CN104613869B - Method and system for detecting elliptical hole group based on maximum inscribed circle - Google Patents
Method and system for detecting elliptical hole group based on maximum inscribed circle Download PDFInfo
- Publication number
- CN104613869B CN104613869B CN201510043349.8A CN201510043349A CN104613869B CN 104613869 B CN104613869 B CN 104613869B CN 201510043349 A CN201510043349 A CN 201510043349A CN 104613869 B CN104613869 B CN 104613869B
- Authority
- CN
- China
- Prior art keywords
- circle
- ellipse
- oval
- image
- elliptical aperture
- 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.)
- Active
Links
Abstract
The invention discloses a method and a system for detecting an elliptical hole group based on a maximum inscribed circle; the method comprises the steps: acquiring image information of a workpeice, performing image pretreatment to the acquired image information, blocking the image information according to the distribution of elliptical holes on the image information and solving the maximum inscribed circle of the elliptical holes in each block of images; calculating the length of a minor semi-axis, the length of a major semi-axis and an inclined angle of the elliptical holes according to the maximum inscribed circle; comparing the length of the minor semi-axis, the length of the major semi-axis and the inclined angle of the elliptical holes with the size of a standard elliptical hole and judging whether the elliptical hole group on the workpiece is qualified. The method of detecting the elliptical hole group combines with a machine vision technology and an elliptical maximum inscribed circle algorithm and overcomes the disadvantages of high cost, large time consumption and low precision in the traditional detection method for the hole group.
Description
Technical field
The invention belongs to workpiece sensing technical field, a kind of more particularly to elliptical aperture group based on maximum inscribed circle is detected
Method and system.
Background technology
In mechanical part processing, it is an indispensable ring that the dimensions of the part to producing carries out detection
Section.Traditional detection method has receiver ga(u)ge measurement and three coordinate machine detection.But, receiver ga(u)ge measurement inspection is to measured hole group
Actual size and shape measurement sensitivity it is not high.Three coordinate machine detection has higher technical requirements to operating personnel, and
It is relatively costly.With the continuous improvement of scientific and technological level, machine vision technique is progressively applied to the on-line monitoring of workpiece.For ellipse
The machine vision of circular Curve is processed, and researcher is constantly explored in terms of various, by using oval symmetry, string
The technologies such as the geometric propertieses such as midpoint, gradient information, random Hough transformation and method, effectively reduce from different perspectives oval inspection
The space-time consumption of survey.But ellipse is detected using geometric properties and gradient information, its accuracy of detection is easily made an uproar by image background
The interference of sound, and random Hough transformation there is also invalid accumulation that parameter space is caused because of the randomness of sampled point etc. no
Foot.
The content of the invention
In order to solve the technical problem that above-mentioned background technology is proposed, the present invention is intended to provide a kind of based on maximum inscribed circle
Elliptical aperture group detection method and system, overcome that conventional holes group detection method high cost, time loss be big, the low shortcoming of precision.
In order to realize above-mentioned technical purpose, the technical scheme is that：
A kind of elliptical aperture group detection method based on maximum inscribed circle, comprises the following steps：
(1) workpiece image information is gathered；
(2) image information to gathering carries out Image semantic classification；
(3) piecemeal is carried out to image information according to the oval pore size distribution in image information, there is 1 ellipse on every block of image
Hole；
(4) semi-minor axis length, major semiaxis length and the inclination of elliptical aperture in every block of image are gone out using maximum inscribed circle Algorithm for Solving
Angle；
(5) the semi-minor axis length of elliptical aperture, major semiaxis length and inclination angle and standard ellipse hole size are contrasted, is judged work
Whether the elliptical aperture group on part is qualified.
Wherein, be followed successively by image denoising, to image the step of Image semantic classification described in step (2) carry out binaryzation and
Rim detection is carried out to image.
Wherein, the rim detection is Canny rim detections.
Wherein, the particular content of step (4) is as follows：
A () calculates oval m bar horizontal scanning lines, and by i-th horizontal scanning line and oval intersection point ai1、ai2Count collection
Close S, i=1,2 ..., m；
B () calculates all in S set | ai1ai2| midpoint ai, horizontal sweep dotted line is obtained by least square fitting,
And horizontal sweep dotted line is obtained with oval intersection point A1、A2, calculate line segment | A1A2| midpoint M1；
C () solves the vertical scanning dotted line of ellipse and the intersection point institute line of ellipse according to step (a), the method for (b)
The midpoint M of section2, with | M1M2| midpoint O1For the center of circle, | M1M2| take round C for diameter1；
D () obtained point O1Horizontal linear with ellipse intersection point P1、P2, with O1For the center of circle, max | O1P1|, | O1P2| be
Radius makees circle C2；
If e () justifies C2There are 4 intersection points with ellipse, P is designated as successively3、P4、P5、P6, or circle C2There are 3 intersection points with ellipse, i.e.,
P3With P4Overlap or P5With P6Overlap, then with arc lengthWithFor scope, circle C is calculated1Each interior point is in the range of being somebody's turn to do
Oval boundary point minimum range dmin, and charge to set H；If circle C2During with oval only one of which or two intersection points, then calculate
Circle C1Minimum range d of each the interior point to oval all boundary pointsmin, and charge to set H；
F () obtains the max { d in set Hmin, and max { dminCorresponding C1Interior point O；
(g) centered on O, max { dminIt is radius, make circle and hand over ellipse in N1、N22 points, this circle is oval most imperial palace
The circle of contact, | ON1| as oval semi-minor axis is long, and the tiltangleθ and ellipse short shaft place straight line of ellipse are tried to achieve respectively
H () is in line segment | N1N2| above take point Kj, j=1,2 ..., n, will | N1N2| n+1 parts are divided into, K is crossedjMake | N1N2| hang down
Line hands over oval and Dj1, Dj2, calculate dj=| Dj1Dj2|/2, by { Kj, djCount set Q；
I () is to the element { K in set Qj, djLeast square fitting is utilized, try to achieve { Kj, djRespective function maximum
dmax, i.e., oval major semiaxis is long.
Present invention additionally comprises the detecting system based on above-mentioned elliptical aperture group detection method, including work stage, light-emitting component, take the photograph
Light source is radiated at work by camera, image pick-up card, data processing module, memory, console and alarm, the light-emitting component
On part platform, video camera shoots the image of workpiece in work stage, and sends workpiece image to data processing by image pick-up card
Module, data processing module calculates the sized data of elliptical aperture group on workpiece using maximum inscribed circle algorithm, and the data are protected
Deposit in memory, while transmit the data to console, console is by the elliptical aperture packet size for calculating and gauge little progress
Row is contrasted, and according to comparison the action of alarm equipment alarm and work stage is driven.
The beneficial effect brought using above-mentioned technical proposal：
Elliptical aperture group detection method of the present invention using machine vision technique in combination with oval maximum inscribed circle algorithm, can
With the size for accurately determining elliptical aperture group in a short period of time.Detect relative to traditional elliptical aperture group, with time-consuming short, essence
The advantages of spending high, can be efficiently applied to the Aulomatizeted Detect of elliptical aperture group workpiece.
Description of the drawings
Fig. 1 is the flow chart of detection method.
Fig. 2～Fig. 6 is each step schematic diagram that elliptical aperture maximum inscribed circle is obtained in detection method.
Fig. 7 is the structural representation of detecting system of the present invention.
Specific embodiment
Below with reference to accompanying drawing, technical scheme is described in detail.
The flow chart of detection method as shown in Figure 1, a kind of elliptical aperture group detection method based on maximum inscribed circle,
Comprise the following steps：
(1) workpiece image information is gathered.
(2) image information to gathering carries out Image semantic classification.Due to there is noise in image sampling process, this is right
The late detection precision of part image and it is time-consuming on can all cause certain error.So, in the image sample of device to hole group workpiece
Before carrying out relative dimensions measurement, noise is first farthest reduced.To reduce noise, using median filtering method and morphology
Opening operation removes the method that Small object method combines.Secondly, rim detection is made to the image after denoising, is calculated using Canny detections
Son.
(3) piecemeal is carried out to image information according to the oval pore size distribution in image information, there is 1 ellipse on every block of image
Hole.
