CN109035236A - Casting fin detection method and device - Google Patents
Casting fin detection method and device Download PDFInfo
- Publication number
- CN109035236A CN109035236A CN201810846614.XA CN201810846614A CN109035236A CN 109035236 A CN109035236 A CN 109035236A CN 201810846614 A CN201810846614 A CN 201810846614A CN 109035236 A CN109035236 A CN 109035236A
- Authority
- CN
- China
- Prior art keywords
- casting
- image
- tested
- flash
- reference picture
- 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
- 238000005266 casting Methods 0.000 title claims abstract description 239
- 238000001514 detection method Methods 0.000 title claims abstract description 65
- 238000012545 processing Methods 0.000 claims abstract description 25
- 238000005286 illumination Methods 0.000 claims abstract description 13
- 238000003709 image segmentation Methods 0.000 claims description 12
- 206010020112 Hirsutism Diseases 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 11
- 238000012360 testing method Methods 0.000 abstract description 4
- 238000000034 method Methods 0.000 description 21
- 230000006870 function Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000011218 segmentation Effects 0.000 description 5
- 239000003990 capacitor Substances 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 239000002184 metal Substances 0.000 description 3
- 239000004033 plastic Substances 0.000 description 3
- 229920003023 plastic Polymers 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 210000003733 optic disk Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
A kind of casting fin detection method and device are provided, the casting fin detection method includes: the original image for obtaining the tested casting of image acquisition device under preset condition, and the preset condition is using diffusing reflection light source and from the back illumination measured object of measured object；By in the original image background and tested casting be split, to obtain casting image；Opening operation calculating is carried out to the casting image, obtains reference picture；Difference processing is carried out to the casting image and the reference picture, whether has flash with the determination tested casting.The embodiment of the present invention meets in automated manufacturing system to the intelligent requirements of product sequence detection, improves the efficiency of detection and the reliability of testing result.
Description
Technical field
The present invention relates to mould manufacturing fields, more particularly to a kind of casting fin detection method and device.
Background technique
Major part metal and plastic products in process of production, because of objective process flow, are inevitably present at present
Certain flaw, mark, erosion, scratch, flash etc..Especially when that can not be closed completely with grinding tool, generation
Flash, these flashes seriously affect workpiece quality.Therefore, during mechanograph work piece production, for flash detection very
It is important, it is an important link for guaranteeing product quality.
To the detection of casting fin or using artificial conventional method in current production technology, by experience and naked eyes
The case where observation with certain subjectivity and does not know to recognize flash, and there are missing inspections, false retrieval, causes detection efficiency low, and
A large amount of manpowers are expended simultaneously.
Summary of the invention
In view of the above situation, it is necessary to for the low problem of casting fin detection efficiency in the prior art, provide a kind of casting
Part flash detection method and device.
A kind of casting fin detection method, comprising:
The original image of the tested casting of image acquisition device under preset condition is obtained, the preset condition is to use
Diffusing reflection light source and back illumination measured object from measured object；
By in the original image background and tested casting be split, to obtain casting image；
Opening operation calculating is carried out to the casting image, obtains reference picture；
Difference processing is carried out to the casting image and the reference picture, with the determination tested casting whether hairiness
Side.
Further, above-mentioned casting fin detection method, wherein it is described to the casting image and the reference picture into
Row difference is handled, and includes: with the whether deckle-edged step of the determination tested casting
Difference processing is carried out to the casting image and the reference picture, obtains the profile of the tested casting；
Each profile point on the profile of the tested casting is calculated at a distance from the boundary of the reference picture, is obtained more
A distance value；
When any one distance value is greater than threshold distance, determine on the tested casting there is flash.
Further, above-mentioned casting fin detection method, wherein described that opening operation calculating is carried out to the casting image
Step includes:
Using the circle of the radius less than the tested casting as the basic unit of opening operation, the casting image is opened
Operation calculates.
Further, above-mentioned casting fin detection method, wherein the whether deckle-edged step of the determination tested casting
After rapid further include:
When the tested casting has flash, the beginning and end of the flash region is determined；
Calculate separately the angle of the starting point and the terminal relative to the tested casting center.
Further, above-mentioned casting fin detection method, wherein the starting point of the determination flash region and end
Point the step of include:
The region contour of the reference picture is expanded into a pixel outward, to obtain the boundary of the reference picture；
Determine two endpoints of the intersection in the region and the boundary where the flash, and respectively as the flash institute
Beginning and end in region.
Further, above-mentioned casting fin detection method, wherein the background by the original image and tested casting
Part is split, to include: the step of obtaining casting image
Using LBF model by the original image background and tested casting be split, to obtain casting image.
The embodiment of the invention also provides a kind of casting fin detection devices, including image collecting device, lighting device for this
And image processor, the lighting device are mounted on the back side of tested casting region, described image processor includes:
Module is obtained, it is described for obtaining the original image of the tested casting of image acquisition device under preset condition
Preset condition is using diffusing reflection light source and from the back illumination measured object of measured object；
Image segmentation module, for by the original image background and tested casting be split, to obtain casting
Image；
First computing module obtains reference picture for carrying out opening operation calculating to the casting image；
Processing module, it is described tested with determination for carrying out difference processing to the casting image and the reference picture
Whether casting has flash.
Further, above-mentioned casting fin detection device, wherein the processing module is specifically used for:
Difference processing is carried out to the casting image and the reference picture, obtains the profile of the tested casting；
Each profile point on the profile of the tested casting is calculated at a distance from the boundary of the reference picture, is obtained more
A distance value；
When any one distance value is greater than threshold distance, determine on the tested casting there is flash.
Further, above-mentioned casting fin detection device, wherein first computing module is specifically used for:
Using the circle of the radius less than the tested casting as the basic unit of opening operation, the casting image is opened
Operation calculates.
Further, above-mentioned casting fin detection device, further includes:
Determining module, for determining the beginning and end of the flash region when the tested casting has flash；
Second computing module, for calculating separately the angle of the starting point and the terminal relative to the tested casting center
Degree.
Further, above-mentioned casting fin detection device, wherein the determining module is specifically used for:
The region contour of the reference picture is expanded into a pixel outward, to obtain the boundary of the reference picture；
Determine two endpoints of the intersection in the region and the boundary where the flash, and respectively as the flash institute
Beginning and end in region.
Further, above-mentioned casting fin detection device, wherein described image segmentation module is specifically used for:
Using LBF model by the original image background and tested casting be split, to obtain casting image.
The embodiment of the present invention obtains the original image of tested casting using bright field diffusing reflection back illumination methods, is having in this way
Conducive to the casting image zooming-out object to acquisition, background is highlighted, and casting conspicuousness target is black, can be significantly
Improve the speed of subsequent singulation flash.Using the method for image segmentation by tested casting and background segment, and by morphology
Opening operation original image is handled after, subtract opening operation from casting image treated image, can accurate Ground Split
The image of the edge contour of casting out is carried out by the edge contour to casting apart from calculating, so as to accurately judge to be tested
It whether there is flash on casting.The embodiment of the present invention, which meets in automated manufacturing system, wants the intelligence of product sequence detection
It asks, improves the efficiency of detection and the reliability of testing result.
Detailed description of the invention
Fig. 1 is the flow chart of the casting fin detection method in first embodiment of the invention；
The location diagram of Fig. 2 image collecting device and lighting device；
Fig. 3 is the flow chart of the casting fin detection method in second embodiment of the invention；
Fig. 4 is the schematic diagram of the casting image obtained after image segmentation in second embodiment of the invention；
Fig. 5 is the schematic diagram that the image of casting profile is tested in second embodiment of the invention；
Fig. 6 is the position view of flash in second embodiment of the invention.
Fig. 7 is the structural block diagram of the casting fin detection device in third embodiment of the invention；
Fig. 8 is the structural block diagram of the image processor in third embodiment of the invention；
Fig. 9 is the electrical block diagram of warning device in third embodiment of the invention.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and for explaining only the invention, and is not considered as limiting the invention.
Referring to following description and drawings, it will be clear that these and other aspects of the embodiment of the present invention.In these descriptions
In attached drawing, some particular implementations in the embodiment of the present invention are specifically disclosed, to indicate to implement implementation of the invention
Some modes of the principle of example, but it is to be understood that the scope of embodiments of the invention is not limited.On the contrary, of the invention
Embodiment includes all changes, modification and the equivalent fallen within the scope of the spirit and intension of attached claims.
Referring to Fig. 1, this method is applied to casting fin for the casting fin detection method in first embodiment of the invention
In detection device, which includes image collecting device, lighting device and image processor.The Image Acquisition
Device is used for the image using casting, and cmos image acquisition device can be used.The lighting device is used in casting detection process
Middle offer light source, in order to get the image for being clearly tested casting.As shown in Fig. 2, when it is implemented, the lighting device is pacified
Mounted in the back side of tested casting region, i.e., back illumination from tested casting can highlight casting profile.The lighting device uses
Diffusing reflection light source can effectively extract casting salient region by using light field diffused backlit light structures.The image processor
For the image of acquisition to be analyzed and handled, computer equipment or special-purpose imageprocessor may be, for example,.The casting fin
Detection method includes step S11~S14.
Step S11 obtains the original image of the tested casting of image acquisition device under preset condition, the default item
Part is using diffusing reflection light source and from the back illumination measured object of measured object.
The step of this method, can be executed by the image processor of casting fin detection device, which obtains figure
As the original image for the tested casting that acquisition device acquires on a preset condition based.The preset condition is to use irreflexive illumination
Device is from the back side illuminaton of the tested casting casting.Pass through the image for the tested casting that diffusing reflection, bright field backlight acquire, back
Jing Weiliang, target is darker, can significantly improve the speed of subsequent image segmentation.
Step S12, by the original image background and tested casting be split, to obtain casting image.
It is split by the original image that the method for image segmentation is tested casting, by the object in original image from background
Middle separation.There are many existing image segmentation algorithm methods, such as the dividing method based on threshold value, the segmentation side based on edge
Method, the dividing method based on region, dividing method based on clustering etc..In the present embodiment, using LBF (Local
Binary Fitting) model carry out background and measured object segmentation.LBF model is a kind of active contour mould based on region
Type, the algorithm obtain the grayscale information of image using Gaussian function, and without carrying out local gray level Threshold segmentation, gray scale can be with
Approximatively think that there is no deviation fields in the overall situation.When LBF model carries out entirety segmentation, calculation amount is small, convergence of developing is slow fastly,
It is high-efficient.
Step S13 carries out opening operation calculating to the casting image, obtains reference picture.
Step S14 carries out difference processing to the casting image and the reference picture, is with the determination tested casting
It is no to have flash.
Edge in order to determine casting needs to obtain the edge image of casting, with the presence or absence of flash to carry out edge image
Analysis.Flash detection in region is carried out using regional morphology in the present embodiment, the flash at the edge that generally casts a sword is rendered as protrusion
Part subtracts opening operation result using the opening operation of regional morphology from original image.When carrying out opening operation to casting image
Suitable opening operation basic structural unit is determined according to the geomery of casting.The circle of the present embodiment medium casting, therefore use
Circle is used as basic structural unit.Round radius is slightly less than the radius of casting, such as round radius ratio casting radius is slightly less than
Casting edge flash is rejected after 0.01mm can ensure that opening operation, also can avoid removing entire casting object.
Further, it on the basis of above-mentioned opening operation, can once be opened using the window of 5*5 as structural element again
Operation calculates, and further rejects small flash.Opening operation calculating, obtained reference picture medium casting repeatedly are carried out to casting image
It is object contour smoothing, clear.
Difference processing is carried out to casting image and reference picture, i.e., after the object area in original image being subtracted opening operation
Region, so that flash be split.Determine whether tested casting has flash by difference treated image.Specifically,
Determine that the whether deckle-edged specific steps of the tested casting include:
Difference processing is carried out to the casting image and the reference picture, obtains the profile of the tested casting；
Each profile point on the profile of the tested casting is calculated at a distance from the boundary of the reference picture, is obtained more
A distance value；
When any one distance value is greater than threshold distance, determine on the tested casting there is flash.
Wherein, casting image and reference picture carry out difference processing, obtain the profile of tested casting.It calculates on the profile
For each profile point at a distance from reference image border, which refers to vertical range.Here with the tested expection after opening operation
For reference figuration, range conversion is carried out by the region to opening operation to realize the calculating of distance.When on the profile of tested casting
Any one profile point when being greater than preset threshold distance, determine that there are flashes on the tested casting.The pre-determined distance can basis
Actual needs is configured, such as is set as 0.1mm.
The present embodiment obtains the original image of tested casting using bright field diffusing reflection back illumination methods, is being conducive in this way
To the casting image zooming-out object of acquisition, background is highlighted, and casting conspicuousness target is black, can significantly be improved
The speed of subsequent singulation flash.Using the method for image segmentation by tested casting and background segment, and pass through opening in morphology
After operation handles original image, opening operation is subtracted from casting image treated image, can accurately be partitioned into casting
The image of the edge contour of part is carried out apart from calculating by the edge contour to casting, so as to accurately judge tested casting
It is upper to whether there is flash.The present embodiment meets in automated manufacturing system to the intelligent requirements of product sequence detection, improves
The efficiency of detection and the reliability of testing result.
Referring to Fig. 3, for the casting fin detection method in second embodiment of the invention, including step S21~S26.
Step S21 obtains the original image of the tested casting of image acquisition device under preset condition, the default item
Part is using diffusing reflection light source and from the back illumination measured object of measured object.
Carried on the back from the back side illuminaton of the tested casting casting by diffusing reflection, bright field using irreflexive lighting device
The image of the tested casting of light collection, background be it is bright, target is darker, can significantly improve subsequent image segmentation speed.
Step S22, using LBF model by the original image background and tested casting be split, to be cast
Part image.
LBF model is a kind of movable contour model based on region, which obtains the gray scale of image using Gaussian function
Information, and determine by the parameter size of non-negative kernel function the range in the gray value region of fitting.Original image is subjected to figure
As obtaining the casting image (as shown in Figure 4) of removal background after segmentation.
Step S23 carries out opening operation calculating to the casting image, obtains reference picture.
Step S24 carries out difference processing to the casting image and the reference picture, obtains the wheel of the tested casting
It is wide.
The present embodiment is handled casting image using the opening operation in regional morphology, obtains reference picture.And it is right
Casting image and reference picture carry out difference processing, obtain the image (as shown in Figure 5) of tested casting profile, and the contour images are clear
It is clear the case where showing casting edge.The opening operation is used as basic structural unit using circle, and circle is sized to be slightly smaller than casting
Size may insure that the flash on casting can reject in this way, while will not getting rid of whole object.To ensure boundary
Upper small flash region can also reject, and small flash is further rejected as structural element using the window of 5*5 here.
Step S25, calculate the boundary of each profile point and the reference picture on the profile of the tested casting away from
From obtaining multiple distance values.
Step S26 determines on the tested casting there is flash when any one distance value is greater than threshold distance, and
Determine the beginning and end of the flash region.
Each profile point on tested casting profile is calculated at a distance from reference image border, the distance be refer to vertically away from
From.Here reference figuration is expected to tested after opening operation, range conversion is carried out by the region to opening operation come realize away from
From calculating.When any one profile point on the profile of tested casting is greater than preset threshold distance, the tested casting is determined
On there are flashes.When determining has flash on casting, the beginning and end of the flash region is detected.
Specifically, the step of determining the beginning and end of the flash region includes:
The region contour of the reference picture is expanded into a pixel outward, to obtain the boundary of the reference picture；
Determine two endpoints of the intersection in the region and the boundary where the flash, and respectively as the flash institute
Beginning and end in region.
The boundary of reference picture is obtained by expanding the position of a pixel outward on original region, flash region it is every
A connected component all intersects with boundary, by skeleton operator, the endpoint containing intersecting area can be marked off, to any one flash
Region can determine two endpoints, the respectively beginning and end of the flash.
By in morphology range conversion and bone frame can precisely obtain the dimension information of flash, for small hair
Side also can be used the gray scale morphology and reliably detect.
Step S27 calculates separately the angle of the starting point and the terminal relative to the tested casting center.
The present embodiment can calculate the angle of the starting point and terminal of flash relative to tested casting center using arctan function
Degree.As shown in fig. 6, being starting point, the angle of terminal of one of flash.
It should be understood that the flash quantity on casting detected is indefinite in the present embodiment, it may be possible to one may also when
It is multiple, when there are multiple flashes, then it needs to be determined that the beginning and end position of each flash region.Each flash rises
Point is identical with the confirmation method of the position of terminal.
Further, it can be sent out as a kind of enforceable mode of the invention when determining has flash on tested casting
Warning note out.The warning note realizes that the warning device includes buzzer and LED alarm lamp by triggering warning device.
Casting fin detector in the present embodiment can use under a variety of occasions, especially cast in metal and plastics
In part production process, in the sharp keen flash that edge generates, the size and location information of flash can be precisely provided, after being convenient for
Phase handles the rejecting of flash, is of great significance to casting quality context of detection.Meet in automated manufacturing system to product
The intelligence of process detection, improves the efficiency of detection and the reliability of testing result.
Referring to Fig. 7, for the casting fin detection device in third embodiment of the invention, the casting fin detection device packet
Image processor 10 is included, and the image collecting device 20, lighting device 30 and the warning device 40 that connect with the image processor 10.
The lighting device is for providing light source in casting detection process, in order to get the figure for being clearly tested casting
Picture.When it is implemented, the lighting device 30 is mounted on the back side of tested casting region, the i.e. back illumination from tested casting, it can
To highlight casting profile.The lighting device 30 uses diffusing reflection light source, that is, uses light field diffused backlit light structures, can effectively mention
Take casting salient region.
The image collecting device 20 is used for the image using casting, and cmos image acquisition device can be used.Image Acquisition
The original image for the tested casting that device 20 acquires is sent to the analysis and processing that image processor carries out image, to determine the quilt
Survey size and position of the edge with the presence or absence of flash and the flash of casting.Specifically, the image processor as shown in Figure 8
Include:
Module 101 is obtained, for obtaining the original image of the tested casting of image acquisition device under preset condition, institute
Stating preset condition is using diffusing reflection light source and from the back illumination measured object of measured object；
Image segmentation module 102, for by the original image background and tested casting be split, to be cast
Part image；
First computing module 103 obtains reference picture for carrying out opening operation calculating to the casting image；
Processing module 104, for carrying out difference processing to the casting image and the reference picture, with the determination quilt
Survey whether casting has flash.
Further, above-mentioned casting fin detection device, wherein the processing module 104 is specifically used for:
Difference processing is carried out to the casting image and the reference picture, obtains the profile of the tested casting；
Each profile point on the profile of the tested casting is calculated at a distance from the boundary of the reference picture, is obtained more
A distance value；
When any one distance value is greater than threshold distance, determine on the tested casting there is flash.
Further, above-mentioned casting fin detection device, wherein first computing module 103 is specifically used for:
Using the circle of the radius less than the tested casting as the basic unit of opening operation, the casting image is opened
Operation calculates.
Further, above-mentioned casting fin detection device, described image processor further include:
Determining module 105, for determining starting point and the end of the flash region when the tested casting has flash
Point；
Second computing module 106, for calculating separately the starting point and the terminal relative to the tested casting center
Angle.
Further, above-mentioned casting fin detection device, wherein the determining module 105 is specifically used for:
The region contour of the reference picture is expanded into a pixel outward, to obtain the boundary of the reference picture；
Determine two endpoints of the intersection in the region and the boundary where the flash, and respectively as the flash institute
Beginning and end in region.
Further, above-mentioned casting fin detection device, wherein described image segmentation module 102 is specifically used for:
Using LBF model by the original image background and tested casting be split, to obtain casting image.
As shown in figure 9, the warning device 40 include a control circuit 41 and the buzzer 41 that is connect with the control circuit and
LED alarm lamp 42, the control circuit include a monostable flipflop 43, and three poles connecting with the monostable flipflop 43
Pipe Q1.74LS122 chip for example can be used in the monostable flipflop 43, and positive pulse output end Q passes through resistance connection one or three
The base stage of pole pipe Q1, the collector of triode Q1 connect the buzzer 41, and emitter connects LED alarm lamp 42, LED alarm
Lamp 42 is grounded.The one capacitor C1 of external capacitor end CX connection of the monostable flipflop 43, capacitor C1 connection first resistor R1,
The other end of first resistor R1 is connect with one end of second resistance R2, and the other end of second resistance R2 is connect with buzzer 41.
The positive triggering input terminal B1 of the monostable flipflop is connect with image processor 10.Image processor is according to tested casting image point
The result of analysis exports corresponding electric signal control buzzer and LED alarm lamp work.
Specifically, when image processor analyzes the tested casting, there are the monostable flipflops 43 when flash, triggered again
Continuous impulse signal is converted into high level, under the high level triggering of the signal of output end Q output, driver triode drives bee
Ring device 41 and LED alarm lamp 42 work.It should be noted that 43 output end signal pulse of monostable flipflop need to be greater than acquisition letter
Number integration period.
Further, which further includes a display screen 50 connecting with image processor 10 and control
Panel 60.Multiple keys are arranged on the control panel 60 to be respectively used to control the function of casting fin detection device.Example
Such as, the opening and closing of the casting fin detection device, and reset and the output side of control casting fin detection device are controlled
Formula.
The display screen 50 is connect with image processor 10, for receiving the flash parameterized information of the transmission of image processor 10
Such as size and location information, and the information that real-time dynamicly display image processor 10 is sent, in order to which user checks.
Casting fin detection device in the present embodiment can use under a variety of occasions, especially in metal and plastics
During castings production, in the sharp keen flash that edge generates, the size and location information of flash can be precisely provided, is convenient for
Later period handles the rejecting of flash, is of great significance to casting quality context of detection.Meanwhile the present embodiment in the present embodiment
In the used consumptive material price of casting fin detection device it is cheap, forming cost is lower, can be widely popularized in castings production process
In middle quality testing link.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction
The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicates, propagates or pass
Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment
It sets.
The more specific example (non-exhaustive list) of computer-readable medium include the following: there are one or more wirings
Electrical connection section (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other are suitable
Medium, because can then be edited, be interpreted or when necessary with it for example by carrying out optical scanner to paper or other media
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiment or examples in can be combined in any suitable manner.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
Limitations on the scope of the patent of the present invention therefore cannot be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to guarantor of the invention
Protect range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (10)
1. a kind of casting fin detection method characterized by comprising
The original image of the tested casting of image acquisition device under preset condition is obtained, the preset condition is using unrestrained anti-
Penetrate light source and the back illumination measured object from measured object；
By in the original image background and tested casting be split, to obtain casting image；
Opening operation calculating is carried out to the casting image, obtains reference picture；
Difference processing is carried out to the casting image and the reference picture, whether has flash with the determination tested casting.
2. the casting fin detection method as described in right wants 1, which is characterized in that described to the casting image and the reference
Image carries out difference processing, includes: with the whether deckle-edged step of the determination tested casting
Difference processing is carried out to the casting image and the reference picture, obtains the profile of the tested casting；
Each profile point on the profile of the tested casting is calculated at a distance from the boundary of the reference picture, obtain it is multiple away from
From value；
When any one distance value is greater than threshold distance, determine on the tested casting there is flash.
3. the casting fin detection method as described in right wants 1, which is characterized in that described to carry out opening operation to the casting image
The step of calculating includes:
Using the circle of the radius less than the tested casting as the basic unit of opening operation, opening operation is carried out to the casting image
It calculates.
4. the casting fin detection method as described in right wants 1, which is characterized in that the determination tested casting whether hairiness
After the step of side further include:
When the tested casting has flash, the beginning and end of the flash region is determined；
Calculate separately the angle of the starting point and the terminal relative to the tested casting center.
