CN111476797B - Image segmentation method for overlapping pits in shot blasting forming - Google Patents
Image segmentation method for overlapping pits in shot blasting forming Download PDFInfo
- Publication number
- CN111476797B CN111476797B CN202010195473.7A CN202010195473A CN111476797B CN 111476797 B CN111476797 B CN 111476797B CN 202010195473 A CN202010195473 A CN 202010195473A CN 111476797 B CN111476797 B CN 111476797B
- Authority
- CN
- China
- Prior art keywords
- image
- pits
- pit
- shot blasting
- dividing
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000005422 blasting Methods 0.000 title claims abstract description 28
- 238000003709 image segmentation Methods 0.000 title claims abstract description 16
- 239000002184 metal Substances 0.000 claims description 9
- 239000002245 particle Substances 0.000 claims description 9
- 230000000877 morphologic effect Effects 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000005480 shot peening Methods 0.000 claims description 5
- 238000005520 cutting process Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims 1
- 230000011218 segmentation Effects 0.000 abstract description 8
- 239000007769 metal material Substances 0.000 description 4
- 238000001514 detection method Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000011179 visual inspection Methods 0.000 description 2
- 235000002566 Capsicum Nutrition 0.000 description 1
- 239000006002 Pepper Substances 0.000 description 1
- 235000016761 Piper aduncum Nutrition 0.000 description 1
- 235000017804 Piper guineense Nutrition 0.000 description 1
- 244000203593 Piper nigrum Species 0.000 description 1
- 235000008184 Piper nigrum Nutrition 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003116 impacting effect Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- 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
Abstract
The invention discloses an image segmentation method for overlapping pits in shot blasting forming, which is based on a machine vision system, wherein a light source of the machine vision system generates a reflection center different from the brightness of the pits at the lowest position of the pits, the center position of the pits is determined based on the reflection center, and the overlapping pits are segmented according to the center position of the pits. The method solves the problems that the existing method for acquiring the segmented pits based on the image edges is relatively difficult and the robustness of the edge segmentation algorithm is greatly reduced.
Description
Technical Field
The invention relates to the field of shot blasting forming, in particular to an image segmentation method for overlapping pits in shot blasting forming.
Background
The shot blasting forming is to generate metal material flow and stress layer on the surface of the metal material by a large number of shots impacting the surface of the metal material at high speed, so as to deform the metal material, thereby achieving the purpose of forming the metal piece. The method does not need a die, so that the method is widely applied in the aerospace field.
During the shot peening process, the impact energy to the metal surface is much higher than for shot peening. After the shot forming process is completed, a visually visible pit is left on the metal surface. For metal parts of different thickness and different materials, the size of the pit affects the comprehensive mechanical properties of the part. Too large a pit can reduce the fatigue performance of the metal part, and therefore pit size detection of the machined part surface is required.
Currently, measurement of pit size is mainly accomplished by means of manual visual inspection. Because the mutual overlapping rate between the pits is high during the shot blasting, the manual visual inspection cannot be completed. If the machine vision system is adopted for detection, the first problem to be solved is to divide mutually overlapped pits. If the division of the pit cannot be effectively realized, the subsequent measurement of the pit diameter cannot be performed in the future. Based on the requirement, the invention provides a segmentation algorithm of the overlapped pits, and the segmentation problem of the overlapped pits is effectively solved.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide an image segmentation method for overlapping pits in shot blasting forming, so as to solve the problems in the prior art.
The technical problems solved by the invention can be realized by adopting the following technical scheme:
an image segmentation method for overlapping pits in shot-peening forming is based on a machine vision system, wherein a light source of the machine vision system generates a reflection center different from the brightness of the pits at the lowest position of the pits, the image segmentation method determines the central position of the pits based on the reflection center, and segments the overlapped pits according to the central position of the pits.
