CN109191439A - A kind of target workpiece surface knife mark defect inspection method - Google Patents
A kind of target workpiece surface knife mark defect inspection method Download PDFInfo
- Publication number
- CN109191439A CN109191439A CN201810949195.2A CN201810949195A CN109191439A CN 109191439 A CN109191439 A CN 109191439A CN 201810949195 A CN201810949195 A CN 201810949195A CN 109191439 A CN109191439 A CN 109191439A
- Authority
- CN
- China
- Prior art keywords
- workpiece surface
- target workpiece
- knife mark
- mark defect
- defect inspection
- 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 33
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000007689 inspection Methods 0.000 title claims abstract description 20
- 238000007619 statistical method Methods 0.000 claims abstract description 5
- 238000001914 filtration Methods 0.000 claims description 3
- 239000013077 target material Substances 0.000 claims 6
- 238000001514 detection method Methods 0.000 abstract description 12
- 238000012797 qualification Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007781 pre-processing 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
- 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
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The present invention relates to Surface Flaw Detection technical field more particularly to a kind of target workpiece surface knife mark defect inspection methods.This method is the following steps are included: (1) obtains target workpiece surface image；(2) the pixel intensity average value of target workpiece surface image is counted；(3) according to the pixel intensity average value of step (2), average brightness change curve is obtained；(4) characteristic on average brightness change curve is extracted；(5) threshold value is set, it is for statistical analysis to characteristic, carry out knife mark defect dipoles.A kind of target workpiece surface knife mark defect inspection method provided by the invention, can more effectively, more accurately detect the uneven knife mark defect of target workpiece surface.
Description
Technical field
The present invention relates to Surface Flaw Detection technical fields more particularly to a kind of target workpiece surface knife mark defect to examine
Survey method.
Background technique
It is under normal circumstances using artificial detection for the defects detection of workpiece surface during traditional work piece production
Method.With scientific and technical continuous development, there is mechanical vision inspection technology.The inspection designed using this new technology
Examining system and method can effectively detect workpiece not by the interference of external environment and subjective factor.
But for high-purity target, due to target workpiece dead-soft, there are many processing and cause uniform thin knife mark in surface.
Although these knife marks be it is qualified, be easy to cause the methods of contours extract erroneous detection.And in production process, uneven knife mark defect
It is few to there is quantity, and without rule is repeated, this causes defect characteristic not classify well, and frequency domain characteristic is unobvious.Existing mould
The methods of plate matching, not only detection speed is slow, also lacks robustness for different situations, missing inspection false detection rate is high, for uneven
Knife mark defect cannot be effectively detected out.
Summary of the invention
In view of the drawbacks of the prior art or technical need, the purpose of the present invention is to provide a kind of target workpiece surface knife marks
Defect inspection method can more effectively, more accurately detect the uneven knife mark defect of target workpiece surface.
To achieve the above object, the present invention is the following technical schemes are provided: a kind of target workpiece surface knife mark defects detection side
Method, comprising the following steps:
(1) target workpiece surface image is obtained；
(2) the pixel intensity average value of target workpiece surface image is counted；
(3) according to the pixel intensity average value of step (2), average brightness change curve is obtained；
(4) characteristic on average brightness change curve is extracted；
(5) threshold value is set, it is for statistical analysis to characteristic, carry out knife mark defect dipoles.
Further, further comprising the steps of between step (1) and step (2): target workpiece surface image to be carried out pre-
Processing.
Further, pretreatment is specially filtering, denoising.
Further, the method for the pixel intensity average value of target workpiece surface image is counted in step (2) are as follows:
(1) using the center of target workpiece surface as origin, polar coordinate system is established；
It (2) is radius by the center of circle, 1 pixel of the center of target workpiece surface, circumference where uniformly acquiring respective radius
On all pixels brightness, and calculate average value；
(3) increase radius by step-length of 1 pixel, continue to count the pixel intensity average value on circumference, until radius reaches
To target workpiece surface radius size.
Further, in step (3), average brightness change curve is song of the pixel intensity average value with radius change
Line.
Further, in step (4), characteristic specifically: peak value and surrounding number on average brightness change curve
According to relative variation, peak width.
Further, in step (5), threshold value specifically: relative variation minimum is 0.05, and the peak of peak width is
3。
Compared with prior art, the present invention beneficial effect is: a kind of target workpiece surface knife mark provided by the invention is scarce
Detection method is fallen into, can effectively detect the uneven knife mark defect of high-purity target workpiece surface, and uneven knife can be quantified
Line defect information, such as number, position, effectively avoid occurring situations such as missing inspection, erroneous detection in detection process.
Detailed description of the invention
Fig. 1 is a kind of flow chart of target workpiece surface knife mark defect inspection method provided in an embodiment of the present invention.
Specific embodiment
Carry out more detailed description with reference to the accompanying drawing and by embodiment to the present invention, it should be understood that this place
The specific embodiment of description only to explain the present invention, is not intended to restrict the invention.
As shown in Figure 1, a kind of target workpiece surface knife mark defect inspection method the following steps are included:
(1) target workpiece surface image is obtained；
(2) the pixel intensity average value of target workpiece surface image, method are counted specifically:
Firstly, establishing polar coordinate system using the center of target workpiece surface as origin；
Then, it is radius by the center of circle, 1 pixel of the center of target workpiece surface, uniformly acquires circle where respective radius
All pixels brightness on week, and calculate average value；
Then, increase radius by step-length of 1 pixel, continue to count the pixel intensity average value on circumference, until radius
Reach target workpiece surface radius size；
(3) according to the pixel intensity average value of step (2), average brightness change curve, average brightness variation are obtained
Curve is curve of the pixel intensity average value with radius change；
(4) characteristic on average brightness change curve, characteristic are extracted specifically: average brightness variation is bent
Relative variation, the peak width of peak value and ambient data on line；
(5) threshold value, threshold value are set specifically: relative variation minimum is 0.05, and the peak of peak width is 3, to spy
It is for statistical analysis to levy data, carries out knife mark defect dipoles.
Method for statistical analysis to characteristic in step (5), carrying out knife mark defect dipoles are as follows:
First, it is determined that whether the relative variation of peak value and ambient data on average brightness change curve is greater than
0.05, if relative variation is not more than 0.05, judge this knife mark qualification；If relative variation is greater than 0.05, carry out down
The judgement of one step；
Next, it is determined that whether the peak width on average brightness change curve less than 3, if peak width is not less than 3, judges
This knife mark qualification；If peak width less than 3, judges that this knife mark is unqualified.
On average brightness change curve, it can be sentenced according to the relative variation and peak width of peak value and ambient data
The Qualification of breaking line, simultaneously as average brightness change curve is curve of the pixel intensity average value with radius change,
Respective radius can be found from corresponding peak value, and then the specific location of uneven knife mark defect can be accurately positioned.
Between step (1) and step (2), can with the following steps are included: pre-processed to target workpiece surface image,
Pretreatment is specially filtering, denoising.
A kind of target workpiece surface knife mark defect inspection method provided by the invention, can effectively detect high-purity target work
The uneven knife mark defect in part surface, and uneven knife mark defect information, such as number, position can be quantified, it effectively avoids examining
Occurs situations such as missing inspection, erroneous detection during surveying.
The above is only a preferred embodiment of the present invention, it is noted that come for those of ordinary skill in the art
Say, without departing from the principle of the present invention, several flexible or other embodiments can also be made, these it is flexible or other
Embodiment also should be regarded as protection scope of the present invention.
Claims (7)
1. a kind of target workpiece surface knife mark defect inspection method, it is characterised in that: the described method comprises the following steps:
(1) target workpiece surface image is obtained；
(2) the pixel intensity average value of the target workpiece surface image is counted；
(3) according to the pixel intensity average value of step (2), average brightness change curve is obtained；
(4) characteristic on the average brightness change curve is extracted；
(5) threshold value is set, it is for statistical analysis to the characteristic, carry out knife mark defect dipoles.
2. target material surface knife mark defect inspection method according to claim 1, it is characterised in that: in step (1) and step
(2) further comprising the steps of between: the target workpiece surface image is pre-processed.
3. target material surface knife mark defect inspection method according to claim 2, it is characterised in that: the pretreatment is specially
Filtering, denoising.
4. target material surface knife mark defect inspection method according to claim 1, it is characterised in that: count institute in step (2)
The method for stating the pixel intensity average value of target workpiece surface image are as follows:
(1) using the center of the target workpiece surface as origin, polar coordinate system is established；
It (2) is radius by the center of circle, 1 pixel of the center of the target workpiece surface, circumference where uniformly acquiring respective radius
On all pixels brightness, and calculate average value；
(3) increase radius by step-length of 1 pixel, continue to count the pixel intensity average value on circumference, until radius reaches institute
State target workpiece surface radius size.
5. target material surface knife mark defect inspection method according to claim 1, it is characterised in that: described bright in step (3)
Spending mean variation curve is curve of the pixel intensity average value with radius change.
6. target material surface knife mark defect inspection method according to claim 1, it is characterised in that: in step (4), the spy
Levy data specifically: relative variation, the peak width of peak value and ambient data on the average brightness change curve.
7. target material surface knife mark defect inspection method according to claim 6, it is characterised in that: in step (5), the threshold
Value specifically: the minimum of the relative variation is 0.05；The peak of the peak width is 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810949195.2A CN109191439A (en) | 2018-08-20 | 2018-08-20 | A kind of target workpiece surface knife mark defect inspection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810949195.2A CN109191439A (en) | 2018-08-20 | 2018-08-20 | A kind of target workpiece surface knife mark defect inspection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109191439A true CN109191439A (en) | 2019-01-11 |
Family
ID=64918441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810949195.2A Pending CN109191439A (en) | 2018-08-20 | 2018-08-20 | A kind of target workpiece surface knife mark defect inspection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109191439A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112669321A (en) * | 2021-03-22 | 2021-04-16 | 常州微亿智造科技有限公司 | Sand blasting unevenness detection method based on feature extraction and algorithm classification |
| CN112767400A (en) * | 2021-04-08 | 2021-05-07 | 常州微亿智造科技有限公司 | Defect detection method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0682390A (en) * | 1992-06-26 | 1994-03-22 | Kawasaki Steel Corp | Method and apparatus for inspecting surface defect |
| JPH06288933A (en) * | 1993-03-31 | 1994-10-18 | Kawashima Textile Manuf Ltd | Method and device for detecting surface flaw of sheet or the like |
| CN101063662A (en) * | 2007-05-15 | 2007-10-31 | 广州市万世德包装机械有限公司 | Method for detecting empty bottle bottom defect and device for detecting empty bottle bottom defect based on DSP |
| CN103035185A (en) * | 2011-09-30 | 2013-04-10 | 伊姆普斯封闭式股份有限公司 | Method for brightness correction of defective pixels of digital monochrome image |
| CN105823763A (en) * | 2015-01-07 | 2016-08-03 | 宝山钢铁股份有限公司 | Method for measuring fluorescence intensity used for automatic magnetic powder inspection and apparatus thereof |
| CN106846300A (en) * | 2016-12-28 | 2017-06-13 | 诺仪器（中国）有限公司 | A kind of method for determining optical fiber splicer electrode bar position in the picture |
| CN107462580A (en) * | 2016-06-02 | 2017-12-12 | 住友化学株式会社 | Defect inspecting system, film manufacturing device and defect detecting method |
-
2018
- 2018-08-20 CN CN201810949195.2A patent/CN109191439A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0682390A (en) * | 1992-06-26 | 1994-03-22 | Kawasaki Steel Corp | Method and apparatus for inspecting surface defect |
| JPH06288933A (en) * | 1993-03-31 | 1994-10-18 | Kawashima Textile Manuf Ltd | Method and device for detecting surface flaw of sheet or the like |
| CN101063662A (en) * | 2007-05-15 | 2007-10-31 | 广州市万世德包装机械有限公司 | Method for detecting empty bottle bottom defect and device for detecting empty bottle bottom defect based on DSP |
| CN103035185A (en) * | 2011-09-30 | 2013-04-10 | 伊姆普斯封闭式股份有限公司 | Method for brightness correction of defective pixels of digital monochrome image |
| CN105823763A (en) * | 2015-01-07 | 2016-08-03 | 宝山钢铁股份有限公司 | Method for measuring fluorescence intensity used for automatic magnetic powder inspection and apparatus thereof |
| CN107462580A (en) * | 2016-06-02 | 2017-12-12 | 住友化学株式会社 | Defect inspecting system, film manufacturing device and defect detecting method |
| CN106846300A (en) * | 2016-12-28 | 2017-06-13 | 诺仪器（中国）有限公司 | A kind of method for determining optical fiber splicer electrode bar position in the picture |
Non-Patent Citations (3)
| Title |
|---|
| GUANGZHONG CAO等: "Large-Complex-Surface Defect Detection byHybrid Gradient Threshold Segmentationand Image Registration", 《IEEEACCESS》 * |
| 张鼎等: "大型集装箱船高强度钢甲板裂纹缺陷的安全寿命评估", 《船舶力学》 * |
| 李武斌: "热轧圆钢表面缺陷视觉在线检测算法研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112669321A (en) * | 2021-03-22 | 2021-04-16 | 常州微亿智造科技有限公司 | Sand blasting unevenness detection method based on feature extraction and algorithm classification |
| CN112669321B (en) * | 2021-03-22 | 2021-08-03 | 常州微亿智造科技有限公司 | Sand blasting unevenness detection method based on feature extraction and algorithm classification |
| CN112767400A (en) * | 2021-04-08 | 2021-05-07 | 常州微亿智造科技有限公司 | Defect detection method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108460757B (en) | Mobile phone TFT-LCD screen Mura defect online automatic detection method | |
| CN108230324B (en) | Visual detection method for microdefect on surface of magnetic shoe | |
| CN105139386B (en) | A kind of image processing method of fast automatic detecting electric connector solder joint defective work | |
| CN101995223B (en) | Chip appearance detection method and system | |
| CN103439338B (en) | Film defects sorting technique | |
| WO2020110667A1 (en) | Surface defect detecting method, surface defect detecting device, method for manufacturing steel material, steel material quality control method, steel material manufacturing equipment, method for creating surface defect determination model, and surface defect determination model | |
| CN107490582B (en) | Assembly line workpiece detection system | |
| CN104118609B (en) | Labeling quality determining method and device | |
| CN107290347B (en) | Automatic honeycomb carrier defect detection method | |
| KR101477665B1 (en) | Defect detection method in heterogeneously textured surface | |
| CN115020267A (en) | Semiconductor surface defect detection method | |
| CN110288584A (en) | Ceramic hot-dip aluminizing detection method of surface flaw and device based on machine vision | |
| CN110070523B (en) | Foreign matter detection method for bottle bottom | |
| WO2017071406A1 (en) | Method and system for detecting pin of gold needle element | |
| JP2011013007A (en) | Magnetic particle flaw inspection apparatus | |
| CN105205803A (en) | Display panel defect detection method | |
| CN109191439A (en) | A kind of target workpiece surface knife mark defect inspection method | |
| Lin et al. | Surface defect detection of machined parts based on machining texture direction | |
| CN113155839A (en) | Steel plate outer surface defect online detection method based on machine vision | |
| CN110648330A (en) | Defect detection method for camera glass | |
| CN108805854B (en) | Method for rapidly counting tablets and detecting completeness of tablets in complex environment | |
| CN113916893A (en) | Method for detecting die-cutting product defects | |
| CN109785290A (en) | Normalized steel plate defect detection method is shone based on local light | |
| CN108280825A (en) | A kind of liquid crystal display emargintion detection method | |
| CN107833222B (en) | Nonmetal part surplus detection device and method |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190111 |