5. the casting fin detection method as described in right wants 4, which is characterized in that rise the determination flash region
Point and the step of terminal include:
The region contour of the reference picture is expanded into a pixel outward, to obtain the boundary of the reference picture；
Determine two endpoints of the intersection in the region and the boundary where the flash, and respectively as the flash location
The beginning and end in domain.
6. the casting fin detection method as described in right wants 1, which is characterized in that the background by the original image and
Tested casting is split, to include: the step of obtaining casting image
Using LBF model by the original image background and tested casting be split, to obtain casting image.
7. a kind of casting fin detection device, which is characterized in that including image collecting device, lighting device and image processor,
The lighting device is mounted on the back side of tested casting region, and described image processor includes:
Module is obtained, it is described default for obtaining the original image of the tested casting of image acquisition device under preset condition
Condition is using diffusing reflection light source and from the back illumination measured object of measured object；
Image segmentation module, for by the original image background and tested casting be split, to obtain casting image；
First computing module obtains reference picture for carrying out opening operation calculating to the casting image；
Processing module, for carrying out difference processing to the casting image and the reference picture, with the determination tested casting
Whether flash is had.
8. casting fin detection device as claimed in claim 7, which is characterized in that the processing module is specifically used for:
Difference processing is carried out to the casting image and the reference picture, obtains the profile of the tested casting；
Each profile point on the profile of the tested casting is calculated at a distance from the boundary of the reference picture, obtain it is multiple away from
From value；
When any one distance value is greater than threshold distance, determine on the tested casting there is flash.
9. casting fin detection device as claimed in claim 7, which is characterized in that first computing module is specifically used for:
Using the circle of the radius less than the tested casting as the basic unit of opening operation, opening operation is carried out to the casting image
It calculates.
10. casting fin detection device as claimed in claim 7, which is characterized in that further include:
Determining module, for determining the beginning and end of the flash region when the tested casting has flash；
Second computing module, for calculating separately the angle of the starting point and the terminal relative to the tested casting center.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810846614.XA CN109035236B (en) | 2018-07-27 | 2018-07-27 | Casting burr detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810846614.XA CN109035236B (en) | 2018-07-27 | 2018-07-27 | Casting burr detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109035236A true CN109035236A (en) | 2018-12-18 |
| CN109035236B CN109035236B (en) | 2024-02-23 |
Family
ID=64646249
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810846614.XA Active CN109035236B (en) | 2018-07-27 | 2018-07-27 | Casting burr detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109035236B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114387438A (en) * | 2022-03-23 | 2022-04-22 | 武汉锦辉压铸有限公司 | Machine vision-based die casting machine parameter regulation and control method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102080786A (en) * | 2010-10-18 | 2011-06-01 | 丰铁流 | Multi-pyramid light emitting diode (LED) diffuse reflection backlight source |
| CN203750868U (en) * | 2013-11-20 | 2014-08-06 | 南京信息工程大学 | Computer vision-based burr detection device |
| CN104075659A (en) * | 2014-06-24 | 2014-10-01 | 华南理工大学 | Three-dimensional imaging recognition method based on RGB structure light source |
| CN104981105A (en) * | 2015-07-09 | 2015-10-14 | 广东工业大学 | Detecting and error-correcting method capable of rapidly and accurately obtaining element center and deflection angle |
| CN106017328A (en) * | 2015-12-17 | 2016-10-12 | 广东正业科技股份有限公司 | Method and device for measuring various types of line widths |
| CN106296636A (en) * | 2015-06-02 | 2017-01-04 | 征图新视（江苏）科技有限公司 | The detection method of printing image and detection device |
| CN106404793A (en) * | 2016-09-06 | 2017-02-15 | 中国科学院自动化研究所 | Method for detecting defects of bearing sealing element based on vision |
