet;42, defective products collecting box;43, non-defective unit conveying mechanism;431, the second motor;
432, third conveyor belt;433, third fibre optical sensor;434, third cylinder;435, the second roll shaft;44, non-defective unit collects machine
Structure;441, the 4th conveyor belt;442, third motor;5, cabinet;6, image processing software;7, PLC control system;8, to be detected
Mask;D1, dirty detected rule frame;E1, ear band detected rule frame;N1, nose bar detected rule frame.
Specific embodiment
The embodiments of the present invention are described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning
Same or similar element or element with the same or similar functions are indicated to same or similar label eventually.Below by ginseng
The embodiment for examining attached drawing description is exemplary, it is intended to for explaining the utility model, and should not be understood as to the utility model
Limitation.
In the description of the present invention, it should be understood that term " length ", " width ", "upper", "lower", " preceding ",
The orientation or positional relationship of the instructions such as " rear ", "left", "right", "vertical", "horizontal", "top", "bottom" "inner", "outside" is based on attached
Orientation or positional relationship shown in figure, is merely for convenience of describing the present invention and simplifying the description, rather than indication or suggestion
Signified device or element must have a particular orientation, be constructed and operated in a specific orientation, therefore should not be understood as to this
The limitation of utility model.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include one or more of the features.The meaning of " plurality " is two or two in the description of the present invention,
More than, unless otherwise specifically defined.
In the present invention unless specifically defined or limited otherwise, term " installation ", " connected ", " connection ", " Gu
It is fixed " etc. terms shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or integral;It can be
Mechanical connection, is also possible to be electrically connected;It can be directly connected, two can also be can be indirectly connected through an intermediary
The interaction relationship of connection or two elements inside element.It for the ordinary skill in the art, can basis
Concrete condition understands the concrete meaning of above-mentioned term in the present invention.
It please refers to shown in Fig. 1, the utility model embodiment provides a kind of mask defect detecting device, comprising: feed mechanism
1, conveying mechanism 2, image acquisition mechanism 3, image processing software 6, sorting mechanism 4, cabinet 5 and PLC control system 7, wherein
PLC control system 7 be arranged in cabinet 5, and respectively with feed mechanism 1, conveying mechanism 2, image acquisition mechanism 3, image procossing
Software 6, sorting mechanism 4 are electrically connected.
Wherein, cabinet 5 is used as arrying main body, and one end or side of cabinet 5 is arranged in feed mechanism 1, and feed mechanism 1 is used
In offer mask 8 to be detected;The setting of conveying mechanism 2 is in 5 upper surface of cabinet, and conveying mechanism 2 is for mask 8 to be detected to be delivered to
At image acquisition mechanism 3;The setting of image acquisition mechanism 3 is in 5 upper surface of cabinet, and image acquisition mechanism 3 is for acquiring mouth to be detected
Product image is simultaneously transferred in image processing software 6 by the product image of cover 8, and image processing software 6 is arranged on cabinet 5, is used
It is compared in product image and preset mask standard, mask 8 to be detected is judged as non-defective unit or defective products, and will judgement
As a result it is transferred in PLC control system 7, PLC control system 7 controls sorting mechanism 4 and non-defective unit and defective products are distinguished collection.
It is provided by the utility model that self-feeding is realized by feed mechanism 1, conveying mechanism 2, mask 8 to be detected is conveyed
To 3 lower section of image acquisition mechanism, the product image that image acquisition mechanism 3 acquires mask 8 to be detected is transferred to image processing software 6
Middle to carry out automatic comparison processing, judging result information feeds back to PLC control system 7, then is controlled by PLC control system 7 point
It selects mechanism 4 to sort non-defective unit and defective products, realizes that the automatic detection of mask 8 to be detected, automatic distinguishing are collected, so that this reality
There is save the cost with the mask defect detecting device of novel offer, detection efficiency is high, and detection accuracy is high, and product quality is secure
The advantages of.
