CN108414614A - Fluorescentmagnetic particle(powder) automatic flaw detection sense colors image pre-processing method - Google Patents
Fluorescentmagnetic particle(powder) automatic flaw detection sense colors image pre-processing method Download PDFInfo
- Publication number
- CN108414614A CN108414614A CN201810037248.3A CN201810037248A CN108414614A CN 108414614 A CN108414614 A CN 108414614A CN 201810037248 A CN201810037248 A CN 201810037248A CN 108414614 A CN108414614 A CN 108414614A
- Authority
- CN
- China
- Prior art keywords
- image
- flaw detection
- powder
- processing method
- extracted
- 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
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
- G01N27/72—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables
- G01N27/82—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws
- G01N27/83—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws by investigating stray magnetic fields
- G01N27/84—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws by investigating stray magnetic fields by applying magnetic powder or magnetic ink
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Chemical & Material Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Investigating Or Analyzing Materials By The Use Of Magnetic Means (AREA)
Abstract
A kind of fluorescentmagnetic particle(powder) automatic flaw detection sense colors image pre-processing method provided by the invention, includes the following steps:Step 1, original color image is extracted from colorful CCD camera;Step 2, original color image is converted into oscillogram;Step 3, target fluorescent color value is converted into target pixel value;Step 4, image is extracted.Compared with prior art, beneficial effects of the present invention are as follows:Denoising, segmentation preferably are carried out to the image collected, effectively inhibit the interference such as poly- magnetic, external illumination, shade, to achieve the purpose that simplified recognizer and processing time.
Description
Technical field
The present invention relates to carry out automatic flaw detection using fluorescentmagnetic particle(powder) mode to workpiece surface or near surface based on machine vision
Detection.
Background technology
The non-destructive testing of traditional military product usually carries out the differentiation of product defects by manually.And aerial blade, routine
Batch production product component such as firearms, bearing roller detection, it is often necessary to several inspectors complete thousands of parts daily
Detection, inevitably will appear missing inspection, erroneous judgement problem caused by inspector's asthenopia in actually detected.Moreover, non-destructive testing
Technology forward direction Nondestructive Evaluation direction is developed, and automation and intelligence are trends of the times.Product defects image automatic identification technology is
The key point of intelligent non-destructive detecting device certainly will be used widely in non-destructive testing industry.
Invention content
For the defects in the prior art, the object of the present invention is to provide a kind of fluorescentmagnetic particle(powder) based on machine vision is automatic
The fluorescentmagnetic particle(powder) automatic flaw detection sense colors image pre-processing method of carrying out flaw detection system.
In order to solve the above technical problems, a kind of fluorescentmagnetic particle(powder) automatic flaw detection sense colors image preprocessing provided by the invention
Method includes the following steps:
Step 1, original color image is extracted from colorful CCD camera;
Step 2, original color image is converted into oscillogram;
Step 3, target fluorescent color value is converted into target pixel value;
Step 4, image is extracted.
Preferably, step 2 includes:
Step 2.1, coloured image G picture element matrixs are extracted;
Step 2.2, it obtains G pixel distributions histogram and histogram is converted into oscillogram.
Preferably, step 3 includes:
Step 3.1, the spectrum calibration Region growing reflected under ultraviolet light according to fluorescence magnetic flaw detection ink;
Step 3.2, according to RGB color value table spotting pixel value.
Preferably, step 4 includes:
Step 4.1, the valley value of target pixel value both sides in oscillogram is obtained;
Step 4.2, area image is extracted;Wherein the upper limit of area image and lower limit are the valley value of oscillogram.
Compared with prior art, beneficial effects of the present invention are as follows:Denoising preferably is carried out to the image collected, is divided
It cuts, effectively inhibits the interference such as poly- magnetic, external illumination, shade, to achieve the purpose that simplified recognizer and processing time.
Description of the drawings
Upon reading the detailed description of non-limiting embodiments with reference to the following drawings, other feature mesh of the invention
And advantage will become more apparent upon.
Fig. 1 is fluorescentmagnetic particle(powder) automatic flaw detection sense colors image pre-processing method flow chart of the present invention.
Specific implementation mode
With reference to specific embodiment, the present invention is described in detail.Following embodiment will be helpful to the technology of this field
Personnel further understand the present invention, but the invention is not limited in any way.It should be pointed out that the ordinary skill of this field
For personnel, without departing from the inventive concept of the premise, several changes and improvements can also be made.These belong to the present invention
Protection domain.
The present invention is directed to the coloured image extracted in fluorescentmagnetic particle(powder) automatic flaw detection detection process and carries out a kind of pretreated side
Method, for this method according to coloured image rgb pixel characteristic distributions, the coloured image acquired to colored CDD cameras extracts target picture
Plain area image, this method preferably carry out denoising, segmentation to the image collected, effectively inhibit poly- magnetic, external illumination, the moon
The interference such as shadow, to achieve the purpose that simplified recognizer and processing time.
Specifically, as shown in Figure 1, being located in advance according to a kind of fluorescentmagnetic particle(powder) automatic flaw detection sense colors image provided by the invention
Reason method carries out tri- color of R, G, B for the collected original image of colorful CCD camera and decomposes, extracts coloured image G pixel squares
Battle array, histogram is made by the quantity of each pixel contained by G picture element matrixs, according to the gray value of iridescent spectra length conversion in histogram
Spotting iridescent pixel in figure, and extract object pixel in G picture element matrixs and constitute image.Include the following steps:
Step 1, colorful CCD camera extract original image;
Step 2 extracts coloured image G picture element matrixs;
Step 3 draws G pixel distributions histogram and is converted into oscillogram;
Target fluorescent color value is converted into target pixel value by step 4;
Step 5 finds both sides valley value in the oscillogram of object pixel place;
Step 6 extracts area image by bound of valley value.
In the real work of automatic flaw detection detection, the collected ccd image of institute will appear poly- magnetic, shade, illumination interference
Equal noises, this judges that there are larger interferences to the intelligent measurement of defect.So directly sharp in the presence of these interference
Denoising, region segmentation, feature extraction are carried out with gray level image then can miss that Interference Detection is made defect and is judged by accident, influence to examine
Survey efficiency and accuracy.To solve this problem, the color spectrum feature detected according to fluorescentmagnetic particle(powder), with RGB color value, to original
Image first carries out effective image extraction, that is, extracts yellowish green color image in original image, then carry out subsequent processing.
By RGB color value table, the color that the workpiece, defect that is detected by fluorescentmagnetic particle(powder) is reflected, in RGB color value, R,
B values are smaller, and G values are larger, and when extracting image, the threshold values determination of R, G, B need to be determined according to specific characterization processes environment.To original
Figure carries out color value extraction by R, G, B area threshold values respectively, hence it is evident that finds, by being carried out to the collected original image of machine camera
The extraction of RGB color value target area image can effectively inhibit the interference such as poly- magnetic, external illumination, shade.
Specific embodiments of the present invention are described above.It is to be appreciated that the invention is not limited in above-mentioned
Particular implementation, those skilled in the art can make a variety of changes or change within the scope of the claims, this not shadow
Ring the substantive content of the present invention.In the absence of conflict, the feature in embodiments herein and embodiment can arbitrary phase
Mutually combination.
Claims (4)
1. a kind of fluorescentmagnetic particle(powder) automatic flaw detection sense colors image pre-processing method, which is characterized in that include the following steps:
Step 1, original color image is extracted from colorful CCD camera;
Step 2, original color image is converted into oscillogram;
Step 3, target fluorescent color value is converted into target pixel value;
Step 4, image is extracted.
2. fluorescentmagnetic particle(powder) automatic flaw detection sense colors image pre-processing method according to claim 1, which is characterized in that step
Rapid 2 include:
Step 2.1, coloured image G picture element matrixs are extracted;
Step 2.2, it obtains the distribution histogram of G picture element matrixs and histogram is converted into oscillogram.
3. fluorescentmagnetic particle(powder) automatic flaw detection sense colors image pre-processing method according to claim 2, which is characterized in that step
Rapid 3 include:
Step 3.1, the spectrum calibration Region growing reflected under ultraviolet light according to fluorescence magnetic flaw detection ink;
Step 3.2, according to RGB color value table spotting pixel value.
4. fluorescentmagnetic particle(powder) automatic flaw detection sense colors image pre-processing method according to claim 3, which is characterized in that step
Rapid 4 include:
Step 4.1, the valley value of target pixel value both sides in oscillogram is obtained;
Step 4.2, area image is extracted;Wherein the upper limit of area image and lower limit are the valley value of oscillogram.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810037248.3A CN108414614A (en) | 2018-01-15 | 2018-01-15 | Fluorescentmagnetic particle(powder) automatic flaw detection sense colors image pre-processing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810037248.3A CN108414614A (en) | 2018-01-15 | 2018-01-15 | Fluorescentmagnetic particle(powder) automatic flaw detection sense colors image pre-processing method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108414614A true CN108414614A (en) | 2018-08-17 |
Family
ID=63125705
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810037248.3A Pending CN108414614A (en) | 2018-01-15 | 2018-01-15 | Fluorescentmagnetic particle(powder) automatic flaw detection sense colors image pre-processing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108414614A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4433289A (en) * | 1981-01-15 | 1984-02-21 | Magnaflux Corporation | Method for inspecting steel billets with a dry mixture of magnetic particles and a water soluble carrier solid |
CN102024029A (en) * | 2010-11-30 | 2011-04-20 | 辽宁师范大学 | Local visual attention-based color image retrieving method |
CN104134219A (en) * | 2014-08-12 | 2014-11-05 | 吉林大学 | Color image segmentation algorithm based on histograms |
CN105510429A (en) * | 2015-11-06 | 2016-04-20 | 苏州磁星检测设备有限公司 | Image-processing-based fluorescent magnetic powder flaw detection test method and test system |
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 |
-
2018
- 2018-01-15 CN CN201810037248.3A patent/CN108414614A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4433289A (en) * | 1981-01-15 | 1984-02-21 | Magnaflux Corporation | Method for inspecting steel billets with a dry mixture of magnetic particles and a water soluble carrier solid |
CN102024029A (en) * | 2010-11-30 | 2011-04-20 | 辽宁师范大学 | Local visual attention-based color image retrieving method |
CN104134219A (en) * | 2014-08-12 | 2014-11-05 | 吉林大学 | Color image segmentation algorithm based on histograms |
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 |
CN105510429A (en) * | 2015-11-06 | 2016-04-20 | 苏州磁星检测设备有限公司 | Image-processing-based fluorescent magnetic powder flaw detection test method and test system |
Non-Patent Citations (1)
Title |
---|
吴远峰 等: "基于机器视觉的智能检测方法研究", 《第十一届全国磁粉渗透检测技术年会论文集》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Omid et al. | An expert egg grading system based on machine vision and artificial intelligence techniques | |
CN109187553B (en) | On-line intelligent identification method for deteriorated eggs based on machine vision | |
CN105865329B (en) | The acquisition system and method for the bundled round steel end face center coordinate of view-based access control model | |
CN109900719B (en) | Visual detection method for blade surface knife lines | |
CN114913177B (en) | Automobile part defect detection method based on Hough circle | |
CN102521564A (en) | Method for identifying tea leaves based on colors and shapes | |
CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
CN110554052A (en) | artificial board surface defect detection method and system | |
CN113935666B (en) | Building decoration wall tile abnormity evaluation method based on image processing | |
CN106370668A (en) | Online visual inspection apparatus and method of internal quality of salted egg | |
CN110632092A (en) | Insulator surface contamination distribution characteristic detection method based on hyperspectral technology | |
CN101726492A (en) | On-line real-time detection device of hyperspectral food and operation method thereof | |
CN112067618A (en) | Product quality defect acquisition and analysis system based on imaging | |
Liu et al. | An automatic system for bearing surface tiny defect detection based on multi-angle illuminations | |
CN105510429B (en) | Fluorescent magnetic particle flaw detection detection method based on image procossing and detecting system | |
CN112102278A (en) | Metal workpiece machining surface defect detection method based on computer vision | |
CN109682821B (en) | Citrus surface defect detection method based on multi-scale Gaussian function | |
CN110186929A (en) | A kind of real-time product defect localization method | |
CN108414614A (en) | Fluorescentmagnetic particle(powder) automatic flaw detection sense colors image pre-processing method | |
CN115343313A (en) | Visual identification method based on artificial intelligence | |
CN109272480B (en) | Detection method for boundary of immiscible solution | |
CN210775265U (en) | Artificial board surface defect detection system | |
Cui et al. | Automated pattern recognition and defect inspection system | |
CN114742823A (en) | Intelligent detection method for scratches on surface of object | |
CN112697681B (en) | Method for detecting color fastness to light grade of furniture based on machine vision |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180817 |