CN106079338A - Embedded mold protection device based on wavelet passivation and image processing method thereof - Google Patents
Embedded mold protection device based on wavelet passivation and image processing method thereof Download PDFInfo
- Publication number
- CN106079338A CN106079338A CN201610459520.8A CN201610459520A CN106079338A CN 106079338 A CN106079338 A CN 106079338A CN 201610459520 A CN201610459520 A CN 201610459520A CN 106079338 A CN106079338 A CN 106079338A
- Authority
- CN
- China
- Prior art keywords
- image
- controller
- pixel
- passivation
- wavelet
- 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
- 238000002161 passivation Methods 0.000 title claims abstract description 27
- 238000003672 processing method Methods 0.000 title claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 25
- 238000001914 filtration Methods 0.000 claims abstract description 14
- 238000012706 support-vector machine Methods 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 38
- 230000008569 process Effects 0.000 claims description 30
- 238000002347 injection Methods 0.000 claims description 25
- 239000007924 injection Substances 0.000 claims description 25
- 238000000354 decomposition reaction Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 10
- 229920003023 plastic Polymers 0.000 claims description 10
- 239000004033 plastic Substances 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000001746 injection moulding Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 2
- 241000256844 Apis mellifera Species 0.000 claims 1
- 238000002372 labelling Methods 0.000 claims 1
- 238000007781 pre-processing Methods 0.000 abstract 1
- 238000004891 communication Methods 0.000 description 6
- 238000013461 design Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003860 storage 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
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 208000002925 dental caries Diseases 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 239000012943 hotmelt Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C45/00—Injection moulding, i.e. forcing the required volume of moulding material through a nozzle into a closed mould; Apparatus therefor
- B29C45/17—Component parts, details or accessories; Auxiliary operations
- B29C45/84—Safety devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C45/00—Injection moulding, i.e. forcing the required volume of moulding material through a nozzle into a closed mould; Apparatus therefor
- B29C45/17—Component parts, details or accessories; Auxiliary operations
- B29C45/76—Measuring, controlling or regulating
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C45/00—Injection moulding, i.e. forcing the required volume of moulding material through a nozzle into a closed mould; Apparatus therefor
- B29C45/17—Component parts, details or accessories; Auxiliary operations
- B29C45/84—Safety devices
- B29C45/844—Preventing damage caused by obstructions or foreign matter caught between mould halves during mould closing, e.g. moulded parts or runners
Landscapes
- Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Mechanical Engineering (AREA)
- Image Processing (AREA)
- Injection Moulding Of Plastics Or The Like (AREA)
Abstract
The invention discloses an embedded mold protection device based on wavelet passivation and an image processing method thereof, wherein OMAPL138 is used as a hardware platform, an image processing algorithm uses graying and mean filtering for image preprocessing, the wavelet passivation highlights residues, and then a support vector machine is used for judging whether residues exist in the wavelet passivated and binarized images, so that the accuracy is greatly improved.
Description
[technical field]
The present invention relates to a kind of embedded mould protection device based on small echo passivation and image processing method thereof.
[background technology]
Along with industrial expansion, the production automation is as a Main way of industrial development, simultaneously need to take into account production
Safety and high efficiency, but at present the process of plastic castings is: controller of plastic injection molding controls mould of plastics matched moulds, then toward mould
Intracavity injects the plastic liquid of hot melt shape, and through after a period of time, controller controls mould die sinking, and then thimble is by workpiece top
Going out, in order to not damage die cavity, it is to avoid after die cavity damages, foundry goods there will be the situations such as overlap, deformation, injection machine is other to be typically all equipped with
One workman, now workman will check whether die cavity has residue, it is judged that operates controller of plastic injection molding after not having residue and enters
Row secondary mould closing, the method is it cannot be guaranteed that safety of workers, and does not possess industrial production automation.
At present, general mold protecting device be all by one be specifically designed to the industrial computer of operation image Processing Algorithm, one
Being enclosed between industrial computer and controller of plastic injection molding the image acquisition transmitting data to form with control equipment, industrial computer is adopted by image
Collection obtains view data with controlling equipment, then runs residue evaluation algorithm, it is thus achieved that result issues image by communications protocol
Gathering and control equipment, image acquisition and control equipment, further according to analysis result and controller of plastic injection molding communication, transmit matched moulds ginseng
Examining signal, the method need to install industrial computer in production scene, and cost is high, is not suitable for high-volume injection machine production scene, therefore deposits
In certain limitation.
