CN110174404A - A kind of online defect detecting device of powder and system - Google Patents
A kind of online defect detecting device of powder and system Download PDFInfo
- Publication number
- CN110174404A CN110174404A CN201910421225.7A CN201910421225A CN110174404A CN 110174404 A CN110174404 A CN 110174404A CN 201910421225 A CN201910421225 A CN 201910421225A CN 110174404 A CN110174404 A CN 110174404A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- product
- detection
- powder
- 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
- 239000000843 powder Substances 0.000 title claims abstract description 60
- 230000007547 defect Effects 0.000 title claims abstract description 46
- 238000001514 detection method Methods 0.000 claims abstract description 100
- 238000012545 processing Methods 0.000 claims abstract description 22
- 230000005540 biological transmission Effects 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims abstract description 8
- 230000008676 import Effects 0.000 claims description 9
- 230000009467 reduction Effects 0.000 claims description 9
- 230000004069 differentiation Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000012797 qualification Methods 0.000 claims description 5
- 238000011946 reduction process Methods 0.000 claims description 5
- 238000000034 method Methods 0.000 abstract description 9
- 239000000047 product Substances 0.000 description 99
- 238000004458 analytical method Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 239000011159 matrix material Substances 0.000 description 7
- 230000000694 effects Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 239000006227 byproduct Substances 0.000 description 2
- 238000004040 coloring Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000010287 polarization Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- UJKWLAZYSLJTKA-UHFFFAOYSA-N edma Chemical compound O1CCOC2=CC(CC(C)NC)=CC=C21 UJKWLAZYSLJTKA-UHFFFAOYSA-N 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/28—Measuring arrangements characterised by the use of optical techniques for measuring areas
- G01B11/285—Measuring arrangements characterised by the use of optical techniques for measuring areas using photoelectric detection means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
- G01J3/50—Measurement of colour; Colour measuring devices, e.g. colorimeters using electric radiation detectors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/85—Investigating moving fluids or granular solids
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8806—Specially adapted optical and illumination features
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/94—Investigating contamination, e.g. dust
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N2021/845—Objects on a conveyor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/85—Investigating moving fluids or granular solids
- G01N2021/8592—Grain or other flowing solid samples
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Biochemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The present invention relates to field of mechanical technique, the online defect detecting device of specially a kind of powder and system, including bottom plate, the support base being mounted at the top of bottom plate, the powder transmission board being arranged at the top of support base.In the online defect detecting device of the powder and system, it is handled by image of the image processing module to acquisition, area is carried out to the product in image after processing by image detection module, shape, the detection of color and spot, product image database is established by database module, and it is compared with the product image of detection, judge whether product is qualified product, quickly product defects in image can be detected, improve detection efficiency, pass through setting image training reason module, the image data of substandard product and the image data of qualified products are acquired simultaneously, the image data of substandard product is inputted into generator, and the mapped sample of the image data of qualified products and generator is trained, optimize in database and differentiates, improve detection accuracy.
Description
Technical field
The present invention relates to field of mechanical technique, the online defect detecting device of specially a kind of powder and system.
Background technique
Powder in process of production, unavoidably will appear the defect in terms of area, shape, color and stain, lack
Sunken powder is unqualified powder, needs to reject.
Existing powder defects detection is generally divided into human eye differentiation and machine differentiates two kinds, can be smart although being differentiated using human eye
Each powder of the observation of standard, investment in human resources is big, and low efficiency, and machine is used to differentiate, although essence that is high-efficient, but differentiating
Accuracy is lower.In consideration of it, it is proposed that a kind of online defect detecting device of powder and system.
Summary of the invention
The purpose of the present invention is to provide a kind of online defect detecting device of powder and systems, to solve above-mentioned background technique
Although middle proposition can accurately observe each powder using human eye differentiation, investment in human resources is big, and low efficiency, and uses machine
Device differentiates, although high-efficient, the lower problem of the precision differentiated.
To achieve the above object, on the one hand, the present invention provides a kind of online defect detecting device of powder, including bottom plate, peace
Support base at the top of the bottom plate, the powder transmission board being arranged at the top of the support base, the top of the powder transmission board
Portion is provided with the acquisition device for being acquired to powder image, and the acquisition device includes a pair of of supported rod erecting, the branch
Connection transverse slat is installed, the side of the connection transverse slat is equipped with detection case, the side peace of the detection case at the top of support upright bar
Equipped with multiple mounting plates, one end of the mounting plate is equipped with industrial camera, and the bottom of the industrial camera is provided with polariscope
Piece.
Preferably, the supported rod erecting and the connection transverse slat are welded and fixed, and the detection case is welded on the company
It connects on the inner wall of transverse slat.
Preferably, the detection case is in " recessed " shape structure, top plate is installed at the top of the detection case, the top plate
Two sides are provided with fixed strip, and the fixed strip is fixed at the top of the detection case by multiple fastening bolts, the top of the top plate
Portion offers multiple through slots.
Preferably, the industrial camera and the through slot are located on same level straight line.
Preferably, the side of the detection case is also equipped with industrial computer.
On the other hand, the present invention also provides a kind of powders in wire defect detection system, including described in above-mentioned any one
The online defect detecting device of powder, defect detecting system is provided in the industrial computer, and the defect detecting system includes figure
As processing module, image detection module and database module;
Described image processing module is for handling the image of acquisition;
Product after described image detection module is used to handle in image carries out the detection of area, shape, color and spot;
The database module is compared for establishing product image database, and with the product image of detection, judges product
It whether is qualified product.
Preferably, described image processing module includes Binary color image module and image noise reduction module;
The Binary color image module is used for the product and background progress binary conversion treatment in image;
Described image noise reduction module is used to carry out noise reduction process to the bitmap after removal Binary color image.
Preferably, described image detection module includes product area detecting module, shape of product detection module, product face
Color detection module and product spot detection module;
The product area detecting module is for detecting the product area in image;
The shape of product detection module is for detecting the shape of product in image;
The product colour detection module is for detecting the product colour in figure;
The product spot detection module is for detecting the product spot in figure.
Preferably, the database module includes image training reason module and image comparison module, described image training
Managing module includes sample collection module, sample generation module and sample discrimination module;
The sample collection module is for acquiring the image data of substandard product and the image data of qualified products;
The image data of substandard product is inputted generator by the sample generation module, and by the picture number of qualified products
It is trained according to the mapped sample with generator;
The sample discrimination module judges whether qualification for will identify to the product in image.
Preferably, image comparison module includes image import modul and output object module;
Described image import modul is used to import image processing module treated image data in sample discrimination module;
The output object module is used to export the differentiation result for importing image data.
Compared with prior art, beneficial effects of the present invention:
1, in the online defect detecting device of the powder and system, by industrial camera, the powder of detection case bottom is transmitted
Plate carries out Image Acquisition, while the camera lens side of industrial camera is equipped with polarized lenses, passes through polariscopic polarization of light technology
Principle can reduce the reflective of metal surface, to guarantee that industrial camera acquired image is clear, contrast is strong, and noise is few,
Improve Image Acquisition effect.
2, in the online defect detecting device of the powder and system, by image processing module to the image of acquisition at
Reason is carried out the detection of area, shape, color and spot to the product in image after processing by image detection module, passes through number
Product image database is established according to library module, and is compared with the product image of detection, judges whether product is qualified product, it can be fast
Speed detects product defects in image, improves detection efficiency.
3, in the online defect detecting device of the powder and system, by setting image training reason module, while acquisition does not conform to
The image data of substandard product is inputted generator, and will closed by the image data of lattice product and the image data of qualified products
The image data of lattice product and the mapped sample of generator are trained, and are differentiated in optimization database, are improved detection accuracy.
Detailed description of the invention
Fig. 1 is overall structure diagram of the invention;
Fig. 2 is acquisition device structural schematic diagram of the invention;
Fig. 3 is detection case structural schematic diagram of the invention;
Fig. 4 is industrial camera of the invention and industrial computer data interaction module;
Fig. 5 is defect detecting system module map of the invention;
Fig. 6 is image processing module schematic diagram of the invention;
Fig. 7 is image detection module schematic diagram of the invention;
Fig. 8 is database module schematic diagram of the invention;
Fig. 9 is image training module schematic diagram of the invention;
Figure 10 is image comparison module diagram of the invention.
In figure: 1, bottom plate;2, support base;3, powder transmission board;4, acquisition device;41, supported rod erecting;42, detection case;
421, top plate;422, fixed strip;423, fastening bolt;424, through slot;43, mounting plate;44, industrial camera;45, polarized lenses;
46, transverse slat is connected;5, industrial computer.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
In the description of the present invention, it is to be understood that, term " center ", " longitudinal direction ", " transverse direction ", " length ", " width ",
" thickness ", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside", " up time
The orientation or positional relationship of the instructions such as needle ", " counterclockwise " is to be based on the orientation or positional relationship shown in the drawings, and is merely for convenience of
The description present invention and simplified description, rather than the equipment of indication or suggestion meaning or element must have a particular orientation, with spy
Fixed orientation construction and operation, therefore be not considered as limiting the invention.
In the description of the present invention, the meaning of " plurality " is two or more, unless otherwise specifically defined.
Embodiment 1
On the one hand, the present invention provides a kind of online defect detecting device of powder, as shown in Figure 1-Figure 3, including bottom plate 1, peace
Mounted in the top of bottom plate 1 support base 2, the powder transmission board 3 at 2 top of support base is set, the top of powder transmission board 3 is provided with
Acquisition device 4 for being acquired to powder image, acquisition device 4 include a pair of of supported rod erecting 41, the top of supported rod erecting 41
Portion is equipped with connection transverse slat 46, and the side of connection transverse slat 46 is equipped with detection case 42, and the side of detection case 42 is equipped with multiple peaces
Loading board 43, one end of mounting plate 43 are equipped with industrial camera 44, and the bottom of industrial camera 44 is provided with polarized lenses 45, detection case
42 be in " recessed " shape structure, and the top of detection case 42 is equipped with top plate 421, and the two sides of top plate 421 are provided with fixed strip 422, fixed
Item 422 is fixed on 42 top of detection case by multiple fastening bolts 423, and the top of top plate 421 offers multiple through slots 424.
In the present embodiment, supported rod erecting 41 and connection transverse slat 46 are welded and fixed, and detection case 42 is welded on connection transverse slat 46
Inner wall on, convenient for will test the top that case 42 is fixed on connection transverse slat 46, while the bottom of supported rod erecting 41 is welded on bottom plate 1
On, 3 top of powder transmission board is mounted on convenient for will test case 42.
Further, industrial camera 44 and through slot 424 are located on same level straight line, pass through through slot convenient for industrial camera 44
The powder image transmitted in 424 pairs of powder transmission boards 3 is acquired.
In addition, industrial camera 44 selects ccd image sensor, specifically, SHARP company, Japan can be selected in industrial camera 44
The RJ2421AB0PB chip of production is 1/4type solid-state version photodiode structure colour plane array CCD image sensor, effectively
Pixel number is that 320k (512H*Q582V), pixel dimension reaches 7.2 μm * 4.7 μm, there is common and two kinds of way of outputs of mirror image, should
CCD includes Mg, G, Cy, Ye color compensation filter, and built-in output amplifier and exposure inhibit structure, and electronic shutter is in 1/50-
It can be changed within the scope of 1/10000s, sensitivity 720mV, eliminate than being -105dB, be mainly characterized by: steady noise and towing
Low, no insertion and image fault, output signal is pal mode standard, and resolution ratio can reach 330 Horizontal TV
Lines meets powder detection demand.
In addition to this, the top of detection case 42 offers multiple threaded holes being threadedly coupled with fastening bolt 423, and being convenient for will
Fastening bolt 423 is screwed into detection case 42, realizes that fixed strip 422 is mounted on the top of detection case 42.
The online defect detecting device of the powder of the present embodiment when being detected, industrial camera 44 is powered on, it is made
Work, industrial camera 44 carries out Image Acquisition through powder transmission board 3 of the through slot 424 to 42 bottom of detection case, when powder passes through
When powder transmission board 3 is close to 42 side of detection case, industrial camera 44 captures image of the powder in powder transmission board 3, while work
The camera lens side of industry camera 44 is equipped with polarized lenses 45, by polariscopic polarization of light technical principle, can reduce metal
Surface it is reflective, to guarantee that 44 acquired image of industrial camera is clear, contrast is strong, and noise is few, improve Image Acquisition effect
Fruit.
Embodiment 2
As second of embodiment of the invention, for the ease of the image that acquires of industrial camera 44 handled, and sentence
Powder in disconnected image whether there is defect, and the present invention staff is additionally provided with industrial motor 5, as a kind of preferred embodiment, such as
Shown in Fig. 4 and Fig. 5, the present invention also provides a kind of powders in wire defect detection system, and the powder including above-mentioned any one is online
Defect detecting device is provided with defect detecting system in industrial computer 5, and defect detecting system includes image processing module, image
Detection module and database module, image processing module is for handling the image of acquisition, and image detection module is for locating
Product after reason in image carries out the detection of area, shape, color and spot, and database module is for establishing product image data
Library, and compared with the product image of detection, judge whether product is qualified product, and the side of detection case 42 is also equipped with industrial computer
5。
In the present embodiment, industrial camera 44 and industrial computer 5 are transmitted by Ethernet realization data, are convenient for industrial camera
The image data of 44 acquisitions, which is transmitted in industrial computer 5, to be analyzed.
Further, industrial computer 5 is real as the algorithm of image procossing using the TMS320DM642 model DSP of TI company
Existing platform is selected timing dispensing controller part of the XC95144 of Xilinx company as Image Acquisition, is expanded on this hardware foundation
Having filled SDRAM realizes the storage of image, manages to realize crucial point when image.
Specifically, industrial camera 44 acquires out product analog picture signal, and it is converted into electric signal, it then will amplification
Analog signal be converted into the digital signal of standard by analog-digital converter AD9822, CPLD caching is sent by Ethernet,
It is input in the RAM of DSP finally by the channel EDMA, carries out video procession in dsp.
The powder of the present embodiment wire defect detection system defect detecting system when in use, pass through image processing module
The image of acquisition is handled, by image detection module in image after processing product carry out area, shape, color and
The detection of spot is established product image database by database module, and is compared with the product image of detection, judges that product is
No is qualified product.
Embodiment 3
As the third embodiment of the invention, for the ease of carrying out binaryzation and noise reduction process, the present inventor to image
Member makes improvements image processing module, as a kind of preferred embodiment, as shown in fig. 6, image processing module includes colour two
Value module and image noise reduction module, Binary color image module are used for the product and background progress binary conversion treatment in image,
Image noise reduction module is used to carry out noise reduction process to the bitmap after removal Binary color image.
In the present embodiment, Binary color image module step is as follows:
S1, gray value f (i, j) of the image at pixel (i, j) is set, considers (2 ω centered on pixel (i, j)
+ 1) × (2 ω+1) window;
S2, the threshold value T (i, j) for calculating each pixel (i, j) in image;
S3, binaryzation is carried out point by point with b (i, j) value to pixel (i, j) each in image.
Specifically, calculating the formula of the threshold value T (i, j) of each pixel (i, j) in image in step S2 are as follows:
Specifically, the formula of binaryzation is carried out in step S3 point by point are as follows:
It is worth noting that Binary color image module principle is as follows: the value of gray level image is stored with I, if I is N × M,
I border extension is N × M at (N+2) × (M+2) extend matrix, the size of reading original image I first, not due to the element in I
It is each is at the center of 3 × 3 windows, so needing to be extended gray level image I.(N+2) × (M is created first
+ 2) matrix extend, pixel entend (i+1, j+1)=I (i, j) in matrix I, and the first row and last line,
The filling foundation of one column and last column is to be filled using its close row or column as symmetry axis.It traverses from entend (2,2)
To the pixel of entend (N+1, M+1), and take the maximum pixel max and minimum pixel of 3 × 3 windows centered on current pixel
Min finds out threshold value t according to formula t=0.5 × (max+min), gray level image matrix I assignment in another matrix B, Yi Miangai
Become currently available gray level image matrix, traverse the matrix B, to current grayvalue compared with t, if it is greater than assigning 1, is judged to mesh
Pixel class is marked, otherwise assigns 0, as background pixel class, the bianry image B that shows.
In addition, image noise reduction module is handled the bitmap after Binary color image using image difference algorithm, figure is realized
The noise reduction effect of picture, image difference algorithm are exactly to choose a stationary reference frame as background image, with every in image sequence
One frame does difference with reference to background, to each pixel of defeated people's image, the difference of it and pixel in corresponding background image is calculated, if F
(i, j) indicates that current frame image, B (i, j) indicate background image, then difference image D (i, j) algorithmic formula are as follows:
D (i, j)=F (i, j)-B (i, j)
The powder of the present embodiment wire defect detection system image processing module when in use, pass through Binary color image mould
Block is to the product and background progress binary conversion treatment in image, by image noise reduction module to the bitmap after removal Binary color image
Carry out noise reduction process.
Embodiment 4
As the 4th kind of embodiment of the invention, for the ease of detecting to the product in image, the present invention staff is also
It is provided with image detection module, as a kind of preferred embodiment, as shown in fig. 7, image detection module includes product area detecting
Module, shape of product detection module, product colour detection module and product spot detection module, product area detecting module are used for
Product area in image is detected, shape of product detection module is produced for detecting to the shape of product in image
For detecting to the product colour in figure, product spot detection module is used for dirty to the product in figure product color detection module
Stain is detected.
In the present embodiment, product area detecting module realizes that spot-analysis algorithm is to image based on spot-analysis algorithm
The connected domain of middle same pixel is analyzed, which is known as Blob, and Blob analysis can provide image for machine vision applications
In spot quantity, position, shape and direction, the topological structure between related spot can also be provided, convenient for calculate image in
The area of product obtains the area information of product on image by spot-analysis algorithm, thus the real inspection to product integrality
It surveys.
Specifically, in the scanning process of connected region, while obtaining the geometrical characteristic of connected region, including connected region
Line segment boundary point, minimum circumscribed rectangle, area, perimeter and position of form center etc., when measuring target area size, target area
Domain area parameters S () can be used as a kind of scale of measurement, and to region R (x, y), S () is positioned as pixel number in the region
Mesh, it may be assumed that
Further, shape of product detection module is realized based on edge analysis algorithm, and edge analysis algorithm passes through threshold value point
The bianry image of acquisition is cut after defect mending, needs to carry out two-dimensional silhouette of the contours extract to obtain target in image, this reality
It applies example and contour extraction processing, principle is carried out to bianry image using the method for emptying internal point are as follows: it is assumed that background color is black
Color, color of object are white, can be true if having a pixel for white in original image, and when its 8 consecutive points are all white
The fixed point is internal point, then by the point deletion, that is, internal point is all emptied.
Specifically, in bianry image, it is assumed that background pixel gray value is 0, and product grey scale pixel value is 1, boundary profile
Extracting rule it is as follows:
(1) if, center pixel value be 0, why be worth regardless of remaining adjacent 8 pixel, retain center pixel value 0 without exception;
(2) if, center pixel value be 1, and 8 pixel values of remaining adjacent are all 1, then changing center pixel value is 0;
(3), center pixel value all in addition to the conditions already mentioned, is changed to 1.
According to above-mentioned rule, the profile of product, obtains the profile information of product on image in you can get it image, realizes pair
The detection of shape of product.
In addition, the Threshold segmentation basic principle in edge analysis algorithm are as follows: if the gray scale interval of image f (x, y) is
[Zmin, Zmax], a threshold value Z is set in the sectiont, and Zmin< Zt< Zmax, all gray values in image is enabled to be less than or equal to
ZtThe gray scale of pixel be all 0, be greater than ZtThe new gray scale of pixel be all 1, i.e., by such Threshold segmentation construct one it is defeated
Bianry image f outt(x, y):
In addition to this, product colour detection module on the picture that spot-analysis is handled by reusing image difference algorithm
Obtain the image of each product on image, then to each product utilization colour RGB parser to the colouring information of product into
Row extracts, and is then compared with learning the colouring information of setting in advance, to realize the color detection to product, wherein RGB tri-
Conversion formula of the primary colors to gray scale are as follows:
Gray=0.30*R+0.59*G+0.11*B
In addition, product spot detection module by the product image after image difference by spot-analysis algorithm, it is real
Now the spot spot above product is detected.
The powder of the present embodiment wire defect detection system image detection module when in use, pass through product area detecting
Module detects the product area in image, is examined by shape of product detection module to the shape of product in image
It surveys, the product colour in figure is detected by product colour detection module, by product spot detection module in figure
Product spot is detected.
Embodiment 5
As the 5th kind of embodiment of the invention, for the ease of establishing image product database, and pass through the product of detection
Image and the database of foundation compare, and complete product qualification determination, the present invention staff also sets up database module, as one
Kind preferred embodiment, as Figure 8-Figure 10, database module include image training reason module and image comparison module, image instruction
Practicing reason module includes sample collection module, sample generation module and sample discrimination module, and sample collection module does not conform to for acquiring
The image data of substandard product is inputted life by the image data of lattice product and the image data of qualified products, sample generation module
It grows up to be a useful person, and the mapped sample of the image data of qualified products and generator is trained, sample discrimination module is used for will be to figure
Product as in is identified, and judges whether qualification, and image comparison module includes image import modul and output object module,
Image import modul is used to import image processing module treated image data in sample discrimination module, exports object module
For exporting the differentiation result for importing image data.
In the present embodiment, in sample generation module, the substandard product image data of acquisition is denoted as pz, qualified products figure
As data are denoted as pdata, generator is denoted as G, using the network structure of multi-layer perception (MLP), is indicated that mapping can be led with the parameter of MLP
G (z), the optimization formula for generating G are as follows:
Further, sample generation module concrete principle are as follows: m sample is extracted from qualified products image data, simultaneously
M noise sample is extracted from substandard product image data and is sent into generator G, and generating data is
Sample discrimination module is denoted as arbiter D, is with the parameter of new iteration arbiter D by gradient rise methodSo that maximizationThe process is in a suboptimum
N times can be repeated by changing in loop iteration, it is ensured that maximize cost function.
It is worth noting that output object module uses " Sigmoid function " transformation to indicate arbiter with " 0 " and " 1 "
It is final to differentiate as a result, its formula is as follows:
The powder of the present embodiment wire defect detection system database module in use, being acquired by sample collection module
The image data of substandard product and the image data of qualified products, by sample generation module by the picture number of substandard product
According to input generator, and the mapped sample of the image data of qualified products and generator is trained, mould is differentiated by sample
Block judges whether qualification for identifying to the product in image, and output is imported picture number by output object module
According to differentiation result.
The basic principles, main features and advantages of the present invention have been shown and described above.The technology of the industry
For personnel it should be appreciated that the present invention is not limited to the above embodiments, described in the above embodiment and specification is only the present invention
Preference, be not intended to limit the invention, without departing from the spirit and scope of the present invention, the present invention also has various
Changes and improvements, these changes and improvements all fall within the protetion scope of the claimed invention.The claimed scope of the invention is by institute
Attached claims and its equivalent thereof.
Claims (10)
1. a kind of online defect detecting device of powder, including bottom plate (1), the support base (2) being mounted at the top of the bottom plate (1),
The powder transmission board (3) being arranged at the top of the support base (2), it is characterised in that: the top of the powder transmission board (3) is arranged
There is the acquisition device (4) for being acquired to powder image, the acquisition device (4) includes a pair of of supported rod erecting (41), institute
It states and connection transverse slat (46) is installed at the top of supported rod erecting (41), the side of connection transverse slat (46) is equipped with detection case
(42), the side of the detection case (42) is equipped with multiple mounting plates (43), and one end of the mounting plate (43) is equipped with industry
The bottom of camera (44), the industrial camera (44) is provided with polarized lenses (45).
2. the online defect detecting device of powder according to claim 1, it is characterised in that: the supported rod erecting (41) and institute
It states connection transverse slat (46) to be welded and fixed, and the detection case (42) is welded on the inner wall of connection transverse slat (46).
3. the online defect detecting device of powder according to claim 1, it is characterised in that: the detection case (42) is in " recessed "
Shape structure is equipped with top plate (421) at the top of the detection case (42), and the two sides of the top plate (421) are provided with fixed strip
(422), the fixed strip (422) is fixed at the top of the detection case (42) by multiple fastening bolts (423), the top plate
(421) multiple through slots (424) are offered at the top of.
4. the online defect detecting device of powder according to claim 3, it is characterised in that: the industrial camera (44) and institute
Through slot (424) is stated to be located on same level straight line.
5. the online defect detecting device of powder according to claim 1, it is characterised in that: the side of the detection case (42)
It is also equipped with industrial computer (5).
6. a kind of powder is examined in wire defect detection system, including powder described in any one of claim 1-5 in line defect
Survey device, it is characterised in that: defect detecting system is provided in the industrial computer (5), the defect detecting system includes figure
As processing module, image detection module and database module;
Described image processing module is for handling the image of acquisition;
Product after described image detection module is used to handle in image carries out the detection of area, shape, color and spot;
The database module is compared for establishing product image database, and with the product image of detection, whether judges product
For qualified product.
7. powder according to claim 6 is in wire defect detection system, it is characterised in that: described image processing module includes
Binary color image module and image noise reduction module;
The Binary color image module is used for the product and background progress binary conversion treatment in image;
Described image noise reduction module is used to carry out noise reduction process to the bitmap after removal Binary color image.
8. powder according to claim 6 is in wire defect detection system, it is characterised in that: described image detection module includes
Product area detecting module, shape of product detection module, product colour detection module and product spot detection module;
The product area detecting module is for detecting the product area in image;
The shape of product detection module is for detecting the shape of product in image;
The product colour detection module is for detecting the product colour in figure;
The product spot detection module is for detecting the product spot in figure.
9. powder according to claim 6 is in wire defect detection system, it is characterised in that: the database module includes figure
As training reason module and image comparison module, described image training reason module include sample collection module, sample generation module and
Sample discrimination module;
The sample collection module is for acquiring the image data of substandard product and the image data of qualified products;
The image data of substandard product is inputted generator by the sample generation module, and by the image data of qualified products and
The mapped sample of generator is trained;
The sample discrimination module judges whether qualification for will identify to the product in image.
10. powder according to claim 9 is in wire defect detection system, it is characterised in that: described image contrast module packet
Include image import modul and output object module;
Described image import modul is used to import image processing module treated image data in sample discrimination module;
The output object module is used to export the differentiation result for importing image data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910421225.7A CN110174404B (en) | 2019-05-20 | 2019-05-20 | Medicine grain online defect detection device and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910421225.7A CN110174404B (en) | 2019-05-20 | 2019-05-20 | Medicine grain online defect detection device and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110174404A true CN110174404A (en) | 2019-08-27 |
CN110174404B CN110174404B (en) | 2023-03-31 |
Family
ID=67691675
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910421225.7A Active CN110174404B (en) | 2019-05-20 | 2019-05-20 | Medicine grain online defect detection device and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110174404B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110608686A (en) * | 2019-10-31 | 2019-12-24 | 大连理工大学 | Visual measurement method and device for part with chamfer |
CN110639840A (en) * | 2019-11-05 | 2020-01-03 | 杭州升恒科技有限公司 | Full-automatic bubble cap visual detection mechanism and detection method thereof |
CN111175300A (en) * | 2020-01-30 | 2020-05-19 | 上海市奉贤区中心医院 | Real-time observation system for drug resistance generation of bacteria |
CN115077387A (en) * | 2022-08-22 | 2022-09-20 | 成都岁生科技有限责任公司 | Wedge detection method based on point cloud technology |
CN116151691A (en) * | 2023-04-13 | 2023-05-23 | 山东一方制药有限公司 | Traditional Chinese medicine formula granule preparation quality supervision system based on artificial intelligence |
CN117589641A (en) * | 2024-01-19 | 2024-02-23 | 北京春风药业有限公司 | Particle screening detection system for traditional Chinese medicine particle production |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102654464A (en) * | 2012-03-13 | 2012-09-05 | 浙江工业大学 | Copper strip surface defect detection system based on multi-feature fuzzy recognition |
CN102879404A (en) * | 2012-10-07 | 2013-01-16 | 复旦大学 | System for automatically detecting medical capsule defects in industrial structure scene |
CN104458755A (en) * | 2014-11-26 | 2015-03-25 | 吴晓军 | Multi-type material surface defect detection method based on machine vision |
CN107525808A (en) * | 2017-07-27 | 2017-12-29 | 佛山市南海区广工大数控装备协同创新研究院 | Blister medication classification and the online visible detection method of defect on a kind of production line |
CN109719057A (en) * | 2019-03-03 | 2019-05-07 | 西南大学 | A kind of wheat imperfect grain detection device based on image processing techniques |
-
2019
- 2019-05-20 CN CN201910421225.7A patent/CN110174404B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102654464A (en) * | 2012-03-13 | 2012-09-05 | 浙江工业大学 | Copper strip surface defect detection system based on multi-feature fuzzy recognition |
CN102879404A (en) * | 2012-10-07 | 2013-01-16 | 复旦大学 | System for automatically detecting medical capsule defects in industrial structure scene |
CN104458755A (en) * | 2014-11-26 | 2015-03-25 | 吴晓军 | Multi-type material surface defect detection method based on machine vision |
CN107525808A (en) * | 2017-07-27 | 2017-12-29 | 佛山市南海区广工大数控装备协同创新研究院 | Blister medication classification and the online visible detection method of defect on a kind of production line |
CN109719057A (en) * | 2019-03-03 | 2019-05-07 | 西南大学 | A kind of wheat imperfect grain detection device based on image processing techniques |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110608686A (en) * | 2019-10-31 | 2019-12-24 | 大连理工大学 | Visual measurement method and device for part with chamfer |
CN110608686B (en) * | 2019-10-31 | 2021-03-26 | 大连理工大学 | Visual measurement method and device for part with chamfer |
CN110639840A (en) * | 2019-11-05 | 2020-01-03 | 杭州升恒科技有限公司 | Full-automatic bubble cap visual detection mechanism and detection method thereof |
CN111175300A (en) * | 2020-01-30 | 2020-05-19 | 上海市奉贤区中心医院 | Real-time observation system for drug resistance generation of bacteria |
CN115077387A (en) * | 2022-08-22 | 2022-09-20 | 成都岁生科技有限责任公司 | Wedge detection method based on point cloud technology |
CN115077387B (en) * | 2022-08-22 | 2022-10-28 | 成都岁生科技有限责任公司 | Wedge detection method based on point cloud technology |
CN116151691A (en) * | 2023-04-13 | 2023-05-23 | 山东一方制药有限公司 | Traditional Chinese medicine formula granule preparation quality supervision system based on artificial intelligence |
CN117589641A (en) * | 2024-01-19 | 2024-02-23 | 北京春风药业有限公司 | Particle screening detection system for traditional Chinese medicine particle production |
CN117589641B (en) * | 2024-01-19 | 2024-04-02 | 北京春风药业有限公司 | Particle screening detection system for traditional Chinese medicine particle production |
Also Published As
Publication number | Publication date |
---|---|
CN110174404B (en) | 2023-03-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110174404A (en) | A kind of online defect detecting device of powder and system | |
CN113516660B (en) | Visual positioning and defect detection method and device suitable for train | |
CN111402226A (en) | Surface defect detection method based on cascade convolution neural network | |
CN106226157B (en) | Concrete structure member crevices automatic detection device and method | |
CN111047655B (en) | High-definition camera cloth defect detection method based on convolutional neural network | |
CN105547834B (en) | The measuring method of quick stress-strain diagram measuring system based on binocular vision | |
CN102221559A (en) | Online automatic detection method of fabric defects based on machine vision and device thereof | |
CN110473178A (en) | A kind of open defect detection method and system based on multiple light courcess fusion | |
CN107014819A (en) | A kind of solar panel surface defects detection system and method | |
US4378495A (en) | Method and apparatus for setup of inspection devices for glass bottles | |
CN101063659A (en) | System for detecting paper flaw of paper sheet | |
CN111266315A (en) | Ore material online sorting system and method based on visual analysis | |
Ali et al. | A cascading fuzzy logic with image processing algorithm–based defect detection for automatic visual inspection of industrial cylindrical object’s surface | |
CN102621154B (en) | Method and device for automatically detecting cloth defects on line based on improved differential box multi-fractal algorithm | |
CN106483143A (en) | A kind of solar energy photovoltaic panel dust stratification on-Line Monitor Device and its detection method | |
CN110189375A (en) | A kind of images steganalysis method based on monocular vision measurement | |
CN105763871A (en) | Real time detection system and detection method for camera definition | |
CN110096980A (en) | Character machining identifying system | |
CN113362276B (en) | Visual detection method and system for plates | |
CN108414531A (en) | A kind of fexible film defect detecting device and its detection method based on machine vision | |
CN110873718A (en) | Steel plate surface defect detection system and method based on machine vision | |
CN106093051A (en) | Paper roll tangent plane burr detection method based on machine vision and device | |
EP2297674A1 (en) | Optical detection and classification of empty objects in a system for returning empties | |
CN116091506B (en) | Machine vision defect quality inspection method based on YOLOV5 | |
CN210377552U (en) | Fruit is multiaspect image acquisition device for classification |
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 |