Further, the image segmentation method includes the following steps:
1) Acquiring an image of the metal surface, and preprocessing the image to remove interference information in the image;
2) Binarizing the image to separate shot blasting pit areas in the image;
3) Performing morphological opening operation on the image to remove interference particle information with the size far smaller than the size of the pit in the image;
4) Dividing the shot blasting pit background, namely dividing the shot blasting pit area outline image from the image;
5) Extracting the reflection center features, namely dividing the reflection center image of the pit from the shot blasting pit area outline image;
6) Dividing the watershed image, namely dividing a shot blasting pit area into a plurality of areas according to the position of the reflection center of the pit, wherein each divided area corresponds to one pit;
7) And performing MASK image processing, namely performing MASK image processing on images obtained by dividing the pit image and the watershed image, dividing the overlapped pits, and finishing image division of the overlapped pits by sharp edge cutting operation.
Further, the method for extracting the reflective center features in the step 5) comprises the following steps:
subtracting the image processed in the step 3) from the shot blasting pit area outline image segmented in the step 4) to obtain a reflection center image, wherein reflection centers in the reflection center image are in one-to-one correspondence with pits.
Furthermore, in the step 3), the selection of the morphological opening operation structural element for the image is determined according to the size of the pit and the pixels of the image.
Further, the method for extracting the reflective center features in the step 5) comprises a de-interference algorithm.
Drawings
Fig. 1 is a flowchart of an image segmentation method of overlapping pits in shot peening forming according to the present invention.
Fig. 2 is a raw image of a metal surface peen pit according to the present invention.
FIG. 3 is a pre-processed and binarized image according to the present invention.
Fig. 4 is an image of a morphological open operation according to the present invention.
Fig. 5 is a segmented image of a pit background according to the present invention.
Fig. 6 is a reflective center image of a pit according to the present invention.
FIG. 7 is a watershed area-segmented image according to the present invention.
Fig. 8 is an image of a separated crater according to the present invention.
Detailed Description
The invention is further described in connection with the following detailed description, in order to make the technical means, the creation characteristics, the achievement of the purpose and the effect of the invention easy to understand.
Referring to fig. 1 to 8, the image segmentation method of overlapping pits in shot forming according to the present invention is based on a machine vision system whose light source generates a reflection center different from the brightness of the pit at the lowest position of the pit, determines the center position of the pit based on the reflection center, and segments the overlapping pits according to the center position of the pit.
The image segmentation method comprises the following steps:
1) Acquiring an image of the metal surface, and preprocessing the image to remove interference information in the image;
2) Binarizing the image to separate shot blasting pit areas in the image;
3) Performing morphological opening operation on the image to remove interference particle information with the size far smaller than the size of the pit in the image;
4) Dividing the shot blasting pit background, namely dividing the shot blasting pit area outline image from the image;
5) Extracting the reflection center features, namely dividing the reflection center image of the pit from the shot blasting pit area outline image;
6) Dividing the watershed image, namely dividing a shot blasting pit area into a plurality of areas according to the position of the reflection center of the pit, wherein each divided area corresponds to one pit;
7) And performing MASK image processing, namely performing MASK image processing on images obtained by dividing the pit image and the watershed image, dividing the overlapped pits, and finishing image division of the overlapped pits by sharp edge cutting operation.
Generally, machine vision systems all include an assembly light source that functions to provide a stable light source that results in a consistent quality of the image obtained. Because of the particularity of the shot-blast formed pit, the shape is a concave circular surface. There will be a reflection for the light source at the centre of the pit on the acquired image, forming a reflection centre, as shown in figure 2.
Image preprocessing: the main purpose is to remove noise and other interference information in the original image.
The shot blasting image is obtained by the existence of various noise and other interference information of the salt pepper, and the noise ratio of the image can be reduced by the interference information, so that the accuracy and the robustness of subsequent image processing are affected. Therefore, the original image needs to be preprocessed, and the main purpose of the preprocessing is to remove noise and the like in the original image and improve the signal-to-noise ratio of the image. The preprocessing algorithm mainly comprises median filtering, smooth filtering and the like. And selecting a proper preprocessing algorithm according to the specific condition of the acquired image, setting proper parameters, and denoising the image.
Image binarization: the main purpose is to segment the main area of the peen pit from the image.
The invention adopts a self-adaptive binarization method, mainly comprises a plurality of self-adaptive binarization algorithms such as a common clustering binarization algorithm, a maximum entropy threshold method and the like, and the selection of the algorithm is selected according to the specific condition of the image.
Morphological opening removes background interfering particles: the main purpose is to remove the interference particle information with the size far smaller than the size of the pit in the image;
the crater is a target feature of the image, but non-characteristic interference particles (such as scratches) with sizes exist in the background of the image, and particle information with sizes far smaller than the size of the crater in the image is removed under the condition that the target feature is not damaged too much;
and (5) bullet pit background segmentation: the purpose is to divide the bullet pit from the image background completely;
after the previous pretreatment, binarization, opening operation and other algorithm treatment, the signal to noise ratio of the pit image is obviously improved compared with the background. Generally, the reflective center is a hole. The holes can be partially filled after being processed by a morphological-based hole filling algorithm. After the processing, the discrimination between the shot blasting pit and the background is obvious, and the division between the pit and the background is realized.
And (3) extracting reflection center characteristics: the purpose is to divide the reflecting center in the center of the bullet pit;
the main method comprises the following steps: subtracting the pre-segmentation image from the pre-segmentation image of the pit background in the previous step to obtain a reflective central characteristic image, and removing some small interference particle points according to the particle area and the like. Thus, in the resulting image, a reflective center "pins" a pit. For the superimposed image, after this partial processing, how many reflection centers are, means how many shot blast pits are.
Dividing images by a watershed method: the image is divided into individual pit areas according to the position of the reflection center point.
And (3) carrying out watershed image segmentation processing based on the obtained reflection center characteristics. After being treated by a watershed method, the whole image is divided into N areas, and each divided area corresponds to one pit;
MASK image processing: the algorithm process provided by the invention is completed by performing MASK image processing on the bullet hole segmentation image and the watershed segmentation image, dividing the overlapped bullet holes, performing sharp edge cutting operation and the like.
The foregoing has shown and described the basic principles and main features of the present invention and the advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (3)
1. An image segmentation method for overlapping pits in shot blasting forming is based on a machine vision system and is characterized in that a light source of the machine vision system generates a reflection center different from the brightness of the pits at the lowest position of the pits, the image segmentation method determines the central position of the pits based on the reflection center, and segments the overlapped pits according to the central position of the pits;
the image segmentation method comprises the following steps:
1) Acquiring an image of the metal surface, and preprocessing the image to remove interference information in the image;
2) Binarizing the image to separate shot blasting pit areas in the image;
3) Performing morphological opening operation on the image to remove interference particle information with the size far smaller than the size of the pit in the image;
4) Dividing the shot blasting pit background, namely dividing the shot blasting pit area outline image from the image;
5) Extracting the reflection center features, namely dividing the reflection center image of the pit from the shot blasting pit area outline image; the method for extracting the reflective center features comprises the following steps:
subtracting the shot blasting pit area outline image segmented in the step 4) from the image processed in the step 3) to obtain a reflection center image, wherein reflection centers in the reflection center image are in one-to-one correspondence with pits;
6) Dividing the watershed image, namely dividing a shot blasting pit area into a plurality of areas according to the position of the reflection center of the pit, wherein each divided area corresponds to one pit;
7) And performing MASK image processing, namely performing MASK image processing on images obtained by dividing the pit image and the watershed image, dividing the overlapped pits, and finishing image division of the overlapped pits by sharp edge cutting operation.
2. The method according to claim 1, wherein the selection of the morphological open operation structure element for the image in the step 3) is determined according to the pit size and the image pixel.
3. The method for image segmentation of overlapping shots in shot peening forming according to claim 1, wherein said step 5) of light reflection center feature extraction method comprises a de-interference algorithm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010195473.7A CN111476797B (en) | 2020-03-19 | 2020-03-19 | Image segmentation method for overlapping pits in shot blasting forming |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010195473.7A CN111476797B (en) | 2020-03-19 | 2020-03-19 | Image segmentation method for overlapping pits in shot blasting forming |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111476797A CN111476797A (en) | 2020-07-31 |
CN111476797B true CN111476797B (en) | 2023-10-10 |
Family
ID=71747753
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010195473.7A Active CN111476797B (en) | 2020-03-19 | 2020-03-19 | Image segmentation method for overlapping pits in shot blasting forming |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111476797B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108169236A (en) * | 2016-12-07 | 2018-06-15 | 广州映博智能科技有限公司 | A kind of cracks of metal surface detection method of view-based access control model |
CN109191421A (en) * | 2018-07-04 | 2019-01-11 | 沈阳工业大学 | Cylindricality lithium battery periphery pit visible detection method |
CN109682839A (en) * | 2019-01-25 | 2019-04-26 | 中国船舶重工集团公司第七一六研究所 | A kind of metal arc Surface Flaw online test method |
JP2019100937A (en) * | 2017-12-06 | 2019-06-24 | 日東電工株式会社 | Defect inspection device and defect inspection method |
CN110542692A (en) * | 2018-05-28 | 2019-12-06 | 衢州飞瑞特种陶瓷有限公司 | Visual detection system for surface defects of bearing ball |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6478841B2 (en) * | 2015-07-01 | 2019-03-06 | キヤノン株式会社 | Image processing apparatus and image processing method |
-
2020
- 2020-03-19 CN CN202010195473.7A patent/CN111476797B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108169236A (en) * | 2016-12-07 | 2018-06-15 | 广州映博智能科技有限公司 | A kind of cracks of metal surface detection method of view-based access control model |
JP2019100937A (en) * | 2017-12-06 | 2019-06-24 | 日東電工株式会社 | Defect inspection device and defect inspection method |
CN110542692A (en) * | 2018-05-28 | 2019-12-06 | 衢州飞瑞特种陶瓷有限公司 | Visual detection system for surface defects of bearing ball |
CN109191421A (en) * | 2018-07-04 | 2019-01-11 | 沈阳工业大学 | Cylindricality lithium battery periphery pit visible detection method |
CN109682839A (en) * | 2019-01-25 | 2019-04-26 | 中国船舶重工集团公司第七一六研究所 | A kind of metal arc Surface Flaw online test method |
Non-Patent Citations (1)
Title |
---|
韦冬冬.《基于凹点匹配的重叠图像分割算法》.《计算机与应用化学》.2010,第27卷(第1期),全文. * |
Also Published As
Publication number | Publication date |
---|---|
CN111476797A (en) | 2020-07-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106251361B (en) | A kind of rail surface defects image self-adapting division method | |
CN109682839B (en) | Online detection method for surface defects of metal arc-shaped workpiece | |
Aminzadeh et al. | Automatic thresholding for defect detection by background histogram mode extents | |
CN106780486A (en) | A kind of Surface Defects in Steel Plate image extraction method | |
CN107369136A (en) | Composite polycrystal-diamond face crack visible detection method | |
CN113240663B (en) | Conveyor belt ore granularity detection method based on edge response fusion algorithm | |
CN114972326A (en) | Defective product identification method for heat-shrinkable tube expanding process | |
CN106157303A (en) | A kind of method based on machine vision to Surface testing | |
CN104700092A (en) | Small-character number identification method based on template and feature matching | |
CN115830033A (en) | Automobile hub surface defect detection method based on machine vision | |
CN114092403A (en) | Grinding wheel wear detection method and system based on machine vision | |
CN115880248B (en) | Surface scratch defect identification method and visual detection equipment | |
CN116757990A (en) | Railway fastener defect online detection and identification method based on machine vision | |
CN111192273A (en) | Digital shot blasting coverage rate measuring method based on computer vision technology | |
CN109859187B (en) | Explosive-pile ore rock particle image segmentation method | |
CN115049657A (en) | Glass defect detection method | |
CN115100174B (en) | Ship sheet metal part paint surface defect detection method | |
CN112529893A (en) | Hub surface flaw online detection method and system based on deep neural network | |
CN116109637A (en) | System and method for detecting appearance defects of turbocharger impeller based on vision | |
CN111476797B (en) | Image segmentation method for overlapping pits in shot blasting forming | |
CN116486091A (en) | Fan blade defect area rapid segmentation method and system based on artificial intelligence | |
CN107967690B (en) | Self-adaptive ferrographic abrasive particle image binarization processing method | |
CN111389741A (en) | Automatic sorting system for detecting surface defects of automobile brake pads based on machine vision | |
CN111553886B (en) | Self-adaptive identification method for particles in CT image of asphalt mixture | |
CN108230334B (en) | High-concentration wind-blown sand image segmentation method based on gray threshold |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |