CN105741304A - Laser stripe center extraction algorithm - Google Patents
Laser stripe center extraction algorithm Download PDFInfo
- Publication number
- CN105741304A CN105741304A CN201610117836.9A CN201610117836A CN105741304A CN 105741304 A CN105741304 A CN 105741304A CN 201610117836 A CN201610117836 A CN 201610117836A CN 105741304 A CN105741304 A CN 105741304A
- Authority
- CN
- China
- Prior art keywords
- laser stripe
- image
- stripe center
- center extraction
- algorithm
- 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
- 238000000605 extraction Methods 0.000 title claims abstract description 19
- 238000001914 filtration Methods 0.000 claims abstract description 12
- 238000009826 distribution Methods 0.000 claims abstract description 9
- 238000009499 grossing Methods 0.000 claims abstract description 3
- 238000000034 method Methods 0.000 abstract description 12
- 238000003466 welding Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a laser stripe center extraction algorithm, comprising steps of performing smooth filtering on the image according to the vertical direction in order to eliminate high frequency interference, performing transverse filtering on the image in order to highlight the image characteristic information, performing smoothing processing on the image, obtaining a gradient distribution curve through processing the three groups of data, finding out the maximum value from the gradient curve, which is where the laser stripe center is positioned. The laser stripe center extraction algorithmis obtained through improvement on the gradient algorithm and the order of magnitude of the improvement algorithm reaches 104. The laser stripe center extraction algorithm is high in resolution, avoids the laser stripe breakage caused by centroid method and the extremum method.
Description
Technical field
The present invention relates to welding, image processing field, be specifically related to a kind of laser stripe center extraction algorithm.
Background technology
At present, the industrialized level of China is more and more higher, and large-scale component application at the scene also gets more and more.Welding is the important means of large-scale component assembling at the scene, and as an important key technology of heavy industry, welding quality and efficiency affect quality, cycle and the cost that main equipment manufactures.Use Mobile welding machine people to replace human weld, stablizing of welding quality can not only be ensured, moreover it is possible to effectively shorten manufacturing schedule, reduce manufacturing cost.The automatic welding of mobile apparatus people be unable to do without machine vision and image processing techniques, is that active vision method is followed the tracks of in weld seam process in employing, and the extraction at laser stripe center is most important, and the precision of center extraction is directly connected to the precision of welding tracking.Carrying out laser stripe center extraction with the conventional calculation such as centroid method, extremum method and be likely to result in laser stripe fracture, this is unallowed in detection of discharge orifice in such as shipbuilding, therefore must have the algorithm that new adaptability is high in certain applications.
Summary of the invention
It is an object of the invention to provide a kind of laser stripe center extraction algorithm, with the problem solving to propose in above-mentioned background technology.
For achieving the above object, the present invention provides following technical scheme: a kind of laser stripe center extraction method, it is characterised in that: comprise the following steps:
(1) by image by longitudinally carrying out smothing filtering to eliminate High-frequency Interference;
(2) image is carried out laterally filtering with prominent image feature information;
(3) image is smoothed;
(4) Gradient distribution curve is obtained by three groups of data more than processing;
(5) find out the extreme point in Gradient distribution curve, be the laser stripe center of correspondence.
As the further scheme of the present invention: described step (1) specific algorithm is:
(i is j) that the (i, j) gray value of individual pixel, row is the output valve of longitudinally filtering, and i is the line number of image, and j is the columns of image, and image edge pixels is carried out respective handling for Gray in formula.
As the present invention further scheme: in step (2), specific algorithm is:
In formula, N participates in average pixel number, and n is the original position of reconnaissance.
As the present invention further scheme: in step (3), specific algorithm is:
In formulaFor the gray scale vector after smoothing processing
As the present invention further scheme: in step (4), specific algorithm is:
。
Find out the extreme point in Gradient distribution curve, be the laser stripe center of correspondence.
Compared with prior art, the invention has the beneficial effects as follows: the order of magnitude of inventive algorithm has reached 104, there is significantly high resolution, avoid the weak point of the laser stripe fracture that the conventional algorithm such as centroid method, extremum method causes simultaneously.
Detailed description of the invention
Fig. 1 show the schematic diagram of application longitudinal direction laser stripe of the present invention.
Fig. 2 show the schematic diagram of application transverse direction laser stripe of the present invention.
Fig. 3 is Fig. 1 the 300th behavior example from the bottom up of the present invention, draws the gray level schematic diagram of correspondence.
Fig. 4 is after the algorithm steps (4) of the present invention, the array that must make new advances and the gray level schematic diagram of image.
Detailed description of the invention
Below in conjunction with the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is only a part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art obtain under not making creative work premise, broadly fall into the scope of protection of the invention.
Before carrying out laser stripe center extraction, it is possible to carry out other pretreatment to improve the calculating speed of the present invention, such as adopt dynamic RIO(RegionOfInterest) acquisition.The present invention is applicable to the laser stripe that is laterally or longitudinally distributed, and form is 256 color BMP, and the image of other form is please changed in advance, such as Fig. 1, shown in 2.
The present invention is directed longitudinal laser stripe extracting method shown in Fig. 1, the extracting method of Fig. 2 laterally shown laser stripe is similar, step (1) in invention and (2) are swapped by corresponding processing method order, namely first carry out horizontal filtering, then carry out longitudinal filtering.
Carry out laser stripe extraction for Fig. 1 by the algorithm of the present invention, pending image be scanned, draw the gray value of image pixel, with Fig. 1 the 300th behavior example from the bottom up, show that the gray level of correspondence is Fig. 3,
Array is undertaken by inventive algorithm step, after step (4), the array that must make new advances and the gray level of image, shown in Fig. 4,
The order of magnitude after calculating has reached 104, there is significantly high resolution.All image lines process according to this, can obtain the distribution at laser stripe center in image.
Claims (6)
1. a laser stripe center extraction method, it is characterised in that comprise the following steps:
(1) by image by longitudinally carrying out smothing filtering to eliminate High-frequency Interference;
(2) image is carried out laterally filtering with prominent image feature information;
(3) image is smoothed;
(4) Gradient distribution curve is obtained by three groups of data more than processing;
(5) find out the extreme point in Gradient distribution curve, be the laser stripe center of correspondence.
2. laser stripe center extraction method according to claim 1, it is characterised in that by image by longitudinally carrying out smothing filtering, algorithm particularly as follows:
(i is j) that the (i, j) gray value of individual pixel, row is the output valve of longitudinally filtering, and i is picturedeep, and j is picturewide, and image edge pixels is carried out respective handling for Gray in formula.
3. laser stripe center extraction method according to claim 1, it is characterised in that image is carried out laterally filtering with prominent image feature information, algorithm particularly as follows:
In formula, N participates in average pixel number, and n is the original position of reconnaissance.
4. laser stripe center extraction method according to claim 1, it is characterised in that image is smoothed, algorithm particularly as follows:
In formula, column1 (i) is the gray scale vector after smoothing processing.
5. laser stripe center extraction method according to claim 1, it is characterised in that the algorithm of Gradient distribution curve particularly as follows:
Column2 (i)=abs (diff (column (i)-row (i))) * column1 (i).
6. laser stripe center extraction method according to claim 1, it is characterised in that find out the extreme point in Gradient distribution curve, is the laser stripe center of correspondence.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610117836.9A CN105741304A (en) | 2016-03-02 | 2016-03-02 | Laser stripe center extraction algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610117836.9A CN105741304A (en) | 2016-03-02 | 2016-03-02 | Laser stripe center extraction algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105741304A true CN105741304A (en) | 2016-07-06 |
Family
ID=56248955
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610117836.9A Pending CN105741304A (en) | 2016-03-02 | 2016-03-02 | Laser stripe center extraction algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105741304A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107563991A (en) * | 2017-08-01 | 2018-01-09 | 大连理工大学 | The extraction of piece surface fracture laser striation and matching process |
CN107621226A (en) * | 2017-07-18 | 2018-01-23 | 深圳大学 | The 3-D scanning method and system of multi-view stereo vision |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102663781A (en) * | 2012-03-23 | 2012-09-12 | 南昌航空大学 | Sub-pixel level welding center extraction method based on visual sense |
-
2016
- 2016-03-02 CN CN201610117836.9A patent/CN105741304A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102663781A (en) * | 2012-03-23 | 2012-09-12 | 南昌航空大学 | Sub-pixel level welding center extraction method based on visual sense |
Non-Patent Citations (1)
Title |
---|
郭亮等: "船舱流水孔自动识别跟踪焊接***", 《焊接学报》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107621226A (en) * | 2017-07-18 | 2018-01-23 | 深圳大学 | The 3-D scanning method and system of multi-view stereo vision |
CN107563991A (en) * | 2017-08-01 | 2018-01-09 | 大连理工大学 | The extraction of piece surface fracture laser striation and matching process |
CN107563991B (en) * | 2017-08-01 | 2019-08-20 | 大连理工大学 | Piece surface is broken extraction and the matching process of laser striation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107478657A (en) | Stainless steel surfaces defect inspection method based on machine vision | |
CN105913407B (en) | A method of poly focal power image co-registration is optimized based on differential chart | |
CN103136752B (en) | Image magnification method based on edge extraction | |
CN102496161A (en) | Method for extracting contour of image of printed circuit board (PCB) | |
CN105139391B (en) | A kind of haze weather traffic image edge detection method | |
CN102883175A (en) | Methods for extracting depth map, judging video scene change and optimizing edge of depth map | |
CN104236480A (en) | Line-structured light machine vision hexagonal billet steel profile measuring device and method | |
CN108088381A (en) | A kind of contactless minim gap method for measuring width based on image procossing | |
CN103293168B (en) | Fruit surface defect detection method based on visual saliency | |
CN105488512A (en) | Sift feature matching and shape context based test paper inspection method | |
CN115880288B (en) | Detection method, system and computer equipment for electronic element welding | |
CN102663384A (en) | Curve identification method based on Bezier control point searching and apparatus thereof | |
CN102663781A (en) | Sub-pixel level welding center extraction method based on visual sense | |
CN105741304A (en) | Laser stripe center extraction algorithm | |
CN104408727B (en) | A kind of image border smear detecting method and system | |
CN114332079A (en) | Plastic lunch box crack detection method, device and medium based on image processing | |
CN110310295B (en) | Weld contour extraction method and system | |
CN107507130A (en) | A kind of quickly QFN chip pins image obtains and amplification method | |
CN104573635B (en) | A kind of little height recognition methods based on three-dimensional reconstruction | |
CN103411562B (en) | A kind of structured light strip center extraction method based on dynamic programming and average drifting | |
CN111738936A (en) | Image processing-based multi-plant rice spike length measuring method | |
CN102967277A (en) | Method for measuring depth of parallelism of orienting pipes | |
CN110349142A (en) | Defect sample generation method, model training method, system and the electronic equipment of steel coil end-face | |
CN102193194B (en) | Distance computing device and lens correction system and method using same | |
CN104915937B (en) | Quick simple lens based on frequency domain matrix decomposition calculates imaging method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160706 |