CN111141758A - Method for detecting surface defects of inner cylinder - Google Patents
Method for detecting surface defects of inner cylinder Download PDFInfo
- Publication number
- CN111141758A CN111141758A CN201911377243.6A CN201911377243A CN111141758A CN 111141758 A CN111141758 A CN 111141758A CN 201911377243 A CN201911377243 A CN 201911377243A CN 111141758 A CN111141758 A CN 111141758A
- Authority
- CN
- China
- Prior art keywords
- improved
- detected
- inner cylindrical
- cylindrical surface
- industrial camera
- 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
Images
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
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/954—Inspecting the inner surface of hollow bodies, e.g. bores
-
- 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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- 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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
- G01N2021/0106—General arrangement of respective parts
- G01N2021/0112—Apparatus in one mechanical, optical or electronic block
-
- 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
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/954—Inspecting the inner surface of hollow bodies, e.g. bores
- G01N2021/9548—Scanning the interior of a cylinder
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention provides a method for detecting surface defects of an inner cylinder, which comprises the following steps: the improved type industrial camera detection device comprises a traditional rotary table and an improved conveyor belt, wherein a traditional type inner cylindrical surface to be detected is clamped at the center of the top of the traditional rotary table, a traditional type single industrial camera is bolted at the right side of the top of the traditional type inner cylindrical surface to be detected, an improved type inner cylindrical surface to be detected is sequentially clamped at the top of the improved conveyor belt from left to right, and a plurality of improved type industrial cameras are sequentially bolted at the top of the improved type inner cylindrical surface to be detected from left to right. According to the invention, through the structural cooperation of the improved conveyor belt, the improved to-be-detected inner cylindrical surface and the improved industrial camera, the accuracy and the integrity of the acquisition surface of the improved to-be-detected inner cylindrical surface are improved, the mechanical structure and the detection flow are greatly simplified, a clamping device and a rotary table which are necessary in the traditional scheme are not needed, and a plurality of stations are not needed; the speed of detection is improved, and the work piece only needs to pass through the conveyer belt conveying and can accomplish the detection.
Description
Technical Field
The invention relates to the field of part detection, in particular to a method for detecting surface defects of an inner cylinder.
Background
The defect detection generally refers to the detection of the surface defects of the article, and the surface defect detection refers to the detection of the defects such as spots, pits, scratches, color differences, defects and the like on the surface of a workpiece by adopting an advanced machine vision detection technology.
When a user detects the defects of the inner surfaces of parts such as a bearing ring, the traditional method usually needs to use a clamping device to place the parts on a rotary table, the rotary table rotates for a circle, a camera positioned above the rotary table obliquely collects image data of the inner surfaces, the camera collects the image data once when the rotary table rotates for each angle, the detection of one part needs to be collected for multiple times, so a series of mechanical structures are required to be added, for example, the rotary table and the clamping device need to be arranged with an independent station, meanwhile, the flow is more complicated, the detection method is complicated, and the detection rate of the defects of the parts is reduced.
Therefore, it is necessary to provide a method for detecting defects on the surface of the inner cylinder to solve the above problems.
Disclosure of Invention
The invention provides a method for detecting the surface defects of an inner cylinder, which solves the problems that the existing detection method is complicated in flow and low in part defect detection rate in the using process.
