CN109146871A - Crack identification method and device - Google Patents
Crack identification method and device Download PDFInfo
- Publication number
- CN109146871A CN109146871A CN201811013768.7A CN201811013768A CN109146871A CN 109146871 A CN109146871 A CN 109146871A CN 201811013768 A CN201811013768 A CN 201811013768A CN 109146871 A CN109146871 A CN 109146871A
- Authority
- CN
- China
- Prior art keywords
- area
- magnetic shoe
- shoe product
- crackle
- product image
- 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
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000001514 detection method Methods 0.000 claims abstract description 63
- 208000037656 Respiratory Sounds Diseases 0.000 claims description 72
- 230000005855 radiation Effects 0.000 claims description 21
- 239000000284 extract Substances 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 15
- 230000011218 segmentation Effects 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 10
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 230000007547 defect Effects 0.000 abstract description 17
- 238000005516 engineering process Methods 0.000 abstract description 11
- 238000010586 diagram Methods 0.000 description 15
- 238000012360 testing method Methods 0.000 description 5
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012797 qualification Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000004590 computer program Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- VMXUWOKSQNHOCA-UKTHLTGXSA-N ranitidine Chemical compound [O-][N+](=O)\C=C(/NC)NCCSCC1=CC=C(CN(C)C)O1 VMXUWOKSQNHOCA-UKTHLTGXSA-N 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000005491 wire drawing Methods 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
-
- 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
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Investigating Or Analyzing Materials By The Use Of Magnetic Means (AREA)
Abstract
The invention discloses a crack identification method and device. Wherein, the method comprises the following steps: acquiring a magnetic tile product image of a magnetic tile product to be detected; acquiring a target detection area of the magnetic tile product image based on a preset mode; extracting a characteristic region in the target detection region, wherein the characteristic region is a region with cracks in the magnetic tile product; and extracting an initial crack line from the characteristic region, and obtaining a target crack line according to the initial crack line. The invention solves the technical problem of low reliability of the detection result caused by adopting a manual mode to detect the crack defects of the magnetic shoe product in the related technology.
Description
Technical field
The present invention relates to technical field of vision detection, recognition methods and device in particular to a kind of crackle.
Background technique
The consistency of magnetic shoe product is poor, and surface wire drawing textural characteristics and color homogeneity are bad, and at present for magnetic shoe
The detection of surface crack defect also depend primarily on artificial visual sampling observation, do not only result in the detection efficiency of magnetic shoe product compared with
It is low, it can not accurately detect the crack defect of magnetic shoe product.Another aspect can not manually concentrate one's energy to focus for a long time
It is higher to will lead to False Rate in magnetic shoe product testing result for fine crack defect.
Manual type is used to carry out detecting caused detection to the crack defect of magnetic shoe product in the related technology for above-mentioned
As a result the lower problem of reliability, currently no effective solution has been proposed.
Summary of the invention
The embodiment of the invention provides a kind of recognition methods of crackle and devices, at least to solve in the related technology using people
The lower technical problem of the reliability of testing result caused by work mode detects the crack defect of magnetic shoe product.
According to an aspect of an embodiment of the present invention, a kind of recognition methods of crackle is provided, comprising: obtain to be detected
The magnetic shoe product image of magnetic shoe product;The object detection area of the magnetic shoe product image is obtained based on predetermined way;Extract institute
State the characteristic area in object detection area, wherein the characteristic area is that there are the regions of crackle in the magnetic shoe product;From
It extracts in the characteristic area by initial crack lines, and according to the initial crack lines and obtains target crackle lines.
At least one of optionally, in the following manner, it obtains the magnetic shoe product image of magnetic shoe product to be detected: passing through
Industrial camera obtains the magnetic shoe product image;The magnetic shoe product image is obtained by high-energy hard radiation.
Optionally, obtaining the magnetic shoe product image by high-energy hard radiation includes: by the magnetic shoe to be detected
Product is placed on the detection zone of the high-energy hard radiation;By adjusting the predefined parameter of the high-energy hard radiation,
Obtain the magnetic shoe product image, wherein the predefined parameter includes at least one of: wavelength, frequency.
Optionally, the object detection area for obtaining the magnetic shoe product image based on predetermined way includes: based on gray scale threshold
Value partitioning scheme splits multiple first presumptive areas from the magnetic shoe product image;Determine that the multiple first is predetermined
The area of each first presumptive area in region;The multiple first is filtered out according to the area of each first presumptive area
The first presumptive area of part in presumptive area, obtains object detection area.
Optionally, the characteristic area in the object detection area is extracted includes: based on gray level threshold segmentation side
Formula splits multiple second presumptive areas from the object detection area;It determines every in the multiple second presumptive area
The area of a second presumptive area;The maximum second area of area in the multiple second presumptive area is extracted as institute
State characteristic area.
Optionally, extract initial crack lines from the characteristic area includes: to carry out to the characteristic area
After value processing, predetermined slit region is extracted in the way of dynamic threshold;Region is carried out to the predetermined slit region
Expansion process;It is carrying out obtaining the initial crack lines in the predetermined slit region after the expansion process of region.
Optionally, according to the initial crack lines obtain target crackle lines include: to the initial crack lines into
Row operation splitting obtains a plurality of discontinuous straightway;Operation is fitted to a plurality of discontinuous straightway, is obtained more
The continuous straightway of item;According to the target crackle lines determining in a plurality of continuous straightway.
Another aspect according to an embodiment of the present invention, additionally provides a kind of identification device of crackle, comprising: first obtains
Unit is taken, for obtaining the magnetic shoe product image of magnetic shoe product to be detected;Second acquisition unit, for being obtained based on predetermined way
Take the object detection area of the magnetic shoe product image;Extraction unit, for extracting the characteristic area in the object detection area
Domain, wherein the characteristic area is that there are the regions of crackle in the magnetic shoe product;Third acquiring unit is used for from the spy
It extracts in sign region by initial crack lines, and according to the initial crack lines and obtains target crackle lines.
Optionally, the first acquisition unit includes at least one of: first obtains module, for passing through industrial camera
Obtain the magnetic shoe product image;Second obtains module, for obtaining the magnetic shoe product image by high-energy hard radiation.
Optionally, the second acquisition module comprises determining that submodule, for placing the magnetic shoe product to be detected
In the detection zone of the high-energy hard radiation;Acquisition submodule, for by adjusting the pre- of the high-energy hard radiation
Determine parameter, obtains the magnetic shoe product image, wherein the predefined parameter includes at least one of: wavelength, frequency.
Optionally, the second acquisition unit includes: the first segmentation module, will be more for being based on gray level threshold segmentation mode
A first presumptive area is split from the magnetic shoe product image;First determining module, for determining the multiple first
The area of each first presumptive area in presumptive area;Third obtains module, for according to each first presumptive area
Area filters out the first presumptive area of part in the multiple first presumptive area, obtains object detection area.
Optionally, the extraction unit includes: the second segmentation module, for based on gray level threshold segmentation mode by multiple the
Two presumptive areas are split from the object detection area;Second determining module, for determining that the multiple second is predetermined
The area of each second presumptive area in region;Third determining module is used for area in the multiple second presumptive area most
Big second area is extracted as the characteristic area.
Optionally, the third acquiring unit includes: extraction module, for the characteristic area carry out average value processing it
Afterwards, predetermined slit region is extracted in the way of dynamic threshold;Processing module, for being carried out to the predetermined slit region
Region expansion process;4th obtains module, for carrying out in the predetermined slit region after the expansion process of region, obtains described first
Beginning crackle lines.
Optionally, the third acquiring unit further include: the 5th obtains module, for carrying out to the initial crack lines
Operation splitting obtains a plurality of discontinuous straightway;6th obtains module, for carrying out to a plurality of discontinuous straightway
Fit operation obtains a plurality of continuous straightway;4th determining module, for being determined according in a plurality of continuous straightway
The target crackle lines.
Another aspect according to an embodiment of the present invention, additionally provides a kind of storage medium, the storage medium includes
The program of storage, wherein described program execute it is any one of above-mentioned described in crackle recognition methods.
Another aspect according to an embodiment of the present invention, additionally provides a kind of processor, the processor is for running
Program, wherein described program run when execute it is any one of above-mentioned described in crackle recognition methods.
In embodiments of the present invention, using the magnetic shoe product image for obtaining magnetic shoe product to be detected;Based on predetermined way
Obtain the object detection area of magnetic shoe product image;Extract the characteristic area in object detection area, wherein characteristic area is magnetic
There are the regions of crackle in watt product;It extracts from characteristic area and is obtained by initial crack lines, and according to initial crack lines
Target crackle lines, the recognition methods of the crackle provided through the embodiment of the present invention may be implemented to magnetic shoe product to be detected into
The purpose of row automatic detection has reached the qualification rate for improving magnetic shoe product and has saved the technical effect of cost of labor, simultaneously
Also labour has been liberated, production efficiency is improved, and then has solved and magnetic shoe product is split using manual type in the related technology
The lower technical problem of the reliability of testing result caused by line defect is detected.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is the flow chart of the recognition methods of crackle according to an embodiment of the present invention;
Fig. 2 is the schematic diagram of magnetic shoe product image according to an embodiment of the present invention;
Fig. 3 is the schematic diagram of magnetic shoe product according to an embodiment of the present invention;
Fig. 4 is the schematic diagram of object detection area according to an embodiment of the present invention;
Fig. 5 is the schematic diagram of characteristic area according to an embodiment of the present invention;
Fig. 6 is the schematic diagram of predetermined slit region according to an embodiment of the present invention;
Fig. 7 is the schematic diagram of initial crack lines according to an embodiment of the present invention;
Fig. 8 is the schematic diagram of the crackle lines according to an embodiment of the present invention that set the goal;
Fig. 9 is the flow chart of the recognition methods of optional crackle according to an embodiment of the present invention;
Figure 10 is the schematic diagram of the identification device of crackle according to an embodiment of the present invention.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The model that the present invention protects all should belong in member's every other embodiment obtained without making creative work
It encloses.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
For ease of description, below in the embodiment of the present invention part noun or term be described in detail.
Gray threshold: be all brightness values in image are divided into according to specified brightness value (i.e. threshold value) higher than threshold value and
Lower than two classes of threshold value, the black and white mask image generated in this way can separate the biggish atural object of contrast difference, such as land
Ground and water body, to be further processed respectively to land or water body.
Embodiment 1
According to embodiments of the present invention, a kind of embodiment of the method for the recognition methods of crackle is provided, it should be noted that
The step of process of attached drawing illustrates can execute in a computer system such as a set of computer executable instructions, also,
It, in some cases, can be to be different from shown in sequence execution herein although logical order is shown in flow charts
The step of out or describing.
Fig. 1 is the flow chart of the recognition methods of crackle according to an embodiment of the present invention, as shown in Figure 1, the identification of the crackle
Method includes the following steps:
Step S102 obtains the magnetic shoe product image of magnetic shoe product to be detected.
In order to realize the full-automatic detection of magnetic shoe product surface crackle, need to obtain realtime graphic (the i.e. magnetic shoe of magnetic shoe
Product image), and analyze using image processing techniques the crack of magnetic shoe product surface, wherein Fig. 2 is according to the present invention
The schematic diagram of the magnetic shoe product image of embodiment.
At least one of it is alternatively possible in the following manner, obtain the magnetic shoe product image of magnetic shoe product to be detected:
Magnetic shoe product image is obtained by industrial camera;Magnetic shoe product image is obtained by high-energy hard radiation.That is, in addition to that can lead to
The magnetic shoe product image that industrial camera obtains magnetic shoe product to be detected is crossed, it is also possible to using high-energy hard radiation (example
Such as, X-ray) obtain the magnetic shoe product image of magnetic shoe product to be detected.Wherein, Fig. 3 is magnetic according to an embodiment of the present invention
The schematic diagram of watt product can be placed magnetic shoe product to be detected when being obtained magnetic shoe product image by the way of the latter
In effective detection zone of high-energy hard radiation, obtained by parameters such as the wavelength of adjusting high-energy hard radiation and frequencies
Ideal magnetic shoe product image.
It that is to say, obtaining magnetic shoe product image by high-energy hard radiation may include: by magnetic shoe product to be detected
It is placed on the detection zone of high-energy hard radiation;By adjusting the predefined parameter of high-energy hard radiation, magnetic shoe product is obtained
Image, wherein predefined parameter includes at least one of: wavelength, frequency.
Step S104 obtains the object detection area of magnetic shoe product image based on predetermined way.
Step S106 extracts the characteristic area in object detection area, wherein characteristic area is to exist to split in magnetic shoe product
The region of line.
Step S108 is extracted initial crack lines from characteristic area, and is obtained target according to initial crack lines and split
Streakline item.
Through the above steps, the magnetic shoe product image of available magnetic shoe product to be detected;It is obtained based on predetermined way
The object detection area of magnetic shoe product image;Extract the characteristic area in object detection area, wherein characteristic area is that magnetic shoe produces
There are the regions of crackle in product;It extracts from characteristic area by initial crack lines, and according to initial crack lines and obtains target
Crackle lines.Relative to artificial mesh is depended on when the surface crack defect to magnetic shoe product detects in the related technology
Depending on sampling observation, it is easy to cause the detection efficiency of magnetic shoe product lower, can not accurately detects the disadvantage of the crack defect of magnetic shoe product
End.The recognition methods of the crackle provided through the embodiment of the present invention may be implemented to carry out automation inspection to magnetic shoe product to be detected
The purpose of survey has reached the qualification rate for improving magnetic shoe product and has saved the technical effect of cost of labor, while also having liberated labor
Power improves production efficiency, and then solves and carried out in the related technology using crack defect of the manual type to magnetic shoe product
The lower technical problem of the reliability of testing result caused by detecting.
As an optional embodiment of the present invention, the object detection area of magnetic shoe product image is obtained based on predetermined way
It may include: to be split multiple first presumptive areas from magnetic shoe product image based on gray level threshold segmentation mode;It determines
The area of each first presumptive area in multiple first presumptive areas;It is filtered out according to the area of each first presumptive area multiple
The first presumptive area of part in first presumptive area, obtains object detection area.
For example, can use gray threshold algorithm (gray level threshold segmentation mode) for the black region in magnetic shoe product image
(i.e. the first presumptive area) is split, and small black region is excluded according to the size of each black region, then
The black region edge extracted is subjected to round and smooth processing using convex body profile deformation algorithm, obtains object detection area.
Wherein, Fig. 4 is the schematic diagram of object detection area according to an embodiment of the present invention.
After obtaining object detection area, the recognition methods of the crackle further include: by the feature in object detection area
Extracted region comes out.Wherein, the characteristic area in object detection area is extracted may include: based on gray level threshold segmentation
Mode splits multiple second presumptive areas from object detection area;It determines each second in multiple second presumptive areas
The area of presumptive area;The maximum second area of area in multiple second presumptive areas is extracted as characteristic area.
For example, gray threshold algorithm can be continued with by the white area (i.e. the second presumptive area) inside black region
It extracts, and extracts the maximum white area of area after dividing, that is to say the white area of middle, recycle form
The edge of the round and smooth processing white area of algorithm is learned, to obtain characteristic area.Wherein, Fig. 5 is feature according to an embodiment of the present invention
The schematic diagram in region.
Preferably, extract initial crack lines from characteristic area may include: to carry out from mean value to characteristic area
After reason, predetermined slit region is extracted in the way of dynamic threshold;Region expansion process is carried out to predetermined slit region;
It is carrying out in the predetermined slit region after the expansion process of region, is obtaining initial crack lines.
For example, after obtaining characteristic area, average value processing then is carried out to characteristic area, carry out average value processing it
Afterwards, black slit region (i.e. predetermined slit region) is extracted using dynamic threshold algorithm, and it is swollen to carry out region appropriate
Swollen processing expands black slit region.Wherein, Fig. 6 is the schematic diagram of predetermined slit region according to an embodiment of the present invention.
Specifically, obtaining target crackle lines according to initial crack lines may include: to divide initial crack lines
Solution operation, obtains a plurality of discontinuous straightway;Operation is fitted to a plurality of discontinuous straightway, is obtained a plurality of continuous
Straightway;According to target crackle lines determining in a plurality of continuous straightway.
That is, after carrying out expansion processing to black slit region, it is also necessary to using looking for line segment to calculate in black slit region
Method all extracts potential crackle (i.e. initial crack lines).Fig. 7 is initial crack line according to an embodiment of the present invention
The schematic diagram of item, as shown in fig. 7, potential crackle be all it is continuous, can be by linear regression decomposition algorithm by potential crack
Crackle lines resolve into multiple discontinuous straightways, and utilize less parallel line regression fit algorithm, each straightway intended
Synthesize complete lines, and can will be real by certain screening regular (for example, the gray scale of lines, length and width)
Crack defect extracted from magnetic shoe product image.Fig. 8 is showing for the crackle lines according to an embodiment of the present invention that set the goal
It is intended to.
The recognition methods for the crackle recorded with reference to the accompanying drawing to the embodiment of the present invention is described in detail.
Fig. 9 is the flow chart of the recognition methods of optional crackle according to an embodiment of the present invention, as shown in figure 9, this method
The following steps are included:
Step S901 obtains the realtime graphic (magnetic shoe product image) of magnetic shoe product to be detected.
Step S902 is separated object detection area using gray threshold algorithm from realtime graphic.I.e. black region mentions
It takes.
Step S903 is separated characteristic area using gray threshold algorithm and Morphology Algorithm from object detection area.
I.e. white area extracts.
Step S904 is extracted slit region using dynamic threshold and Morphology Algorithm.
Step S905 is extracted the potential crack lines in slit region using line algorithm is looked for.
Step S906 is decomposed and less parallel line fitting algorithm, extraction crack defect using straight line.
The recognition methods of the crackle provided through the embodiment of the present invention may be implemented to identify using mechanical vision inspection technology
The crack defect of magnetic shoe product surface, it is necessary first to build the realtime graphic that automation equipment obtains magnetic shoe product, magnetic shoe is produced
Product split to obtain magnetic shoe product image from background, and by white area (i.e. the second fate in magnetic shoe product image
Domain namely crackle region) it splits, then crackle region is split using dynamic threshold algorithm, finally
Using looking for line algorithm to find out potential crackle, by linear regression decomposition and less parallel line regression fit, obtain really
Crack defect.
Embodiment 2
A kind of identification device of crackle is additionally provided according to embodiments of the present invention, it should be noted that the embodiment of the present invention
The identification device of crackle can be used for executing the recognition methods of crackle provided by the embodiment of the present invention.Below to of the invention real
The identification device for applying the crackle of example offer is introduced.
Figure 10 is the schematic diagram of the identification device of crackle according to an embodiment of the present invention, as shown in Figure 10, the knowledge of the crackle
Other device may include: first acquisition unit 1001, second acquisition unit 1003, extraction unit 1005 and third acquiring unit
1007.The identification device of the crackle is described in detail below.
First acquisition unit 1001, for obtaining the magnetic shoe product image of magnetic shoe product to be detected.
Second acquisition unit 1003, for obtaining the object detection area of magnetic shoe product image based on predetermined way.
Extraction unit 1005, for extracting the characteristic area in object detection area, wherein characteristic area is magnetic shoe product
It is middle that there are the regions of crackle.
Third acquiring unit 1007, for extracting from characteristic area by initial crack lines, and according to initial crack line
Item obtains target crackle lines.
In embodiments of the present invention, the magnetic shoe product figure of magnetic shoe product to be detected can be obtained using first acquisition unit
Picture;Then the object detection area of magnetic shoe product image is obtained based on predetermined way using second acquisition unit;And utilize extraction
Unit extracts the characteristic area in object detection area, wherein characteristic area is the region in magnetic shoe product there are crackle;And
It is extracted from characteristic area by initial crack lines using third acquiring unit, and obtains target crackle according to initial crack lines
Lines.It is taken out relative to depending on to manually visualize in the related technology when the surface crack defect to magnetic shoe product detects
Inspection, the drawbacks of being easy to cause the detection efficiency of magnetic shoe product lower, can not accurately detect the crack defect of magnetic shoe product.It is logical
The recognition methods for crossing crackle provided in an embodiment of the present invention may be implemented to carry out automatic detection to magnetic shoe product to be detected
Purpose has reached the qualification rate for improving magnetic shoe product and has saved the technical effect of cost of labor, while also having liberated labour,
Production efficiency is improved, and then solves in the related technology the crack defect of magnetic shoe product detect using manual type and lead
The lower technical problem of the reliability of the testing result of cause.
As an optional embodiment of the present invention, above-mentioned first acquisition unit may include at least one of: first
Module is obtained, for obtaining magnetic shoe product image by industrial camera;Second obtains module, for passing through high-energy hard radiation
Obtain magnetic shoe product image.
As an optional embodiment of the present invention, above-mentioned second acquisition module may include: determining submodule, and being used for will
Magnetic shoe product to be detected is placed on the detection zone of high-energy hard radiation;Acquisition submodule, for by adjusting high-energy
The predefined parameter of hard radiation obtains magnetic shoe product image, wherein predefined parameter includes at least one of: wavelength, frequency.
As an optional embodiment of the present invention, above-mentioned second acquisition unit may include: the first segmentation module, be used for
Multiple first presumptive areas are split from magnetic shoe product image based on gray level threshold segmentation mode;First determining module,
For determining the area of each first presumptive area in multiple first presumptive areas;Third obtains module, for according to each the
The area of one presumptive area filters out the first presumptive area of part in multiple first presumptive areas, obtains object detection area.
As an optional embodiment of the present invention, said extracted unit may include: the second segmentation module, for being based on
Gray level threshold segmentation mode splits multiple second presumptive areas from object detection area;Second determining module, is used for
Determine the area of each second presumptive area in multiple second presumptive areas;Third determining module, for making a reservation for multiple second
The maximum second area of area is extracted as characteristic area in region.
As an optional embodiment of the present invention, above-mentioned third acquiring unit may include: extraction module, for spy
After levying region progress average value processing, predetermined slit region is extracted in the way of dynamic threshold;Processing module, for pair
Predetermined slit region carries out region expansion process;4th obtains module, for the predetermined crackle after carrying out region expansion process
In region, initial crack lines are obtained.
As an optional embodiment of the present invention, above-mentioned third acquiring unit can also include: the 5th acquisition module, use
In carrying out operation splitting to initial crack lines, a plurality of discontinuous straightway is obtained;6th obtain module, for it is a plurality of not
Continuous straightway is fitted operation, obtains a plurality of continuous straightway;4th determining module, for according to a plurality of continuous
Target crackle lines are determined in straightway.
The identification device of above-mentioned crackle may include processor and memory, and above-mentioned first acquisition unit 1001, second obtains
Unit 1003 is taken, extraction unit 1005 and third acquiring unit 1007 etc. are used as program unit storage in memory, by
Processor executes above procedure unit stored in memory to realize corresponding function.
Include kernel in above-mentioned processor, is gone in memory to transfer corresponding program unit by kernel.Kernel can be set
One or more is extracted from characteristic area by initial crack lines by adjusting kernel parameter, and according to initial crack lines
Obtain target crackle lines.
Above-mentioned memory may include the non-volatile memory in computer-readable medium, random access memory
(RAM) and/or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM), memory includes extremely
A few storage chip.
Another aspect according to an embodiment of the present invention, additionally provides a kind of storage medium, and storage medium includes storage
Program, wherein program executes the recognition methods of any one of above-mentioned crackle.
Another aspect according to an embodiment of the present invention additionally provides a kind of processor, and processor is used to run program,
Wherein, the recognition methods of any one of above-mentioned crackle is executed when program is run.
A kind of equipment is additionally provided in embodiments of the present invention, which includes processor, memory and be stored in storage
On device and the program that can run on a processor, processor performs the steps of when executing program to be obtained magnetic shoe to be detected and produces
The magnetic shoe product image of product;The object detection area of magnetic shoe product image is obtained based on predetermined way;Extract object detection area
In characteristic area, wherein characteristic area is the region in magnetic shoe product there are crackle;Extracting from characteristic area initially to split
Streakline item, and target crackle lines are obtained according to initial crack lines.
A kind of computer program product is additionally provided in embodiments of the present invention, when being executed on data processing equipment,
It is adapted for carrying out the program of initialization there are as below methods step: obtaining the magnetic shoe product image of magnetic shoe product to be detected;Based on pre-
Determine the object detection area that mode obtains magnetic shoe product image;Extract the characteristic area in object detection area, wherein characteristic area
Domain is the region in magnetic shoe product there are crackle;It extracts from characteristic area by initial crack lines, and according to initial crack line
Item obtains target crackle lines.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
In the above embodiment of the invention, it all emphasizes particularly on different fields to the description of each embodiment, does not have in some embodiment
The part of detailed description, reference can be made to the related descriptions of other embodiments.
In several embodiments provided herein, it should be understood that disclosed technology contents can pass through others
Mode is realized.Wherein, the apparatus embodiments described above are merely exemplary, such as the division of the unit, Ke Yiwei
A kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or components can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of unit or module
It connects, can be electrical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
On unit.It can some or all of the units may be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can for personal computer, server or network equipment etc.) execute each embodiment the method for the present invention whole or
Part steps.And storage medium above-mentioned includes: that USB flash disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic or disk etc. be various to can store program code
Medium.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (10)
1. a kind of recognition methods of crackle characterized by comprising
Obtain the magnetic shoe product image of magnetic shoe product to be detected;
The object detection area of the magnetic shoe product image is obtained based on predetermined way;
Extract the characteristic area in the object detection area, wherein the characteristic area is to exist to split in the magnetic shoe product
The region of line;
It extracts from the characteristic area by initial crack lines, and according to the initial crack lines and obtains target fault line
Item.
2. the method according to claim 1, wherein at least one of in the following manner, obtaining to be detected
The magnetic shoe product image of magnetic shoe product:
The magnetic shoe product image is obtained by industrial camera;
The magnetic shoe product image is obtained by high-energy hard radiation.
3. according to the method described in claim 2, it is characterized in that, obtaining the magnetic shoe product figure by high-energy hard radiation
As including:
The magnetic shoe product to be detected is placed on to the detection zone of the high-energy hard radiation;
By adjusting the predefined parameter of the high-energy hard radiation, the magnetic shoe product image is obtained, wherein the predetermined ginseng
Number includes at least one of: wavelength, frequency.
4. the method according to claim 1, wherein obtaining the mesh of the magnetic shoe product image based on predetermined way
Marking detection zone includes:
Multiple first presumptive areas are split from the magnetic shoe product image based on gray level threshold segmentation mode;
Determine the area of each first presumptive area in the multiple first presumptive area;
It is predetermined that the part first in the multiple first presumptive area is filtered out according to the area of each first presumptive area
Region obtains object detection area.
5. the method according to claim 1, wherein the characteristic area in the object detection area is extracted
To include:
Multiple second presumptive areas are split from the object detection area based on gray level threshold segmentation mode;
Determine the area of each second presumptive area in the multiple second presumptive area;
The maximum second area of area in the multiple second presumptive area is extracted as the characteristic area.
6. according to the method described in claim 5, it is characterized in that, being extracted from the characteristic area by initial crack lines
Include:
After carrying out average value processing to the characteristic area, predetermined slit region is extracted in the way of dynamic threshold;
Region expansion process is carried out to the predetermined slit region;
It is carrying out obtaining the initial crack lines in the predetermined slit region after the expansion process of region.
7. according to the method described in claim 6, it is characterized in that, obtaining target crackle lines according to the initial crack lines
Include:
Operation splitting is carried out to the initial crack lines, obtains a plurality of discontinuous straightway;
Operation is fitted to a plurality of discontinuous straightway, obtains a plurality of continuous straightway;
According to the target crackle lines determining in a plurality of continuous straightway.
8. a kind of identification device of crackle characterized by comprising
First acquisition unit, for obtaining the magnetic shoe product image of magnetic shoe product to be detected;
Second acquisition unit, for obtaining the object detection area of the magnetic shoe product image based on predetermined way;
Extraction unit, for extracting the characteristic area in the object detection area, wherein the characteristic area is the magnetic shoe
There are the regions of crackle in product;
Third acquiring unit, for extracting from the characteristic area by initial crack lines, and according to the initial crack line
Item obtains target crackle lines.
9. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein described program right of execution
Benefit require any one of 1 to 7 described in crackle recognition methods.
10. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run
Benefit require any one of 1 to 7 described in crackle recognition methods.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811013768.7A CN109146871B (en) | 2018-08-31 | 2018-08-31 | Crack identification method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811013768.7A CN109146871B (en) | 2018-08-31 | 2018-08-31 | Crack identification method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109146871A true CN109146871A (en) | 2019-01-04 |
CN109146871B CN109146871B (en) | 2021-09-24 |
Family
ID=64826194
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811013768.7A Active CN109146871B (en) | 2018-08-31 | 2018-08-31 | Crack identification method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109146871B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109727244A (en) * | 2019-01-18 | 2019-05-07 | 深圳至汉装备科技有限公司 | A kind of magnetic shoe surface crack testing method |
CN111155659A (en) * | 2020-01-22 | 2020-05-15 | 哈尔滨工业大学 | Connection node and crack identification method |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6184924B1 (en) * | 1997-05-23 | 2001-02-06 | Siemag Transplan Gmbh | Method and device for the automatic detection of surface defects for continuously cast products with continuous mechanical removal of the material |
CN102253050A (en) * | 2011-03-14 | 2011-11-23 | 广州市盛通建设工程质量检测有限公司 | Automatic detection method and device for magnetic tile surface defect based on machine vision |
CN102353680A (en) * | 2011-07-08 | 2012-02-15 | 中国科学院宁波材料技术与工程研究所 | Method for evaluating surface detects of small-sized workpieces and flow for detecting unqualified workpieces |
CN102393397A (en) * | 2011-08-30 | 2012-03-28 | 成都四星液压制造有限公司 | System and method for detecting surface defects of magnetic shoe |
CN103198322A (en) * | 2013-01-18 | 2013-07-10 | 江南大学 | Magnetic tile surface defect feature extraction and defect classification method based on machine vision |
US20140348415A1 (en) * | 2013-05-27 | 2014-11-27 | ThinkSmart IT Solutions Private Limited | System and method for identifying defects in welds by processing x-ray images |
CN104867130A (en) * | 2015-04-21 | 2015-08-26 | 浙江工业大学 | Self-adaptive segmentation method based on crack image subarea gray scale mean value |
CN105046705A (en) * | 2015-07-13 | 2015-11-11 | 浙江工业大学 | Crack edge detection method based on fuzzy theory |
CN106600593A (en) * | 2016-12-19 | 2017-04-26 | 福州大学 | Aluminum ceramic ball surface detect detection method |
-
2018
- 2018-08-31 CN CN201811013768.7A patent/CN109146871B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6184924B1 (en) * | 1997-05-23 | 2001-02-06 | Siemag Transplan Gmbh | Method and device for the automatic detection of surface defects for continuously cast products with continuous mechanical removal of the material |
CN102253050A (en) * | 2011-03-14 | 2011-11-23 | 广州市盛通建设工程质量检测有限公司 | Automatic detection method and device for magnetic tile surface defect based on machine vision |
CN102353680A (en) * | 2011-07-08 | 2012-02-15 | 中国科学院宁波材料技术与工程研究所 | Method for evaluating surface detects of small-sized workpieces and flow for detecting unqualified workpieces |
CN102393397A (en) * | 2011-08-30 | 2012-03-28 | 成都四星液压制造有限公司 | System and method for detecting surface defects of magnetic shoe |
CN103198322A (en) * | 2013-01-18 | 2013-07-10 | 江南大学 | Magnetic tile surface defect feature extraction and defect classification method based on machine vision |
US20140348415A1 (en) * | 2013-05-27 | 2014-11-27 | ThinkSmart IT Solutions Private Limited | System and method for identifying defects in welds by processing x-ray images |
CN104867130A (en) * | 2015-04-21 | 2015-08-26 | 浙江工业大学 | Self-adaptive segmentation method based on crack image subarea gray scale mean value |
CN105046705A (en) * | 2015-07-13 | 2015-11-11 | 浙江工业大学 | Crack edge detection method based on fuzzy theory |
CN106600593A (en) * | 2016-12-19 | 2017-04-26 | 福州大学 | Aluminum ceramic ball surface detect detection method |
Non-Patent Citations (5)
Title |
---|
SHUGUANG WU 等: ""A segment algorithm for crack dection"", 《2012 IEEE SYMPOSIUM ON ELECTRICAL & ELECTRONICS ENGINEERING (EEESYM)》 * |
余永维 等: ""磁瓦表面图像的自适应形态学滤波缺陷提取方法"", 《计算机辅助设计与图形学学报》 * |
徐科 等: "《金属表面质量在线检测技术》", 31 October 2016 * |
胡春明 等: "《雷达目标识别原理识别与实验技术》", 31 December 2017, 国防工业出版社 * |
胡环星: ""基于机器视觉的磁瓦表面缺陷检测技术研究"", 《中国优秀硕士学位论文全文数据库-信息科技辑》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109727244A (en) * | 2019-01-18 | 2019-05-07 | 深圳至汉装备科技有限公司 | A kind of magnetic shoe surface crack testing method |
CN109727244B (en) * | 2019-01-18 | 2020-12-08 | 深圳至汉装备科技有限公司 | Magnetic shoe surface crack detection method |
CN111155659A (en) * | 2020-01-22 | 2020-05-15 | 哈尔滨工业大学 | Connection node and crack identification method |
CN111155659B (en) * | 2020-01-22 | 2022-02-18 | 哈尔滨工业大学 | Connection node and crack identification method |
Also Published As
Publication number | Publication date |
---|---|
CN109146871B (en) | 2021-09-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109596634B (en) | Cable defect detection method and device, storage medium and processor | |
EP3633605A1 (en) | Information processing device, information processing method, and program | |
Ivorra et al. | Assessment of grape cluster yield components based on 3D descriptors using stereo vision | |
CN108022251B (en) | Method and system for extracting central line of tubular structure | |
Anandan et al. | Fabric defect detection using discrete curvelet transform | |
Alharbi et al. | Automatic counting of wheat spikes from wheat growth images | |
US20170344846A1 (en) | Image processing apparatus, image processing method and program | |
Thalji et al. | Iris Recognition using robust algorithm for eyelid, eyelash and shadow avoiding | |
CN106530311B (en) | Sectioning image processing method and processing device | |
Dixit et al. | Image texture analysis-survey | |
CN108663382A (en) | The method and device of the paper surface defects detection of view-based access control model conspicuousness | |
JP2007048006A (en) | Image processor and image processing program | |
CN111684461B (en) | Method, device, system and storage medium for determining characteristic data of image data | |
CN109146871A (en) | Crack identification method and device | |
CN105023272A (en) | Crop leaf insect pest detection method and system | |
Deshmukh et al. | Segmentation of microscopic images: A survey | |
Jenifa et al. | Classification of cotton leaf disease using multi-support vector machine | |
Singhal et al. | A comparative approach for image segmentation to identify the defected portion of apple | |
Li et al. | Sublingual vein extraction algorithm based on hyperspectral tongue imaging technology | |
Gupta et al. | Adaptive thresholding for skin lesion segmentation using statistical parameters | |
CN109211919A (en) | Method and device for identifying magnetic tile defect area | |
Ciobanu et al. | Iris identification based on optimized lab histograms applied to iris partitions | |
CN108256578B (en) | Gray level image identification method, device, equipment and readable storage medium | |
CN109949298A (en) | A kind of image segmentation quality evaluating method based on clustering learning | |
CN112465817B (en) | Pavement crack detection method based on directional filter |
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 |