Therefore, the defect of above-mentioned existence how is overcome, it has also become the important topic that those skilled in the art are urgently to be resolved hurrily.
[summary of the invention]
Instant invention overcomes the deficiency of above-mentioned technology, it is provided that a kind of embedded mould protection device based on small echo passivation
And image processing method, the image processing apparatus constituted by embedded system, complete image procossing and carry out with other equipment
Communication and warning etc. control function, substantially increase the suitability and automatization.
For achieving the above object, present invention employs following technical proposal:
A kind of embedded mould protection device based on small echo passivation, includes shell 1, is provided with process in described shell 1
The image procossing of injection machine die cavity original image and output control signal and protection controller 2, described image procossing and protection control
Device 2 processed connect have for shoot the camera 3 of injection machine die cavity original image, buzzer siren 4, for is connected with injection machine and general
Warning message is transferred to the communicator 5 of injection machine, and the camera 3 after described controller 2 judges image processor 4 process shoots die cavity
Image memory is at residue, then controller 2 is reported to the police by buzzer siren 4 and is transferred to by warning message by communicator 5
Injection machine.
Described image procossing is connected with protection controller 2 LED alarm 6.
Described image procossing is connected with protection controller 2 image buffer 7 of image after caching process.
Described image procossing is connected VGA display 8 with protection controller 2.
A kind of image processing method of embedded mould protection device based on small echo passivation, its step is as follows:
A, image procossing and protection controller 2 obtain the original image of injection machine die cavity by camera 3;
B, with protection controller 2, original image carried out gray processing process by image procossing, analyze and obtain original image
In each pixel R, G and B component, R, G of each pixel and B component are substituted into equation below computing: temp=(r*
299+g*587+b*114+500)/1000, calculate the temp value of each pixel, and the temp value of each pixel is covered former
Beginning image slices vegetarian refreshments, draws gray level image;
C, image procossing and protection controller 2 carry out medium filtering process to gray level image, with 3 pixels of 3 pixel *
It is multiple gray level image modules that point divides gray level image, thus obtains the gray value of 9 pixels in gray level image module, will
9 pixel gray values in each gray level image module carry out equation below computing respectively: gx, y=med{f (x-k, y-l),
(k, l ∈ W) }, the med in formula is median operation, i.e. the pixel in W matrix is first carried out size sequence, then obtains in W matrix
The intermediate value of pixel, and with the Mesophyticum tried to achieve for the pixel value of each gray level image module centers point, obtain medium filtering figure
Picture;
D, image procossing and protection controller 2 carry out 3 layers of wavelet transform process to medium filtering image, pass through wavelet basis functionWherein a is contraction-expansion factor, and τ is shift factor, and (x y) represents that two dimension is the least to make Ψ
Ripple, then two dimension continuous wavelet is defined as:
Wherein,Expression Ψ (x, yardstick y) stretches and two-dimension displacement,Little in order to ensure
Before and after wave conversion, its energy is constant and the normalization factor that introduces, obtains 3 layers of wavelet image;
E, image procossing and protection controller 2 carry out small echo Passivation Treatment to 3 layers of wavelet image, the most respectively to 3 layers
The low frequency decomposition coefficient of wavelet image carries out enhancement process, high-frequency decomposition coefficient carries out attenuation processing, as decomposition coefficient c
(i) > 405 time, then carry out low frequency decomposition coefficient enhancement process, to its weight increase by 4 times, i.e. c (i)=4*c (i);When c (i)≤
When 405, then carry out high frequency coefficient attenuation processing, its weight is decayed to original 0.1, i.e. c (i)=0.1*c (i), obtains little
Ripple passivation image;
F, image procossing carry out binary conversion treatment, through wavelet function feedback with protection controller 2 to small echo passivation image
After image be designated as f (x, y), then the image after binaryzation is
Wherein threshold is the threshold value that binaryzation is chosen, and obtains binary image;
G, image procossing and protection controller 2 carry out the number statistics of pixel 0 and 1 to binary image, and this are added up
Data store as an array;
H, multiple original images are shot for same injection machine die cavity, and each original image is carried out at step 1-7 image
Reason, it is thus achieved that the array of every pictures, by each array input linear kernel function: K (xi,xj)=xi·xj, two class sample x will be obtainedi,
yi, wherein i=1,2 ... n, n are the sample number obtained, and work as xiFor sample class w containing residue1Time, yi=1, work as xiFor not
Sample class w containing residue2Time, yi=-1, the array property i.e. containing residue is labeled as 1, the array property mark of noresidue
It is designated as-1, and Training Support Vector Machines, i.e. tries to achieve disaggregated model:In parameter a*,
b*;
I, when image procossing with protection controller 2 judge that array property is labeled as 1, when i.e. die cavity is contained within residue, figure
To be fed back in controller of plastic injection molding containing residue information by communicator 5 with protection controller 2 as processing, and pass through buzzing
Alarm 4 is reported to the police, and when controller 2 judges that array property is labeled as 1, i.e. there is not residue in die cavity, controller 2 is not
Action.
The invention has the beneficial effects as follows:
1, the image processing apparatus that the present invention is only made up of embedded system, just can complete image procossing and other equipment
Carry out communication, warning etc. and control function, than general by carrying out the industrial computer of image procossing as host computer and as slave computer
The image processing apparatus of control circuit composition is compacter, and space, required production scene is little, can preferably adapt to different work
Environment, has saved many costs than traditional mould protecting industrial computer to be installed;
2, use small echo passivation to be passivated the image after gray scale processing, highlight the profile of die cavity, simultaneously, it is to avoid
The image processing algorithms such as the most commonly used difference shadow method and matching method need to carry out in advance the rigors of image calibration, improve
Real-time and the precision, beneficially later stage of algorithm judge whether mold cavity exists residue;
3, after using statistics binaryzation, the method for 0 and 1 pixel number of image carries out judging whether die cavity contains residual
Thing is rapider with the judgment mode of each pixel pointwise contrast of samples pictures than the picture typically collected, simultaneously
Lower to the storage capacity requirement of image processing system, meet the characteristic of embedded system;
4, use support vector machine when training mode, train two disaggregated models whether containing residue, using
Use this two disaggregated model to judge in the die cavity image collected during pattern and whether contain residue.
5, realizing noncontact and fully automatically realize mould defencive function, the safety improving injection machine production is autonomous with complete
Property.
[accompanying drawing explanation]
Fig. 1 is the structural representation of the present invention;
Fig. 2 is image procossing of the present invention and one of protection controller circuitry figure;
Fig. 3 is the two of image procossing of the present invention and protection controller circuitry figure;
Fig. 4 is the three of image procossing of the present invention and protection controller circuitry figure;
Fig. 5 is the four of image procossing of the present invention and protection controller circuitry figure;
Fig. 6 is communicator circuit diagram of the present invention;
Fig. 7 is one of image buffer circuit diagram of the present invention;
Fig. 8 is the two of image buffer circuit diagram of the present invention;
Fig. 9 is VGA display circuit of the present invention;
Figure 10 is buzzer siren of the present invention and LED alarm circuit figure;
Figure 11 is mold cavity original image;
Figure 12 is the die cavity image after mould gray processing and medium filtering;
Figure 13 is the die cavity image after small echo passivation and two-value.
[detailed description of the invention]
Feature of present invention and other correlated characteristic are described in further detail by embodiment below in conjunction with accompanying drawing, in order to
Understanding in technical staff of the same trade:
As it is shown in figure 1, a kind of embedded mould protection device based on small echo passivation, include shell 1, described shell 1
Inside it is provided with the image procossing processing injection machine die cavity original image and output control signal and protection controller 2, at described image
Reason with protect controller 2 be connected have for shoot the camera 3 of injection machine die cavity original image, buzzer siren 4, for injection
Machine connects and warning message is transferred to the communicator 5 of injection machine, and described controller 2 judges the phase after image processor 4 process
Machine 3 shoots die cavity image memory at residue, then controller 2 is reported to the police by buzzer siren 4 and will be reported to the police by communicator 5
Information is transferred to injection machine.
Wherein, described image procossing is connected with protection controller 2 LED alarm 6, and described image procossing controls with protection
Device 2 connects the image buffer 7 having image after caching process, and described image procossing is connected VGA with protection controller 2 and shows
Device 8.