In order to solve the above technical problem, the present invention provides a method for detecting defects on the surface of an inner cylinder, comprising: the improved industrial camera detection device comprises a traditional turntable and an improved conveyor belt, wherein a traditional inner cylindrical surface to be detected is clamped at the center of the top of the traditional turntable, a traditional single industrial camera is bolted to the right side of the top of the traditional inner cylindrical surface to be detected, an improved inner cylindrical surface to be detected is sequentially clamped at the top of the improved conveyor belt from left to right, and a plurality of improved industrial cameras are sequentially bolted to the top of the improved inner cylindrical surface to be detected from left to right;
the operation steps are as follows:
A. the improved to-be-detected inner cylindrical surface is orderly and slowly transmitted on the improved conveyor belt, then the improved industrial camera carries out image acquisition on the corresponding improved to-be-detected inner cylindrical surface, and then the region of interest is extracted;
B. after the extraction of the region of interest is completed, accurately positioning the improved inner cylindrical surface to be detected by adopting a local threshold method;
C. extracting an improved image of the inner cylindrical surface to be detected for subsequent analysis, screening the image obtained by subtracting the mean value from the original image by using gray value characteristics according to the property of the defect to obtain a difference image, and then carrying out binarization on the difference image to segment a defect area;
D. after the defect segmentation is finished, identifying and classifying the defects according to the properties of different defects;
E. and processing and analyzing the acquired image of the single improved industrial camera, and unifying a plurality of processing results to obtain a defect result of the inner surface of the single improved inner cylindrical surface to be detected.
Preferably, the number of the improved industrial cameras is at least three, and the improved industrial cameras are symmetrically distributed along the center of the improved conveyor belt.
Preferably, the improved industrial camera acquires image data for a single time, and the area of the image shot by the improved industrial camera is more than one third of the inner surface of the inner cylindrical surface to be detected.
Preferably, the number of the modified inner cylindrical surfaces to be detected is divided into groups of three, and the modified inner cylindrical surfaces to be detected are located at the center of the top surface of the modified conveyor belt.
Preferably, the improved to-be-detected inner cylindrical surfaces are respectively and correspondingly located right below the improved industrial camera, and shot images of the improved to-be-detected inner cylindrical surfaces are distributed in a symmetrical state.
Compared with the related art, the method for detecting the surface defects of the inner cylinder has the following beneficial effects:
the invention provides a method for detecting surface defects of an inner cylinder,
1. according to the invention, through the structural cooperation of the improved conveyor belt, the improved to-be-detected inner cylindrical surface and the improved industrial camera, the accuracy and the integrity of the acquisition surface of the improved to-be-detected inner cylindrical surface are improved, the mechanical structure and the detection flow are greatly simplified, a clamping device and a rotary table which are necessary in the traditional scheme are not needed, and a plurality of stations are not needed; the detection speed is improved, and the workpiece can be detected only by being conveyed by the conveyor belt; the device has a plurality of detection functions, and if necessary, the same processing method can be used for simultaneously detecting the defects of the upper surface and the outer cylindrical surface;
2. the improved industrial camera is at least three and is symmetrically distributed along the center of the improved conveyor belt, the surface image of the improved inner cylindrical surface to be detected can be uniformly collected, the picture collection integrity of the improved industrial camera is improved, the area of the shot image of the improved industrial camera is larger than one third of the inner surface of the improved inner cylindrical surface to be detected, the picture collection area of the improved inner cylindrical surface to be detected is enlarged, the picture collection effect of the improved inner cylindrical surface to be detected is further enhanced, the improved industrial camera is divided into three groups and is positioned at the center of the top surface of the improved conveyor belt, the improved industrial camera is convenient to collect pictures of the improved inner cylindrical surface to be detected, the improved inner cylindrical surface to be detected is prevented from being mistakenly collected, the improved inner cylindrical surface to be detected is correspondingly positioned right below the improved industrial camera, and the shot images are paired The acquired pictures of the improved inner cylindrical surface to be detected can be symmetrically acquired by the aid of the state distribution, and the image acquisition definition of the improved inner cylindrical surface to be detected is further enhanced.
Drawings
FIG. 1 is a schematic diagram of a conventional structure of a method for detecting defects on the surface of an inner cylinder according to a preferred embodiment of the present invention;
FIG. 2 is a schematic structural view of a modification of the FIG. 1;
fig. 3 is a flowchart of the process shown in fig. 2.
Reference numbers in the figures: 1. a conventional type turntable; 2. the inner cylindrical surface to be detected is of a traditional type; 3. a conventional single industrial camera; 4. an improved conveyor belt; 5. an improved inner cylindrical surface to be detected; 6. an improved industrial camera.
Detailed Description
The invention is further described with reference to the following figures and embodiments.
Referring to fig. 1, fig. 2 and fig. 3 in combination, in which fig. 1 is a schematic diagram of a conventional structure of a preferred embodiment of a method for detecting defects on an inner cylindrical surface according to the present invention, fig. 2 is a schematic diagram of an improved structure shown in fig. 1, and fig. 3 is a flowchart of processing shown in fig. 2. A method of detecting defects on an inner cylindrical surface, comprising: the detection device comprises a traditional turntable 1 and an improved conveyor belt 4, wherein a traditional inner cylindrical surface 2 to be detected is clamped at the center of the top of the traditional turntable 1, a traditional single industrial camera 3 is bolted to the right side of the top of the traditional inner cylindrical surface 2 to be detected, an improved inner cylindrical surface 5 to be detected is sequentially clamped at the top of the improved conveyor belt 4 from left to right, and a plurality of improved industrial cameras 6 are sequentially bolted to the top of the improved inner cylindrical surface 5 to be detected from left to right;
the operation steps are as follows:
A. the improved to-be-detected inner cylindrical surface 5 is orderly and slowly transmitted on the improved conveyor belt 4, then the improved industrial camera 6 is used for carrying out image acquisition on the corresponding improved to-be-detected inner cylindrical surface 5, and then region-of-interest extraction is carried out, because the illumination angles of the improved industrial camera 6 at different positions are different, the gray level of the image shot by each surface of the improved to-be-detected inner cylindrical surface 5 is greatly different, and the region-of-interest can be extracted according to the change of the gray level;
B. after the extraction of the region of interest is completed, accurately positioning the improved inner cylindrical surface 5 to be detected by adopting a local threshold method;
C. extracting an image of the improved to-be-detected inner cylindrical surface 5 for subsequent analysis, screening the image obtained by subtracting the mean value from the original image by using gray value characteristics according to the property of the defect to obtain a difference image, and then binarizing the difference image to segment a defect region;
D. after the defect segmentation is finished, identifying and classifying the defects according to the properties of different defects;
E. the processing and analysis of the image acquired by the single improved industrial camera 6 are completed, and a plurality of processing results are unified at this time, so that the defect result of the inner surface of the single improved inner cylindrical surface 5 to be detected is obtained.
The first embodiment is as follows:
a method of detecting defects on an inner cylindrical surface, comprising: the detection device comprises a traditional turntable 1 and an improved conveyor belt 4, wherein a traditional inner cylindrical surface 2 to be detected is clamped at the center of the top of the traditional turntable 1, a traditional single industrial camera 3 is bolted to the right side of the top of the traditional inner cylindrical surface 2 to be detected, an improved inner cylindrical surface 5 to be detected is sequentially clamped at the top of the improved conveyor belt 4 from left to right, and a plurality of improved industrial cameras 6 are sequentially bolted to the top of the improved inner cylindrical surface 5 to be detected from left to right;
the operation steps are as follows:
A. the improved to-be-detected inner cylindrical surface 5 is orderly and slowly transmitted on the improved conveyor belt 4, then the improved industrial camera 6 is used for carrying out image acquisition on the corresponding improved to-be-detected inner cylindrical surface 5, and then region-of-interest extraction is carried out, because the illumination angles of the improved industrial camera 6 at different positions are different, the gray level of the image shot by each surface of the improved to-be-detected inner cylindrical surface 5 is greatly different, and the region-of-interest can be extracted according to the change of the gray level;
B. after the extraction of the region of interest is completed, accurately positioning the improved inner cylindrical surface 5 to be detected by adopting a local threshold method;
C. extracting an image of the improved to-be-detected inner cylindrical surface 5 for subsequent analysis, screening the image obtained by subtracting the mean value from the original image by using gray value characteristics according to the property of the defect to obtain a difference image, and then binarizing the difference image to segment a defect region;
D. after the defect segmentation is finished, identifying and classifying the defects according to the properties of different defects;
E. the processing and analysis of the image acquired by the single improved industrial camera 6 are completed, and a plurality of processing results are unified at this time, so that the defect result of the inner surface of the single improved inner cylindrical surface 5 to be detected is obtained.
Example two:
in example one, the following additional steps were added:
the number of the improved industrial cameras 6 is at least three, and the improved industrial cameras 6 are symmetrically distributed along the center of the improved conveyor belt 4.
A method of detecting defects on an inner cylindrical surface, comprising: the detection device comprises a traditional turntable 1 and an improved conveyor belt 4, wherein a traditional inner cylindrical surface 2 to be detected is clamped at the center of the top of the traditional turntable 1, a traditional single industrial camera 3 is bolted to the right side of the top of the traditional inner cylindrical surface 2 to be detected, an improved inner cylindrical surface 5 to be detected is sequentially clamped at the top of the improved conveyor belt 4 from left to right, and a plurality of improved industrial cameras 6 are sequentially bolted to the top of the improved inner cylindrical surface 5 to be detected from left to right;
the operation steps are as follows:
A. the improved to-be-detected inner cylindrical surface 5 is orderly and slowly transmitted on the improved conveyor belt 4, then the improved industrial camera 6 is used for carrying out image acquisition on the corresponding improved to-be-detected inner cylindrical surface 5, and then region-of-interest extraction is carried out, because the illumination angles of the improved industrial camera 6 at different positions are different, the gray level of the image shot by each surface of the improved to-be-detected inner cylindrical surface 5 is greatly different, and the region-of-interest can be extracted according to the change of the gray level;
B. after the extraction of the region of interest is completed, accurately positioning the improved inner cylindrical surface 5 to be detected by adopting a local threshold method;
C. extracting an image of the improved to-be-detected inner cylindrical surface 5 for subsequent analysis, screening the image obtained by subtracting the mean value from the original image by using gray value characteristics according to the property of the defect to obtain a difference image, and then binarizing the difference image to segment a defect region;
D. after the defect segmentation is finished, identifying and classifying the defects according to the properties of different defects;
E. the processing and analysis of the image acquired by the single improved industrial camera 6 are completed, and a plurality of processing results are unified at this time, so that the defect result of the inner surface of the single improved inner cylindrical surface 5 to be detected is obtained.
Example three:
the following additional steps were added in example two:
the image data collected by the improved industrial camera 6 is single time, and the area of the shot image of the improved industrial camera 6 is larger than one third of the inner surface of the improved to-be-detected inner cylindrical surface 5.
A method of detecting defects on an inner cylindrical surface, comprising: the detection device comprises a traditional turntable 1 and an improved conveyor belt 4, wherein a traditional inner cylindrical surface 2 to be detected is clamped at the center of the top of the traditional turntable 1, a traditional single industrial camera 3 is bolted to the right side of the top of the traditional inner cylindrical surface 2 to be detected, an improved inner cylindrical surface 5 to be detected is sequentially clamped at the top of the improved conveyor belt 4 from left to right, and a plurality of improved industrial cameras 6 are sequentially bolted to the top of the improved inner cylindrical surface 5 to be detected from left to right;
the operation steps are as follows:
A. the improved to-be-detected inner cylindrical surface 5 is orderly and slowly transmitted on the improved conveyor belt 4, then the improved industrial camera 6 is used for carrying out image acquisition on the corresponding improved to-be-detected inner cylindrical surface 5, and then region-of-interest extraction is carried out, because the illumination angles of the improved industrial camera 6 at different positions are different, the gray level of the image shot by each surface of the improved to-be-detected inner cylindrical surface 5 is greatly different, and the region-of-interest can be extracted according to the change of the gray level;
B. after the extraction of the region of interest is completed, accurately positioning the improved inner cylindrical surface 5 to be detected by adopting a local threshold method;
C. extracting an image of the improved to-be-detected inner cylindrical surface 5 for subsequent analysis, screening the image obtained by subtracting the mean value from the original image by using gray value characteristics according to the property of the defect to obtain a difference image, and then binarizing the difference image to segment a defect region;
D. after the defect segmentation is finished, identifying and classifying the defects according to the properties of different defects;
E. the processing and analysis of the image acquired by the single improved industrial camera 6 are completed, and a plurality of processing results are unified at this time, so that the defect result of the inner surface of the single improved inner cylindrical surface 5 to be detected is obtained.
Example four:
in example three, the following additional steps were added:
the number of the modified inner cylindrical surfaces 5 to be detected is divided into groups of three, and the modified inner cylindrical surfaces 5 to be detected are located at the center of the top surface of the modified conveyor belt 4.
A method of detecting defects on an inner cylindrical surface, comprising: the detection device comprises a traditional turntable 1 and an improved conveyor belt 4, wherein a traditional inner cylindrical surface 2 to be detected is clamped at the center of the top of the traditional turntable 1, a traditional single industrial camera 3 is bolted to the right side of the top of the traditional inner cylindrical surface 2 to be detected, an improved inner cylindrical surface 5 to be detected is sequentially clamped at the top of the improved conveyor belt 4 from left to right, and a plurality of improved industrial cameras 6 are sequentially bolted to the top of the improved inner cylindrical surface 5 to be detected from left to right;
the operation steps are as follows:
A. the improved to-be-detected inner cylindrical surface 5 is orderly and slowly transmitted on the improved conveyor belt 4, then the improved industrial camera 6 is used for carrying out image acquisition on the corresponding improved to-be-detected inner cylindrical surface 5, and then region-of-interest extraction is carried out, because the illumination angles of the improved industrial camera 6 at different positions are different, the gray level of the image shot by each surface of the improved to-be-detected inner cylindrical surface 5 is greatly different, and the region-of-interest can be extracted according to the change of the gray level;
B. after the extraction of the region of interest is completed, accurately positioning the improved inner cylindrical surface 5 to be detected by adopting a local threshold method;
C. extracting an image of the improved to-be-detected inner cylindrical surface 5 for subsequent analysis, screening the image obtained by subtracting the mean value from the original image by using gray value characteristics according to the property of the defect to obtain a difference image, and then binarizing the difference image to segment a defect region;
D. after the defect segmentation is finished, identifying and classifying the defects according to the properties of different defects;
E. the processing and analysis of the image acquired by the single improved industrial camera 6 are completed, and a plurality of processing results are unified at this time, so that the defect result of the inner surface of the single improved inner cylindrical surface 5 to be detected is obtained.
Example five:
in example four, the following additional steps were added:
the improved to-be-detected inner cylindrical surfaces 5 are respectively and correspondingly located right below the improved industrial camera 6, and shot images of the improved to-be-detected inner cylindrical surfaces 5 are distributed in a symmetrical state.
A method of detecting defects on an inner cylindrical surface, comprising: the detection device comprises a traditional turntable 1 and an improved conveyor belt 4, wherein a traditional inner cylindrical surface 2 to be detected is clamped at the center of the top of the traditional turntable 1, a traditional single industrial camera 3 is bolted to the right side of the top of the traditional inner cylindrical surface 2 to be detected, an improved inner cylindrical surface 5 to be detected is sequentially clamped at the top of the improved conveyor belt 4 from left to right, and a plurality of improved industrial cameras 6 are sequentially bolted to the top of the improved inner cylindrical surface 5 to be detected from left to right;
the operation steps are as follows:
A. the improved to-be-detected inner cylindrical surface 5 is orderly and slowly transmitted on the improved conveyor belt 4, then the improved industrial camera 6 is used for carrying out image acquisition on the corresponding improved to-be-detected inner cylindrical surface 5, and then region-of-interest extraction is carried out, because the illumination angles of the improved industrial camera 6 at different positions are different, the gray level of the image shot by each surface of the improved to-be-detected inner cylindrical surface 5 is greatly different, and the region-of-interest can be extracted according to the change of the gray level;
B. after the extraction of the region of interest is completed, accurately positioning the improved inner cylindrical surface 5 to be detected by adopting a local threshold method;
C. extracting an image of the improved to-be-detected inner cylindrical surface 5 for subsequent analysis, screening the image obtained by subtracting the mean value from the original image by using gray value characteristics according to the property of the defect to obtain a difference image, and then binarizing the difference image to segment a defect region;
D. after the defect segmentation is finished, identifying and classifying the defects according to the properties of different defects;
E. the processing and analysis of the image acquired by the single improved industrial camera 6 are completed, and a plurality of processing results are unified at this time, so that the defect result of the inner surface of the single improved inner cylindrical surface 5 to be detected is obtained.
Compared with the related art, the method for detecting the surface defects of the inner cylinder has the following beneficial effects:
according to the invention, through the structural matching of the improved conveyor belt 4, the improved to-be-detected inner cylindrical surface 5 and the improved industrial camera 6, the accuracy and the integrity of the acquisition surface of the improved to-be-detected inner cylindrical surface 5 are improved, the mechanical structure and the detection flow are greatly simplified, a clamping device and a rotary table which are necessary in the traditional scheme are not needed, and a plurality of stations are not needed; the detection speed is improved, and the workpiece can be detected only by being conveyed by the conveyor belt; the device has multiple detection functions, and if necessary, the same processing method can be used for simultaneously detecting the defects of the upper surface and the outer cylindrical surface.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (5)
1. A method for detecting defects on the surface of an inner cylinder, comprising: the improved type detection device comprises a traditional turntable (1) and an improved conveyor belt (4), wherein a traditional type to-be-detected inner cylindrical surface (2) is clamped at the center of the top of the traditional turntable (1), a traditional single industrial camera (3) is bolted to the right side of the top of the traditional type to-be-detected inner cylindrical surface (2), an improved type to-be-detected inner cylindrical surface (5) is sequentially clamped at the top of the improved conveyor belt (4) from left to right, and a plurality of improved type industrial cameras (6) are sequentially bolted at the top of the improved type to-be-detected inner cylindrical surface (5) from left to right;
the operation steps are as follows:
A. the improved to-be-detected inner cylindrical surface (5) is orderly and slowly transmitted on the improved conveyor belt (4), then the improved industrial camera (6) carries out image acquisition on the corresponding improved to-be-detected inner cylindrical surface (5), then the interesting region extraction is carried out, and due to different illumination angles of the light sources, the gray scales of the images of each surface of the improved to-be-detected inner cylindrical surface (5) shot by the improved industrial camera (6) at different positions are greatly different, and the interesting region can be extracted according to the change of the gray scales;
B. after the extraction of the region of interest is finished, accurately positioning the improved inner cylindrical surface (5) to be detected by adopting a local threshold method;
C. extracting an image of the improved to-be-detected inner cylindrical surface (5) for subsequent analysis, screening the image obtained by subtracting the mean value from the original image by using gray value characteristics according to the property of the defect to obtain a difference image, and then carrying out binarization on the difference image to segment a defect area;
D. after the defect segmentation is finished, identifying and classifying the defects according to the properties of different defects;
E. the processing and analysis of the image collected by the single improved industrial camera (6) are completed, and a plurality of processing results are unified at the moment to obtain a defect result of the inner surface of the single improved inner cylindrical surface (5) to be detected.
2. The method for detecting defects on the inner cylindrical surface according to claim 1, wherein the number of the improved industrial cameras (6) is at least three, and the improved industrial cameras (6) are symmetrically distributed along the center of the improved conveyor belt (4).
3. The method for detecting defects on the surface of an inner cylindrical surface according to claim 1, wherein the improved industrial camera (6) acquires image data for a single time, and the area of the image taken by the improved industrial camera (6) is more than one third of the area of the inner surface of the improved inner cylindrical surface (5) to be detected.
4. The method for detecting defects on the surface of an inner cylinder according to claim 1, characterized in that the number of said modified inner cylinders (5) to be detected is divided into groups of three, said modified inner cylinders (5) to be detected being located at the center of the top surface of the modified conveyor belt (4).
5. The method for detecting defects on the surface of an inner cylinder as defined in claim 1, wherein the improved inner cylinders (5) to be detected are respectively and correspondingly located right below the improved industrial camera (6), and the images of the improved inner cylinders (5) to be detected are distributed in a symmetrical state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911377243.6A CN111141758A (en) | 2019-12-27 | 2019-12-27 | Method for detecting surface defects of inner cylinder |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911377243.6A CN111141758A (en) | 2019-12-27 | 2019-12-27 | Method for detecting surface defects of inner cylinder |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111141758A true CN111141758A (en) | 2020-05-12 |
Family
ID=70521027
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911377243.6A Pending CN111141758A (en) | 2019-12-27 | 2019-12-27 | Method for detecting surface defects of inner cylinder |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111141758A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0842415A1 (en) * | 1995-08-04 | 1998-05-20 | Image Processing Systems, Inc. | Bottle thread inspection system and method of operating same |
| CN103810475A (en) * | 2014-02-19 | 2014-05-21 | 百度在线网络技术（北京）有限公司 | Target object recognition method and apparatus |
| CN104502356A (en) * | 2015-01-05 | 2015-04-08 | 江苏大学 | Automatic detection method for defects of inner surface of sliding bearing on basis of computer vision |
| CN104567677A (en) * | 2015-01-05 | 2015-04-29 | 江苏大学 | Multi-index high-speed dynamic detection and material dividing method and device of annular sliding bearing |
| CN204685514U (en) * | 2015-05-06 | 2015-10-07 | 周大鹏 | The video checkout gear of cylindrical product |
| CN106702870A (en) * | 2017-03-14 | 2017-05-24 | 深圳汇创联合自动化控制有限公司 | Road crack detecting system |
| CN108007368A (en) * | 2017-11-30 | 2018-05-08 | 江苏理工学院 | The device that a kind of bearing inner race is detected and classified |
| CN108596909A (en) * | 2018-05-09 | 2018-09-28 | 芜湖哈特机器人产业技术研究院有限公司 | Hollow cylinder Surface Flaw Detection system and method |
| CN109772724A (en) * | 2019-03-14 | 2019-05-21 | 溧阳市新力机械铸造有限公司 | A kind of flexible detection and analysis system of casting emphasis surface and internal flaw |
| CN109961455A (en) * | 2017-12-22 | 2019-07-02 | 杭州萤石软件有限公司 | Target detection method and device |
| CN110057836A (en) * | 2019-05-15 | 2019-07-26 | 浙江汉振智能技术有限公司 | A kind of cylinder type hollow pipe visual detection equipment and its detection method |
-
2019
- 2019-12-27 CN CN201911377243.6A patent/CN111141758A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0842415A1 (en) * | 1995-08-04 | 1998-05-20 | Image Processing Systems, Inc. | Bottle thread inspection system and method of operating same |
| CN103810475A (en) * | 2014-02-19 | 2014-05-21 | 百度在线网络技术（北京）有限公司 | Target object recognition method and apparatus |
| CN104502356A (en) * | 2015-01-05 | 2015-04-08 | 江苏大学 | Automatic detection method for defects of inner surface of sliding bearing on basis of computer vision |
| CN104567677A (en) * | 2015-01-05 | 2015-04-29 | 江苏大学 | Multi-index high-speed dynamic detection and material dividing method and device of annular sliding bearing |
| CN204685514U (en) * | 2015-05-06 | 2015-10-07 | 周大鹏 | The video checkout gear of cylindrical product |
| CN106702870A (en) * | 2017-03-14 | 2017-05-24 | 深圳汇创联合自动化控制有限公司 | Road crack detecting system |
| CN108007368A (en) * | 2017-11-30 | 2018-05-08 | 江苏理工学院 | The device that a kind of bearing inner race is detected and classified |
| CN109961455A (en) * | 2017-12-22 | 2019-07-02 | 杭州萤石软件有限公司 | Target detection method and device |
| CN108596909A (en) * | 2018-05-09 | 2018-09-28 | 芜湖哈特机器人产业技术研究院有限公司 | Hollow cylinder Surface Flaw Detection system and method |
| CN109772724A (en) * | 2019-03-14 | 2019-05-21 | 溧阳市新力机械铸造有限公司 | A kind of flexible detection and analysis system of casting emphasis surface and internal flaw |
| CN110057836A (en) * | 2019-05-15 | 2019-07-26 | 浙江汉振智能技术有限公司 | A kind of cylinder type hollow pipe visual detection equipment and its detection method |
Non-Patent Citations (3)
| Title |
|---|
| ESRI中国信息技术有限公司: "《第十四届Esri中国用户大户论文集》", 30 September 2016 * |
| 杜克飞: "基于机器视觉的滑动轴承内表面缺陷自动检测系统设计", 《机械工程师》 * |
| 罗庆生等著: "《智能作战机器人》", 30 November 2013 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109724984B (en) | Defect detection and identification device and method based on deep learning algorithm | |
| CN102621156B (en) | Image-processing-based automatic micro part sorting system | |
| CN103090804B (en) | Automatic detection system and detection method of finished product magnet ring image | |
| US5926268A (en) | System and method for stress detection in a molded container | |
| US5926556A (en) | Systems and methods for identifying a molded container | |
| CN108896574B (en) | Bottled liquor impurity detection method and system based on machine vision | |
| CN109900711A (en) | Workpiece, defect detection method based on machine vision | |
| CN103706575B (en) | A kind of online classification sorting equipment of eyeglass based on two-stage image collection and method | |
| US20060244959A1 (en) | Inspecting apparatus and method for foreign matter | |
| CN104502356A (en) | Automatic detection method for defects of inner surface of sliding bearing on basis of computer vision | |
| WO1997046329A9 (en) | System and method for stress detection in a molded container | |
| CN110403232A (en) | A kind of cigarette quality detection method based on second level algorithm | |
| CN107102009A (en) | A kind of method of the cylinder spool quality testing based on machine vision | |
| CN104483320A (en) | Digitized defect detection device and detection method of industrial denitration catalyst | |
| CN109142509B (en) | Round steel magnetic powder flaw detection method and device | |
| CN210071686U (en) | Fruit grading plant based on orthogonal binocular machine vision | |
| CN111812103A (en) | Image acquisition device, visual detection system and detection point extraction method | |
| CN111672773B (en) | Product surface defect detection system and detection method based on machine vision | |
| CN110554052A (en) | artificial board surface defect detection method and system | |
| Fu et al. | Medicine glass bottle defect detection based on machine vision | |
| Liu et al. | An automatic system for bearing surface tiny defect detection based on multi-angle illuminations | |
| CN112733882A (en) | Cylinder sleeve surface defect detection method, system and equipment based on deep learning | |
| CN111330874A (en) | Detection device and detection method for pollution or impurity defects of bottom area of medicine bottle | |
| JP2002214153A (en) | Foreign matter inspecting device and method in liquid filled vessel | |
| CN108663376B (en) | Seamless steel tube quality detection device and detection 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200512 |