Specifically, in the present embodiment, image acquisition mechanism 3 includes: the bracket 35 being set on cabinet 5 and is set to branch
Camera 32 on frame 35, camera 32 are used to acquire the product image of mask 8 to be detected, and camera 32 is located at 2 top of conveying mechanism, phase
Machine 32 and image processing software 6 are electrically connected, and camera lens 33 is provided on camera 32, and camera lens 33 is used to be aligned the to be detected of lower section
Mask 8 is additionally provided with the first fibre optical sensor 31 for incuding mask 8 to be detected, the first optical fiber on bracket 35 or cabinet 5
Sensor 31 is for incuding whether 33 lower section of camera lens needs to be detected mask 8.Wherein, camera 32 and the first fibre optical sensor 31 pass through
Cable and PCL control system are electrically connected.
Preferably, in the present embodiment, image acquisition mechanism 3 further include: the light source 34 being set on cabinet 5, light source 34
For treating detection 8 light filling of mask, the clarity that camera 32 acquires product image, light source 34 and PLC control system 7 is effectively ensured
It is electrically connected.In the present embodiment, light source 34 is direct LED backlight 34, further ensure that camera 32 acquires product
The clarity of image.In other embodiments, light source 34 is side entering-type LED backlight source 34.
When the first fibre optical sensor 31, which senses, to be needed to be detected mask 8 below camera lens 33, triggering is sent to camera 32 and is clapped
According to signal, the product image taken pictures is passed to image processing software 6 by camera 32, and image processing software 6 is according to preset
Mask standard is compared automatically, and comparing result is fed back to PLC control system 7, and PLC control system 7 controls sorting mechanism 4
Detection mask 8 is treated to be sorted.
In the present embodiment, feed mechanism 1 includes: the first pallet 12, the first cylinder 11 and the second fibre optical sensor 13.Its
In, the first pallet 12 is for carrying mask 8 to be detected, and the first cylinder 11 is for pushing away the mask to be detected 8 in the first pallet 12
It is sent on conveying mechanism 2, whether the second fibre optical sensor 13 needs to be detected mask 8 for incuding in the first pallet 12;First gas
Cylinder 11 and the second fibre optical sensor 13 are electrically connected by cable and PLC control system 7.
In the present embodiment, the first pallet 12, the first cylinder 11 and the second fibre optical sensor 13 (are not drawn by rack in figure
One end of cabinet 5 is set out), and mask 8 to be detected is placed on the first pallet by automatic feeder by mask 8 to be detected one by one
On 12, in other embodiments, by the way that manually mask 8 to be detected is placed on one by one on the first pallet 12.When the second optical fiber passes
After sensor 13 senses that mask 8 to be detected is fallen on the first pallet 12, mask 8 to be detected is pushed to defeated by the work of the first cylinder 11
It send in mechanism 2, then automatically reverts to original position.
Specifically, in the present embodiment, conveying mechanism 2 includes: two group of first roll shaft 24, is respectively arranged at one group of first roller
The first conveyor belt 22 and the second conveyor belt 23 on axis 24, and, for driving the rotation of the first roll shaft 24 so that first is defeated
The first motor 21 for sending belt 22 and the second conveyor belt 23 to operate, mask 8 to be detected are defeated in the first conveyor belt 22 and second
It send and is conveyed between belt 23, first motor 21 and PLC control system 7 are electrically connected.
Wherein, the first conveyor belt 22 and the second conveyor belt 23 are setting up and down, the first conveyor belt 22 and the second conveying
Spacing between belt 23 is less than thickness of the mask 8 to be detected under not by external force, the first conveyor belt 22 and second defeated
It send belt 23 to clamp mask 8 to be detected to convey, guarantees the positional stability that mask 8 to be detected conveys.First conveyor belt 22
Synchronous belt is used with the second conveyor belt 23.
In the present embodiment, sorting mechanism 4 includes: the defective products separating mechanism 41 for being set to 2 discharge end of conveying mechanism, if
It is placed in the defective products collecting box 42 of 41 lower section of defective products separating mechanism, is set to the non-defective unit conveyer of 2 discharge end of conveying mechanism
Structure 43, and, it is set to the non-defective unit collecting mechanism 44 of 43 discharge end of non-defective unit conveying mechanism.
Wherein, defective products separating mechanism 41 includes: movable is set between conveying mechanism 2 and non-defective unit conveying mechanism 43
Second pallet 412, and, the second cylinder that be set to 412 lower section of the second pallet, that the second pallet 412 of driving rises or falls
411.Defective products collecting box 42 is located at 412 lower section of the second pallet, and the second cylinder 411 is electrically connected by cable with PLC control system 7
It connects.
When image processing software 6 judges mask 8 to be detected for defective products, PLC control system 7 controls the second cylinder 411
Work, the second cylinder 411 drive the second pallet 412 to rise, and defective products falls into defective products through 2 discharge end of conveying mechanism automatically and collects
In case 42, then the second cylinder 411 drives the decline of the second pallet 412 to reset.
Wherein, non-defective unit conveying mechanism 43 includes: two group of second roll shaft 435, and two are respectively arranged at two group of second roll shaft 435
On third conveyor belt 432;And for driving the second roll shaft 435 to rotate so that two third conveyor belts 432 operated
Second motor 431, non-defective unit are conveyed between two third conveyor belts 432, and the second motor 431 is controlled by cable and PLC
System 7 processed is electrically connected.
When image processing software 6 judges mask 8 to be detected for non-defective unit, non-defective unit is sent to two article through the second pallet 412
At three conveyor belts 432, PLC control system 7 controls the work of the second motor 431, and the second motor 431 drives two thirds to convey skin
Band 432 moves, and non-defective unit clamping is delivered on non-defective unit collecting mechanism 44.
Wherein, non-defective unit conveying mechanism 43 further include: be set to the third fibre optical sensor of 432 discharge end of third conveyor belt
433 and third cylinder 434, the pushing direction of third cylinder 434 is down-set, third fibre optical sensor 433 and third cylinder 434
It is electrically connected with the PLC control system 7.
After third fibre optical sensor 433 senses non-defective unit, PLC control system 7 controls third cylinder 434, and non-defective unit is downward
It pushes, drops into non-defective unit steadily on non-defective unit collecting mechanism 44.
Specifically, in the present embodiment, non-defective unit collecting mechanism 44 includes: to be set under 432 discharge end of third conveyor belt
4th conveyor belt 441 of side, and, the third motor 442 of driving the 4th conveyor belt 441 operating, third motor 442 passes through
Cable and PLC control system 7 are electrically connected.Reach preset stacking number when the non-defective unit in the 4th conveyor belt 441 stacks quantity
After amount, third motor 442 drives the 4th conveyor belt 441 to operate a mask width position, to make non-defective unit by certain amount
Neat is arranged in the 4th conveyor belt 441.Two articles of third conveyor belts 432 are all made of synchronous with the 4th conveyor belt 441
Band.
In the present embodiment, first motor 21 is stepper motor or servo motor, the second motor 431 and third motor 442
For speed regulating motor, in the present embodiment, preset mask standard is according to the quality requirement self-setting for producing mask producer.
As shown in figures 1 to 6, the utility model embodiment also provides a kind of mask defect inspection method, this method comprises:
S1, acquired by the camera 32 that is connected with image processing software 6 background image without mask 8 to be detected and acquisition to
Detect mask 8 product image, and by four vertex of product image be respectively labeled as P1 (0,0), P2 (w, 0), P3 (0, h),
P4 (w, h);
S2, product image and background image subtraction are obtained into residual image;
S3, residual image is converted to grayscale image, and image binaryzation is carried out to grayscale image and handles to obtain binary image;
S4, the image expansion that binary image is fixed to number and Image erosion processing, and calculated using contours extract
Method extracts the product profile of mask 8 to be detected, selects the wherein maximum two product profiles of area, and uses to it minimum external
Rectangle algorithm extracts the minimum circumscribed rectangle of mask 8 to be detected;
If mask 8 to be detected is defective products when S5, extraction minimum circumscribed rectangle failure;If extracting minimum circumscribed rectangle
When success, then the length value and width value of minimum circumscribed rectangle are calculated, and by length value and width value and preset mask mark
Quasi- value compares to obtain difference;
If S6, difference exceed preset difference range, mask 8 to be detected is defective products;If difference is set in advance
In fixed difference range, then four apex coordinates P11, P12, P13, P14 and the center of minimum rectangle of minimum rectangle are exported
Point Pc1 (cx, cy);It wherein, is that mask length is bad when length value exceeds preset difference range, when width value is beyond pre-
If difference range when, be mask width it is bad;
S7, the connecting line L1 (P13, P14) for calculating point P13 and P14, point P3 and P4 connecting line L2 (P3, P4), and calculate
Included angle A between L1 and L2 out;Calculate central point Pc1 (cx, cy) relative to product image central point Pc0 (w/2, h/2) it
Between horizontal direction offset Hx and vertical direction offset Vy;
S8, gray scale head portrait is translated using the offset Vy of obtained horizontal direction offset Hx and vertical direction
Operation, so that central point Pc1 (cx, cy) and product image central point Pc0 (w/2, h/2) is overlapped to obtain gray scale displacement images;
Wherein four apex coordinates of gray scale displacement images are P21, P22, P23 and P24 respectively, and the central point of gray scale displacement images is
Pc2 (cx, cy);
S9, gray scale displacement images are rotated with central point Pc1 (cx, cy) for origin, rotation angle is the degree of included angle A
Number, to obtain gray scale rotation image;Wherein, four apex coordinates of gray scale rotation image are P31, P32, P33 and P34 respectively,
Central point is Pc2 (cx, cy), at this point, Pc0 (w/2, h/2) and Pc2 (cx, cy) are overlapped;
S10, gray scale rotation image is compared with preset mask standard, if exceeding the range of mask standard, for
Defective products;Conversely, being then non-defective unit in the range of mask standard.
Specifically, preset mask standard include: two ears band detected rule frame E1, a nose detected rule frame N1 and
One dirty detected rule frame D1;Wherein, step S10 further includes following processing step:
S101, image is rotated for gray scale, treats the ear of detection mask 8 with detected rule frame E1 using pre-set ear
Band defect is detected, and ear band detected rule frame E1 is preset respectively two ear regions, using contours extract algorithm pair
Ear of the ear with detection zone is calculated and is judged with the attribute of image outline, if attribute of the ear with image outline be not preset
In mask critical field, be then judged as that ear band is bad, if attribute of the ear with image outline in preset mask critical field,
Continue to judge in next step;Attribute of its middle ear with image outline include: quantity, profile length, contour area, profile it is continuous
Property;
S102, image is rotated for gray scale, detection mask 8 is treated using the pre-set nose detected rule frame N1
Nose strip defect detected, nose detected rule frame N1 is preset in nose strip area, using contours extract algorithm to nose item
The attribute of the nose image outline of detection zone is calculated and is judged, if the attribute of nose image outline is not in preset mask
In critical field, then it is judged as that nose item is bad, if the attribute of nose image outline uses in preset mask critical field
Minimum circumscribed rectangle algorithm calculates the minimum circumscribed rectangle of nose item, and exports four apex coordinates of minimum circumscribed rectangle in
Heart point coordinate, judge minimum circumscribed rectangle four apex coordinates and center point coordinate whether preset mask critical field it
It is interior, if being judged as that nose item is bad not within preset mask critical field, if within preset mask critical field,
Continue to judge in next step;Wherein, the attribute of nose image outline include: quantity, profile length, contour area, profile it is continuous
Property;
S103, image is rotated for gray scale, the dirty of detection mask 8 is treated using pre-set dirty detected rule frame D1
Dirty defect is detected, and avoids that dirty detection is arranged outside ear band solder joint and nose strip area in the mask body of mask 8 to be detected
Regular frame D1 is handled dirty detection zone using fixed threshold binary conversion treatment algorithm, is schemed after counting binary conversion treatment
As interior non-zero points quantity, if non-zero points quantity is judged as dirty bad, if non-zero not within the mask critical field of setting
Point quantity determines that mask 8 to be detected is non-defective unit within the mask critical field of setting.
Specifically: in step s3, before carrying out image binaryzation processing to gray level image, image first being carried out to gray scale head portrait
Local enhancement processing, to increase interpretation and the recognition effect of image.
Wherein, image local increase processing includes: traversal image area pixel value, above or equal to the pixel of designated value
Value increases setting value, and the pixel value for being less than designated value is all set to 0.
Mask defect inspection method provided by the utility model point is identified in the way of image procossing with mode identification technology
The length and width of mask carry out dimensional measurement, and the ear band, nose item and dirty defect of mask are identified and detected, instead of artificial
Detection, reduces production cost, improves finished product quality, improve production efficiency, improve the economic benefit of enterprise, adopt
It is detected with camera 32, the speed of production that testing cost can be reduced, detection speed is promoted, accelerate mask product.
The above is only the preferred embodiment of the utility model only, is not intended to limit the utility model, all at this
Made any modifications, equivalent replacements, and improvements etc., should be included in the utility model within the spirit and principle of utility model
Protection scope within.
Claims (10)
1. a kind of mask defect detecting device characterized by comprising
Cabinet (5);
Feed mechanism (1) provides mask to be detected (8);
Conveying mechanism (2) conveys the mask (8) to be detected;
Image acquisition mechanism (3) acquires the product image of the mask (8) to be detected;
Image processing software (6) carries out the product image to be judged as non-defective unit or defective products according to preset mask standard;
Sorting mechanism (4) distinguishes collection to the defective products and the non-defective unit;
And it is electrically connected the feed mechanism (1), the conveying mechanism (2), described image collecting mechanism (3), described image
Processing software (6), the PLC control system (7) of the sorting mechanism (4).
2. a kind of mask defect detecting device according to claim 1, it is characterised in that: described image collecting mechanism (3)
Include:
The bracket (35) being set on the cabinet (5);
It is set to camera (32) on the bracket (35), being electrically connected with described image processing software (6);
It is set to camera lens (33) on the camera (32), to be directed at the mask to be detected (8);
And the induction mask (8) to be detected is located at the first fibre optical sensor (31) below the camera lens (33);
The camera (32) and first fibre optical sensor (31) and PCL control system are electrically connected.
3. a kind of mask defect detecting device according to claim 2, it is characterised in that: described image collecting mechanism (3)
Further include: light source (34) is set on the cabinet (5) to mask (8) light filling to be detected, the light source (34) and institute
State PLC control system (7) electric connection.
4. a kind of mask defect detecting device according to claim 3, it is characterised in that: the light source (34) is straight-down negative
LED backlight (34).
5. a kind of mask defect detecting device according to claim 1, it is characterised in that: the feed mechanism (1) includes:
First pallet (12) carries the mask (8) to be detected;
The mask (8) to be detected in first pallet (12) is pushed to the conveying mechanism (2) by the first cylinder (11)
On;
Second fibre optical sensor (13) incudes the mask (8) to be detected in first pallet (12);
First cylinder (11) and second fibre optical sensor (13) and the PLC control system (7) are electrically connected.
6. a kind of mask defect detecting device according to claim 5, it is characterised in that: the conveying mechanism (2) includes:
Two group of first roll shaft (24);
The first conveyor belt (22) and the second conveyor belt (23) on first roll shaft (24) described in being respectively arranged at one group;
And for driving first roll shaft (24) to rotate so that first conveyor belt (22) and the second conveying skin
The first motor (21) of band (23) operating;
The mask to be detected (8) carries out defeated between first conveyor belt (22) and second conveyor belt (23)
It send.
7. a kind of mask defect detecting device according to claim 1, it is characterised in that: the sorting mechanism (4) includes:
It is set to the defective products separating mechanism (41) of the conveying mechanism (2) discharge end;
The defective products collecting box (42) being set to below the defective products separating mechanism (41);
It is set to the non-defective unit conveying mechanism (43) of the conveying mechanism (2) discharge end;
And it is set to the non-defective unit collecting mechanism (44) of non-defective unit conveying mechanism (43) discharge end.
8. a kind of mask defect detecting device according to claim 7, it is characterised in that: the defective products separating mechanism
(41) include:
Movable the second pallet (412) being set between the conveying mechanism (2) and the non-defective unit conveying mechanism (43);
And it is set to below second pallet (412), driving second pallet (412) rises or falls second
Cylinder (411);
The defective products collecting box (42) is located at below second pallet (412), second cylinder (411) and the PLC
Control system (7) electrical connection.
9. a kind of mask defect detecting device according to claim 8, it is characterised in that: the non-defective unit conveying mechanism (43)
Include:
Two group of second roll shaft (435);
Two be respectively arranged at two groups described in third conveyor belt (432) on the second roll shaft (435);
And for drive second roll shaft (435) to rotate so that two third conveyor belts (432) operatings second
Motor (431);
The non-defective unit is conveyed between two third conveyor belts (432).
10. a kind of mask defect detecting device according to claim 9, it is characterised in that: the non-defective unit conveying mechanism
(43) further include: be set to the third fibre optical sensor (433) and third cylinder of third conveyor belt (432) discharge end
(434), the pushing direction of the third cylinder (434) is down-set, the third fibre optical sensor (433) and the third gas
Cylinder (434) and the PLC control system (7) are electrically connected;
The non-defective unit collecting mechanism (44) includes: the 4th conveying being set to below third conveyor belt (432) discharge end
Belt (441), and, drive the third motor (442) of the 4th conveyor belt (441) operating.
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201821928918.2U CN209707395U (en) | 2018-11-20 | 2018-11-20 | A kind of mask defect detecting device |
PCT/CN2019/070255 WO2020103310A1 (en) | 2018-11-20 | 2019-01-03 | Mask defect detection device and method |
JP2020562815A JP7055223B2 (en) | 2018-11-20 | 2019-01-03 | Mask defect inspection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201821928918.2U CN209707395U (en) | 2018-11-20 | 2018-11-20 | A kind of mask defect detecting device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN209707395U true CN209707395U (en) | 2019-11-29 |
Family
ID=68636607
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201821928918.2U Expired - Fee Related CN209707395U (en) | 2018-11-20 | 2018-11-20 | A kind of mask defect detecting device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN209707395U (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110897233A (en) * | 2020-02-13 | 2020-03-24 | 广州市普理司科技有限公司 | Flexible AI vision full-automatic mask machine |
CN112495837A (en) * | 2020-12-07 | 2021-03-16 | 苏州金峰物联网技术有限公司 | Cross belt sorting method, sorting control system and cross belt sorting system |
-
2018
- 2018-11-20 CN CN201821928918.2U patent/CN209707395U/en not_active Expired - Fee Related
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110897233A (en) * | 2020-02-13 | 2020-03-24 | 广州市普理司科技有限公司 | Flexible AI vision full-automatic mask machine |
CN112495837A (en) * | 2020-12-07 | 2021-03-16 | 苏州金峰物联网技术有限公司 | Cross belt sorting method, sorting control system and cross belt sorting system |
CN112495837B (en) * | 2020-12-07 | 2022-05-10 | 苏州金峰物联网技术有限公司 | Cross belt sorting method, sorting control system and cross belt sorting system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109374635A (en) | A kind of mask defect detecting device and method | |
CN109374634B (en) | Online mask detection system and method | |
CN209264585U (en) | A kind of mask on-line detecting system | |
JP7055223B2 (en) | Mask defect inspection method | |
CN206038557U (en) | Full -automatic device of going up unloading and visual detection | |
CN209707395U (en) | A kind of mask defect detecting device | |
CN206038558U (en) | Multistation visual detection equipment | |
CN208321367U (en) | A kind of cargo automatic sorting apparatus | |
WO2020103324A1 (en) | On-line mask detection system and method | |
CN108333316B (en) | Casing detection machine | |
CN110239792B (en) | Clothes recovery device | |
CN106586138A (en) | Automatic detection and material recovery equipment and automatic packaging machine | |
CN203578237U (en) | Full-automatic heel wire appearance detection equipment | |
CN114618788A (en) | Glove sorting device and method based on visual detection | |
CN106696473A (en) | Automatic sorting type laser marking machine | |
CN209006207U (en) | A kind of online visual detection equipment | |
CN109622392B (en) | Automatic soft capsule video sorting device | |
CN209051017U (en) | SCARA loading and unloading Optimum Design system | |
CN109201501B (en) | Fine lemon sorting robot | |
CN208098654U (en) | The automatic detection device of cylindrical plug needle | |
CA2783577A1 (en) | Automatic online defective elements-checking-and-removing device for flexographic printing presses | |
CN211839102U (en) | High-speed automatic measurement system for precise iron core | |
CN201793050U (en) | Machine vision-based device for automatically detecting surface seasoning bag loss of container | |
CN210604354U (en) | Cloth pattern and character online acquisition device | |
CN204564592U (en) | The automatic Rough Inspection production line of silicon ingot |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20191129 |