| WO2017032308A1 (en) * | 2015-08-25 | 2017-03-02 | 广州视源电子科技股份有限公司 | Pcb board detection method and apparatus |
| CN107808378A (en) * | 2017-11-20 | 2018-03-16 | 浙江大学 | Complicated structure casting latent defect detection method based on vertical co-ordination contour feature |
-
2018
- 2018-07-27 CN CN201810846614.XA patent/CN109035236B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102080786A (en) * | 2010-10-18 | 2011-06-01 | 丰铁流 | Multi-pyramid light emitting diode (LED) diffuse reflection backlight source |
| CN203750868U (en) * | 2013-11-20 | 2014-08-06 | 南京信息工程大学 | Computer vision-based burr detection device |
| CN104075659A (en) * | 2014-06-24 | 2014-10-01 | 华南理工大学 | Three-dimensional imaging recognition method based on RGB structure light source |
| CN106296636A (en) * | 2015-06-02 | 2017-01-04 | 征图新视（江苏）科技有限公司 | The detection method of printing image and detection device |
| CN104981105A (en) * | 2015-07-09 | 2015-10-14 | 广东工业大学 | Detecting and error-correcting method capable of rapidly and accurately obtaining element center and deflection angle |
| WO2017032308A1 (en) * | 2015-08-25 | 2017-03-02 | 广州视源电子科技股份有限公司 | Pcb board detection method and apparatus |
| CN106017328A (en) * | 2015-12-17 | 2016-10-12 | 广东正业科技股份有限公司 | Method and device for measuring various types of line widths |
| CN106404793A (en) * | 2016-09-06 | 2017-02-15 | 中国科学院自动化研究所 | Method for detecting defects of bearing sealing element based on vision |
| CN107808378A (en) * | 2017-11-20 | 2018-03-16 | 浙江大学 | Complicated structure casting latent defect detection method based on vertical co-ordination contour feature |
Non-Patent Citations (2)
| Title |
|---|
| 李冬: "基于FPGA的金属毛刺视觉检测系统研究与实现", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》, pages 022 - 1345 * |
| 郭杰;雷刚;陈健生;向守兵;: "基于机器视觉的钢包头检测系统设计", 液晶与显示, no. 05, pages 4 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114387438A (en) * | 2022-03-23 | 2022-04-22 | 武汉锦辉压铸有限公司 | Machine vision-based die casting machine parameter regulation and control method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109035236B (en) | 2024-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11221107B2 (en) | Method for leakage detection of underground pipeline corridor based on dynamic infrared thermal image processing | |
| CN109822398B (en) | Numerical control machine tool broken cutter detection system and method based on deep learning | |
| CN106846734B (en) | A kind of fatigue driving detection device and method | |
| CN104331710B (en) | On off state identifying system | |
| CN104574353B (en) | The surface defect decision method of view-based access control model conspicuousness | |
| EP2575077A2 (en) | Road sign detecting method and road sign detecting apparatus | |
| US8965068B2 (en) | Apparatus and method for discriminating disguised face | |
| CN102628854A (en) | Automobile instrument board detection system and method | |
| Zhang et al. | A multi-feature fusion based traffic light recognition algorithm for intelligent vehicles | |
| CN110930357A (en) | In-service steel wire rope surface defect detection method and system based on deep learning | |
| CN105354985A (en) | Fatigue driving monitoring device and method | |
| CN106909879A (en) | A kind of method for detecting fatigue driving and system | |
| CN104915642B (en) | Front vehicles distance measuring method and device | |
| CN109115775B (en) | Betel nut grade detection method based on machine vision | |
| CN108009574A (en) | A kind of rail clip detection method | |
| Su et al. | A new local-main-gradient-orientation HOG and contour differences based algorithm for object classification | |
| CN108073940A (en) | A kind of method of 3D object instance object detections in unstructured moving grids | |
| KR20190114241A (en) | Apparatus for algae classification and cell countion based on deep learning and method for thereof | |
| CN113221603A (en) | Method and device for detecting shielding of monitoring equipment by foreign matters | |
| CN109035236A (en) | Casting fin detection method and device | |
| CN114998205A (en) | Method for detecting foreign matters in bottle in liquid filling process based on optical means | |
| CN102496030B (en) | Identification method and identification device for dangerous targets in power monitoring system | |
| CN108563997B (en) | Method and device for establishing face detection model and face recognition | |
| Ashourian et al. | Real time implementation of a license plate location recognition system based on adaptive morphology | |
| CN113793322A (en) | Method for automatically detecting magnetic material, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |