CN106442556A - Device and method for detecting surface defects of perforated plate workpiece - Google Patents
Device and method for detecting surface defects of perforated plate workpiece Download PDFInfo
- Publication number
- CN106442556A CN106442556A CN201611007125.2A CN201611007125A CN106442556A CN 106442556 A CN106442556 A CN 106442556A CN 201611007125 A CN201611007125 A CN 201611007125A CN 106442556 A CN106442556 A CN 106442556A
- Authority
- CN
- China
- Prior art keywords
- image
- value
- pixel
- threshold value
- special
- 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.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 16
- 238000001514 detection method Methods 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000012546 transfer Methods 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 31
- 238000001228 spectrum Methods 0.000 claims description 31
- 230000005540 biological transmission Effects 0.000 claims description 14
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 230000002950 deficient Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 6
- 230000003287 optical effect Effects 0.000 claims description 6
- 238000005286 illumination Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 description 6
- 238000003709 image segmentation Methods 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000003708 edge detection Methods 0.000 description 3
- 239000003550 marker Substances 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 102000002274 Matrix Metalloproteinases Human genes 0.000 description 2
- 108010000684 Matrix Metalloproteinases Proteins 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000005571 horizontal transmission Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 208000020564 Eye injury Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Classifications
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
-
- 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
- G01N21/8851—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
Landscapes
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Textile Engineering (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a device and method for detecting surface defects of a perforated plate workpiece. The system comprises a transfer system, a special-shaped illuminating light source, an industrial charge coupled device (CCD) image sensor, an image acquisition card and a processor. A to-be-detected perforated plate workpiece is horizontally arranged in the transfer system; the special-shaped illuminating light source adopts a shed-shaped structure light source of which the top is arc-shaped and the horizontal section is rectangular, and is arranged at the periphery of a lens of the industrial CCD image sensor; the industrial CCD image sensor comprises a camera main body, a lens and an interface C; the camera main body adopts an industrial CCD camera and is connected with the lens through the interface C; the lens is arranged on the inner side of the special-shaped illuminating light source and is perpendicular to the to-be-detected perforated plate workpiece; the image acquisition card serves as the connector of an image acquisition part and an image processing part; the processor is used for realizing the operation of corresponding codes in a programming environment, calculating and marking the defect positions and intuitively displaying the defect positions. According to the detection device disclosed by the invention, the surface defect positions can be accurately displayed, and the workpiece defect information is acquired instead of human eyes, therefore, the detection accuracy is high.
Description
Technical field
The present invention relates to a kind of tabular workpiece with hole surface defect detection apparatus and method, belong to field of visual inspection.
Background technology
Tabular workpiece with hole, is widely used in machine tool processing, medical apparatus and instruments manufacture, vehicle fitting side in recent years
Face.Most of manufacturers still adopt manual type to find tabular workpiece with hole surface defect at present, not only big to human eye injury,
And efficiency is low, high cost is it is impossible to accurately find the particular location of Surface Flaw, and easily make one to produce vision by mistake
Difference, leads to workpiece quality to decline, missing inspection, flase drop, greatly reduce product price and the market competitiveness.
Zeng You manufacturer passes through technological improvement, using laser scanning inspection, irradiates workpiece with the point source of multiple spot arrangement
Surface, the integrated degree of surface of the work is judged by the default degree observing the point source reaching receiver board.This detection side
Not only action is complicated for method, needs to arrange the luminous point position of laser generator in advance, and the cost of laser generator and later stage
Maintenance cost is also higher, increased the cost of carrying out flaw detection.
Content of the invention
For above-mentioned prior art, the invention provides a kind of tabular workpiece with hole surface defect detection apparatus and method,
In order to solve the technical problem existing for above-mentioned tabular workpiece with hole surface defects detection.
The technical scheme that a kind of present invention tabular workpiece with hole surface defect detection apparatus are achieved is:This device includes
Transmission system, special-shaped lighting source, industrial CCD imageing sensor, image pick-up card and processor;Described transmission system is used for
Horizontal transmission tabular to be detected workpiece with hole, and transmitted with uniform rectilinear's form;Described special-shaped lighting source is used for carrying
For Uniform Illumination light source, and special-shaped lighting source can cover entirely tabular workpiece with hole region to be detected;Described
Industrial CCD imageing sensor is used for converting optical signals into the signal of telecommunication, completes the collecting part of image;Described image acquisition
Block for receiving the signal of telecommunication from photographic head collection, and the analogue signal collected is changed through A/D, image information is carried out
Storage and process, and by data information transfer to processor;Described processor is to realize respective code in programmed environment
Run, calculate, mark defective locations and intuitively show;
Described tabular workpiece with hole to be detected is horizontally placed in described transmission system;Described special-shaped lighting source is top
The canopy shape structure light sources that arc, horizontal section are rectangle, and special-shaped lighting source can cover entirely described to be detected
Tabular workpiece with hole region;Described special-shaped lighting source is arranged on the camera lens four of described industrial CCD imageing sensor
Week, and be connected with described industrial CCD imageing sensor;The mathematical expression of the described geometric model of special-shaped lighting source
Formula is:
(1)
Wherein,、For unknown parameter coefficient,、、For boundary value;Described industrial CCD imageing sensor includes:Shooting owner
Body, camera lens and C interface;Described camera body adopts industrial CCD video camera;Described camera body passes through C with camera lens
Interface connects;Described camera lens is arranged on inside described special-shaped lighting source, and with holes perpendicular to described tabular to be detected
Workpiece;Described image pick-up card is the interface of image acquisition part and image processing section.
A kind of tabular workpiece with hole detection method of surface flaw proposed by the present invention, is using a kind of above-mentioned tabular work with holes
Part surface defect detection apparatus, and according to following steps:
Described tabular workpiece with hole to be detected is horizontally placed in described transmission system, and evenly from mirror in the form of straight line
Move past below head, the complete image information of camera lens Real-time Collection;Described industrial CCD imageing sensor converts optical signals into
The signal of telecommunication, then the signal of telecommunication collecting from photographic head through described image pick-up card reception, and by the analogue signal collecting
Through A/D conversion, image information is stored and is processed, and given described process by image pick-up card by data information transfer
Device;Within a processor, first pass through programming software and pretreatment is carried out to image, improve visual effect and the definition of image, bag
Containing histogram equalization processing, normalized, medium filtering, further according to characteristics of image, binary conversion treatment is carried out to image;Connect
And use edge detecting technology, sketch out the profile of each object while noise suppression with marginal point, some needs of analysis of the image
The target of identification;Then pass through image Segmentation Technology, in contrast images, the out-of-the way position of saliency value carries out zone marker, finally carries
Take characteristics of image, and intuitively find defect position.
The remaining algorithm of step one, spectrum calculates:
First two dimensional discrete Fourier transform is carried out to the gray level image of input, image is proceeded to frequency domain from spatial domain:, wherein,For gray level image spatial domain coordinate,For gray level image frequency domain coordinate;
(2)
Wherein,For this Fourier spectrum value.Ask amplitude spectrum and phase spectrum again:
(3)
(4)
Amplitude spectrum is taken the logarithm, obtains the Log spectrum of its amplitude:
(5)
Then smothing filtering is carried out to Log spectrum, obtain the approximate shape of Log spectrum:
(6)
Wherein,It is oneSmoothing filter,Spatial domain bandwidth for smoothing filter.Ask for both differences,
Obtain composing residual error:
(7)
To spectrum residual errorAnd phase spectrumCarry out two-dimentional inverse Fourier transform, obtain
(8)
Wherein,Represent the saliency value of every point coordinates in gray level image.
Step 2, the setting of threshold value:
The present invention adopts two methods to arrange threshold value, and respectively by threshold value and the saliency value pair with pixel each in piece image
The pixel that saliency value is more than or equal to threshold value is labeled as " 1 " to ratio, is designated as target area;Saliency value is less than the pixel of threshold value
It is labeled as " 0 ", be designated as background area.
Threshold value is solved according to adaptive thresholding algorithm.WillIt is set to the average saliency value of given image:
(9)
Wherein,、The length of correspondence image and width.By the often place saliency value of the image obtaining and adaptive thresholdRelatively, will be big
It is labeled as " 1 " in the pixel equal to threshold value, be labeled as " 0 " less than the pixel of threshold value, and all pictures in this width image
Vegetarian refreshments collection shares and is formed by 0,1OKColumn matrixRepresent.
Threshold value is solved according to big law.This width image saliency value scope is designated as, (Notable for maximum
Value).Pre-set a threshold valueAbove-mentioned image saliency value is divided into two classes:,,
And willWithIt is designated as target and background respectively, both inter-class variances are:
(10)
(11)
(12)
Wherein,Represent that in image, saliency value is less thanNumber of pixels,Represent that in image, saliency value is optionally greater than's
Number of pixels,Be less thanTotal pixel average saliency value,Be optionally greater thanTotal pixel average saliency value;
So thatValue maximumValue is exactly required threshold value, that is,.Again willCompare with the often place saliency value of image, will
It is labeled as " 1 " more than or equal to the pixel of threshold value, be labeled as " 0 " less than the pixel of threshold value, and all in this width image
Pixel point set is with being formed by 0,1OKColumn matrixRepresent.
Step 3, marking of defects
By matrixWith matrixCorresponding element is multiplied, and obtains new matrix.I.e.:.Can by matrix dot product formula
Know, matrixIt is also to be made up of element 0,1, element 1 represents that this pixel saliency value is all higher than equal to two threshold values, i.e. target image
Overlapping positions.Find three matrixes according still further to order from left to right, from top to bottom successively、、Middle element is 1 company
The connected region of each matrix is designated as by logical area respectively、、 .Choose matrix, to matrixIn
All elements are sued for peace, and remember and are;To matrixMiddle all elements summation, remembers and is.Introduce function, order(13)
IfThen it is assumed that for defective locations at r.If being less thanThen it is assumed that being error-detecting, workpiece is intact herein
Fall into.
Compared with prior art, the invention has the beneficial effects as follows:
A kind of tabular workpiece with hole surface defect detection apparatus and method that the present invention provides, are replaced existing using special-shaped lighting source
Some point sources, can uniform irradiation, there is not equation of light phenomenon, solve tabular workpiece with hole Surface testing to be detected and illuminated
Degree impact leads to gather not fogging clear problem.The present invention for tabular workpiece with hole image to be detected acquisition mode not
There is the synchronous time difference, tabular workpiece with hole surface defect positions to be detected can be shown in real time, software and hardware exchanges degree height it is adaptable to
The visual imaging of dynamic object thing, and precision of images height, color rendition degree are high.
Brief description
A kind of tabular workpiece with hole surface defect detection apparatus structure chart that Fig. 1 provides for the present invention;
The special-shaped lighting light source structure schematic diagram that Fig. 2 provides for the present invention;
A kind of detecting system flow chart of tabular workpiece with hole surface defect detection apparatus that Fig. 3 provides for the present invention.
In figure:1- transmission system, 2- tabular to be detected workpiece with hole, 3- special-shaped lighting source, 4- industrial CCD image sensing
Device, 5- image pick-up card, 6- processor.
Specific embodiment
With reference to specific embodiment, the present invention is described in further detail.
As shown in figure 1, a kind of present invention tabular workpiece with hole surface defect detection apparatus, shine including transmission system 1, special-shaped
Mingguang City source 3, industrial CCD imageing sensor 4, image pick-up card 5 and processor 6.Described transmission system 1 is used for horizontal transmission institute
The tabular workpiece with hole 2 to be detected stated, and transmitted with uniform rectilinear's form;Described special-shaped lighting source 3 is used for providing
Uniform Illumination light source, and special-shaped lighting source 3 can cover entirely tabular workpiece with hole 2 region to be detected;Described
Industrial CCD imageing sensor 4 is used for converting optical signals into the signal of telecommunication, completes the collecting part of image;Described image is adopted
Truck 5 is used for receiving the signal of telecommunication from photographic head collection, and the analogue signal collected is changed through A/D, to image information
Stored and processed, and data information transfer is given described processor 6;Described processor 6 is real in programmed environment
The operation of existing respective code, calculates, marks defective locations and intuitively show.
Described tabular workpiece with hole 2 to be detected is horizontally placed in described transmission system 1;Described special-shaped lighting source
3 is the canopy shape structure light source that top is that arc, horizontal section are rectangle, and special-shaped lighting source 3 can cover entirely described
Tabular workpiece with hole 2 region to be detected;Described special-shaped lighting source 3 is arranged on described industrial CCD image sensing
The camera lens surrounding of device 4, and be connected with described industrial CCD imageing sensor 4;The geometry of described special-shaped lighting source 3
The mathematic(al) representation of model is:
(1)
Wherein,、For unknown parameter coefficient,、、For boundary value;Described industrial CCD imageing sensor 4 includes imaging owner
Body, camera lens and C interface;Described camera body adopts industrial CCD video camera;Logical between described camera body and camera lens
Cross C interface to connect;Described camera lens is perpendicular to described tabular workpiece with hole 2 to be detected;Described image pick-up card 5 is image
Collecting part and the interface of image processing section.
