CN108072331A - Using the method for machine vision metrology Roundness of Workpiece - Google Patents
Using the method for machine vision metrology Roundness of Workpiece Download PDFInfo
- Publication number
- CN108072331A CN108072331A CN201611006297.8A CN201611006297A CN108072331A CN 108072331 A CN108072331 A CN 108072331A CN 201611006297 A CN201611006297 A CN 201611006297A CN 108072331 A CN108072331 A CN 108072331A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- image
- round
- circularity
- 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
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
- G01B11/2408—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures for measuring roundness
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Processing (AREA)
Abstract
A kind of machine vision method of round its circularity of object detection, this method is included using a camera, circular object is placed on objective table, the image of the round object is gathered using the camera, image data is stored in the memory for the processing system being connected with the camera, the processing system handles image, calculates the circularity of round object automatically.The image processing process includes the use of C V processing models；C V processing models include the function of three Victoria C V-types.Parameter lambda 1 and λ 2 are which used, is limited to 0.8 1.0 and 0.75 1.0；Because can improve particularly the image of circular object under low-contrast circumstances can discrimination degree, so as to ensure the accuracy of roundness measurement.
Description
Technical field
The present invention relates to machine vision metrology field, relate to the use of the parameter of machine vision metrology workpiece.
Background technology
The method of existing measurement Roundness of Workpiece is mostly using roundness measuring equipment (Roundness measuring
Instrument) it is to utilize the dimensional measuring instrument for turning round method of principal axes measurement circularity.Roundness measuring equipment is divided into sensor swinging and work
Make two kinds of patterns of platform swinging.During measurement, measured piece with precision bearing system is concentric installs, precision bearing system is sensed with inductance type length
Device or workbench make accurate circular motion.Sensor, amplifier, wave filter by instrument etc. calculate knot with the use of output
Fruit.It is taken time and effort using this method, and cost is higher, it is difficult to meet the needs of large quantities of measurements.Machine vision technique is using bat
It takes the photograph instrument and obtains data, measuring speed is fast, and cost is relatively low, is suitble to the needs of large quantities of measurements.But machine vision is used at present
Measuring the processing for data can be because workpiece image edge blurry influences measurement accuracy, and the present invention uses brand-new data processing
Method improves measurement accuracy, and not larger impact data processing speed, can meet high-volume measurement request.
The content of the invention
A kind of machine vision method of round its circularity of object detection, this method are included using a camera, by roundel
Body is placed on objective table, and the image of the round object is gathered using the camera, and image data is stored in and the photograph
In the memory for the processing system that camera is connected, the processing system handles image, calculates round object automatically
Circularity.The image processing process includes the use of C-V processing models；C-V processing models include the function of three-dimensional C-V types, the letter
Number is
Wherein：C1And C2It is the u in the inside and outside spaces of curve C0Average value.λ 1 and λ 2 is constant.
Dirac can be utilized to accord with δ, Heaviside function operator H and symbolic measurementIt is inferred to based on symbol
Distance functionEuler-lagrange equatioies：
The discrete form of formula (2), wherein μ are obtained with finite difference method, v is greater than null constant.Pass through the mould
Type realizes the change in topology of geometry, obtains continuous image boundary.Extraction image boundary and then the seat for passing through the image
Cursor position calculates the circularity of round object；Wherein for parameter lambda 1 and λ 2, value be respectively 0.8-1.1 and 0.75-1.0 it
Between.
Illustrate in the prior art for the value of above-mentioned two parameter there is no special, only by virtue of experience taken
Value, and for profile extraction for different shapes, if value is different, very big influence can be brought, be mainly contrast compared with
It edge blurry when low or even is difficult to extract edge image.For the edge contour of curvature approach infinity or broken line type, if taking
The value of λ 1 and λ 2 are 1, and lines particularly connect than more visible, and for class of a curve profile after edge contour filters noise in calculating
λ 1 and λ 2 are then each defined between 0.8-1.0 and 0.75-1.0 by the curve of subcircular, are so obtained than λ 1=λ 2=1
Image is clearer.This is primarily due to coefficient μ, and v is greater than waiting zero constant, for the convenience of calculating, if ordering μ=v=0,
Then
In the case, compared according to many experiments data result, in λ 1 and λ 2, be each defined in 0.8-1.0 and 0.75-
The image of 1.0 extractions can discrimination degree highest.
Parameter lambda 1 and λ 2 can be ordered in the above method, value is respectively 0.92,0.88；And μ=v=0 at this time.
Description of the drawings
Fig. 1 workpiece portion boundary image enlarged drawings that λ 1=λ 2=1 are extracted in the prior art
The workpiece portion boundary image enlarged drawing that Fig. 2 present invention is extracted in λ 1=0.92, λ 2=0.88
Specific embodiment
It is complete to include step 1 using machine vision progress roundness measurement：Processing of taking pictures is carried out to original workpiece；Step
2：To the image procossing of shooting into gray-scale map；Step 3：Gray-scale map is processed into artwork master；Step 4：The artwork master is carried out
Data processing removes border；Step 5：Eliminate noise；Step 6：Roundness calculation.The inventive point of the present invention is in the step in basis
Rapid 4, data processing is carried out to artwork master, so as to remove border.
A kind of machine vision method of round its circularity of object detection, this method are included using a camera, by roundel
Body is placed on objective table, and the image of the round object is gathered using the camera, and image data is stored in and the photograph
In the memory for the processing system that camera is connected, the processing system handles image, calculates round object automatically
Circularity.The image processing process includes the use of C-V processing models；Have the function that C-V processing models include three-dimensional C-V types, it should
Function is：
Wherein：C1And C2It is the u in the inside and outside spaces of curve C0Average value.λ 1 and λ 2 is constant.
Dirac can be utilized to accord with δ, Heaviside function operator H and symbolic measurementIt is inferred to based on symbol
Distance functionEuler-lagrange equatioies.
Wherein order λ 1=0.92；λ 2=0.88, then
If as shown in Figure 1, by parameter lambda 1=λ 2=1, when extracting edge image, side when can be because of data processing itself
There is fusion phenomenon when edge and not high figure viewed from behind contrast so that parts of images lacks.And to parameter lambda 1 and λ 2 by for round
After workpiece adjustment, μ=v=0 is even ordered at this time, influences the sharpening adjustment of later stage edge position images, but because adjusting at this time
λ 1=0.92 afterwards, λ 2=0.88, edge of work image magnification figure after data processing is referring to Fig. 2, compared to Fig. 1,
The not high zone boundary of contrast can be reduced well.
The image obtained by this mode can do border effective segmentation, beneficial to later data processing.It may be noted that
Be：Unmentioned content is all that those skilled in the art can be accomplished based on the prior art in description of the invention, therefore
It does not record in the present specification.
Claims (2)
1. a kind of machine vision method of round its circularity of object detection, this method is included using a camera, by circular object
It is placed on objective table, the image of the round object is gathered using the camera, image data is stored in and the photograph
In the memory for the processing system that machine is connected, the processing system handles image, calculates the circle of round object automatically
Degree.The image processing process includes the use of C-V processing models；C-V processing models include the function of three-dimensional C-V types, the function
For：
<mrow>
<mtable>
<mtr>
<mtd>
<mrow>
<mi>F</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>c</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>c</mi>
<mn>2</mn>
</msub>
<mo>,</mo>
<mi>C</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>&mu;</mi>
<mo>&CenterDot;</mo>
<mi>a</mi>
<mi>r</mi>
<mi>e</mi>
<mi>a</mi>
<mrow>
<mo>(</mo>
<mi>C</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mi>v</mi>
<mo>&CenterDot;</mo>
<mi>v</mi>
<mi>o</mi>
<mi>l</mi>
<mi>u</mi>
<mi>m</mi>
<mi>e</mi>
<mrow>
<mo>(</mo>
<mi>C</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<msub>
<mi>&lambda;</mi>
<mn>1</mn>
</msub>
<mo>&CenterDot;</mo>
<msub>
<mo>&Integral;</mo>
<mrow>
<mi>i</mi>
<mi>n</mi>
<mi>s</mi>
<mi>i</mi>
<mi>d</mi>
<mi>e</mi>
<mrow>
<mo>(</mo>
<mi>C</mi>
<mo>)</mo>
</mrow>
</mrow>
</msub>
<msup>
<mrow>
<mo>|</mo>
<msub>
<mi>u</mi>
<mn>0</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>,</mo>
<mi>z</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msub>
<mi>c</mi>
<mn>1</mn>
</msub>
<mo>|</mo>
</mrow>
<mn>2</mn>
</msup>
<mi>d</mi>
<mi>x</mi>
<mi>d</mi>
<mi>y</mi>
<mi>d</mi>
<mi>z</mi>
<mo>+</mo>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>&lambda;</mi>
<mn>2</mn>
</msub>
<mo>&CenterDot;</mo>
<msub>
<mo>&Integral;</mo>
<mrow>
<mi>o</mi>
<mi>u</mi>
<mi>t</mi>
<mi>s</mi>
<mi>i</mi>
<mi>d</mi>
<mi>e</mi>
<mrow>
<mo>(</mo>
<mi>C</mi>
<mo>)</mo>
</mrow>
</mrow>
</msub>
<msup>
<mrow>
<mo>|</mo>
<msub>
<mi>u</mi>
<mn>0</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>,</mo>
<mi>z</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msub>
<mi>c</mi>
<mn>2</mn>
</msub>
<mo>|</mo>
</mrow>
<mn>2</mn>
</msup>
<mi>d</mi>
<mi>x</mi>
<mi>d</mi>
<mi>y</mi>
<mi>d</mi>
<mi>z</mi>
</mrow>
</mtd>
</mtr>
</mtable>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein：C1And C2It is the u in the inside and outside spaces of curve C0Average value.λ 1 and λ 2 is constant.
δ, Heaviside function operator H and symbolic measurement are accorded with using diracIt is inferred to based on symbolic measurement
Euler-lagrange equatioies：
The discrete form of formula (2), wherein μ are obtained with finite difference method, v is greater than null constant.It is real by the model
The change in topology of existing geometry, obtains continuous image boundary.Extraction image boundary and then the coordinate bit for passing through the image
The circularity for calculating round object is put, wherein for parameter lambda 1 and λ 2, value is respectively between 0.8-1.1 and 0.75-1.0.
2. the machine vision method of round its circularity of object detection as described in claim 1, wherein for parameter lambda 1 and λ 2, takes
Value is respectively 0.92,0.88；And μ=v=0 at this time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611006297.8A CN108072331A (en) | 2016-11-16 | 2016-11-16 | Using the method for machine vision metrology Roundness of Workpiece |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611006297.8A CN108072331A (en) | 2016-11-16 | 2016-11-16 | Using the method for machine vision metrology Roundness of Workpiece |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108072331A true CN108072331A (en) | 2018-05-25 |
Family
ID=62163060
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611006297.8A Pending CN108072331A (en) | 2016-11-16 | 2016-11-16 | Using the method for machine vision metrology Roundness of Workpiece |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108072331A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070058865A1 (en) * | 2005-06-24 | 2007-03-15 | Kang Li | System and methods for image segmentation in n-dimensional space |
| CN102542567A (en) * | 2011-12-19 | 2012-07-04 | 中国农业大学 | Image multi-target self-adaptation dividing method and image multi-target self-adaptation dividing system based on wavelet variation module |
| CN104732213A (en) * | 2015-03-23 | 2015-06-24 | 中山大学 | Computer-assisted lump detecting method based on mammary gland magnetic resonance image |
| CN105825217A (en) * | 2016-03-22 | 2016-08-03 | 辽宁师范大学 | Hyperspectral image interested area automatic extraction method based on active contour model |
| CN105865372A (en) * | 2016-06-16 | 2016-08-17 | 四川理工学院 | Pipeline roundness value automatic detection system and detection method |
-
2016
- 2016-11-16 CN CN201611006297.8A patent/CN108072331A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070058865A1 (en) * | 2005-06-24 | 2007-03-15 | Kang Li | System and methods for image segmentation in n-dimensional space |
| CN102542567A (en) * | 2011-12-19 | 2012-07-04 | 中国农业大学 | Image multi-target self-adaptation dividing method and image multi-target self-adaptation dividing system based on wavelet variation module |
| CN104732213A (en) * | 2015-03-23 | 2015-06-24 | 中山大学 | Computer-assisted lump detecting method based on mammary gland magnetic resonance image |
| CN105825217A (en) * | 2016-03-22 | 2016-08-03 | 辽宁师范大学 | Hyperspectral image interested area automatic extraction method based on active contour model |
| CN105865372A (en) * | 2016-06-16 | 2016-08-17 | 四川理工学院 | Pipeline roundness value automatic detection system and detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107063228B (en) | Target attitude calculation method based on binocular vision | |
| CN107798326B (en) | Contour vision detection method | |
| CN103236064B (en) | A kind of some cloud autoegistration method based on normal vector | |
| JP6415066B2 (en) | Information processing apparatus, information processing method, position and orientation estimation apparatus, robot system | |
| CN110310331B (en) | Pose estimation method based on combination of linear features and point cloud features | |
| CN109483887B (en) | Online detection method for contour accuracy of forming layer in selective laser melting process | |
| CN102706291B (en) | Method for automatically measuring road curvature radius | |
| CN109272542A (en) | A kind of determination method of three-dimension object volume | |
| WO2018030010A1 (en) | Road surface estimation device, vehicle control device, road surface estimation method, and program | |
| CN108802051B (en) | System and method for detecting bubble and crease defects of linear circuit of flexible IC substrate | |
| CN105258647B (en) | A kind of visible detection method of automobile lock riveting point | |
| CN114170284B (en) | Multi-view point cloud registration method based on active landmark point projection assistance | |
| CN105184792A (en) | Circular saw web wear extent online measuring method | |
| CN116862960A (en) | Workpiece morphology point cloud registration method, device, equipment and storage medium | |
| CN108986160A (en) | A kind of image laser center line extraction method containing specular light interference | |
| JP2013130508A (en) | Three-dimension measurement method, three-dimension measurement program, and robot device | |
| CN113607058B (en) | Straight blade size detection method and system based on machine vision | |
| CN108335332A (en) | A kind of axial workpiece central axes measurement method based on binocular vision | |
| CN111738907B (en) | Train pantograph detection method based on binocular calibration and image algorithm | |
| CN108072331A (en) | Using the method for machine vision metrology Roundness of Workpiece | |
| TW200949472A (en) | On-board two-dimension contour detection method and system | |
| CN114485399B (en) | Dimension detection system and method | |
| CN109815966A (en) | A kind of mobile robot visual odometer implementation method based on improvement SIFT algorithm | |
| CN115578534A (en) | 3D model reconstruction method for welding seam | |
| TWI444586B (en) | System and method for detecting form-position tolerances of an object |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180525 |
|
| WD01 | Invention patent application deemed withdrawn after publication |