CN108535287A - Based on X-Ray imaging techniques foreign matter detection system, method and device - Google Patents
Based on X-Ray imaging techniques foreign matter detection system, method and device Download PDFInfo
- Publication number
- CN108535287A CN108535287A CN201810271938.5A CN201810271938A CN108535287A CN 108535287 A CN108535287 A CN 108535287A CN 201810271938 A CN201810271938 A CN 201810271938A CN 108535287 A CN108535287 A CN 108535287A
- Authority
- CN
- China
- Prior art keywords
- pixel
- region
- module
- array
- value
- 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
- 238000003384 imaging method Methods 0.000 title claims abstract description 95
- 238000001514 detection method Methods 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000012790 confirmation Methods 0.000 claims abstract description 6
- 238000013507 mapping Methods 0.000 claims description 36
- 239000011159 matrix material Substances 0.000 claims description 30
- 230000033001 locomotion Effects 0.000 claims description 20
- 238000005070 sampling Methods 0.000 claims description 19
- 229910002056 binary alloy Inorganic materials 0.000 claims description 12
- 230000007246 mechanism Effects 0.000 claims description 9
- 230000002950 deficient Effects 0.000 claims description 7
- 230000015572 biosynthetic process Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000009790 rate-determining step (RDS) Methods 0.000 claims description 6
- 238000013480 data collection Methods 0.000 claims description 5
- 238000012795 verification Methods 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims description 3
- 230000008450 motivation Effects 0.000 claims 1
- 239000000047 product Substances 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 229910052751 metal Inorganic materials 0.000 description 4
- 239000002184 metal Substances 0.000 description 4
- 239000003814 drug Substances 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 150000002739 metals Chemical class 0.000 description 2
- 239000004575 stone Substances 0.000 description 2
- 238000000862 absorption spectrum Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005674 electromagnetic induction Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000001727 in vivo Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052755 nonmetal Inorganic materials 0.000 description 1
- 150000002843 nonmetals Chemical class 0.000 description 1
- 230000000505 pernicious effect Effects 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 239000011265 semifinished product Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 229910001220 stainless steel Inorganic materials 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
- G01N23/02—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material
- G01N23/04—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material and forming images of the material
-
- G01V5/20—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides one kind being based on X Ray imaging technique foreign matter detection systems, including detection control module (5), the detection control module (5) includes with lower module：Data acquisition module：Point body gray scale array D is generated according to the imaging data that x-ray imaging system (3) obtains；Data processing module：Processing is carried out to a body gray scale array D and obtains borderline region array A；Foreign matter confirmation module：Foreign matter identification information is generated according to borderline region array A.Correspondingly, the present invention also provides one kind being based on X Ray imaging techniques foreign matter detecting methods and device.The X Ray that the present invention uses check system by software automatic discrimination, and the high speed detection that not only realizing can not possibly manually accomplish differentiates, but also can reach the discrimination precision and accuracy of human eye None- identified.
Description
Technical field
The present invention relates to food, drug and fine chemistry industry detection fields, and in particular, to different based on X-Ray imaging techniques
Quality testing examining system, method and device.
Background technology
Foreign bodies detection：Whether it is mixed with inedible in detection raw material, semi-finished product and product or human body or key may be set
The standby pernicious foreign matter damaged, for ensureing food, the safety of drug.The prior art is mostly using electromagnetic induction or vortex sense
The metal detection machine of principle is answered, and there are two apparent limitations for these metal detection machines, one is stone, glass etc. cannot be detected
Non-metal foreign body, the second is for the larger product of salinity and moisture, due to the electric conductivity and magnetic conductivity band of material itself
The material effect come, will significantly affect its detection result to metals such as metallic foreign body, especially non-magnetic stainless steels.
It is usually used in airport and station and checks that system is imaged by X-Ray for the X-Ray of luggage security check, and is by artificial judgment
No dangerous article, cannot achieve software automatic discrimination, and then cannot achieve the high speed detection that can not possibly manually accomplish and differentiate,
It is unable to reach the discrimination precision and accuracy of human eye None- identified.
Invention content
For the defects in the prior art, the object of the present invention is to provide one kind being based on X-Ray imaging technique foreign bodies detections
System, method and device.
X-Ray imaging technique foreign matter detecting methods are based on according to provided by the invention, including detection rate-determining steps, the inspection
Rate-determining steps are surveyed to comprise the steps of：
Data collection steps：Point body gray scale array D is generated according to the imaging data that x-ray imaging system obtains；
Data processing step：Processing is carried out to a body gray scale array D and obtains borderline region array A；
Foreign matter verification step：Foreign matter identification information is generated according to borderline region array A.
Preferably, the data collection steps comprise the steps of：
Width one-dimensional array generation step：It is corresponded to according to multiple sampling locations on x-ray imaging system detection width direction
Imaging data, generate a point body one-dimensional gray scale array [D0,D1,D2...,Dn], DnIndicate n-th of sampling on x-ray imaging system
The corresponding imaging data in position；
In formula：W is the width of x-ray imaging system detection；Spixel is the size of each pixel；
Width transmits two-dimensional array generation step：Obtain the point body one after the one or more setpoint distances of conveyer system movement
Gray scale array is tieed up, combination obtains point body gray scale array D：
In formula, DmnAfter indicating that conveyer system moves m setpoint distance, n-th of sampling location corresponds on x-ray imaging system
Imaging data.