As shown in Fig. 2, Fig. 3, Fig. 4 and Fig. 5, image procossing is OMAPL138 main control chip with protection controller 2.
As shown in Figure 6, communicator 5 uses asynchronous serial bus communication modes and injection machine to carry out communication, by result
Feed back to injection machine.
As shown in Figure 7 and Figure 8, image buffer 8 includes two parts, and one is to carry out algorithm in system operation
Needing the DDR2 used during process, it stores the view data in each calculating process, and another is FLASH, after storage computing
The number of pixel 0 and 1 of every pictures, it is ensured that after system power failure, the algorithm of native system and the training sample of support vector machine
This storehouse is not lost.
As it is shown in figure 9, the result of image procossing after each algorithm computing is mainly shown by VGA display 9.
As shown in Figure 10, alarm module is made up of buzzer siren 4 and LED alarm 6, when algorithm judges mould now
Intracavity has residue and reports to the police and LED flicker with regard to driving buzzer circuit to carry out.
During work, comprise the following steps:
Step A: when external equipment inputs a high level by Transistor-Transistor Logic level to the D4 pin in Fig. 2, OMAPL138 will
By the pin W19VP_DIN [0] from Fig. 5, W18VP_DIN [1], W17VP_DIN [2], V7VP_DIN [3], W16VP_DIN
[4]、R14VP_DIN[5]、V16VP_DIN[6]、U18VP_DIN[7]、P17VP_DIN[8]、R15VP_DIN[9]、R19VP_
DIN[10]、R18VP_DIN[11]、T16VP_DIN[12]、U19VP_DIN[13]、V19VP_DIN[14]、V18VP_DIN[15]
Obtain view data;
Step B: by the pin U15DDR_D [0] in Fig. 5, U1DDR_D [1], V14DDR_D [2], U13DDR_D [3],
V13DDR_D[4]、V12DDR_D[5]、W12DDR_D[6]、W11DDR_D[7]、T13DDR_D[8]、T11DDR_D[9]、
T10DDR_D[10]、T12DDR_D[11]、U10DDR_D[12]、V10DDR_D[13]、U11DDR_D[14]、W10DDR_D[15]
Cache one group of instant view data in DDR2;
Step C: call image processing algorithm, processes view data, in the result cache of process to DDR2, adds up at algorithm
After the number of complete image 0 and 1 pixel, result is saved in FLASH by pin G17SPI_SIMO and H17SPI_SOMI in Fig. 4
In;
Step D: after judging, by image processing algorithm, the result whether die cavity contains residue, by drawing in Fig. 4
Foot F17UART_RXD and F16UART_TXD sends result to the controller of plastic injection molding of outside;
Step E: if it is judged that die cavity contains residue will drive warning circuit by the pin B3GPIO0 [5] in Fig. 2
Report to the police and drive LED flashing circuit to warn by pin C3GPIO0 [1].
A kind of image processing method of embedded mould protection device based on small echo passivation, its step is as follows:
A, image procossing and protection controller 2 obtain the original image of injection machine die cavity by camera 3, with 7 set 800*400
The mold cavity image of pixel is example, and such as the original image that Figure 11 is the 5th mold chamber, Figure 11 left side is the mould having residue
Chamber image, placed one piece of plastic product of this mould in the plastics forming die cavity of die cavity middle, for noresidue on the right of Figure 11
Thing die cavity image.