A kind of tabular workpiece with hole detection method of surface flaw proposed by the present invention, is using a kind of above-mentioned tabular work with holes
Part surface defect detection apparatus, and according to following steps:
Described tabular workpiece with hole 2 to be detected is horizontally placed in described transmission system 1, and in the form of straight line evenly from
Move past below camera lens, the complete image information of camera lens Real-time Collection;Optical signalling is turned by described industrial CCD imageing sensor 4
It is changed to the signal of telecommunication, then receives the signal of telecommunication from photographic head collection through described image pick-up card 5, and the simulation collecting is believed
Number through A/D conversion, image information is stored and is processed, and by image pick-up card 5 by data information transfer give described
Processor 6;In processor 6, first pass through programming software and pretreatment is carried out to image, improve the visual effect of image and clear
Degree, comprises histogram equalization processing, normalized, medium filtering, further according to characteristics of image, image is carried out at binaryzation
Reason;It is then used by edge detecting technology, sketches out the profile of each object while noise suppression with marginal point, analysis of the image is some
Need the target of identification;Then pass through image Segmentation Technology, in contrast images, the out-of-the way position of saliency value carries out zone marker,
Extract characteristics of image afterwards, and intuitively find defect position.
As shown in figure 3, a kind of testing process of tabular workpiece with hole surface defect detection apparatus is followed successively by light source and irradiating, scheming
As collection transmission, Image semantic classification, Image Edge-Detection, image segmentation and image recognition, final marking of defects.
Light source irradiates using described special-shaped lighting source 3 to described tabular workpiece with hole 2 projection uniform light to be detected.
Image acquisition is transmitted as the complete view data of described camera lens Real-time Collection, by described industrial CCD image
Sensor 4 converts optical signals into the signal of telecommunication, then receives, through described image pick-up card 5, the telecommunications collecting from photographic head
Number, and the analogue signal collected is changed through A/D, image information is acquired store and transmits.
The processor 6 that Image semantic classification is described sets up grey level histogram to image first, pixel in discovery image directly perceived
The distribution situation of brightness;Again rectangular histogram is carried out equalizing, normalized, so that the uniform gray level of image is distributed, increase contrast,
Image detail becomes apparent from;Then carry out medium filtering, image is filtered with noise, the detailed information of protection signal, and protects figure
As edge;Finally binary conversion treatment is carried out to image, the threshold value setting using the saliency value difference in image, contrast, by each
Pixel is attributed to a region, is " 1 " target area marker, background area is labeled as " 0 ", thus a width gray level image is changed into
Bianry image.
Image Edge-Detection is to sketch out the profile of each object with marginal point, analyzes the mesh needing to identify in image
Mark, that is, project the edge of image to extract characteristics of image.
Image segmentation be to after mark rim detection in image the different point of brightness split, be divided into some not
Overlapping region.
Image recognition is first using the remaining well-marked target detection method of spectrum, described tabular workpiece with hole to be detected 2 to be carried out
Detection, reuses global alignment method and identifies tabular workpiece with hole 2 surface defect positions to be detected.
The remaining algorithm of step one, spectrum calculates:
First two dimensional discrete Fourier transform is carried out to the gray level image of input, image is proceeded to frequency domain from spatial domain:,
Wherein,For gray level image spatial domain coordinate,For gray level image frequency domain coordinate;
(2)
Wherein,For this Fourier spectrum value.Ask amplitude spectrum and phase spectrum again:
(3)
(4)
Amplitude spectrum is taken the logarithm, obtains the Log spectrum of its amplitude:
(5)
Then smothing filtering is carried out to Log spectrum, obtain the approximate shape of Log spectrum:
(6)
Wherein,It is oneSmoothing filter,Spatial domain bandwidth for smoothing filter.Ask for both differences,
Obtain composing residual error:
(7)
To spectrum residual errorAnd phase spectrumCarry out two-dimentional inverse Fourier transform, obtain
(8)
Wherein,Represent the saliency value of every point coordinates in gray level image.
Step 2, the setting of threshold value:
The present invention adopts two methods to arrange threshold value, and respectively by threshold value and the saliency value pair with pixel each in piece image
The pixel that saliency value is more than or equal to threshold value is labeled as " 1 " to ratio, is designated as target area;Saliency value is less than the pixel of threshold value
It is labeled as " 0 ", be designated as background area;
Solved according to adaptive thresholding algorithm.By threshold valueIt is set to the average saliency value of given image:
(9)
Wherein,、The length of correspondence image and width.By the often place saliency value obtaining and adaptive thresholdRelatively, by contrast,
Will be greater than being labeled as " 1 " equal to the pixel of threshold value, be labeled as " 0 " less than the pixel of threshold value, and the institute in this width image
By pixel point set with being formed by 0,1OKColumn matrixRepresent.
Solved according to big law.Image saliency value scope is designated as,(For maximum saliency value).Set in advance
Put a threshold valueAbove-mentioned image saliency value is divided into two classes:,, and willWith
It is designated as target and background respectively, both inter-class variances are:
(10)
(11)
(12)
Wherein,Represent that in image, saliency value is less thanNumber of pixels,Represent that in image, saliency value is optionally greater than's
Number of pixels,Be less thanTotal pixel average saliency value,Be optionally greater thanTotal pixel average saliency value;
So thatValue maximumValue is exactly required threshold value, that is,.Again T is compared with the often place saliency value of image, will
It is labeled as " 1 " more than or equal to the pixel of threshold value, be labeled as " 0 " less than the pixel of threshold value, and all in this width image
Pixel point set is with being formed by 0,1OKColumn matrixRepresent.
Step 3, marking of defects
By matrixWith matrixCorresponding element is multiplied, and obtains new matrix.I.e.:.Can by matrix dot product formula
Know, matrixIt is also to be made up of element 0,1, element 1 represents that this pixel saliency value is all higher than equal to two threshold values, i.e. target image
Overlapping positions.Find three matrixes according still further to order from left to right, from top to bottom successively、、Middle element is 1 company
The connected region of each matrix is designated as by logical area respectively、、 .Choose matrix, to matrixIn
All elements are sued for peace, and remember and are;To matrixMiddle all elements summation, remembers and is.Introduce function,
Order(13)
IfThen it is assumed that for defective locations at r.If being less thanThen it is assumed that being error-detecting, workpiece is intact herein
Fall into.
In the present invention, Image semantic classification, Image Edge-Detection, image Segmentation Technology belong to this area class common knowledge, this
Skilled person can reproduce according to the specific requirement of measured object, will not be described here.
Although above in conjunction with figure, invention has been described, the invention is not limited in above-mentioned specific embodiment party
Formula, above-mentioned specific embodiment is only schematically, rather than circumscribed, and those of ordinary skill in the art is at this
Under bright enlightenment, without deviating from the spirit of the invention, many variations can also be made, these belong to the guarantor of the present invention
Within shield.
Claims (5)
1. a kind of tabular workpiece with hole surface defect detection apparatus are it is characterised in that include transmission system (1), special-shaped illumination light
Source (3), industrial CCD imageing sensor (4), image pick-up card (5) and processor (6);Described transmission system (1) is used for level
The described tabular workpiece with hole (2) to be detected of transmission, and transmitted with uniform rectilinear's form;Described special-shaped lighting source
(3) it is used for providing Uniform Illumination light source, and special-shaped lighting source (3) can cover entirely tabular workpiece with hole (2) to be detected
Region;Described industrial CCD imageing sensor (4) is used for converting optical signals into the signal of telecommunication, completes the collection of image
Part;Described image pick-up card (5) is used for receiving the signal of telecommunication from photographic head collection, and the analogue signal collected is passed through
A/D changes, and image information is stored and processes, and data information transfer is given described processor (6);Described process
Device (6) is the operation realizing respective code in programmed environment, calculates, marks defective locations and intuitively show;
Described tabular workpiece with hole (2) to be detected is horizontally placed in described transmission system (1);Described special-shaped lighting source
(3) it is the canopy shape structure light sources that arc, horizontal section are rectangle for top, and special-shaped lighting source (3) can cover entirely
Described tabular workpiece with hole (2) region to be detected;Described special-shaped lighting source (3) is arranged on described industrial CCD
The camera lens surrounding of imageing sensor (4), and be connected with described industrial CCD imageing sensor (4);Described special-shaped illumination
The mathematic(al) representation of the geometric model of light source (3) is:(1)
Wherein,、For unknown parameter coefficient,、、For boundary value;Described industrial CCD imageing sensor (4) includes shooting owner
Body, camera lens and C interface;Described camera body adopts industrial CCD video camera;Logical between described camera body and camera lens
Cross C interface to connect;Described camera lens is perpendicular to described tabular workpiece with hole (2) to be detected;Described image pick-up card (5) is
Image acquisition part and the interface of image processing section.
2. a kind of tabular workpiece with hole surface defect detection apparatus according to claim 1 it is characterised in that:Described
Special-shaped lighting source (3) is the canopy shape structure light source that top is that arc, horizontal section are rectangle, and special-shaped lighting source (3)
Entirely described tabular workpiece with hole (2) region to be detected can be covered;Described special-shaped lighting source (3) is arranged on work
The camera lens surrounding of industry ccd image sensor (4), and be connected with described industrial CCD imageing sensor (4);Described spy
The mathematic(al) representation of the geometric model of shape lighting source (3) is:
(1)
Wherein,、For unknown parameter coefficient,、、For boundary value.
3. a kind of tabular workpiece with hole detection method of surface flaw is it is characterised in that adopt a kind of plate as claimed in claim 1
Shape workpiece with hole surface defect detection apparatus measure, and comprise the following steps:
The remaining algorithm of step one, spectrum calculates:
First two dimensional discrete Fourier transform is carried out to the gray level image of input, image is proceeded to frequency domain from spatial domain:, wherein,For gray level image spatial domain coordinate,For gray level image frequency domain coordinate;
(2) wherein,For this Fourier spectrum value;
Ask amplitude spectrum and phase spectrum again:
(3)
(4)
Amplitude spectrum is taken the logarithm, obtains the Log spectrum of its amplitude:
(5)
Then smothing filtering is carried out to Log spectrum, obtain the approximate shape of Log spectrum:
(6)
Wherein,It is oneSmoothing filter,Spatial domain bandwidth for smoothing filter;
Ask for both differences, obtain composing residual error:
(7)
To spectrum residual errorAnd phase spectrumCarry out two-dimentional inverse Fourier transform, obtain
(8)
Wherein,Represent the saliency value of every point coordinates in gray level image.
4. the setting of step 2, threshold value:
The present invention adopts two methods to arrange threshold value, and respectively by threshold value and the saliency value pair with pixel each in piece image
The pixel that saliency value is more than or equal to threshold value is labeled as " 1 " to ratio, is designated as target area;Saliency value is less than the pixel of threshold value
It is labeled as " 0 ", be designated as background area;
Solved according to adaptive thresholding algorithm;
By threshold valueIt is set to the average saliency value of given image:(9)
Wherein,、The length of correspondence image and width;By the often place saliency value obtaining and adaptive thresholdRelatively, by contrast, will
It is labeled as " 1 " more than or equal to the pixel of threshold value, be labeled as " 0 " less than the pixel of threshold value, and all in this width image
Pixel point set is with being formed by 0,1OKColumn matrixRepresent;
Solved according to big law;Image saliency value scope is designated as,(For maximum saliency value);Pre-set one
Threshold valueAbove-mentioned image saliency value is divided into two classes:,, and willWithRespectively
It is designated as target and background, both inter-class variances are:
(10)
(11)
(12)
Wherein,Represent that in image, saliency value is less thanNumber of pixels,Represent that in image, saliency value is optionally greater than's
Number of pixels,Be less thanTotal pixel average saliency value,Be optionally greater thanTotal pixel average saliency value;
So thatValue maximumValue is exactly required threshold value, that is,;Again T is compared with the often place saliency value of image, will
It is labeled as " 1 " more than or equal to the pixel of threshold value, be labeled as " 0 " less than the pixel of threshold value, and all in this width image
Pixel point set is with being formed by 0,1OKColumn matrixRepresent.
5. step 3, marking of defects
By matrixWith matrixCorresponding element is multiplied, and obtains new matrix;I.e.:;Can by matrix dot product formula
Know, matrixIt is also to be made up of element 0,1, element 1 represents that this pixel saliency value is all higher than equal to two threshold values, i.e. target figure
The overlapping positions of picture;Find three matrixes according still further to order from left to right, from top to bottom successively、、Middle element is 1
Connected region, respectively the connected region of each matrix is designated as、、 ;
Choose matrix, to matrixMiddle all elements summation, remembers and is;To matrixThe summation of middle all elements, note and
For;
Introduce function, order(13)
IfThen it is assumed that for defective locations at r;If being less thanThen it is assumed that being error-detecting, workpiece is intact herein
Fall into.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611007125.2A CN106442556A (en) | 2016-11-16 | 2016-11-16 | Device and method for detecting surface defects of perforated plate workpiece |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611007125.2A CN106442556A (en) | 2016-11-16 | 2016-11-16 | Device and method for detecting surface defects of perforated plate workpiece |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106442556A true CN106442556A (en) | 2017-02-22 |
Family
ID=58207868
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611007125.2A Pending CN106442556A (en) | 2016-11-16 | 2016-11-16 | Device and method for detecting surface defects of perforated plate workpiece |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106442556A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107014819A (en) * | 2017-06-09 | 2017-08-04 | 杭州电子科技大学 | A kind of solar panel surface defects detection system and method |
CN107680086A (en) * | 2017-09-27 | 2018-02-09 | 电子科技大学 | A kind of existing arc-shaped side has the material profile defect inspection method of straight line again |
CN108732186A (en) * | 2018-07-20 | 2018-11-02 | 梧州学院 | Embedded Surface Flaw automatic checkout system and its control method |
CN109447989A (en) * | 2019-01-08 | 2019-03-08 | 哈尔滨理工大学 | Defect detecting device and method based on motor copper bar burr growth district |
CN109584239A (en) * | 2018-12-13 | 2019-04-05 | 华南理工大学 | A kind of bloom body surface defect detecting system and method based on reflected light |
CN109709105A (en) * | 2019-01-18 | 2019-05-03 | 安徽工程大学 | A kind of hole missing detection device |
CN110288561A (en) * | 2018-03-14 | 2019-09-27 | 浙江大学山东工业技术研究院 | Refractory brick surface scratch recognition methods based on frequency filtering enhancing |
CN111272766A (en) * | 2020-02-20 | 2020-06-12 | 上海普密德自动化科技有限公司 | Surface defect detection system based on vision technology and detection method thereof |
CN111487192A (en) * | 2020-04-26 | 2020-08-04 | 天津海融科技有限公司 | Machine vision surface defect detection device and method based on artificial intelligence |
CN112859189A (en) * | 2020-12-31 | 2021-05-28 | 广东美的白色家电技术创新中心有限公司 | Workpiece detection device, detection method, and computer-readable storage medium |
CN113538432A (en) * | 2021-09-17 | 2021-10-22 | 南通蓝城机械科技有限公司 | Part defect detection method and system based on image processing |
CN113592787A (en) * | 2021-07-13 | 2021-11-02 | 苏州汇川控制技术有限公司 | Light emitting component detection method, light emitting component detection device, terminal equipment and storage medium |
CN114663430A (en) * | 2022-05-18 | 2022-06-24 | 爱科赛智能科技(浙江)有限公司 | PCB surface defect detection method based on frequency domain information double confirmation |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005172559A (en) * | 2003-12-10 | 2005-06-30 | Seiko Epson Corp | Method and device for detecting line defect on panel |
CN102305793A (en) * | 2011-05-11 | 2012-01-04 | 苏州天准精密技术有限公司 | Method and equipment for detecting appearance quality of product |
CN102495069A (en) * | 2011-12-07 | 2012-06-13 | 广东辉丰科技股份有限公司 | Method for detecting defects of chain belts of zipper on basis of digital image processing |
CN102590330A (en) * | 2011-12-29 | 2012-07-18 | 南京理工大学常熟研究院有限公司 | Image processing-based magnetic particle inspection defect intelligent identification detection system |
CN104360501A (en) * | 2014-10-15 | 2015-02-18 | 西安交通大学 | Visual detection method and device for defects of liquid crystal display screen |
CN105181713A (en) * | 2015-07-19 | 2015-12-23 | 中北大学 | Detection device used for optical fiber image inverter surface defects |
CN106053479A (en) * | 2016-07-21 | 2016-10-26 | 湘潭大学 | System for visually detecting workpiece appearance defects based on image processing |
CN206223683U (en) * | 2016-11-16 | 2017-06-06 | 哈尔滨理工大学 | A kind of tabular workpiece with hole surface defect detection apparatus |
-
2016
- 2016-11-16 CN CN201611007125.2A patent/CN106442556A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005172559A (en) * | 2003-12-10 | 2005-06-30 | Seiko Epson Corp | Method and device for detecting line defect on panel |
CN102305793A (en) * | 2011-05-11 | 2012-01-04 | 苏州天准精密技术有限公司 | Method and equipment for detecting appearance quality of product |
CN102495069A (en) * | 2011-12-07 | 2012-06-13 | 广东辉丰科技股份有限公司 | Method for detecting defects of chain belts of zipper on basis of digital image processing |
CN102590330A (en) * | 2011-12-29 | 2012-07-18 | 南京理工大学常熟研究院有限公司 | Image processing-based magnetic particle inspection defect intelligent identification detection system |
CN104360501A (en) * | 2014-10-15 | 2015-02-18 | 西安交通大学 | Visual detection method and device for defects of liquid crystal display screen |
CN105181713A (en) * | 2015-07-19 | 2015-12-23 | 中北大学 | Detection device used for optical fiber image inverter surface defects |
CN106053479A (en) * | 2016-07-21 | 2016-10-26 | 湘潭大学 | System for visually detecting workpiece appearance defects based on image processing |
CN206223683U (en) * | 2016-11-16 | 2017-06-06 | 哈尔滨理工大学 | A kind of tabular workpiece with hole surface defect detection apparatus |
Non-Patent Citations (1)
Title |
---|
陈向伟;张学军;关山;: "基于计算机视觉的微小轴承表面缺陷检测", 机床与液压 * |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107014819A (en) * | 2017-06-09 | 2017-08-04 | 杭州电子科技大学 | A kind of solar panel surface defects detection system and method |
CN107680086A (en) * | 2017-09-27 | 2018-02-09 | 电子科技大学 | A kind of existing arc-shaped side has the material profile defect inspection method of straight line again |
CN107680086B (en) * | 2017-09-27 | 2020-10-23 | 电子科技大学 | Method for detecting material contour defects with arc-shaped edges and linear edges |
CN110288561A (en) * | 2018-03-14 | 2019-09-27 | 浙江大学山东工业技术研究院 | Refractory brick surface scratch recognition methods based on frequency filtering enhancing |
CN108732186A (en) * | 2018-07-20 | 2018-11-02 | 梧州学院 | Embedded Surface Flaw automatic checkout system and its control method |
CN109584239A (en) * | 2018-12-13 | 2019-04-05 | 华南理工大学 | A kind of bloom body surface defect detecting system and method based on reflected light |
CN109584239B (en) * | 2018-12-13 | 2024-02-06 | 华南理工大学 | High-light object surface defect detection system and method based on reflected light |
CN109447989A (en) * | 2019-01-08 | 2019-03-08 | 哈尔滨理工大学 | Defect detecting device and method based on motor copper bar burr growth district |
CN109709105B (en) * | 2019-01-18 | 2021-07-27 | 安徽工程大学 | Hole missing detection device |
CN109709105A (en) * | 2019-01-18 | 2019-05-03 | 安徽工程大学 | A kind of hole missing detection device |
CN111272766A (en) * | 2020-02-20 | 2020-06-12 | 上海普密德自动化科技有限公司 | Surface defect detection system based on vision technology and detection method thereof |
CN111487192A (en) * | 2020-04-26 | 2020-08-04 | 天津海融科技有限公司 | Machine vision surface defect detection device and method based on artificial intelligence |
CN112859189A (en) * | 2020-12-31 | 2021-05-28 | 广东美的白色家电技术创新中心有限公司 | Workpiece detection device, detection method, and computer-readable storage medium |
CN113592787A (en) * | 2021-07-13 | 2021-11-02 | 苏州汇川控制技术有限公司 | Light emitting component detection method, light emitting component detection device, terminal equipment and storage medium |
CN113538432A (en) * | 2021-09-17 | 2021-10-22 | 南通蓝城机械科技有限公司 | Part defect detection method and system based on image processing |
CN113538432B (en) * | 2021-09-17 | 2021-12-21 | 南通蓝城机械科技有限公司 | Part defect detection method and system based on image processing |
CN114663430A (en) * | 2022-05-18 | 2022-06-24 | 爱科赛智能科技(浙江)有限公司 | PCB surface defect detection method based on frequency domain information double confirmation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106442556A (en) | Device and method for detecting surface defects of perforated plate workpiece | |
CN108445007B (en) | Detection method and detection device based on image fusion | |
US11514270B2 (en) | Speckle contrast analysis using machine learning for visualizing flow | |
CN110675346A (en) | Image acquisition and depth map enhancement method and device suitable for Kinect | |
CN105718931B (en) | System and method for determining clutter in acquired images | |
CN110189375A (en) | A kind of images steganalysis method based on monocular vision measurement | |
CN111242888A (en) | Image processing method and system based on machine vision | |
CN114280075A (en) | Online visual inspection system and method for surface defects of pipe parts | |
CN114092682A (en) | Small hardware fitting defect detection algorithm based on machine learning | |
CN110880171A (en) | Detection method of display device and electronic equipment | |
CN109661683B (en) | Structured light projection method, depth detection method and structured light projection device based on image content | |
CN107784645A (en) | Measurement for Digital Image Definition and system, auto focusing method | |
JP2008070242A (en) | Noise-removing method and apparatus, unevenness defect inspecting method and apparatus | |
CN115661110A (en) | Method for identifying and positioning transparent workpiece | |
JP4115378B2 (en) | Defect detection method | |
KR101796551B1 (en) | Speedy calculation method and system of depth information strong against variable illumination | |
CN115343313A (en) | Visual identification method based on artificial intelligence | |
CN113504250A (en) | Peanut aflatoxin detection device and method based on prism type RGB color extraction | |
CN114023249A (en) | LED display screen image light point extraction method and device and LED display screen correction method | |
CN110274911B (en) | Image processing system, image processing apparatus, and storage medium | |
CN114219758A (en) | Defect detection method, system, electronic device and computer readable storage medium | |
TWI510776B (en) | Bubble inspection processing method for glass | |
CN110441315A (en) | Electronic component test equipment and method | |
CN117593302B (en) | Defective part tracing method and system | |
CN110660073B (en) | Straight line edge recognition equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170222 |
|
WD01 | Invention patent application deemed withdrawn after publication |