CN106204631A - Plug-hole detection method based on frequency domain - Google Patents
Plug-hole detection method based on frequency domain Download PDFInfo
- Publication number
- CN106204631A CN106204631A CN201610704539.4A CN201610704539A CN106204631A CN 106204631 A CN106204631 A CN 106204631A CN 201610704539 A CN201610704539 A CN 201610704539A CN 106204631 A CN106204631 A CN 106204631A
- Authority
- CN
- China
- Prior art keywords
- hole
- plug
- frequency domain
- artwork
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20056—Discrete and fast Fourier transform, [DFT, FFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a kind of plug-hole detection method based on frequency domain, it can accurately detect plug-hole number.Including: step A, the artwork that obtains body target area to be detected；After step B, the Fourier transformation that described artwork carried out successively, low-pass filtering, inverse Fourier transform process, then carry out subtraction with described artwork, obtain the sharply marginated frequency domain of hole and process picture；Step C, process in picture at described frequency domain and choose at least one hole and the profile according to selected hole makes template, then in described frequency domain processes picture, do template matching, judge the pass blocking of the hole of position according to the gray scale of each position.The picture of target area is carried out frequency domain process, the sharpness of border making each hole shows, uses at least one of which hole as template, the hole in target area is carried out template matching, accurately judged that by gray scale each perforated is logical or stifled, can accurately calculate plug-hole number.
Description
Technical field
The present invention relates to a kind of plug-hole detection method based on frequency domain.
Background technology
The porous masses such as the catalyst such as porous need to detect plug-hole number, judge that product is the most qualified.With car tail
As a example by the three-way catalyst of gas, three-way catalyst is a kind of cylinder with big density honeycomb hole, to three in prior art
The plug-hole detection method of unit's catalyst is: take the three-way catalyst of a standard as sample, by collected by camera obtain this three
The overhead view image of unit's catalyst sample, utilizes the objective contour of sample top view to make template image；At detection three-way catalyst
Time, gather by each three-way catalyst to be checked as shown in Figure 1 top view (image the most to be detected), by each detection image
Do with template and mate, in theory, the coordinate that each hole is corresponding in template image, can find in image to be detected
Corresponding coordinate, then judges whether hole blocks.But, the method under some extreme case can it fails to match, such as go out
Existing carrier cross section tilts or the situation (as shown in Figures 2 and 3) of large area blocking, it is impossible to accurately detection plug-hole number.
Summary of the invention
For the problems referred to above, it is an object of the invention to provide a kind of plug-hole detection method based on frequency domain, it can be accurate
Detection plug-hole number.
For solving above-mentioned technical problem, the technical solution used in the present invention is:
A kind of plug-hole detection method based on frequency domain, including:
Step A, obtain the artwork of body target area to be detected；
After step B, the Fourier transformation that described artwork carried out successively, low-pass filtering, inverse Fourier transform process then former with described
Figure carries out subtraction, obtains the sharply marginated frequency domain of hole and processes picture；
Step C, process in picture at described frequency domain and choose at least one hole and the profile according to selected hole makes template, so
After process in picture at described frequency domain and to do template matching, judge the pass blocking of the hole of position according to the gray scale of each position.
Preferably, step A includes:
A1, in the entire image of body to be detected use Hough transformation identification body to be detected target area outline, outside crawl
Region in profile forms described artwork, and the region in outline is described target area.
Preferably, step A includes:
A2, described artwork is rotated, make hole arrange along x-axis or y-axis.
It is highly preferred that in step a2, by described artwork binaryzation, retain the border of hole, utilize Hough transformation identification straight
Line, rotates described artwork until described straight line extends along x-axis or extends along x-axis.
Preferably, this plug-hole detection method also includes:
Step D, find doubtful blocking region；
In step C, in described frequency domain processes picture, template matching is done in doubtful blocking region, according to each position in blocking region
Gray scale judge the pass blocking of hole of position.