Preferably, data processing step comprises the steps of：
Grey scale mapping calculates step：According to the mapping curve of setting, the point body gray scale array D of 16 binary system precision is turned
Turn to the grey scale mapping matrix B of 8 binary system precision；
Binaryzation calculates step：Dynamic Binarization calculating is carried out to grey scale mapping matrix B, obtains borderline region array A；
The binaryzation calculates step and comprises the steps of：
Threshold value takes a step：According to the threshold value of setting, the i-th row in grey scale mapping matrix B, the pixel gray level of jth row are taken
Value Bi,jAnd Bi,jThe pixel gray value of surrounding, obtains about Bi,jThreshold value take dot matrix B (i, j)：
In formula, s is that row takes point scale threshold value, t to take point scale threshold value for row；
Frontier district thresholding calculates step：Compare BijWith uHSize：Work as Bij≥uHWhen, enable Bi,jCorresponding Block values are 1；
Work as Bij＜ uHWhen, enable Bi,jCorresponding Block values are 0；
Wherein：P ∈ (1, s), Q ∈ (1, t), P, Q are positive integer；
X=i-P, i-P+1 ... .i ..., i+P-1, i+P；Y=j-Q, j-Q+1 ... .j ..., j+Q-1, j+Q；
In formula：BijFor Bi,jCorresponding calculating fiducial value；
uHFor binaryzation Gray-scale value；
BotTo take point scale setting value for row be P, row is when to take point scale setting value be Q, Bi,jSurrounding pixel point gray value with
Bi,jGray value and；
Bx,yFor x serial number rows in B (i, j), the pixel gray value of y serial numbers row；
BstFor the average value of all pixels point gray value in matrix B (i, j)；
Borderline region binarization step：By Bi,jCorresponding Block values are assigned to the i-th row in borderline region array A, jth row
Pixel Ai,j, obtain the borderline region array A of binaryzation：
Preferably, the foreign matter verification step comprises the steps of：
Initial scene extraction step：The pixel that 0 is assigned a value of in borderline region array A is extracted into acquisition initial background
Collect Au, the pixel that 1 is assigned a value of in borderline region array A is extracted and obtains initial foreground collection Av；
Growth step, any or all step below the growth step：
-- boundary growth step；
-- free growth step；
The boundary growth step comprises the steps of：
Step S1：To initial foreground collection AvThe contrast Yu gradient of pixel carry out a boundary criterion in middle any region
Threshold value comparison, if contrast and gradient in a boundary criterion threshold range, judge that the region is thick boundary；If comparison
Degree and/or gradient then judge that the region is non-boundary outside a boundary criterion threshold range；
Step S2：Secondary boundary criterion threshold value comparison is carried out to the contrast of the pixel of thick boundary corresponding region, if right
Than degree in secondary boundary criterion threshold value, then the pixel in the region is labeled as foreground；If contrast is in secondary boundary criterion
Outside threshold value, then the pixel in the region is labeled as background；
The free growth step comprises the steps of：
Step T1：To initial foreground collection AvThe contrast Yu gradient of pixel are into row block criterion threshold value ratio in middle any region
Compared with if contrast and gradient then follow the steps T2 in block criterion threshold range；If contrast and/or gradient are in block criterion
Outside threshold range, then the pixel in the region is labeled as background；
Step T2：Judging whether pixel is formed in block and adjacent area that pixel in the region is formed block is constituted can
Relationship block, if so, thening follow the steps T3；If it is not, the pixel in the region is then labeled as background；
Step T3：Size selection is carried out to the block that pixel in the region is formed, if size in range of set value, is held
Row step T4；If size is labeled as background outside range of set value, by the pixel in the region；
Step T4：Judge whether the block of pixel formation in the region meets the Alarm of setting, if so, by the area
The pixel in domain is labeled as foreground；If it is not, the pixel in the region is then labeled as background.
The present invention also provides one kind being based on X-Ray imaging technique foreign matter detection systems, including detection control module, described
It includes with lower module to detect control module：
Data acquisition module：Point body gray scale array D is generated according to the imaging data that x-ray imaging system obtains；
Data processing module：Processing is carried out to a body gray scale array D and obtains borderline region array A；
Foreign matter confirmation module：Foreign matter identification information is generated according to borderline region array A.
Preferably, the data acquisition module includes with lower module：
Width one-dimensional array generation module：It is corresponded to according to multiple sampling locations on x-ray imaging system detection width direction
Imaging data, generate a point body one-dimensional gray scale array [D0,D1,D2...,Dn], DnIndicate n-th of sampling on x-ray imaging system
The corresponding imaging data in position；
In formula：W is the width of x-ray imaging system detection；Spixel is the size of each pixel；
Width transmits two-dimensional array generation module：Obtain the point body one after the one or more setpoint distances of conveyer system movement
Gray scale array is tieed up, combination obtains point body gray scale array D：
In formula, DmnAfter indicating that conveyer system moves m setpoint distance, n-th of sampling location corresponds on x-ray imaging system
Imaging data.
Preferably, data processing module includes with lower module：
Grey scale mapping computing module：According to the mapping curve of setting, the point body gray scale array D of 16 binary system precision is turned
Turn to the grey scale mapping matrix B of 8 binary system precision；
Binaryzation computing module：Dynamic Binarization calculating is carried out to grey scale mapping matrix B, obtains borderline region array A；
The binaryzation computing module includes with lower module：
Threshold value takes point module：According to the threshold value of setting, the i-th row in grey scale mapping matrix B, the pixel gray level of jth row are taken
Value Bi,jAnd Bi,jThe pixel gray value of surrounding, obtains about Bi,jThreshold value take dot matrix B (i, j)：
In formula, s is that row takes point scale threshold value, t to take point scale threshold value for row；
Frontier district thresholding computing module：Compare BijWith uHSize：Work as Bij≥uHWhen, enable Bi,jCorresponding Block values are 1；
Work as Bij＜ uHWhen, enable Bi,jCorresponding Block values are 0；
Wherein：P ∈ (1, s), Q ∈ (1, t), P, Q are positive integer；
X=i-P, i-P+1 ... .i ..., i+P-1, i+P；Y=j-Q, j-Q+1 ... .j ..., j+Q-1, j+Q；
In formula：BijFor Bi,jCorresponding calculating fiducial value；
uHFor binaryzation Gray-scale value；
BotTo take point scale setting value for row be P, row is when to take point scale setting value be Q, Bi,jSurrounding pixel point gray value with
Bi,jGray value and；
Bx,yFor x serial number rows in B (i, j), the pixel gray value of y serial numbers row；
BstFor the average value of all pixels point gray value in matrix B (i, j)；
Borderline region binarization block：By Bi,jCorresponding Block values are assigned to the i-th row in borderline region array A, jth row
Pixel Ai,j, obtain the borderline region array A of binaryzation：
Preferably, the foreign matter confirmation module includes with lower module：
Initial scene extraction module：The pixel that 0 is assigned a value of in borderline region array A is extracted into acquisition initial background
Collect Au, the pixel that 1 is assigned a value of in borderline region array A is extracted and obtains initial foreground collection Av；
Pop-in upgrades, any or all module below the pop-in upgrades：
-- boundary pop-in upgrades；
-- free growth module；
The boundary pop-in upgrades includes with lower module：
Module M1：To initial foreground collection AvThe contrast Yu gradient of pixel carry out a boundary criterion in middle any region
Threshold value comparison, if contrast and gradient in a boundary criterion threshold range, judge that the region is thick boundary；If comparison
Degree and/or gradient then judge that the region is non-boundary outside a boundary criterion threshold range；
Module M2：Secondary boundary criterion threshold value comparison is carried out to the contrast of the pixel of thick boundary corresponding region, if right
Than degree in secondary boundary criterion threshold value, then the pixel in the region is labeled as foreground；If contrast is in secondary boundary criterion
Outside threshold value, then the pixel in the region is labeled as background；
The free growth module includes with lower module：
Module N1：To initial foreground collection AvThe contrast Yu gradient of pixel are into row block criterion threshold value ratio in middle any region
Compared with, if contrast and gradient in block criterion threshold range, execution module N2；If contrast and/or gradient are in block criterion
Outside threshold range, then the pixel in the region is labeled as background；
Module N2：Judging whether pixel is formed in block and adjacent area that pixel in the region is formed block is constituted can
Relationship block, if so, execution module N3；If it is not, the pixel in the region is then labeled as background；
Module N3：Size selection is carried out to the block that pixel in the region is formed, if size in range of set value, is held
Row module N4；If size is labeled as background outside range of set value, by the pixel in the region；
Module N4：Judge whether the block of pixel formation in the region meets the Alarm of setting, if so, by the area
The pixel in domain is labeled as foreground；If it is not, the pixel in the region is then labeled as background.
The present invention also provides one kind being based on X-Ray imaging technique detection device for foreign matter, including X-ray generating system, X are penetrated
Line high voltage power supply and identification module, x-ray imaging system and Industrial PC end；X-ray generating system, X-ray high voltage power supply and
Identification module, Industrial PC end are sequentially connected, and x-ray imaging system is connected with Industrial PC end；
The Industrial PC end includes above-mentioned based on X-Ray imaging technique foreign matter detection systems.
Preferably, also include I/O units, movement recognition system, motion, defective product rejecting mechanism and control panel (10)；
Industrial PC end, I/O units, defective product rejecting mechanism are sequentially connected；Industrial PC end, movement recognition system, motion are successively
Connection；Control panel (10) is connected with Industrial PC end.
Compared with prior art, the present invention has following advantageous effect：
1, the X-Ray that the present invention uses checks that system by software automatic discrimination, both realizes the height that can not possibly manually accomplish
Speed detection differentiates, while can reach the discrimination precision and accuracy of human eye None- identified again.
2, the method for discrimination such as grey scale mapping technology, genetic algorithm fuzzy diagnosis that the present invention uses, can significantly improve inspection
Survey sensitivity and accuracy.
3, the present invention can not only check various metals, can also check nonmetallic inclusion, such as：Stone, glass, bone
It is first-class etc.；And executing defective product rejecting mechanism automatically can automatically and accurately reject the product containing foreign matter from production line.
Description of the drawings
Upon reading the detailed description of non-limiting embodiments with reference to the following drawings, other feature of the invention,
Objects and advantages will become more apparent upon：
Fig. 1 is provided by the invention based on X-Ray imaging technique detection device for foreign matter structural schematic diagrams；
Fig. 2 is that grey scale mapping calculates flow chart of steps；
Fig. 3 is the mapping curve in grey scale mapping calculating step；
Fig. 4 is that binaryzation calculates flow chart of steps；
Fig. 5 is that frontier district thresholding calculates flow chart of steps；
Fig. 6 is boundary growth step flow chart；
Fig. 7 is free growth flow chart of steps；
Fig. 8 is free growth logic chart；
Fig. 9 is that boundary grows logic chart.
It is shown in figure：
Specific implementation mode
With reference to specific embodiment, the present invention is described in detail.Following embodiment will be helpful to the technology of this field
Personnel further understand the present invention, but the invention is not limited in any way.It should be pointed out that the ordinary skill of this field
For personnel, without departing from the inventive concept of the premise, various modifications and improvements can be made.These belong to the present invention
Protection domain.
In the description of the present invention, it is to be understood that, term "upper", "lower", "front", "rear", "left", "right", " perpendicular
Directly ", the orientation or positional relationship of the instructions such as "horizontal", "top", "bottom", "inner", "outside" is orientation based on ... shown in the drawings or position
Relationship is set, is merely for convenience of description of the present invention and simplification of the description, device is not indicated or implied the indicated or element is necessary
With specific orientation, with specific azimuth configuration and operation, therefore be not considered as limiting the invention.
As shown in Figure 1, provided by the invention be based on X-Ray imaging technique detection device for foreign matter, X-ray generating system 1, X
Ray high voltage power supply and identification module 2, x-ray imaging system 3 and Industrial PC end 4；X-ray generating system 1, X-ray high pressure
Power supply and identification module 2, Industrial PC end 4 are sequentially connected, and x-ray imaging system 3 is connected with Industrial PC end 4.X-ray generating system
1 generates high-voltage electricity beamlet under the support of X-ray high voltage power supply and identification module 2, and high-voltage electricity beamlet is poly- in speculum and light path
Under the action of burnt system X-ray generating system 1 export generate low energy type stablize X-ray, X-ray penetrate measured object A ' and by
It is irradiated into x-ray imaging system 3 after surveying the foreign matter B ' that object A ' includes in vivo, when practical application, the x-ray imaging system 3 can
Think X-ray linear array imaging system or X-ray linear array detector etc..The light receiving unit of x-ray imaging system 3 receives X-ray,
X-ray is because the item characteristics penetrated are different (article of unlike material has X-ray different absorption spectras) in light path, and thickness is not
Together, the decaying for reaching x-ray imaging system 3 is different, and the light receiving unit of different location is penetrated because of the X of the differential declines degree received
Line obtains the electric signal of different energy levels, after signal processing, by the A/D unit samplings in its system, forms a data acquisition
Obtain the one-dimensional gray scale array of point body of 16 precision.
The Industrial PC end 4 includes to be based on X-Ray imaging technique foreign matter detection systems.Based on X-Ray imaging technique foreign matters
Detecting system, which is characterized in that comprising detection control module 5, the detection control module 5 includes with lower module：Data acquire
Module：Point body gray scale array D is generated according to the imaging data that x-ray imaging system 3 obtains；Data processing module：To a body ash
Degree array D carries out processing and obtains borderline region array A；Foreign matter confirmation module：Foreign matter identification letter is generated according to borderline region array A
Breath.
The data acquisition module includes with lower module：Width one-dimensional array generation module：According to x-ray imaging system 3
The corresponding imaging data in multiple sampling locations on detection width direction generates the one-dimensional gray scale array [D of point body0,D1,D2...,Dn],
DnIndicate the corresponding imaging data in n-th of sampling location on x-ray imaging system 3；
In formula：W is the width that x-ray imaging system 3 detects；Spixel is the size of each pixel；Width
Transmit two-dimensional array generation module：The one-dimensional gray scale array of point body after the one or more setpoint distances of conveyer system movement is obtained,
Combination obtains point body gray scale array D：
In formula, DmnAfter indicating that conveyer system moves m setpoint distance, n-th of sampling location pair on x-ray imaging system 3
The imaging data answered.
Data processing module includes with lower module：Grey scale mapping computing module：As shown in Fig. 2, bent according to the mapping of setting
Line converts the point body gray scale array D of 16 binary system precision to the grey scale mapping matrix B of 8 binary system precision；The mapping
Curve is as shown in figure 3, a is lower intercept in figure, and b is upper intercept, and c is mapping boundary line, r0、r1、r2It is curvature.Binaryzation calculates
Module：Dynamic Binarization calculating is carried out to grey scale mapping matrix B, obtains borderline region array A；The binaryzation computing module packet
Containing with lower module：Threshold value takes point module：According to the threshold value of setting, the i-th row in grey scale mapping matrix B, the pixel ash of jth row are taken
Angle value Bi,jAnd Bi,jThe pixel gray value of surrounding, obtains about Bi,jThreshold value take dot matrix B (i, j)：
In formula, s is that row takes point scale threshold value, t to take point scale threshold value for row；Frontier district thresholding computing module：Compare BijWith
uHSize：Work as Bij≥uHWhen, enable Bi,jCorresponding Block values are 1；Work as Bij＜ uHWhen, enable Bi,jCorresponding Block values are 0；Its
In：P ∈ (1, s), Q ∈ (1, t), P, Q are positive integer；X=i-P, i-P+1 ... .i ...,
i+P-1,i+P；Y=j-Q, j-Q+1 ... .j ..., j+Q-1, j+Q；
In formula：BijFor Bi,jCorresponding calculating fiducial value；uHFor binaryzation Gray-scale value；BotPoint scale setting value is taken for row
When for P, row, to take point scale setting value be Q, Bi,jSurrounding pixel point gray value and Bi,jGray value and；Bx,yFor x sequences in B (i, j)
Number row, the pixel gray value of y serial numbers row；BstFor the average value of all pixels point gray value in matrix B (i, j).Borderline region
Binarization block：By Bi,jCorresponding Block values are assigned to the i-th row in borderline region array A, the pixel A of jth rowi,j, obtain
The borderline region array A of binaryzation：
The foreign matter confirmation module includes with lower module：Initial scene extraction module：It will be assigned a value of in borderline region array A
0 pixel, which extracts, obtains initial background collection Au, the pixel that 1 is assigned a value of in borderline region array A is extracted and is obtained
Obtain initial foreground collection Av；Pop-in upgrades, any or all module below the pop-in upgrades：Boundary pop-in upgrades；Freely give birth to
Long module.
The boundary pop-in upgrades includes with lower module：Module M1：To initial foreground collection AvPixel in middle any region
Contrast and gradient carry out a boundary criterion threshold value comparison, if contrast with gradient in a boundary criterion threshold range
It is interior, then judge that the region is thick boundary；If contrast and/or gradient judge the area outside a boundary criterion threshold range
Domain is non-boundary；Module M2：Secondary boundary criterion threshold value comparison is carried out to the contrast of the pixel of thick boundary corresponding region, if
The pixel in the region is then labeled as foreground by contrast in secondary boundary criterion threshold value；If contrast is sentenced on secondary boundary
Outside according to threshold value, then the pixel in the region is labeled as background
The free growth module includes with lower module：Module N1：To initial foreground collection AvPixel in middle any region
Contrast and gradient into row block criterion threshold value comparison, if contrast with gradient in block criterion threshold range, execute mould
Block N2；If contrast and/or gradient are labeled as background outside block criterion threshold range, by the pixel in the region；Module N2：
Judge pixel is formed in block and adjacent area that pixel in the region is formed block whether constitute can relationship block, if so,
Execution module N3；If it is not, the pixel in the region is then labeled as background；Module N3：The block that pixel in the region is formed
Carry out size selection, if size in range of set value, execution module N4；If size is outside range of set value, the areas Ze Jianggai
The pixel in domain is labeled as background；Module N4：Judge whether the block of pixel formation in the region meets the Alarm of setting,
If so, the pixel in the region is labeled as foreground；If it is not, the pixel in the region is then labeled as background.
Be preferably based on X-Ray imaging techniques detection device for foreign matter also include I/O units (6), movement recognition system (7),
Motion (8), defective product rejecting mechanism (9) and control panel (10)；Industrial PC end (4), I/O units (6), defective product rejecting mechanism (9) according to
Secondary connection；Industrial PC end (4), movement recognition system (7), motion (8) are sequentially connected；Control panel (10) and Industrial PC end
(4) it is connected.The movement of material, rejecting mechanism 9 can be driven to be able to carry out rejecting when detecting foreign matter by motion (8)
Operation, motion (8) are all connected to Industrial PC end 4 with rejecting mechanism 9, conveniently carry out automatically controlling.In addition, control panel
(10) include touch screen human/machine interface, certainly, control panel 10 can also be the structures such as button.It is preferably based on X-Ray imagings
Can also include leakage-preventing radiation, the mechanical structure of waterproof, hommization without tool detachable for cleaning on technology detection device for foreign matter.
Correspondingly, the present invention also provides one kind being based on X-Ray imaging technique foreign matter detecting methods, which is characterized in that packet
The rate-determining steps containing detection, the detection rate-determining steps comprise the steps of：Data collection steps：It is obtained according to x-ray imaging system 3
The imaging data taken generates point body gray scale array D；Data processing step：Processing is carried out to a body gray scale array D and obtains frontier district
Domain array A；Foreign matter verification step：Foreign matter identification information is generated according to borderline region array A.
The data collection steps comprise the steps of：Width one-dimensional array generation step：According to x-ray imaging system 3
The corresponding imaging data in multiple sampling locations on detection width direction generates the one-dimensional gray scale array [D of point body0,D1,D2...,Dn],
DnIndicate the corresponding imaging data in n-th of sampling location on x-ray imaging system 3；In formula：W is x-ray imaging
The width that system 3 detects；Spixel is the size of each pixel；Width transmits two-dimensional array generation step：Obtain conveyer system
The one-dimensional gray scale array of point body after the one or more setpoint distances of movement, combination obtain point body gray scale array D：
In formula, DmnAfter indicating that conveyer system moves m setpoint distance, n-th of sampling location pair on x-ray imaging system 3
The imaging data answered.
Data processing step comprises the steps of：Grey scale mapping calculates step：As shown in Fig. 2, bent according to the mapping of setting
Line converts the point body gray scale array D of 16 binary system precision to the grey scale mapping matrix B of 8 binary system precision；Binaryzation meter
Calculate step：As shown in figure 4, carrying out Dynamic Binarization calculating to grey scale mapping matrix B, borderline region array A is obtained；The two-value
Change calculating step to comprise the steps of：Threshold value takes a step：According to the threshold value of setting, the i-th row, jth in grey scale mapping matrix B are taken
The pixel gray value B of rowi,jAnd Bi,jThe pixel gray value of surrounding, obtains about Bi,jThreshold value take dot matrix B (i, j)：
In formula, s is that row takes point scale threshold value, t to take point scale threshold value for row；Frontier district thresholding calculates step：Such as Fig. 5 institutes
Show, compares BijWith uHSize：Work as Bij≥uHWhen, enable Bi,jCorresponding Block values are 1；Work as Bij＜ uHWhen, enable Bi,jIt is corresponding
Block values are 0；Wherein：P ∈ (1, s), Q ∈ (1, t), P, Q are positive integer；X=i-P, i-P+
1,....i,...,i+P-1,i+P；Y=j-Q, j-Q+1 ... .j ..., j+Q-1, j+Q；
In formula：BijFor Bi,jCorresponding calculating fiducial value；uHFor binaryzation Gray-scale value；BotPoint scale setting value is taken for row
When for P, row, to take point scale setting value be Q, Bi,jSurrounding pixel point gray value and Bi,jGray value and；Bx,yFor x sequences in B (i, j)
Number row, the pixel gray value of y serial numbers row；BstFor the average value of all pixels point gray value in matrix B (i, j)；Borderline region
Binarization step：By Bi,jCorresponding Block values are assigned to the i-th row in borderline region array A, the pixel A of jth rowi,j, obtain
The borderline region array A of binaryzation：
The foreign matter verification step comprises the steps of：Initial scene extraction step：It will be assigned a value of in borderline region array A
0 pixel, which extracts, obtains initial background collection Au, the pixel that 1 is assigned a value of in borderline region array A is extracted and is obtained
Obtain initial foreground collection Av；Growth step, any or all step below the growth step：Boundary growth step；Freely give birth to
Long step.
As shown in figure 9, the boundary growth step comprises the steps of：Step S1：To initial foreground collection AvIn any area
The contrast Yu gradient of pixel carry out a boundary criterion threshold value comparison in domain, if contrast is sentenced on a boundary with gradient
According in threshold range, then judge the region be thick boundary；If contrast and/or gradient outside a boundary criterion threshold range,
Then judge that the region is non-boundary；Step S2：Secondary boundary criterion is carried out to the contrast of the pixel of thick boundary corresponding region
Threshold value comparison, if contrast is labeled as foreground in secondary boundary criterion threshold value, by the pixel in the region；If contrast exists
Outside secondary boundary criterion threshold value, then the pixel in the region is labeled as background.
As shown in figure 8, the free growth step comprises the steps of：Step T1：To initial foreground collection AvIn any area
The contrast Yu gradient of pixel are into row block criterion threshold value comparison in domain, if contrast and gradient are in block criterion threshold range
It is interior, then follow the steps T2；If the pixel in the region is labeled as by contrast and/or gradient outside block criterion threshold range
Background；Step T2：Judge whether the block that pixel is formed in the block and adjacent area of pixel formation in the region constitutes and can close
It is block, if so, thening follow the steps T3；If it is not, the pixel in the region is then labeled as background；Step T3：To picture in the region
The block that vegetarian refreshments is formed carries out size selection, if size in range of set value, thens follow the steps T4；If size is in range of set value
Outside, then the pixel in the region is labeled as background；Step T4：Judge whether the block that pixel is formed in the region meets setting
Alarm, if so, by the pixel in the region be labeled as foreground；If it is not, then by the pixel in the region labeled as the back of the body
Scape.
One skilled in the art will appreciate that in addition to realizing system provided by the invention in a manner of pure computer readable program code
It, completely can be by the way that method and step be carried out programming in logic come so that provided by the invention other than system, device and its modules
System, device and its modules are declined with logic gate, switch, application-specific integrated circuit, programmable logic controller (PLC) and insertion
The form of controller etc. realizes identical program.So system provided by the invention, device and its modules may be considered that
It is a kind of hardware component, and the knot that the module for realizing various programs for including in it can also be considered as in hardware component
Structure；It can also will be considered as realizing the module of various functions either the software program of implementation method can be Hardware Subdivision again
Structure in part.
Specific embodiments of the present invention are described above.It is to be appreciated that the invention is not limited in above-mentioned
Particular implementation, those skilled in the art can make various deformations or amendments within the scope of the claims, this not shadow
Ring the substantive content of the present invention.In the absence of conflict, the feature in embodiments herein and embodiment can arbitrary phase
Mutually combination.
Claims (10)
1. one kind being based on X-Ray imaging technique foreign matter detecting methods, which is characterized in that include detection rate-determining steps, the detection
Rate-determining steps comprise the steps of：
Data collection steps：Point body gray scale array D is generated according to the imaging data that x-ray imaging system (3) obtains；
Data processing step：Processing is carried out to a body gray scale array D and obtains borderline region array A；
Foreign matter verification step：Foreign matter identification information is generated according to borderline region array A.
2. according to claim 1 be based on X-Ray imaging technique foreign matter detecting methods, which is characterized in that the data are adopted
Collection step comprises the steps of：
Width one-dimensional array generation step：It is corresponding according to multiple sampling locations on x-ray imaging system (3) detection width direction
Imaging data generates the one-dimensional gray scale array [D of point body0,D1,D2...,Dn], DnIndicate n-th of sampling on x-ray imaging system (3)
The corresponding imaging data in position；
In formula：W is the width of x-ray imaging system (3) detection；Spixel is the size of each pixel；
Width transmits two-dimensional array generation step：Obtain the one-dimensional ash of point body after the one or more setpoint distances of conveyer system movement
Array is spent, combination obtains point body gray scale array D：
In formula, DmnAfter indicating that conveyer system moves m setpoint distance, n-th of sampling location corresponds on x-ray imaging system (3)
Imaging data.
3. according to claim 2 be based on X-Ray imaging technique foreign matter detecting methods, which is characterized in that data processing walks
Suddenly it comprises the steps of：
Grey scale mapping calculates step：According to the mapping curve of setting, convert the point body gray scale array D of 16 binary system precision to
The grey scale mapping matrix B of 8 binary system precision；
Binaryzation calculates step：Dynamic Binarization calculating is carried out to grey scale mapping matrix B, obtains borderline region array A；
The binaryzation calculates step and comprises the steps of：
Threshold value takes a step：According to the threshold value of setting, the i-th row in grey scale mapping matrix B, the pixel gray value B of jth row are takeni,j
And Bi,jThe pixel gray value of surrounding, obtains about Bi,jThreshold value take dot matrix B (i, j)：
In formula, s is that row takes point scale threshold value, t to take point scale threshold value for row；
Frontier district thresholding calculates step：Compare BijWith uHSize：Work as Bij≥uHWhen, enable Bi,jCorresponding Block values are 1；Work as Bij
＜ uHWhen, enable Bi,jCorresponding Block values are 0；
Wherein：P ∈ (1, s), Q ∈ (1, t), P, Q are positive integer；
X=i-P, i-P+1 ... .i ..., i+P-1, i+P；Y=j-Q, j-Q+1 ... .j ..., j+Q-1, j+Q；
In formula：BijFor Bi,jCorresponding calculating fiducial value；
uHFor binaryzation Gray-scale value；
BotTo take point scale setting value for row be P, row is when to take point scale setting value be Q, Bi,jSurrounding pixel point gray value and Bi,j's
Gray value and；
Bx,yFor x serial number rows in B (i, j), the pixel gray value of y serial numbers row；
BstFor the average value of all pixels point gray value in matrix B (i, j)；
Borderline region binarization step：By Bi,jCorresponding Block values are assigned to the i-th row in borderline region array A, the picture of jth row
Vegetarian refreshments Ai,j, obtain the borderline region array A of binaryzation：
4. according to claim 3 be based on X-Ray imaging technique foreign matter detecting methods, which is characterized in that the foreign matter is true
Recognize step to comprise the steps of：
Initial scene extraction step：The pixel for being assigned a value of 0 in borderline region array A is extracted and obtains initial background collection Au,
The pixel for being assigned a value of 1 in borderline region array A is extracted and obtains initial foreground collection Av；
Growth step, any or all step below the growth step：
-- boundary growth step；
-- free growth step；
The boundary growth step comprises the steps of：
Step S1：To initial foreground collection AvThe contrast Yu gradient of pixel carry out a boundary criterion threshold value in middle any region
Compare, if contrast and gradient in a boundary criterion threshold range, judge that the region is thick boundary；If contrast
And/or gradient then judges that the region is non-boundary outside a boundary criterion threshold range；
Step S2：Secondary boundary criterion threshold value comparison is carried out to the contrast of the pixel of thick boundary corresponding region, if contrast
In secondary boundary criterion threshold value, then the pixel in the region is labeled as foreground；If contrast is in secondary boundary criterion threshold value
Outside, then the pixel in the region is labeled as background；
The free growth step comprises the steps of：
Step T1：To initial foreground collection AvThe contrast Yu gradient of pixel be into row block criterion threshold value comparison in middle any region, if
Contrast in block criterion threshold range, thens follow the steps T2 with gradient；If contrast and/or gradient are in block criterion threshold value model
Outside enclosing, then the pixel in the region is labeled as background；
Step T2：Judging whether pixel is formed in block and adjacent area that pixel in the region is formed block is constituted can relationship
Block, if so, thening follow the steps T3；If it is not, the pixel in the region is then labeled as background；
Step T3：Size selection is carried out to the block that pixel in the region is formed, if size in range of set value, executes step
Rapid T4；If size is labeled as background outside range of set value, by the pixel in the region；
Step T4：Judge whether the block of pixel formation in the region meets the Alarm of setting, if so, by the region
Pixel is labeled as foreground；If it is not, the pixel in the region is then labeled as background.
5. one kind being based on X-Ray imaging technique foreign matter detection systems, which is characterized in that include detection control module (5), the inspection
It includes with lower module to survey control module (5)：
Data acquisition module：Point body gray scale array D is generated according to the imaging data that x-ray imaging system (3) obtains；
Data processing module：Processing is carried out to a body gray scale array D and obtains borderline region array A；
Foreign matter confirmation module：Foreign matter identification information is generated according to borderline region array A.
6. according to claim 5 be based on X-Ray imaging technique foreign matter detection systems, which is characterized in that the data are adopted
It includes with lower module to collect module：
Width one-dimensional array generation module：It is corresponding according to multiple sampling locations on x-ray imaging system (3) detection width direction
Imaging data generates the one-dimensional gray scale array [D of point body0,D1,D2...,Dn], DnIndicate n-th of sampling on x-ray imaging system (3)
The corresponding imaging data in position；
In formula：W is the width of x-ray imaging system (3) detection；Spixel is the size of each pixel；
Width transmits two-dimensional array generation module：Obtain the one-dimensional ash of point body after the one or more setpoint distances of conveyer system movement
Array is spent, combination obtains point body gray scale array D：
In formula, DmnAfter indicating that conveyer system moves m setpoint distance, n-th of sampling location corresponds on x-ray imaging system (3)
Imaging data.
7. according to claim 6 be based on X-Ray imaging technique foreign matter detection systems, which is characterized in that data processing mould
Block includes with lower module：
Grey scale mapping computing module：According to the mapping curve of setting, convert the point body gray scale array D of 16 binary system precision to
The grey scale mapping matrix B of 8 binary system precision；
Binaryzation computing module：Dynamic Binarization calculating is carried out to grey scale mapping matrix B, obtains borderline region array A；
The binaryzation computing module includes with lower module：
Threshold value takes point module：According to the threshold value of setting, the i-th row in grey scale mapping matrix B, the pixel gray value B of jth row are takeni,j
And Bi,jThe pixel gray value of surrounding, obtains about Bi,jThreshold value take dot matrix B (i, j)：
In formula, s is that row takes point scale threshold value, t to take point scale threshold value for row；
Frontier district thresholding computing module：Compare BijWith uHSize：Work as Bij≥uHWhen, enable Bi,jCorresponding Block values are 1；Work as Bij
＜ uHWhen, enable Bi,jCorresponding Block values are 0；
Wherein：P ∈ (1, s), Q ∈ (1, t), P, Q are positive integer；
X=i-P, i-P+1 ... .i ..., i+P-1, i+P；Y=j-Q, j-Q+1 ... .j ..., j+Q-1, j+Q；
In formula：BijFor Bi,jCorresponding calculating fiducial value；
uHFor binaryzation Gray-scale value；
BotTo take point scale setting value for row be P, row is when to take point scale setting value be Q, Bi,jSurrounding pixel point gray value and Bi,j's
Gray value and；
Bx,yFor x serial number rows in B (i, j), the pixel gray value of y serial numbers row；
BstFor the average value of all pixels point gray value in matrix B (i, j)；
Borderline region binarization block：By Bi,jCorresponding Block values are assigned to the i-th row in borderline region array A, the picture of jth row
Vegetarian refreshments Ai,j, obtain the borderline region array A of binaryzation：
8. according to claim 7 be based on X-Ray imaging technique foreign matter detection systems, which is characterized in that the foreign matter is true
It includes with lower module to recognize module：
Initial scene extraction module：The pixel for being assigned a value of 0 in borderline region array A is extracted and obtains initial background collection Au,
The pixel for being assigned a value of 1 in borderline region array A is extracted and obtains initial foreground collection Av；
Pop-in upgrades, any or all module below the pop-in upgrades：
-- boundary pop-in upgrades；
-- free growth module；
The boundary pop-in upgrades includes with lower module：
Module M1：To initial foreground collection AvThe contrast Yu gradient of pixel carry out a boundary criterion threshold value in middle any region
Compare, if contrast and gradient in a boundary criterion threshold range, judge that the region is thick boundary；If contrast
And/or gradient then judges that the region is non-boundary outside a boundary criterion threshold range；
Module M2：Secondary boundary criterion threshold value comparison is carried out to the contrast of the pixel of thick boundary corresponding region, if contrast
In secondary boundary criterion threshold value, then the pixel in the region is labeled as foreground；If contrast is in secondary boundary criterion threshold value
Outside, then the pixel in the region is labeled as background；
The free growth module includes with lower module：
Module N1：To initial foreground collection AvThe contrast Yu gradient of pixel be into row block criterion threshold value comparison in middle any region, if
Contrast and gradient are in block criterion threshold range, then execution module N2；If contrast and/or gradient are in block criterion threshold value model
Outside enclosing, then the pixel in the region is labeled as background；
Module N2：Judging whether pixel is formed in block and adjacent area that pixel in the region is formed block is constituted can relationship
Block, if so, execution module N3；If it is not, the pixel in the region is then labeled as background；
Module N3：Size selection is carried out to the block that pixel in the region is formed, if size in range of set value, executes mould
Block N4；If size is labeled as background outside range of set value, by the pixel in the region；
Module N4：Judge whether the block of pixel formation in the region meets the Alarm of setting, if so, by the region
Pixel is labeled as foreground；If it is not, the pixel in the region is then labeled as background.
9. one kind being based on X-Ray imaging technique detection device for foreign matter, which is characterized in that include X-ray generating system (1), X-ray
High voltage power supply and identification module (2), x-ray imaging system (3) and Industrial PC end (4)；X-ray generating system (1), X-ray
High voltage power supply and identification module (2), Industrial PC end (4) are sequentially connected, and x-ray imaging system (3) is connected with Industrial PC end (4)；
The Industrial PC end (4) includes described in any one of claim 5 to 8 based on X-Ray imaging technique foreign bodies detections system
System.
10. according to claim 9 be based on X-Ray imaging technique detection device for foreign matter, which is characterized in that also include I/O
Unit (6), movement recognition system (7), motion (8), defective product rejecting mechanism (9) and control panel (10)；
Industrial PC end (4), I/O units (6), defective product rejecting mechanism (9) are sequentially connected；Industrial PC end (4), movement recognition system (7), fortune
Motivation structure (8) is sequentially connected；Control panel (10) is connected with Industrial PC end (4).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810271938.5A CN108535287B (en) | 2018-03-29 | 2018-03-29 | Foreign matter detection system, method and device based on X-Ray imaging technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810271938.5A CN108535287B (en) | 2018-03-29 | 2018-03-29 | Foreign matter detection system, method and device based on X-Ray imaging technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108535287A true CN108535287A (en) | 2018-09-14 |
| CN108535287B CN108535287B (en) | 2020-09-15 |
Family
ID=63482626
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810271938.5A Active CN108535287B (en) | 2018-03-29 | 2018-03-29 | Foreign matter detection system, method and device based on X-Ray imaging technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108535287B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109325969A (en) * | 2018-09-29 | 2019-02-12 | 佛山市云米电器科技有限公司 | A kind of intelligence smoke machine hearth dynamic foreign matter detecting method |
| WO2020238817A1 (en) * | 2019-05-24 | 2020-12-03 | Shanghai United Imaging Healthcare Co., Ltd. | Systems and methods for processing x-ray images |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010040217A1 (en) * | 2000-03-28 | 2001-11-15 | Seiji Mizuoka | Connection inspecting apparatus, connection inspecting method, and recording medium for recording programs executing the method |
| JP2002209881A (en) * | 2000-12-25 | 2002-07-30 | Ge Medical Systems Global Technology Co Llc | X-ray diagnostic instrument, its control method, and storage medium |
| CN101897592A (en) * | 2009-05-27 | 2010-12-01 | 深圳迈瑞生物医疗电子股份有限公司 | Method and device for extracting metallic foreign body from X-ray image |
| CN102331430A (en) * | 2011-06-23 | 2012-01-25 | 南京林业大学 | Irregularly shaped meat foreign matter detection system |
| JP2012208084A (en) * | 2011-03-30 | 2012-10-25 | Anritsu Sanki System Co Ltd | X-ray foreign matter detection apparatus |
| CN102937599A (en) * | 2012-10-25 | 2013-02-20 | 中国科学院自动化研究所 | Non-destructive testing systems and method used for detecting a metal-containing object through X-ray detection |
| CN105761266A (en) * | 2016-02-26 | 2016-07-13 | 民政部国家减灾中心 | Method of extracting rectangular building from remote sensing image |
| US20160353167A1 (en) * | 2015-05-29 | 2016-12-01 | Xiaomi Inc. | Method and device for processing identification of video file |
| CN107578035A (en) * | 2017-09-30 | 2018-01-12 | 深圳市颐通科技有限公司 | Human body contour outline extracting method based on super-pixel polychrome color space |
-
2018
- 2018-03-29 CN CN201810271938.5A patent/CN108535287B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010040217A1 (en) * | 2000-03-28 | 2001-11-15 | Seiji Mizuoka | Connection inspecting apparatus, connection inspecting method, and recording medium for recording programs executing the method |
| JP2002209881A (en) * | 2000-12-25 | 2002-07-30 | Ge Medical Systems Global Technology Co Llc | X-ray diagnostic instrument, its control method, and storage medium |
| CN101897592A (en) * | 2009-05-27 | 2010-12-01 | 深圳迈瑞生物医疗电子股份有限公司 | Method and device for extracting metallic foreign body from X-ray image |
| JP2012208084A (en) * | 2011-03-30 | 2012-10-25 | Anritsu Sanki System Co Ltd | X-ray foreign matter detection apparatus |
| CN102331430A (en) * | 2011-06-23 | 2012-01-25 | 南京林业大学 | Irregularly shaped meat foreign matter detection system |
| CN102937599A (en) * | 2012-10-25 | 2013-02-20 | 中国科学院自动化研究所 | Non-destructive testing systems and method used for detecting a metal-containing object through X-ray detection |
| US20160353167A1 (en) * | 2015-05-29 | 2016-12-01 | Xiaomi Inc. | Method and device for processing identification of video file |
| CN105761266A (en) * | 2016-02-26 | 2016-07-13 | 民政部国家减灾中心 | Method of extracting rectangular building from remote sensing image |
| CN107578035A (en) * | 2017-09-30 | 2018-01-12 | 深圳市颐通科技有限公司 | Human body contour outline extracting method based on super-pixel polychrome color space |
Non-Patent Citations (2)
| Title |
|---|
| CHENG-HUANG TUNG: "Binarization of uneven-lighting image by maximizing boundary connectivity", 《JOURNAL OF STATISTICS AND MANAGEMENT SYSTEMS》 * |
| 易国: "X射线食品异物检测系统设计与图像处理方法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109325969A (en) * | 2018-09-29 | 2019-02-12 | 佛山市云米电器科技有限公司 | A kind of intelligence smoke machine hearth dynamic foreign matter detecting method |
| WO2020238817A1 (en) * | 2019-05-24 | 2020-12-03 | Shanghai United Imaging Healthcare Co., Ltd. | Systems and methods for processing x-ray images |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108535287B (en) | 2020-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3349048B1 (en) | Inspection devices and methods for detecting a firearm in a luggage | |
| US10509979B2 (en) | Inspection methods and systems | |
| WO2015067208A1 (en) | Detection method and device | |
| CN107389701A (en) | A kind of PCB visual defects automatic checkout system and method based on image | |
| CN110186940B (en) | Security check identification method and device, computer equipment and storage medium | |
| Chen et al. | The Comparison and Application of Corner Detection Algorithms. | |
| CN106886054A (en) | Dangerous material automatic identification equipment and method based on 3 D X-ray imaging | |
| CN108303747A (en) | The method for checking equipment and detecting gun | |
| CN104700092B (en) | A kind of small characters digit recognition method being combined based on template and characteristic matching | |
| CN105403147B (en) | One kind being based on Embedded bottle embryo detection system and detection method | |
| CN106679567A (en) | Contact net and strut geometric parameter detecting measuring system based on binocular stereoscopic vision | |
| CN106415325B (en) | Object detection in a subject | |
| CN109977877A (en) | A kind of safety check is intelligent to be assisted sentencing drawing method, system and system control method | |
| CN102928435A (en) | Aircraft skin damage identification method and device based on image and ultrasound information fusion | |
| CN103390164A (en) | Object detection method based on depth image and implementing device thereof | |
| CN107230203A (en) | Casting defect recognition methods based on human eye vision attention mechanism | |
| EP3471058A1 (en) | Method and apparatus for detecting human body gender in microwave image | |
| CN106018422A (en) | Matching-based visual outline defect inspection system and method for specially-shaped stamping parts | |
| CN109978940A (en) | A kind of SAB air bag size vision measuring method | |
| CN105510364A (en) | Nondestructive testing system for industrial part flaws based on X rays and detection method thereof | |
| CN108535287A (en) | Based on X-Ray imaging techniques foreign matter detection system, method and device | |
| Zou et al. | The comparison of two typical corner detection algorithms | |
| Liu et al. | Automatic detection and segmentation of laser stripes for industrial measurement | |
| CN102331430A (en) | Irregularly shaped meat foreign matter detection system | |
| CN107300562A (en) | A kind of X-ray lossless detection method of measuring relay finished product contact spacing |
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 |