B, with protection controller 2, original image carried out gray processing process by image procossing, analyze and obtain original image
In each pixel R, G and B component, R, G of each pixel and B component are substituted into equation below computing: temp=(r*
299+g*587+b*114+500)/1000, calculate the temp value of each pixel, and the temp value of each pixel is covered former
Beginning image slices vegetarian refreshments, draws gray level image;
C, image procossing and protection controller 2 carry out medium filtering process to gray level image, with 3 pixels of 3 pixel *
It is multiple gray level image modules that point divides gray level image, thus obtains the gray value of 9 pixels in gray level image module, will
9 pixel gray values in each gray level image module carry out equation below computing respectively: gx, y=med{f (x-k, y-l),
(k, l ∈ W) }, the med in formula is median operation, i.e. the pixel in W matrix is first carried out size sequence, then obtains in W matrix
The intermediate value of pixel, and with the Mesophyticum tried to achieve for the pixel value of each gray level image module centers point, obtain medium filtering figure
Picture, Figure 12 is the design sketch after the 5th mold gray processing and medium filtering, and wherein Figure 12 left side is the mould gray scale having residue
Change and design sketch after medium filtering, for design sketch after the mould gray processing of noresidue and medium filtering on the right of Figure 12;
D, image procossing and protection controller 2 carry out 3 layers of wavelet transform process to medium filtering image, pass through wavelet basis functionWherein a is contraction-expansion factor, and τ is shift factor, make Ψ (x, y) represent two dimension wavelet,
So two dimension continuous wavelet is defined as:
Wherein,Expression Ψ (x, yardstick y) stretches and two-dimension displacement,Little in order to ensure
Before and after wave conversion, its energy is constant and the normalization factor that introduces, obtains 3 layers of wavelet image;
E, image procossing and protection controller 2 carry out small echo Passivation Treatment to 3 layers of wavelet image, the most respectively to 3 layers
The low frequency decomposition coefficient of wavelet image carries out enhancement process, high-frequency decomposition coefficient carries out attenuation processing, as decomposition coefficient c
(i) > 405 time, then carry out low frequency decomposition coefficient enhancement process, to its weight increase by 4 times, i.e. c (i)=4*c (i);When c (i)≤
When 405, then carry out high frequency coefficient attenuation processing, its weight is decayed to original 0.1, i.e. c (i)=0.1*c (i), obtains little
Ripple passivation image;
F, image procossing carry out binary conversion treatment, through wavelet function feedback with protection controller 2 to small echo passivation image
After image be designated as f (x, y), then the image after binaryzation is
Wherein threshold is the threshold value that binaryzation is chosen, and obtains binary image;
G, image procossing and protection controller 2 carry out the number statistics of pixel 0 and 1 to binary image, and this are added up
Data store as an array, Figure 13 be the 5th mold small echo passivation and binaryzation after design sketch, wherein Figure 13
The left side be have residue small echo passivation and binaryzation after design sketch, the profile of residue can be good at discernable, by
Rough physical characteristic in die cavity so that in image also have some die cavitys profile, but to residue differentiate shadow
Ringing little, for the design sketch not having the small echo of residue to be passivated and after binaryzation on the right of Figure 13, statistics obtains there is residue 0 and 1
The value of pixel is respectively 4523 and 315477;The value of 0 and 1 pixel of noresidue is respectively 2023 and 317177;
H, multiple original images are shot for same injection machine die cavity, and each original image is carried out at step 1-7 image
Reason, it is thus achieved that the array of every pictures, by each array input linear kernel function: K (xi,xj)=xi·xj, two class sample x will be obtainedi,
yi, wherein i=1,2 ... n, n are the sample number obtained, and work as xiFor sample class w containing residue1Time, yi=1, work as xiFor not
Sample class w containing residue2Time, yi=-1, the array property i.e. containing residue is labeled as 1, the array property mark of noresidue
It is designated as-1, and Training Support Vector Machines, i.e. tries to achieve disaggregated model:In parameter a*,
b*, it is thus achieved that after the pixels statistics value of these multiple images of die cavity, use it to carry out based on the support vector machine in linear kernel function
Training, it is thus achieved that accuracy rate is 91.66%;
I, when image procossing with protection controller 2 judge that array property is labeled as 1, when i.e. die cavity is contained within residue, figure
To be fed back in controller of plastic injection molding containing residue information by communicator 5 with protection controller 2 as processing, and pass through buzzing
Alarm 4 is reported to the police, and when controller 2 judges that array property is labeled as 1, i.e. there is not residue in die cavity, controller 2 is not
Action.
For verification algorithm performance, the mold cavity image of 7 set 800*400 pixels is used to verify.Every mold has 10
Open the die cavity image having residue, the image of 10 noresidues, wherein extract 4 figures having residue and 4 noresidues
As the template as Training Support Vector Machines, remain 12 and prove sample as algorithm.Use identical experiment condition simultaneously, with
Gray level co-occurrence matrixes matching algorithm, difference shadow method, as performance comparison algorithm, obtain the accuracy rate of three kinds of algorithm detection residues such as
Shown in table 1, each algorithm runs time-consuming as shown in table 2.
Table 1 die cavity residue Detection accuracy
The detection of table 2 die cavity residue is time-consuming
When this programme algorithm applies to the 1st, 4,5,6 and 7 mold, accuracy rate all maintains more than 90%, the 2nd set and the
3 set accuracys rate are relatively low, by this two sets graphical analysis, analyzing illumination in its reason, mainly image acquisition process strong
Spend different, cause having residue and noresidue die cavity image to carry out wavelet transformation and compare with after binaryzation 0 and 1 number of pixels
Close, next step algorithm optimization, only this situation need to be carried out luminosity and compensate.
According to Tables 1 and 2 experimental data, this programme algorithm has higher than gray level co-occurrence matrixes matching algorithm and difference shadow method
Accuracy rate and lower time-consuming.
As it has been described above, this case protection is a kind of embedded mould protection device based on small echo passivation and image procossing thereof
Method, all technical schemes same or like with this case all should be shown as in the protection domain falling into this case.
Claims (5)
1. an embedded mould protection device based on small echo passivation, it is characterised in that: include shell (1), described shell
(1) image procossing processing injection machine die cavity original image and output control signal and protection controller (2), described figure it are provided with in
As process with protect controller (2) be connected have for shooting injection machine die cavity original image camera (3), buzzer siren (4),
For being connected and be transferred to by warning message the communicator (5) of injection machine with injection machine, described controller (2) judges image procossing
Camera (3) shooting die cavity image memory after device (4) process is at residue, then controller (2) is reported to the police by buzzer siren (4)
And by communicator (5), warning message is transferred to injection machine.
A kind of embedded mould protection device based on small echo passivation the most according to claim 1, it is characterised in that: described
Image procossing is connected with protection controller (2) LED alarm (6).
A kind of embedded mould protection device based on small echo passivation the most according to claim 1, it is characterised in that: described
Image procossing is connected with protection controller (2) the image buffer of image after caching process (7).
A kind of embedded mould protection device based on small echo passivation the most according to claim 1, it is characterised in that: described
Image procossing is connected VGA display (8) with protection controller (2).
5. an image processing method for embedded mould protection device based on small echo passivation, its step is as follows:
A, image procossing and protection controller (2) obtain the original image of injection machine die cavity by camera (3);
B, with protection controller (2), original image carried out gray processing process by image procossing, analyze and obtain in original image
Each pixel R, G and B component, R, G of each pixel and B component are substituted into equation below computing: temp=(r*
299+g*587+b*114+500)/1000, calculate the temp value of each pixel, and the temp value of each pixel is covered former
Beginning image slices vegetarian refreshments, draws gray level image;
C, image procossing and protection controller (2) carry out medium filtering process to gray level image, with 3 pixels of 3 pixel *
Dividing gray level image is multiple gray level image modules, thus obtains the gray value of 9 pixels in gray level image module, will be every
9 pixel gray values in individual gray level image module carry out respectively equation below computing: g (x, y)=med{f (x-k, y-l),
(k, l ∈ W) }, the med in formula is median operation, i.e. the pixel in W matrix is first carried out size sequence, then obtains in W matrix
The intermediate value of pixel, and with the Mesophyticum tried to achieve for the pixel value of each gray level image module centers point, obtain medium filtering figure
Picture;
D, image procossing and protection controller (2) carry out 3 layers of wavelet transform process to medium filtering image, pass through wavelet basis functionτ∈R;A > 0, wherein a is contraction-expansion factor, and τ is shift factor, and (x y) represents that two dimension is the least to make Ψ
Ripple, then two dimension continuous wavelet is defined as:
Wherein,Expression Ψ (x, yardstick y) stretches and two-dimension displacement,Little in order to ensure
Before and after wave conversion, its energy is constant and the normalization factor that introduces, obtains 3 layers of wavelet image;
E, image procossing and protection controller (2) carry out small echo Passivation Treatment to 3 layers of wavelet image, little to 3 layers the most respectively
The low frequency decomposition coefficient of wave conversion image carries out enhancement process, high-frequency decomposition coefficient carries out attenuation processing, when decomposition coefficient c (i) >
When 405, then carry out low frequency decomposition coefficient enhancement process, its weight is increased by 4 times, i.e. c (i)=4*c (i);When c (i)≤405
Time, then carry out high frequency coefficient attenuation processing, its weight is decayed to original 0.1, i.e. c (i)=0.1*c (i), obtains small echo blunt
Change image;
F, image procossing carry out binary conversion treatment, through wavelet function feedback with protection controller (2) to small echo passivation image
After image be designated as f (x, y), then the image after binaryzation is
Wherein threshold is the threshold value that binaryzation is chosen, and obtains binary image;
G, image procossing and protection controller (2) carry out the number statistics of pixel 0 and 1 to binary image, and by this statistical number
Store according to as an array;
H, multiple original images are shot for same injection machine die cavity, and each original image is carried out step 1-7 image procossing, obtain
Obtain the array of every pictures, by each array input linear kernel function: K (xi,xj)=xi·xj, two class sample (x will be obtainedi,yi),
Wherein i=1,2 ... n, n are the sample number obtained, and work as xiFor sample class w containing residue1Time, yi=1, work as xiFor not containing
Sample class w of residue2Time, yi=-1, the array property i.e. containing residue is labeled as 1, the array property labelling of noresidue
For-1, and Training Support Vector Machines, i.e. try to achieve disaggregated model:In parameter a*, b*;
I, when image procossing with protection controller (2) judge that array property is labeled as 1, when i.e. die cavity is contained within residue, image
Process and will be fed back in controller of plastic injection molding containing residue information by communicator (5) with protection controller (2), and pass through honeybee
Ring alarm (4) is reported to the police, when controller (2) judges that array property is labeled as 1, when i.e. there is not residue in die cavity, and control
Device processed (2) is failure to actuate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610459520.8A CN106079338B (en) | 2016-06-21 | 2016-06-21 | Embedded mold protection device based on wavelet passivation and image processing method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610459520.8A CN106079338B (en) | 2016-06-21 | 2016-06-21 | Embedded mold protection device based on wavelet passivation and image processing method thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106079338A true CN106079338A (en) | 2016-11-09 |
CN106079338B CN106079338B (en) | 2018-07-31 |
Family
ID=57252066
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610459520.8A Active CN106079338B (en) | 2016-06-21 | 2016-06-21 | Embedded mold protection device based on wavelet passivation and image processing method thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106079338B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109857367A (en) * | 2018-12-13 | 2019-06-07 | 上海集成电路研发中心有限公司 | A kind of wavelet decomposition accelerating circuit of embedded image processing |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS5734914A (en) * | 1980-08-12 | 1982-02-25 | Fukai Kogyo Kk | Detecting method for residue in resin molding machine |
CN201296028Y (en) * | 2007-07-02 | 2009-08-26 | 优志旺电机株式会社 | Die set monitoring device |
WO2011137264A1 (en) * | 2010-04-28 | 2011-11-03 | Mettler-Toledo, Inc. | Thermal imaging of molded objects |
CN102363354A (en) * | 2011-11-02 | 2012-02-29 | 宁波安信数控技术有限公司 | Mechanical-vision-based injection molding machine mold protecting system and method |
CN102529020A (en) * | 2012-01-31 | 2012-07-04 | 温州大学 | Visual-motor integrated device for mould detection and protection as well as part detection and picking |
CN202572915U (en) * | 2012-03-16 | 2012-12-05 | 温州大学 | Control device of injection molding machine with mould protection |
CN203418734U (en) * | 2013-06-19 | 2014-02-05 | 东莞市旭通达模具塑胶有限公司 | Machine vision based multifunctional injection mold control device |
CN104626492A (en) * | 2015-01-08 | 2015-05-20 | 中国计量学院 | Injection molding monitoring detection system based on machine vision and operation method |
CN205929382U (en) * | 2016-06-21 | 2017-02-08 | 电子科技大学中山学院 | Embedded mould protection device based on wavelet passivation |
-
2016
- 2016-06-21 CN CN201610459520.8A patent/CN106079338B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS5734914A (en) * | 1980-08-12 | 1982-02-25 | Fukai Kogyo Kk | Detecting method for residue in resin molding machine |
CN201296028Y (en) * | 2007-07-02 | 2009-08-26 | 优志旺电机株式会社 | Die set monitoring device |
WO2011137264A1 (en) * | 2010-04-28 | 2011-11-03 | Mettler-Toledo, Inc. | Thermal imaging of molded objects |
CN102363354A (en) * | 2011-11-02 | 2012-02-29 | 宁波安信数控技术有限公司 | Mechanical-vision-based injection molding machine mold protecting system and method |
CN102529020A (en) * | 2012-01-31 | 2012-07-04 | 温州大学 | Visual-motor integrated device for mould detection and protection as well as part detection and picking |
CN202572915U (en) * | 2012-03-16 | 2012-12-05 | 温州大学 | Control device of injection molding machine with mould protection |
CN203418734U (en) * | 2013-06-19 | 2014-02-05 | 东莞市旭通达模具塑胶有限公司 | Machine vision based multifunctional injection mold control device |
CN104626492A (en) * | 2015-01-08 | 2015-05-20 | 中国计量学院 | Injection molding monitoring detection system based on machine vision and operation method |
CN205929382U (en) * | 2016-06-21 | 2017-02-08 | 电子科技大学中山学院 | Embedded mould protection device based on wavelet passivation |
Non-Patent Citations (2)
Title |
---|
杨丁等: "基于机器视觉的注塑模具型腔异常检测", 《工程塑料应用》 * |
盛东亮: "《精通MATLAB图像处理》", 31 May 2015, 清华大学出版社 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109857367A (en) * | 2018-12-13 | 2019-06-07 | 上海集成电路研发中心有限公司 | A kind of wavelet decomposition accelerating circuit of embedded image processing |
CN109857367B (en) * | 2018-12-13 | 2023-06-30 | 上海集成电路研发中心有限公司 | Wavelet decomposition accelerating circuit for embedded image processing |
Also Published As
Publication number | Publication date |
---|---|
CN106079338B (en) | 2018-07-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107492098B (en) | It is a kind of based on PCA and CNN high-temperature forging surface defect in position detecting method | |
CN111046948B (en) | Point cloud simulation and deep learning workpiece pose identification and robot feeding method | |
CN111144548B (en) | Method and device for identifying working condition of oil pumping well | |
CN103559499B (en) | RGB vector matching rapid-recognition system and method | |
CN114463677B (en) | Safety helmet wearing detection method based on global attention | |
CN106067031B (en) | Based on artificial mechanism for correcting errors and deep learning network cooperation machine vision recognition system | |
CN111651622A (en) | Three-dimensional imaging-based automatic classification system and method for building aluminum templates | |
CN111400572A (en) | Content safety monitoring system and method for realizing image feature recognition based on convolutional neural network | |
Xia et al. | Workpieces sorting system based on industrial robot of machine vision | |
CN107818563A (en) | A kind of transmission line of electricity bundle spacing space measurement and localization method | |
CN111340834A (en) | Lining plate assembly system and method based on data fusion of laser radar and binocular camera | |
CN115641517A (en) | Machine vision defect identification method and system, edge side device and storage medium | |
CN106079338A (en) | Embedded mold protection device based on wavelet passivation and image processing method thereof | |
CN117114420B (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
Ren et al. | Steel Surface Defect Detection Using Improved Deep Learning Algorithm: ECA-SimSPPF-SIoU-Yolov5 | |
CN105619741B (en) | A kind of mould intelligent detecting method based on Tegra K1 | |
CN107030690A (en) | A kind of mechanical arm barrier-avoiding method of view-based access control model | |
CN114170686A (en) | Elbow bending behavior detection method based on human body key points | |
CN114092478A (en) | Anomaly detection method | |
CN112381867B (en) | Automatic filling method for large-area depth image cavity of industrial sorting assembly line | |
CN117381793A (en) | Material intelligent detection visual system based on deep learning | |
CN113487538A (en) | Multi-target segmentation defect detection method and device and computer storage medium thereof | |
CN205929382U (en) | Embedded mould protection device based on wavelet passivation | |
Daogang et al. | Anomaly identification of critical power plant facilities based on YOLOX-CBAM | |
CN112836607A (en) | Sheep birth period early warning method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20190605 Address after: 528400 No. 56 Dongfu North Road, Nantou Town, Zhongshan City, Guangdong Province Patentee after: Zhongshan Langdi Electric Appliances Co., Ltd. Address before: 528400 No. 1 College Road, Shiqi District, Zhongshan City, Guangdong Province Patentee before: Zhongshan College, Electronic Science &. Technology Univ. |