It is highly preferred that by described artwork binaryzation, retain hole border and blocking region, then to the artwork after binaryzation
Carrying out morphology opening operation, remove normal hole border, remaining area is described doubtful blocking region.
Further, in step C, in frequency domain processes picture in each doubtful plug-hole region, according to template matching, find one
Individual best match position, according to the size and shape of template, obtains the perforated of best match position, utilizes this most preferably to mate
The all of perforated in doubtful plug-hole region is found in the perforated of position, judges the pass blocking of each hole respectively.
Preferably, the method includes successively:
Use the outline of Hough transformation identification body to be detected target area in step A, in the entire image of body to be detected, grab
Taking the region in outline and form described artwork, the region in outline is described target area；Described artwork is rotated,
Hole is made to arrange along x-axis or y-axis；
Step D, by described artwork binaryzation, retain hole border and blocking region, then the artwork after binaryzation carried out shape
State opening operation, removes normal hole border, and remaining area is described doubtful blocking region；
After step B, the Fourier transformation that described artwork carried out successively, low-pass filtering, inverse Fourier transform process then former with described
Figure carries out subtraction, obtains the sharply marginated frequency domain of hole and processes picture；
Step C, process in picture at described frequency domain and choose a hole and the profile according to selected hole makes template, then exist
Frequency domain processes in picture in each doubtful plug-hole region, according to template matching, finds a best match position, big according to template
Little and shape, obtains the perforated of best match position, utilizes the perforated of this best match position to find doubtful plug-hole
All of perforated in region, judges the pass blocking of each hole respectively.
Preferably, described hole array distribution.
Preferably, described body to be detected is the three-way catalyst of vehicle maintenance service.
The present invention uses technique scheme, has the advantage that the picture to target area is carried out compared to existing technology
Frequency domain processes, and makes the sharpness of border of each hole show, employing at least one of which hole is as template, in target area
Hole carries out template matching, is accurately judged that by gray scale each perforated is logical or stifled, can accurately calculate plug-hole number.
Accompanying drawing explanation
Fig. 1 is the top view of the three-way catalyst sample of shooting；
Fig. 2 is the top view of shooting after three-way catalyst tilts；
Fig. 3 is the top view of shooting after three-way catalyst large area plug-hole；
Fig. 4 is the picture of the three-way catalyst after low-pass filtering treatment
Fig. 5 is that the frequency domain of three-way catalyst processes picture.
Detailed description of the invention
Below in conjunction with the accompanying drawings presently preferred embodiments of the present invention is described in detail, so that advantages and features of the invention energy
It is easier to be understood by the person skilled in the art.
It is positioned at as a example by the three-way catalyst processed by automobile, the plug-hole detection method based on frequency domain of the present invention is carried out
Explanation.Certainly, the method for the present invention is not limited to detect three-way catalyst, and other similar porous also has the thing of periodic feature
Body, is all suitable for this method, i.e. each hole is array arrangement.
The method of the present invention in turn includes the following steps: A, detection target area, image rotation；D, image rotation；D, seek
Look for doubtful blocking region；B, target area is carried out frequency-domain analysis process；C, shape facility is utilized to do images match.Below to respectively
Individual step is described in detail.
The purpose of step A is the artwork obtaining the target area treating three-way catalyst, the target area tool of three-way catalyst
Body refers to all perforated in top view as shown in Figure 1.Step A specifically includes:
A1, in the view picture overhead view image of three-way catalyst use Hough transformation identification circle (three-way catalyst is cylinder, its mesh
Mark region corresponds to circle) outline, the region captured in outline forms described artwork, and the region in outline is described
Target area；
A2, described artwork is rotated, make hole arrange along x-axis or y-axis and (from the point of view of popular, be smooth vertical and horizontal arrangement side
To), detailed process is, by described artwork binaryzation, retains the border of hole, utilizes Hough transformation identification straight line, utilize Hough
The statistical property of conversion can find a straight line the longest in target area, this line correspondences in justifying closest to the center of circle
Straight line, and the inclination angle of this straight line seeks to the angle that rotates, rotates described artwork until described according to described angle
Straight line along x-axis extend or.During due to detection, the arragement direction of target Hole is random, is unfavorable for detection, thus to image
Rotating, the arragement direction of hole is become smooth vertical and horizontal, make hole rule arrange, hole distribution is known.
The purpose of step D is to find doubtful blocking region, owing to detection target complete region is the longest, can first do pre-
Sentence, get rid of obvious throughhole portions, only doubtful blocking region is detected.Such as, 4 holes of 2 adjacent row 2 row, at this
There is blocking in individual regional center, although looks total that blocked area has reached the area in single hole, but these 4 holes actual are each
Hole has only blocked 1/4, so the not very blocking of each hole, this region is exactly a kind of doubtful blocking region.Specific practice is: will
Described artwork binaryzation, retains hole border and blocking region, then the artwork after binaryzation is carried out morphology opening operation, go
Except normal hole border, remaining area is described doubtful blocking region.Doubtful blocking region is at artwork and the frequency being described below
Territory process picture and each processing stage picture in there is corresponding relation.
The purpose of step B is that in making target area, porose border is all revealed, and all of hole all has clearly
Boundary separates.Owing to there being the hole of very many regular distribution in target area, show the strongest periodicity, so,
It is especially suitable for frequency domain to process.Grey scale change within hole is mild, and the acute variation of the overwhelming majority is all distributed in hole boundary,
So, in frequency domain processes image, what low frequency part was corresponding is hole interior zone, and HFS corresponds to hole border.Tool
Body is, the artwork after processing of step A carries out Fourier transformation, then carries out low-pass filtering, suppresses high fdrequency component, then carries out inverse
Fourier transformation, can obtain the image that a width smooths very much, and this image cannot see border at normal hole, and
In large area plug-hole region, the border within hole is the most high-visible, as shown in Figure 4.Diagram sheet and artwork sheet are done subtraction fortune
Calculate, just can obtain a width by the most separate image in pertusate for institute border, referred to as frequency domain process image, as shown in Figure 5.
In step C, the frequency domain in step B gained processes in picture, chooses a hole, makes mould according to the shape of hole
Plate.The frequency domain obtained in step B processes in picture, do template matching in the doubtful blocking region that D marks off in steps, sentence
The gray scale of the position of disconnected each coupling, just can determine whether this hole be logical be stifled.Specifically comprise the following steps that in each suspicious region,
First according to template matching, a best match position is found, according to the size and shape (such as regular hexagon) of hole, permissible
Know the perforated of optimal coupling, owing to image is rotated by step a2, so the distribution of hole is known, profit
All of perforated in can finding suspicious region with the hole of optimal coupling, judge respectively each perforated be logical or
Stifled, just can accurately calculate all of plug-hole number.
Above-described embodiment for technology design and the feature of the present invention are described, is only a kind of preferred embodiment, and its purpose exists
In allowing person skilled in the art will appreciate that present disclosure and to implement according to this, the guarantor of the present invention can not be limited with this
Protect scope.All equivalence changes made according to the spirit of the present invention or modification, all should contain in protection scope of the present invention
Within..
Claims (10)
1. a plug-hole detection method based on frequency domain, it is characterised in that including:
Step A, obtain the artwork of body target area to be detected；
After step B, the Fourier transformation that described artwork carried out successively, low-pass filtering, inverse Fourier transform process then former with described
Figure carries out subtraction, obtains the sharply marginated frequency domain of hole and processes picture；
Step C, process in picture at described frequency domain and choose at least one hole and the profile according to selected hole makes template, so
After process in picture at described frequency domain and to do template matching, judge the pass blocking of the hole of position according to the gray scale of each position.
Plug-hole detection method the most according to claim 1, it is characterised in that step A includes:
A1, in the entire image of body to be detected use Hough transformation identification body to be detected target area outline, outside crawl
Region in profile forms described artwork, and the region in outline is described target area.
Plug-hole detection method the most according to claim 1 and 2, it is characterised in that step A includes:
A2, described artwork is rotated, make hole arrange along x-axis or y-axis.
Plug-hole detection method the most according to claim 3, it is characterised in that in step a2, by described artwork binaryzation, protects
Box out the border in hole, utilize Hough transformation identification straight line, rotate described artwork until described straight line extends along x-axis or prolongs along x-axis
Stretch.
Plug-hole detection method the most according to claim 1, it is characterised in that this plug-hole detection method also includes:
Step D, find doubtful blocking region；
In step C, in described frequency domain processes picture, template matching is done in doubtful blocking region, according to each position in blocking region
Gray scale judge the pass blocking of hole of position.
Plug-hole detection method the most according to claim 5, it is characterised in that by described artwork binaryzation, retains hole limit
Boundary and blocking region, then carry out morphology opening operation to the artwork after binaryzation, remove normal hole border, remaining area
For described doubtful blocking region.
7. according to the plug-hole detection method described in claim 5 or 6, it is characterised in that in step C, in frequency domain processes picture
In each doubtful plug-hole region, according to template matching, find a best match position, according to the size and shape of template, obtain
The perforated of best match position, utilize that the perforated of this best match position finds in doubtful plug-hole region is all of
Perforated, judges the pass blocking of each hole respectively.
Plug-hole detection method the most according to claim 1, it is characterised in that include successively:
Use the outline of Hough transformation identification body to be detected target area in step A, in the entire image of body to be detected, grab
Taking the region in outline and form described artwork, the region in outline is described target area；Described artwork is rotated,
Hole is made to arrange along x-axis or y-axis；
Step D, by described artwork binaryzation, retain hole border and blocking region, then the artwork after binaryzation carried out shape
State opening operation, removes normal hole border, and remaining area is described doubtful blocking region；
After step B, the Fourier transformation that described artwork carried out successively, low-pass filtering, inverse Fourier transform process then former with described
Figure carries out subtraction, obtains the sharply marginated frequency domain of hole and processes picture；
Step C, process in picture at described frequency domain and choose a hole and the profile according to selected hole makes template, then exist
Frequency domain processes in picture in each doubtful plug-hole region, according to template matching, finds a best match position, big according to template
Little and shape, obtains the perforated of best match position, utilizes the perforated of this best match position to find doubtful plug-hole
All of perforated in region, judges the pass blocking of each hole respectively.
Plug-hole detection method the most according to claim 1, it is characterised in that described hole array is distributed.
Plug-hole detection method the most according to claim 1, it is characterised in that described body to be detected is vehicle maintenance service
Three-way catalyst.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610704539.4A CN106204631B (en) | 2016-08-23 | 2016-08-23 | Plug-hole detection method based on frequency domain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610704539.4A CN106204631B (en) | 2016-08-23 | 2016-08-23 | Plug-hole detection method based on frequency domain |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106204631A true CN106204631A (en) | 2016-12-07 |
| CN106204631B CN106204631B (en) | 2019-01-15 |
Family
ID=57523436
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610704539.4A Active CN106204631B (en) | 2016-08-23 | 2016-08-23 | Plug-hole detection method based on frequency domain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106204631B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116129331A (en) * | 2023-04-12 | 2023-05-16 | 成都航空职业技术学院 | Method and device for counting number of through holes on surface of rotary part |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102147857A (en) * | 2011-03-22 | 2011-08-10 | 黄晓华 | Image processing method for detecting similar round by using improved hough transformation |
| CN102945368A (en) * | 2012-10-17 | 2013-02-27 | 西安理工大学 | Method for positioning and identifying laser character of beer bottle cap |
| CN103400129A (en) * | 2013-07-22 | 2013-11-20 | 中国科学院光电技术研究所 | Target tracking method based on frequency domain significance |
| CN104091170A (en) * | 2014-06-13 | 2014-10-08 | 电子科技大学 | Automatic mould distinguishing method based on machine vision |
-
2016
- 2016-08-23 CN CN201610704539.4A patent/CN106204631B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102147857A (en) * | 2011-03-22 | 2011-08-10 | 黄晓华 | Image processing method for detecting similar round by using improved hough transformation |
| CN102945368A (en) * | 2012-10-17 | 2013-02-27 | 西安理工大学 | Method for positioning and identifying laser character of beer bottle cap |
| CN103400129A (en) * | 2013-07-22 | 2013-11-20 | 中国科学院光电技术研究所 | Target tracking method based on frequency domain significance |
| CN104091170A (en) * | 2014-06-13 | 2014-10-08 | 电子科技大学 | Automatic mould distinguishing method based on machine vision |
Non-Patent Citations (1)
| Title |
|---|
| 杨扬: "基于帘子布疵点检测系统的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116129331A (en) * | 2023-04-12 | 2023-05-16 | 成都航空职业技术学院 | Method and device for counting number of through holes on surface of rotary part |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106204631B (en) | 2019-01-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107808378B (en) | Method for detecting potential defects of complex-structure casting based on vertical longitudinal and transverse line profile features | |
| CN104318582B (en) | Detection method for bad state of rotating double-lug component pin of high-speed rail contact network | |
| KR101565748B1 (en) | A method and apparatus for detecting a repetitive pattern in image | |
| CN106372667B (en) | A kind of high iron catenary diagonal brace sleeve part screw defective mode detection method | |
| JP6323157B2 (en) | Diagnostic data extraction device, vehicle diagnostic device | |
| WO2017093037A1 (en) | Method for identification of candidate points as possible characteristic points of a calibration pattern within an image of the calibration pattern | |
| CN106485694B (en) | A kind of high iron catenary double-jacket tube connector six-sided nut based on cascade classifier falls off defective mode detection method | |
| JP2014029287A5 (en) | ||
| CN109507219A (en) | A method of automatically analyzing diffraction maximum peak shape in scan-type Laue diffraction map | |
| CN105205828A (en) | Warp knitted fabric flaw detection method based on optimal Gabor filter | |
| CN112232222B (en) | Bullet train axle box end cover bolt loss fault detection method based on image processing | |
| CN106204631A (en) | Plug-hole detection method based on frequency domain | |
| CN102663706A (en) | Adaptive weighted mean value filtering method based on diamond template | |
| CN107766866B (en) | Direction selective contour detection method based on receptive field region | |
| CN101135729A (en) | Method for synthetic aperture radar shelter from shelter from object identification based on supporting vector machine | |
| Lin et al. | A line segment based inshore ship detection method | |
| CN103854023A (en) | Camera blocking detection method based on wavelet transformation and time domain pattern recognition | |
| EP2624170A3 (en) | Method for detecting a predetermined pattern in an image dataset | |
| CN113850815A (en) | Workpiece point cloud obtaining method and device, electronic equipment and storage medium | |
| DE102018210814A1 (en) | Method for the detection of static radar targets with a radar sensor for motor vehicles | |
| JP2007527506A5 (en) | ||
| CN104836990A (en) | Pier anti-collision image monitoring system and monitoring method | |
| CN102663730B (en) | Remote sensing image change detection method based on Treelet and direction adaptive filtering | |
| CN103164857B (en) | A kind of efficient detection method of the short-distance large-deflection circular target based on image | |
| JP2019153986A5 (en) | Information processing equipment, information processing systems, information processing methods, and programs |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 215100 AD District, South Side of 1F-2F Building No. 38 North Guandu Road, Yuexi Street, Wuzhong District, Suzhou City, Jiangsu Province Applicant after: SUZHOU DCCK MEASUREMENT AND CONTROL TECHNOLOGY CO., LTD. Address before: 215123 5th Floor, Block B3, 1258 Jinfeng South Road, Wuzhong District, Suzhou City, Jiangsu Province (Jinqiao Auto Parts Industrial Park) Applicant before: SUZHOU DCCK MEASUREMENT AND CONTROL TECHNOLOGY CO., LTD. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |