CN111307820A - Method for detecting surface defects of ceramic valve core based on machine vision - Google Patents
Method for detecting surface defects of ceramic valve core based on machine vision Download PDFInfo
- Publication number
- CN111307820A CN111307820A CN202010210461.7A CN202010210461A CN111307820A CN 111307820 A CN111307820 A CN 111307820A CN 202010210461 A CN202010210461 A CN 202010210461A CN 111307820 A CN111307820 A CN 111307820A
- Authority
- CN
- China
- Prior art keywords
- image
- ceramic valve
- valve core
- detection
- surface defects
- 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
- 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
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8874—Taking dimensions of defect into account
-
- 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
Abstract
The invention relates to the technical field of detection of ceramic valve cores, and discloses a method for detecting surface defects of a ceramic valve core based on machine vision, which comprises the following steps: respectively weighing the ceramic valve cores with different specifications by using an automatic weighing and classifying system; classifying the ceramic valve cores which are seriously smaller than the standard quality and the ceramic valve cores which are seriously larger than the standard quality, eliminating the ceramic valve cores which are seriously unfilled, small spots, damaged and broken edges, and also eliminating the ceramic valve cores which are seriously incompletely polished; and shooting the ceramic valve core with the standard quality by utilizing the camera equipment, aligning the position of the obtained image, and obtaining an image with consistent pose. The method for detecting the surface defects of the ceramic valve core based on machine vision can solve the problem that the scale difference of different defects on the surface of the ceramic valve core brings influence to the sensitivity of a defect detection system, and reduces the difficulty of increasing the defect detection by the common phenomenon of uneven image gray in the vision processing process.
Description
Technical Field
The invention relates to the technical field of detection of ceramic valve cores, in particular to a method for detecting surface defects of a ceramic valve core based on machine vision.
Background
The ceramic valve core is a core part of the faucet and directly influences the sealing performance and the service life of the faucet. In the batch production process of the ceramic valve core, the surface of the valve core can generate defects such as cracks, small spots, unfilled corners, breakage, incomplete polishing, edge breakage and the like, and the product reject ratio can reach 20% under extreme conditions. The machine vision technology is used for replacing manual vision to detect the surface defects of the ceramic valve core, and the method has the advantages of no contact and damage, high speed, high stability and the like. However, the existing method for detecting the surface defects of the ceramic valve core is difficult to solve the problem that the scale difference of different defects on the surface of the ceramic valve core brings influence to the sensitivity of a defect detection system, and the difficulty of increasing the defect detection by the common phenomenon of uneven image gray scale in the visual processing process is reduced.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a method for detecting the surface defects of the ceramic valve core based on machine vision, which has the advantages of high detection accuracy, reduction of difficulty in defect detection caused by the phenomenon of uneven image gray level, which is common in the vision processing process, and the like, and solves the problem of influence on the sensitivity of a defect detection system caused by the scale difference of different defects on the surface of the ceramic valve core.
(II) technical scheme
In order to achieve the purpose of solving the influence of the scale difference of different defects on the surface of the ceramic valve core on the sensitivity of a defect detection system, the invention provides the following technical scheme: a method for detecting surface defects of a ceramic valve core based on machine vision comprises the following detection steps:
s1, weighing and detecting: respectively weighing the ceramic valve cores with different specifications by using an automatic weighing and classifying system;
s2, classification and screening: classifying the ceramic valve cores which are seriously smaller than the standard quality and the ceramic valve cores which are seriously larger than the standard quality, eliminating the ceramic valve cores which are seriously unfilled, small spots, damaged and broken edges, and also eliminating the ceramic valve cores which are seriously incompletely polished;
s3, image acquisition: shooting a ceramic valve core with standard quality by using camera equipment, aligning the position of the obtained image, and obtaining an image with consistent pose;
s4, image conversion: performing graying processing on an input color image to obtain a grayscale image, calculating grayscale characteristics of the operator image in the grayscale image, solving an optimal threshold value based on a proposed binarization threshold value optimization function, and binarizing the image based on the optimal threshold value;
s5, dividing the surface defects of the ceramic valve core: dividing the surface defects of the ceramic valve core into primary defects and secondary defects;
s6, image preprocessing: the method comprises the steps of using an experiment contrast common region-of-interest extraction method, using an obtained optimal threshold value and extracting a region-of-interest flow, aiming at image noise information, using an experiment contrast common filtering algorithm and taking a peak signal-to-noise ratio and a normalized mean square error as evaluation references;
s7, primary defect detection: extracting geometric shape features of the image by using a first-level defect classifier of a support vector machine, performing dimensionality reduction on the first-level defect image features by using the obtained gray features and adopting a principal component analysis method, optimizing classifier parameters by adopting a particle swarm algorithm, and establishing a first-level defect detection flow;
s8, secondary defect detection: establishing a secondary defect detection flow, determining a fitting function form, performing surface fitting on an image to be detected region by adopting a least square method, performing difference shadow processing on a fitting image and an original image, removing the phenomenon of uneven gray scale caused by illumination, polishing and the like in the image, comparing the extraction result of the ROI edge by a common edge detection algorithm, determining the intersection of the extraction result of the Kirsch edge with continuous edges and no noise points and a difference image to obtain a defect candidate region, selecting image characteristics, constructing a secondary defect classifier, and performing parameter optimization by combining PSO;
s9, mixed defect detection experiment: a two-stage classifier is respectively adopted for carrying out a defect detection experiment on the two-stage defects, and the result shows that the detection accuracy rate meets the requirement; the illumination fluctuation which may occur in the online detection process is simulated, the detection effect of the two-stage classifier is verified by adopting three kinds of intensity illumination, and the result shows that the detection accuracy of the two-stage classifier is stable; and simulating random distribution of defect images during online detection, and performing a primary and secondary mixed defect detection experiment.
Preferably, the automatic weighing and sorting system in the step S1 mainly comprises a conveyor belt, a weighing sensor, a weighing device and a rejecting device.
Preferably, the image pickup device in step S3 is a CCD industrial camera that can obtain a high-quality and high-resolution image.
Preferably, in step S6, the median filter is determined to be M — 3 according to a filter algorithm.
(III) advantageous effects
Compared with the prior art, the invention provides a quantitative cement and material feeding device capable of automatically adding water, which has the following beneficial effects:
according to the method for detecting the surface defects of the ceramic valve core based on the machine vision, the characteristics and the difficulty of visual detection of the surface defects of the ceramic valve core are analyzed by summarizing the current development situation of the ceramic product surface defect detection technology, a research method for dividing the surface defects of the ceramic valve core into primary defects and secondary defects is introduced, a detection system and a graded detection scheme are designed, primary and secondary mixed defect detection experiments are carried out, and the result shows that the detection speed and the accuracy meet the system requirements and the feasibility and the effectiveness of the visual detection method for the surface defects of the ceramic valve core are verified. The designed method is applied to the online detection of a production line, and the result shows that the detection accuracy and speed of the ceramic valve core with the model diameter of 35mm meet the expected requirements, so that the method has practical value and popularization significance.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
A method for detecting surface defects of a ceramic valve core based on machine vision comprises the following detection steps:
s1, weighing and detecting: respectively weighing the ceramic valve cores with different specifications by using an automatic weighing and classifying system;
s2, classification and screening: classifying the ceramic valve cores which are seriously smaller than the standard quality and the ceramic valve cores which are seriously larger than the standard quality, eliminating the ceramic valve cores which are seriously unfilled, small spots, damaged and broken edges, and also eliminating the ceramic valve cores which are seriously incompletely polished;
s3, image acquisition: shooting a ceramic valve core with standard quality by using camera equipment, aligning the position of the obtained image, and obtaining an image with consistent pose;
s4, image conversion: performing graying processing on an input color image to obtain a grayscale image, calculating grayscale characteristics of the operator image in the grayscale image, solving an optimal threshold value based on a proposed binarization threshold value optimization function, and binarizing the image based on the optimal threshold value;
s5, dividing the surface defects of the ceramic valve core: dividing the surface defects of the ceramic valve core into primary defects and secondary defects;
s6, image preprocessing: the method comprises the steps of using an experiment contrast common region-of-interest extraction method, using an obtained optimal threshold value and extracting a region-of-interest flow, aiming at image noise information, using an experiment contrast common filtering algorithm and taking a peak signal-to-noise ratio and a normalized mean square error as evaluation references;
s7, primary defect detection: extracting geometric shape features of the image by using a first-level defect classifier of a support vector machine, performing dimensionality reduction on the first-level defect image features by using the obtained gray features and adopting a principal component analysis method, optimizing classifier parameters by adopting a particle swarm algorithm, and establishing a first-level defect detection flow;
s8, secondary defect detection: establishing a secondary defect detection flow, determining a fitting function form, performing surface fitting on an image to be detected region by adopting a least square method, performing difference shadow processing on a fitting image and an original image, removing the phenomenon of uneven gray scale caused by illumination, polishing and the like in the image, comparing the extraction result of the ROI edge by a common edge detection algorithm, determining the intersection of the extraction result of the Kirsch edge with continuous edges and no noise points and a difference image to obtain a defect candidate region, selecting image characteristics, constructing a secondary defect classifier, and performing parameter optimization by combining PSO;
s9, mixed defect detection experiment: a two-stage classifier is respectively adopted for carrying out a defect detection experiment on the two-stage defects, and the result shows that the detection accuracy rate meets the requirement; the illumination fluctuation which may occur in the online detection process is simulated, the detection effect of the two-stage classifier is verified by adopting three kinds of intensity illumination, and the result shows that the detection accuracy of the two-stage classifier is stable; and simulating random distribution of defect images during online detection, and performing a primary and secondary mixed defect detection experiment.
Automatic weighing classification system mainly includes conveyer belt, weighing sensor, weighing device and removing devices in the S1 step, utilizes industrial robot can be automatic with the ceramic case on the conveyer belt snatch weighing device, realize automatic weighing.
The camera device in the step S3 is a CCD industrial camera which can obtain high-quality and high-resolution images, and can also be installed on a production line to realize rapid camera shooting of the ceramic valve core.
In the step S6, the median filter is determined to be M-3 according to a filter algorithm.
In conclusion, according to the machine vision-based ceramic valve core surface defect detection method, by summarizing the development current situation of the ceramic product surface defect detection technology, the characteristics and the difficulty of visual detection of the ceramic valve core surface defects are analyzed, a research method for dividing the ceramic valve core surface defects into primary defects and secondary defects is introduced, a detection system and a graded detection scheme are designed, a primary defect detection experiment and a secondary defect detection experiment are carried out, and the result shows that the detection speed and the accuracy meet the system requirements, and the feasibility and the effectiveness of the visual detection method of the ceramic valve core surface defects are verified. The designed method is applied to the online detection of a production line, and the result shows that the detection accuracy and speed of the ceramic valve core with the model diameter of 35mm meet the expected requirements, so that the method has practical value and popularization significance.
It is to be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (4)
1. A method for detecting surface defects of a ceramic valve core based on machine vision is characterized by comprising the following steps: the method comprises the following detection steps:
s1, weighing and detecting: respectively weighing the ceramic valve cores with different specifications by using an automatic weighing and classifying system;
s2, classification and screening: classifying the ceramic valve cores which are seriously smaller than the standard quality and the ceramic valve cores which are seriously larger than the standard quality, eliminating the ceramic valve cores which are seriously unfilled, small spots, damaged and broken edges, and also eliminating the ceramic valve cores which are seriously incompletely polished;
s3, image acquisition: shooting a ceramic valve core with standard quality by using camera equipment, aligning the position of the obtained image, and obtaining an image with consistent pose;
s4, image conversion: performing graying processing on an input color image to obtain a grayscale image, calculating grayscale characteristics of the operator image in the grayscale image, solving an optimal threshold value based on a proposed binarization threshold value optimization function, and binarizing the image based on the optimal threshold value;
s5, dividing the surface defects of the ceramic valve core: dividing the surface defects of the ceramic valve core into primary defects and secondary defects;
s6, image preprocessing: the method comprises the steps of using an experiment contrast common region-of-interest extraction method, using an obtained optimal threshold value and extracting a region-of-interest flow, aiming at image noise information, using an experiment contrast common filtering algorithm and taking a peak signal-to-noise ratio and a normalized mean square error as evaluation references;
s7, primary defect detection: extracting geometric shape features of the image by using a first-level defect classifier of a support vector machine, performing dimensionality reduction on the first-level defect image features by using the obtained gray features and adopting a principal component analysis method, optimizing classifier parameters by adopting a particle swarm algorithm, and establishing a first-level defect detection flow;
s8, secondary defect detection: establishing a secondary defect detection flow, determining a fitting function form, performing surface fitting on an image to be detected region by adopting a least square method, performing difference shadow processing on a fitting image and an original image, removing the phenomenon of uneven gray scale caused by illumination, polishing and the like in the image, comparing the extraction result of the ROI edge by a common edge detection algorithm, determining the intersection of the extraction result of the Kirsch edge with continuous edges and no noise points and a difference image to obtain a defect candidate region, selecting image characteristics, constructing a secondary defect classifier, and performing parameter optimization by combining PSO;
s9, mixed defect detection experiment: a two-stage classifier is respectively adopted for carrying out a defect detection experiment on the two-stage defects, and the result shows that the detection accuracy rate meets the requirement; the illumination fluctuation which may occur in the online detection process is simulated, the detection effect of the two-stage classifier is verified by adopting three kinds of intensity illumination, and the result shows that the detection accuracy of the two-stage classifier is stable; and simulating random distribution of defect images during online detection, and performing a primary and secondary mixed defect detection experiment.
2. The method for detecting the surface defects of the ceramic valve core based on the machine vision is characterized in that: the automatic weighing and classifying system in the step S1 mainly comprises a conveyor belt, a weighing sensor, a weighing device and a removing device.
3. The method for detecting the surface defects of the ceramic valve core based on the machine vision is characterized in that: the image pickup device in the step S3 is a CCD industrial camera that can obtain a high-quality and high-resolution image.
4. The method for detecting the surface defects of the ceramic valve core based on the machine vision is characterized in that: in the step S6, the median filter is determined to be M-3 according to a filter algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010210461.7A CN111307820A (en) | 2020-03-24 | 2020-03-24 | Method for detecting surface defects of ceramic valve core based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010210461.7A CN111307820A (en) | 2020-03-24 | 2020-03-24 | Method for detecting surface defects of ceramic valve core based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111307820A true CN111307820A (en) | 2020-06-19 |
Family
ID=71145813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010210461.7A Pending CN111307820A (en) | 2020-03-24 | 2020-03-24 | Method for detecting surface defects of ceramic valve core based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111307820A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113252695A (en) * | 2021-06-16 | 2021-08-13 | 上海启迪睿视智能科技有限公司 | Plastic packaging film defect detection method and detection device based on image processing |
| CN117455915A (en) * | 2023-12-25 | 2024-01-26 | 陕西福坤顺科技有限公司 | Machine vision-based three-axis turntable defect detection method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102116610A (en) * | 2010-11-29 | 2011-07-06 | 科达斯特恩(常州)汽车塑件系统有限公司 | Automatic on-line detection method and device for size of automobile parts based on machine vision |
| CN105548208A (en) * | 2016-02-05 | 2016-05-04 | 湖北工业大学 | Method for detecting surface defects of ceramic valve cores based on machine vision |
| CN105728339A (en) * | 2016-02-05 | 2016-07-06 | 湖北工业大学 | Visual automatic detecting system for ceramic cartridge |
| CN110288584A (en) * | 2019-06-27 | 2019-09-27 | 常州固高智能装备技术研究院有限公司 | Ceramic hot-dip aluminizing detection method of surface flaw and device based on machine vision |
-
2020
- 2020-03-24 CN CN202010210461.7A patent/CN111307820A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102116610A (en) * | 2010-11-29 | 2011-07-06 | 科达斯特恩(常州)汽车塑件系统有限公司 | Automatic on-line detection method and device for size of automobile parts based on machine vision |
| CN105548208A (en) * | 2016-02-05 | 2016-05-04 | 湖北工业大学 | Method for detecting surface defects of ceramic valve cores based on machine vision |
| CN105728339A (en) * | 2016-02-05 | 2016-07-06 | 湖北工业大学 | Visual automatic detecting system for ceramic cartridge |
| CN110288584A (en) * | 2019-06-27 | 2019-09-27 | 常州固高智能装备技术研究院有限公司 | Ceramic hot-dip aluminizing detection method of surface flaw and device based on machine vision |
Non-Patent Citations (2)
| Title |
|---|
| 何小凡: "陶瓷阀芯表面缺陷视觉检测方法的研究", 《中国硕博士学位论文全文数据库（硕士）信息科技辑》, pages 1 - 70 * |
| 汤亮;张董洁;龚发云;汪威;胡新宇;: "基于区域分级的陶瓷阀芯表面缺陷检测系统研究与实现", 组合机床与自动化加工技术, no. 10, pages 82 - 90 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113252695A (en) * | 2021-06-16 | 2021-08-13 | 上海启迪睿视智能科技有限公司 | Plastic packaging film defect detection method and detection device based on image processing |
| CN113252695B (en) * | 2021-06-16 | 2021-09-28 | 上海启迪睿视智能科技有限公司 | Plastic packaging film defect detection method and detection device based on image processing |
| CN117455915A (en) * | 2023-12-25 | 2024-01-26 | 陕西福坤顺科技有限公司 | Machine vision-based three-axis turntable defect detection method |
| CN117455915B (en) * | 2023-12-25 | 2024-03-08 | 陕西福坤顺科技有限公司 | Machine vision-based three-axis turntable defect detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109141232B (en) | Online detection method for disc castings based on machine vision | |
| CN109255787B (en) | System and method for detecting scratch of silk ingot based on deep learning and image processing technology | |
| CN109454006B (en) | Detection and classification method based on device for online detection and classification of chemical fiber spindle tripping defects | |
| CN109115785B (en) | Casting polishing quality detection method and device and use method thereof | |
| CN108389179B (en) | Machine vision-based can cover surface defect detection method | |
| CN108230324B (en) | Visual detection method for microdefect on surface of magnetic shoe | |
| JP7055223B2 (en) | Mask defect inspection method | |
| CN105388162A (en) | Raw material silicon wafer surface scratch detection method based on machine vision | |
| CN108760747A (en) | A kind of 3D printing model surface defect visible detection method | |
| CN107610085A (en) | A kind of welding point defect detecting system based on computer vision | |
| CN106780526A (en) | A kind of ferrite wafer alligatoring recognition methods | |
| CN111307820A (en) | Method for detecting surface defects of ceramic valve core based on machine vision | |
| CN108257171A (en) | Car radar assembling aperture detection method based on light vision | |
| CN109461156B (en) | Threaded sealing plug assembly detection method based on vision | |
| CN110108712A (en) | Multifunctional visual sense defect detecting system | |
| CN102901735B (en) | System for carrying out automatic detections upon workpiece defect, cracking, and deformation by using computer | |
| CN111398287A (en) | Battery pole piece scratch detection system and detection method | |
| CN108889635B (en) | Online visual inspection method for manufacturing defects of ring-pull cans | |
| CN110610516A (en) | Railway fastener nut center positioning method | |
| CN113077437A (en) | Workpiece quality detection method and system | |
| Liu et al. | An automatic system for bearing surface tiny defect detection based on multi-angle illuminations | |
| Feng et al. | Image processing of the grinding wheel surface | |
| CN109701890A (en) | Magnetic tile surface defect detection and method for sorting | |
| CN107024416A (en) | With reference to similitude and the quasi-circular particle mean size detection method of discontinuity | |
| KR101562988B1 (en) | Apparatus and method for detecting surface defects of hot billet |
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 |