(4) maximum inscribed circle of elliptical aperture in every block of image is gone out using maximum inscribed circle Algorithm for Solving, and according to most imperial palace
The circle of contact calculates semi-minor axis length, major semiaxis length and the inclination angle of elliptical aperture.It is comprised the following steps that：
A () calculates oval m bar horizontal scanning lines, and by i-th horizontal scanning line and oval intersection point ai1、ai2Count collection
Close S, i=1,2 ..., m；
B () calculates all in S set | ai1ai2| midpoint ai, horizontal sweep dotted line is obtained by least square fitting,
And horizontal sweep dotted line is obtained with oval intersection point A1、A2, calculate line segment | A1A2| midpoint M1, as shown in Figure 2；
C () solves the vertical scanning dotted line of ellipse and the intersection points B of ellipse according to step (a), the method for (b)1、B2Institute
The midpoint M of line section2, as shown in Figure 3；Then with | M1M2| midpoint O1For the center of circle, | M1M2| take round C for diameter1；
D () obtained point O1Horizontal linear with ellipse intersection point P1、P2, with O1For the center of circle, max | O1P1|, | O1P2| be
Radius makees circle C2；
If e () justifies C2There are 4 intersection points with ellipse, P is designated as successively3、P4、P5、P6, as shown in Figure 4；Or circle C2Have with ellipse
3 intersection points, i.e. P3With P4Overlap or P5With P6Overlap, then with arc lengthWith(work as P for scope3With P4Overlap or P5With
P6During coincidence, corresponding arc length is 1 point), calculate circle C1Most narrow spacing of each the interior point to the oval boundary point in the range of this
From dmin, and set H is charged to, as shown in Figure 5；If circle C2During with oval only one of which or two intersection points, then circle C is calculated1Interior is every
Minimum range d of the individual point to oval all boundary pointsmin, and charge to set H；
F () obtains the max { d in set Hmin, and max { dminCorresponding C1Interior point O；
(g) centered on O, max { dminIt is radius, make circle and hand over ellipse in N1、N22 points, this circle is oval most imperial palace
The circle of contact, | ON1| as oval semi-minor axis is long, and the tiltangleθ and ellipse short shaft place straight line of ellipse are tried to achieve respectivelyIf maximum
Inscribed circle is N with the intersection point of ellipse1(x1,y1)、N2(x2,y2), then have：
H () is in line segment | N1N2| above take point Kj, j=1,2 ..., n, will | N1N2| n+1 parts are divided into, K is crossedjMake | N1N2| hang down
Line hands over oval and Dj1, Dj2, calculate dj=| Dj1Dj2|/2, by { Kj, djSet Q is counted, as shown in Figure 6；
I () is to the element { K in set Qj, djLeast square fitting is utilized, try to achieve { Kj, djRespective function maximum
dmax, i.e., oval major semiaxis is long.
(5) the semi-minor axis length of elliptical aperture, major semiaxis length and inclination angle and standard ellipse hole size are contrasted, is judged work
Whether the elliptical aperture group on part is qualified.
The present invention also includes a kind of detecting system based on above-mentioned elliptical aperture group detection method, including work stage, luminous unit
Part, video camera, image pick-up card, data processing module, memory, console and alarm, as shown in Figure 7.The detecting system
Workflow：Workpiece for measurement is placed in work stage, the illumination that light-emitting component sends is mapped on workpiece for measurement, clapped by video camera
The image of elliptical aperture ancestral on workpiece for measurement is taken the photograph, and Jing image pick-up cards send image to data processing module, data processing mould
Block tries to achieve elliptical aperture packet size on the workpiece using aforementioned maximum inscribed circle algorithm, and sends the sized data to console,
Console pre-sets standard size and error threshold, and the elliptical aperture packet size of measurement is compared with standard size, if both
Error is more than error threshold, illustrates that the workpiece is unqualified, and console just drives alarm equipment alarm, and controls work stage by work to be measured
Part is moved in substandard product.
Above example technological thought only to illustrate the invention, it is impossible to which protection scope of the present invention is limited with this, it is every
According to technological thought proposed by the present invention, any change done on the basis of technical scheme, the scope of the present invention is each fallen within
Within.
Claims (3)
1. a kind of elliptical aperture group detection method based on maximum inscribed circle, it is characterised in that comprise the following steps：
(1) workpiece image information is gathered；
(2) image information to gathering carries out Image semantic classification；
(3) piecemeal is carried out to image information according to the oval pore size distribution in image information, there is 1 elliptical aperture on every block of image；
(4) semi-minor axis length, major semiaxis length and the inclination angle of elliptical aperture in every block of image are gone out using maximum inscribed circle Algorithm for Solving；Tool
Hold in vivo as follows：
A () calculates oval m bar horizontal scanning lines, and by i-th horizontal scanning line and oval intersection point ai1、ai2Count set S, i
=1,2 ..., m；
B () calculates all in S set | ai1ai2| midpoint ai, horizontal sweep dotted line is obtained by least square fitting, and ask
Go out the intersection point A of horizontal sweep dotted line and ellipse1、A2, calculate line segment | A1A2| midpoint M1；
C () solves the vertical scanning dotted line and the intersection point institute line section of ellipse of ellipse according to step (a), the method for (b)
Midpoint M2, with | M1M2| midpoint O1For the center of circle, | M1M2| take round C for diameter1；
D () obtained point O1Horizontal linear with ellipse intersection point P1、P2, with O1For the center of circle, max | O1P1|, | O1P2| it is radius
Make circle C2；
If e () justifies C2There are 4 intersection points with ellipse, P is designated as successively3、P4、P5、P6, or circle C2There are 3 intersection points, i.e. P with ellipse3With
P4Overlap or P5With P6Overlap, then with arc lengthWithFor scope, circle C is calculated1Each interior point arrives ellipse in the range of this
Minimum range d of circle boundary pointmin, and charge to set H；If circle C2During with oval only one of which or two intersection points, then circle C is calculated1
Minimum range d of each the interior point to oval all boundary pointsmin, and charge to set H；
F () obtains the max { d in set Hmin, and max { dminCorresponding C1Interior point O；
(g) centered on O, max { dminIt is radius, make circle and hand over ellipse in N1、N22 points, this circle is oval maximum inscribe
Circle, | ON1| as oval semi-minor axis is long, and the tiltangleθ and ellipse short shaft place straight line of ellipse are tried to achieve respectively
H () is in line segment | N1N2| above take point Kj, j=1,2 ..., n, will | N1N2| n+1 parts are divided into, K is crossedjMake | N1N2| vertical line hand over
Oval and Dj1, Dj2, calculate dj=| Dj1Dj2|/2, by { Kj, djCount set Q；
I () is to the element { K in set Qj, djLeast square fitting is utilized, try to achieve { Kj, djRespective function maximum dmax, i.e.,
It is long for oval major semiaxis；
(5) the semi-minor axis length of elliptical aperture, major semiaxis length and inclination angle and standard ellipse hole size are contrasted, is judged on workpiece
Elliptical aperture group it is whether qualified.
2. a kind of elliptical aperture group detection method based on maximum inscribed circle according to claim 1, it is characterised in that：Step
(2) being followed successively by the step of Image semantic classification described in image denoising, to image carries out binaryzation and carries out edge inspection to image
Survey.
3. a kind of elliptical aperture group detection method based on maximum inscribed circle according to claim 2, it is characterised in that：The side
Edge is detected as Canny rim detections.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510043349.8A CN104613869B (en) | 2015-01-28 | 2015-01-28 | Method and system for detecting elliptical hole group based on maximum inscribed circle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510043349.8A CN104613869B (en) | 2015-01-28 | 2015-01-28 | Method and system for detecting elliptical hole group based on maximum inscribed circle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104613869A CN104613869A (en) | 2015-05-13 |
| CN104613869B true CN104613869B (en) | 2017-05-10 |
Family
ID=53148430
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510043349.8A Active CN104613869B (en) | 2015-01-28 | 2015-01-28 | Method and system for detecting elliptical hole group based on maximum inscribed circle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104613869B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105279756B (en) * | 2015-10-19 | 2018-06-12 | 天津理工大学 | Notch circular arc accessory size visible detection method based on adaptive region segmentation |
| CN106875832A (en) * | 2015-12-10 | 2017-06-20 | 北京航天长峰科技工业集团有限公司 | The polymerization of identifier and depolymerization method in a kind of situation |
| CN106679564B (en) * | 2016-12-15 | 2019-08-02 | 哈尔滨飞机工业集团有限责任公司 | A kind of measurement method of slotted hole |
| CN107454314B (en) * | 2017-07-05 | 2020-06-02 | 深圳市捷高软件信息有限公司 | Image cutting method of single-lens 360-degree panoramic camera |
| CN107967471A (en) * | 2017-09-20 | 2018-04-27 | 北京工业大学 | A kind of table tool automatic identifying method based on machine vision |
| CN109741314A (en) * | 2018-12-29 | 2019-05-10 | 广州博通信息技术有限公司 | A kind of visible detection method and system of part |
| CN111664772B (en) * | 2020-05-29 | 2021-07-02 | 大冶特殊钢有限公司 | Method for rapidly measuring roll hole type long half shaft of three-roll reducing mill |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102445456A (en) * | 2011-10-09 | 2012-05-09 | 河海大学常州校区 | Device and method for nondestructively detecting egg quality based on DSP (Dynamic Signal Processing) machine vision |
| CN102607410A (en) * | 2012-03-01 | 2012-07-25 | 上海大学 | Method for detecting position and attitude of micro cylindrical cavity target by using target collimating sensor |
| CN103033126A (en) * | 2011-09-29 | 2013-04-10 | 鸿富锦精密工业（深圳）有限公司 | Annular object location method and system |
| CN103063159A (en) * | 2012-12-31 | 2013-04-24 | 南京信息工程大学 | Part size measurement method based on charge coupled device (CCD) |
| CN103925878A (en) * | 2014-04-11 | 2014-07-16 | 南京信息工程大学 | Hole set detection method and system based on Hough round convolution transformation algorithm |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0629697B2 (en) * | 1989-08-04 | 1994-04-20 | 理研電子株式会社 | Small hole position detector |
| JP3593885B2 (en) * | 1998-06-01 | 2004-11-24 | 富士ゼロックス株式会社 | Image analysis apparatus and method |
-
2015
- 2015-01-28 CN CN201510043349.8A patent/CN104613869B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103033126A (en) * | 2011-09-29 | 2013-04-10 | 鸿富锦精密工业（深圳）有限公司 | Annular object location method and system |
| CN102445456A (en) * | 2011-10-09 | 2012-05-09 | 河海大学常州校区 | Device and method for nondestructively detecting egg quality based on DSP (Dynamic Signal Processing) machine vision |
| CN102607410A (en) * | 2012-03-01 | 2012-07-25 | 上海大学 | Method for detecting position and attitude of micro cylindrical cavity target by using target collimating sensor |
| CN103063159A (en) * | 2012-12-31 | 2013-04-24 | 南京信息工程大学 | Part size measurement method based on charge coupled device (CCD) |
| CN103925878A (en) * | 2014-04-11 | 2014-07-16 | 南京信息工程大学 | Hole set detection method and system based on Hough round convolution transformation algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104613869A (en) | 2015-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104613869B (en) | Method and system for detecting elliptical hole group based on maximum inscribed circle | |
| CN110163853B (en) | Edge defect detection method | |
| CN109670441B (en) | Method, system, terminal and computer readable storage medium for realizing wearing recognition of safety helmet | |
| CN104504388B (en) | A kind of pavement crack identification and feature extraction algorithm and system | |
| CN110146516B (en) | Fruit grading device based on orthogonal binocular machine vision | |
| CN106290394B (en) | System and method for detecting aluminum extrusion molding defects of CPU radiator | |
| CN104537651B (en) | Proportion detecting method and system for cracks in road surface image | |
| CN106018422B (en) | Based on matched special-shaped stamping parts profile defects vision detection system and method | |
| CN113375566B (en) | Accurate measurement method and system for object size | |
| CN104315977B (en) | Rubber stopper quality detection device and detection method | |
| CN108230307B (en) | Corn broken grain detection method based on contour centroid distance and neural network | |
| CN104197836A (en) | Vehicle lock assembly size detection method based on machine vision | |
| CN106896110A (en) | Product quality detection means and method based on monocular camera machine vision | |
| CN210071686U (en) | Fruit grading plant based on orthogonal binocular machine vision | |
| CN106529551B (en) | Intelligent recognition counting detection method for round-like objects in packaging industry | |
| CN106248680A (en) | A kind of engine commutator quality detecting system based on machine vision and detection method | |
| CN105334228A (en) | Bottled liquid impurity and liquid level detection method based on image processing | |
| CN110807354B (en) | Industrial assembly line product counting method | |
| CN101726265A (en) | Online detection method of parallelism of spring by machine vision system | |
| CN105973903B (en) | A kind of Oral liquid bottle lid detection method | |
| CN107403444A (en) | Identifying system | |
| WO2023134251A1 (en) | Clustering-based light bar extraction method and apparatus | |
| CN113834814B (en) | Glove surface defect detection device | |
| CN109406534A (en) | A kind of medicine bottle bottom pull ring defect detecting device and method | |
| CN103453840A (en) | Automatic detection method for lock core precision of cylinder lock |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20191129 Address after: 221300 No.22, Fumin Road, Pizhou high tech Industrial Development Zone, Xuzhou City, Jiangsu Province (in Pizhou high tech Zone New Energy Technology Research Institute Co., Ltd.) Patentee after: Jiangsu Xinda environmental remote sensing Big Data Application Research Institute Co., Ltd Address before: 210044 Nanjing City, Pukou Province, Nanjing Road, No. 219, No. six, No. Patentee before: Nanjing University of Information Science and Technology |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201120 Address after: 210044 No. 219 Ningliu Road, Jiangbei New District, Nanjing City, Jiangsu Province Patentee after: NANJING University OF INFORMATION SCIENCE & TECHNOLOGY Address before: 221300 No.22, Fumin Road, Pizhou high tech Industrial Development Zone, Xuzhou City, Jiangsu Province (in Pizhou high tech Zone New Energy Technology Research Institute Co., Ltd.) Patentee before: Jiangsu Xinda environmental remote sensing Big Data Application Research Institute Co.,Ltd. |