CN111062919B - Bearing ring appearance defect detection method - Google Patents
Bearing ring appearance defect detection method Download PDFInfo
- Publication number
- CN111062919B CN111062919B CN201911270154.1A CN201911270154A CN111062919B CN 111062919 B CN111062919 B CN 111062919B CN 201911270154 A CN201911270154 A CN 201911270154A CN 111062919 B CN111062919 B CN 111062919B
- Authority
- CN
- China
- Prior art keywords
- defect
- image
- bearing ring
- area
- appearance
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 82
- 238000001514 detection method Methods 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 claims abstract description 37
- 230000008447 perception Effects 0.000 claims abstract description 11
- 230000011218 segmentation Effects 0.000 claims abstract description 10
- 238000013528 artificial neural network Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 11
- 238000003062 neural network model Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000012790 confirmation Methods 0.000 claims description 3
- 238000005520 cutting process Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 230000002950 deficient Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- 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
-
- 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
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a method for detecting appearance defects of a bearing ring, which comprises the following steps: s1, identifying an appearance image of a bearing ring by using a multi-layer perception neural network algorithm, directly judging the bearing ring as NG if a defect is detected, otherwise, entering a step S2; s2, identifying the appearance image of the bearing ring by using a segmentation method, judging that the bearing ring is NG if a defect is detected, and judging that the bearing ring is OK if the defect is detected. The method provided by the invention has high defect detection accuracy, and can solve the compatibility problems caused by the difference of the surface glossiness of the product and the difference between processed products of different equipment.
Description
Technical Field
The invention relates to the field of bearing ring production, in particular to a method for detecting appearance defects of a bearing ring.
Background
The existing bearing ring appearance defect detection method is carried out by adopting a traditional image processing method (an area segmentation method), the method has poor recognition effect on some special defects (such as knocks, slight rust, scratches, pinch injuries, slight turning tool lines, slight nails and the like), is frequently missed in detection, cannot be compatible with the diversity of products (the difference of the surface gloss of the products and the difference of the processed products of different equipment), and has unsatisfactory stability.
Disclosure of Invention
The present invention is directed to a method for detecting an appearance defect of a bearing ring, so as to solve the above-mentioned problems. For this purpose, the invention adopts the following specific technical scheme:
the method for detecting the appearance defect of the bearing ring can comprise the following steps:
s1, identifying an appearance image of a bearing ring by using a multi-layer perception neural network algorithm, directly judging that the bearing ring is NG if a defect is detected, otherwise, entering a step S2;
s2, identifying the appearance image of the bearing ring by using a segmentation method, judging that the bearing ring is NG if a defect is detected, and judging that the bearing ring is OK if the defect is detected.
Further, the step S1 specifically includes the following steps:
s11, carrying out enhancement pretreatment on the appearance image of the input bearing ring;
s12, acquiring image characteristic information;
s13, calling a multi-layer perception neural network model to identify an image;
s14, processing the identification result: if the identification result is OK, entering step S2; if the identification result is NG, the original image and the detection result image are saved for subsequent checking and analysis.
Further, the method further comprises a step S0 of training a multi-layer perception neural network model, wherein the step is carried out according to requirements, and specifically comprises the following steps of:
s01, reading in an appearance sample image of a bearing ring, wherein the appearance sample image comprises an OK sample image and an NG sample image;
s02, carrying out enhancement pretreatment on the image, and increasing the contrast of the image;
s03, creating a multilayer perception neural network model handle;
s04, acquiring image characteristic information: scaling the image for multiple times and obtaining characteristic information;
s05, adding the image characteristics and the category ID to the model handle;
s06, training a model is started, and a model handle is cleared after training is completed.
Further, the method further includes a step of setting relevant parameters in the region segmentation method before the step S2, where the step is performed as required, specifically:
1. selecting a region to be detected by a frame, clicking for confirmation, automatically recording a parameter A1, and storing;
2. setting an area to accurately extract a parameter A2, importing a picture, dragging a sliding block, clicking and writing when the accuracy is high from an interactive interface, and automatically recording and storing the parameter A2;
3. performing region subdivision on the precisely extracted region again, and setting corresponding parameters A3, wherein the region is subdivided into chamfer angles, end surfaces, inner chamfer angles and inner walls;
4. relevant parameter range thresholds of various defects are set, including a defect minimum width, a defect minimum height, a defect minimum area, a defect minimum gray value, a defect maximum width, a maximum height, a maximum area and a maximum gray value.
Further, the step S2 specifically includes the following steps:
s21, performing data conversion on the input image;
s22, defining a rough detection range according to the parameter A1 set before automatically;
s23, accurately extracting reference points of a detection area according to the set parameters A2;
s24, performing fine division on the accurate area again according to the set parameter A3;
s25, preprocessing an original image to increase the contrast of the image;
s26, cutting out a part to be detected according to the subdivided areas in a one-to-one matting mode;
s27, automatically forming n small areas according to the set area dividing number n;
s28, intersection sets are obtained for n small areas, and a required detection area is obtained;
s29, circularly detecting the image, and identifying defects, wherein the method specifically comprises the following steps of:
s291, obtaining histogram information of each region;
s292, judging whether the area is defective or not according to the histogram mean difference of the current area;
s293, if the defect exists, performing binarization according to the minimum gray value of the current area as a lower limit and a constant as an upper limit, and screening the defect according to the set size range;
s294, obtaining coordinates and size of the defect again;
s295, marking a defect position and a defect area according to the obtained coordinates;
s296, if no defect exists, entering the next cycle, and detecting the next area;
s297, outputting an identification result, judging that the defect is NG if the defect is detected, and storing an original image and a detection result picture so as to facilitate subsequent checking and analysis; otherwise, the result is judged to be OK.
By adopting the technical scheme, the invention has the beneficial effects that: the method provided by the invention has high defect detection accuracy, and can solve the compatibility problems caused by the difference of the surface glossiness of the product and the difference between processed products of different equipment.
Drawings
For further illustration of the various embodiments, the invention is provided with the accompanying drawings. The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate embodiments and together with the description, serve to explain the principles of the embodiments. With reference to these matters, one of ordinary skill in the art will understand other possible embodiments and advantages of the present invention. The components in the figures are not drawn to scale and like reference numerals are generally used to designate like components.
FIG. 1 is a general flow chart of the method of the present invention;
FIG. 2 is a flow chart of a method of the present invention for training a model of a multi-layer sensory neural network;
FIG. 3 is a flow chart of the method of the present invention for identifying defects using a multi-layer perceptive neural network algorithm;
FIG. 4 is a flow chart of the method of the present invention for identifying defects using a region segmentation method;
fig. 5 is a schematic illustration of the results of a bearing ring examined using the method of the invention.
Detailed Description
The invention will now be further described with reference to the drawings and detailed description.
As shown in fig. 1 to 4, a method for detecting an appearance defect of a bearing ring may include the steps of:
s1, identifying the bearing ring appearance image by using a multi-layer perception neural network algorithm, if a defect is detected, directly judging that the bearing ring appearance image is NG (bad product), otherwise, entering a step S2. The step S1 specifically comprises the following steps:
s11, enhancing pretreatment is carried out on the appearance image of the input bearing ring, and image contrast is improved, so that obvious chromatic aberration is formed between the defect and the background, and the characteristic extraction of the subsequent step is facilitated;
s12, obtaining image characteristic information, wherein the image characteristic information comprises defect height, width, radius, area, gray scale, roundness, rectangularity, outline, shape, texture and the like;
s13, calling a multi-layer perception neural network model to identify an image;
s14, processing the identification result: if the identification result is OK (good product), entering step S2; if the identification result is NG, the original image and the detection result image are saved for subsequent checking and analysis.
It should be noted that the multi-layer perceptual neural network model needs to be trained prior to image detection. That is, the method further comprises a step S0 of training the multi-layer perceptual neural network model, which is performed as needed, for example, when the bearing ring appearance sample image increases, the training needs to be performed again to ensure that the result is correct.
The method specifically comprises the following steps:
s01, reading in an appearance sample image of a bearing ring, wherein the appearance sample image comprises an OK sample image and an NG sample image;
s02, carrying out enhancement pretreatment on the image, and increasing the contrast of the image;
s03, creating a multilayer perception neural network model handle;
s04, acquiring image characteristic information: scaling the image for multiple times and obtaining characteristic information;
s05, adding the image characteristics and the category ID to the model handle;
s06, starting training a model, and clearing a model handle after training
S2, identifying the appearance image of the bearing ring by using a segmentation method, judging that the bearing ring is NG if a defect is detected, and judging that the bearing ring is OK if the defect is detected. Fig. 5 shows a bearing ring in which a machining failure is detected.
It should be noted that the method further includes a step of setting relevant parameters in the area dividing method before step S2, where some parameters are changed according to needs, for example, according to different product sizes, products processed by different processing devices (different surface gloss), etc., specifically:
1. selecting a region to be detected by a frame, clicking for confirmation, automatically recording a parameter A1, and storing;
2. setting an area to accurately extract a parameter A2, importing a picture, dragging a sliding block, clicking and writing when the accuracy is high from an interactive interface, and automatically recording and storing the parameter A2;
3. performing region subdivision on the precisely extracted region again, and setting corresponding parameters A3, wherein the region can be subdivided into chamfer angles, end surfaces, inner chamfer angles, inner walls and the like;
4. the threshold values of the relevant parameter ranges of various defects are set, and the threshold values can comprise a defect minimum width, a defect minimum height, a defect minimum area, a defect minimum gray value, a defect maximum width, a maximum height, a maximum area, a maximum gray value and the like.
Further, the step S2 specifically includes the following steps:
s21, converting a data stream acquired by a camera to obtain a BMP format digital image, and storing the BMP format digital image into a memory;
s22, defining a rough detection range according to the parameter A1 set before automatically;
s23, accurately extracting reference points of a detection area according to the set parameters A2;
s24, performing fine division on the accurate area again according to the set parameter A3;
s25, preprocessing an original image to increase the contrast of the image;
s26, cutting out a part to be detected according to the subdivided areas in a one-to-one matting mode;
s27, automatically forming n small areas according to the set area dividing number n, wherein n can be determined according to actual needs, n is usually a multiple of 6 for round products, n must be divided by 360 due to the equal division adopted, n must be a multiple of 4 for rectangular products, and the internal longitudinal division of the algorithm is fixed to be 4;
s28, intersection sets are obtained for n small areas, and a required detection area is obtained;
s29, circularly detecting the image and outputting an identification result, wherein the method specifically comprises the following steps of:
s291, obtaining histogram information of each region;
s292, judging whether the area has defects according to the average difference of the histogram of the current area, wherein the average difference parameter can be flexibly set according to actual requirements, for example, very slight defects can be detected, the minimum is 0, only obvious defects are detected, a bit larger than 255 can be set, and normal detection is generally set at about 20;
s293, if the defect exists, performing binarization according to the minimum gray value of the current area as a lower limit and a constant as an upper limit, and screening the defect according to the set size range;
s294, obtaining coordinates and size of the defect again;
s295, marking a defect position and a defect area according to the obtained coordinates;
s296, if no defect exists, entering the next cycle, and detecting the next area;
s297, after all areas are detected, outputting a recognition result, judging that the detection result is NG if the defect is detected, and storing an original image and a detection result picture so as to facilitate subsequent checking and analysis; otherwise, the result is judged to be OK.
Internal test comparison results
Test object: 100 products, among which, OK 80, special defect 5, other natural defect 15.
Detection results of the traditional algorithm: OK 90, NG 10, wherein, special defect missed detection 3, natural defect missed detection 7.
The detection result of the method comprises the following steps: OK 80, NG 20, all defects were detected.
The number of divided areas was additionally changed (24 were changed to 12): OK 84, NG 16, wherein the special defect is all detected, and natural defect 4 missed detection.
In summary, the multi-layer sensing neural network algorithm is matched with the segmentation method, so that the effect is ideal, and the desired effect can be achieved by setting different segmentation numbers according to different products.
While the invention has been particularly shown and described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (3)
1. A method for detecting an appearance defect of a bearing ring, the method comprising the steps of:
s1, identifying an appearance image of a bearing ring by using a multi-layer perception neural network algorithm, directly judging the bearing ring as NG if a defect is detected, otherwise, entering a step S2;
s2, identifying the appearance image of the bearing ring by using a segmentation method, judging that the bearing ring is NG if a defect is detected, and judging that the bearing ring is OK if the defect is detected;
the method further comprises the step of setting relevant parameters in the region segmentation method before the step S2, wherein the step specifically comprises the following steps:
1) Selecting a region to be detected by a frame, clicking for confirmation, automatically recording a parameter A1, and storing;
2) Setting an area to accurately extract a parameter A2, importing a picture, dragging a sliding block, clicking and writing, and automatically recording and storing the parameter A2;
3) Performing region subdivision on the precisely extracted region again, and setting corresponding parameters A3, wherein the region is subdivided into chamfer angles, end surfaces, inner chamfer angles and inner walls;
4) Setting related parameter range thresholds of various defects, including a defect minimum width, a defect minimum height, a defect minimum area, a defect minimum gray value, a defect maximum width, a maximum height, a maximum area and a maximum gray value;
the step S2 specifically includes the following steps:
s21, performing data conversion on the input image;
s22, automatically limiting a detection range according to a parameter A1 set before;
s23, accurately extracting reference points of a detection area according to the set parameters A2;
s24, performing fine division on the accurate area again according to the set parameter A3;
s25, preprocessing an original image to increase the contrast of the image;
s26, cutting out a part to be detected according to the subdivided areas in a one-to-one matting mode;
s27, automatically forming n small areas according to the set area dividing number n;
s28, intersection sets are obtained for n small areas, and a required detection area is obtained;
s29, circularly detecting the image and outputting an identification result, wherein the method specifically comprises the following steps of:
s291, obtaining histogram information of each region;
s292, judging whether the area is defective or not according to the histogram mean difference of the current area;
s293, if the defect exists, performing binarization according to the minimum gray value of the current area as a lower limit and a constant as an upper limit, and screening the defect according to the set size range;
s294, obtaining coordinates and size of the defect again;
s295, marking a defect position and a defect area according to the obtained coordinates;
s296, if no defect exists, entering the next cycle, and detecting the next area;
s297, outputting an identification result, judging that the defect is NG if the defect is detected, and storing an original image and a detection result picture so as to facilitate subsequent checking and analysis; otherwise, the result is judged to be OK.
2. The method for detecting the appearance defect of the bearing ring according to claim 1, wherein the step S1 specifically comprises the following steps:
s11, carrying out enhancement pretreatment on the appearance image of the input bearing ring;
s12, acquiring image characteristic information;
s13, calling a multi-layer perception neural network model to identify an image;
s14, processing the identification result: if the identification result is OK, entering step S2; if the identification result is NG, the original image and the detection result image are saved for subsequent checking and analysis.
3. The method for detecting the appearance defects of the bearing rings according to claim 2, further comprising the step of training a multi-layer perceptual neural network model, comprising in particular the following steps:
s01, reading in an appearance sample image of a bearing ring, wherein the appearance sample image comprises an OK sample image and an NG sample image;
s02, carrying out enhancement pretreatment on the image, and increasing the contrast of the image;
s03, creating a multilayer perception neural network model handle;
s04, acquiring image characteristic information: scaling the image for multiple times and obtaining characteristic information;
s05, adding the image characteristics and the category ID to the model handle;
s06, training a model is started, and a model handle is cleared after training is completed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911270154.1A CN111062919B (en) | 2019-12-12 | 2019-12-12 | Bearing ring appearance defect detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911270154.1A CN111062919B (en) | 2019-12-12 | 2019-12-12 | Bearing ring appearance defect detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111062919A CN111062919A (en) | 2020-04-24 |
| CN111062919B true CN111062919B (en) | 2023-11-03 |
Family
ID=70300651
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911270154.1A Active CN111062919B (en) | 2019-12-12 | 2019-12-12 | Bearing ring appearance defect detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111062919B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112858329A (en) * | 2020-12-31 | 2021-05-28 | 慈溪迅蕾轴承有限公司 | Image detection method for bearing deformed ring |
| CN113532327B (en) * | 2021-07-15 | 2023-09-12 | 合肥图迅电子科技有限公司 | Method for detecting chip morphology in tray based on stripe projection 3D imaging |
| CN116136393B (en) * | 2023-03-02 | 2023-07-28 | 宁波川原精工机械有限公司 | Bearing ring inner ring detection system and method |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2761476A1 (en) * | 1997-03-28 | 1998-10-02 | Lorraine Laminage | METHOD FOR INSPECTING THE SURFACE OF A TRAVELING STRIP BY PRIOR CLASSIFICATION OF DETECTED SURFACE IRREGULARITY |
| JP2006292593A (en) * | 2005-04-12 | 2006-10-26 | Nippon Steel Corp | Flaw detector, flaw detecting method, computer program and recording medium |
| CN101799434A (en) * | 2010-03-15 | 2010-08-11 | 深圳市中钞科信金融科技有限公司 | Printing image defect detection method |
| CN102074031A (en) * | 2011-01-13 | 2011-05-25 | 广东正业科技股份有限公司 | Standard establishment method for observational check machine of printed circuit board |
| CN102157024A (en) * | 2011-05-03 | 2011-08-17 | 西安印钞有限公司 | System and method for on-line secondary detection checking of checking data of large-sheet checking machine |
| WO2016201947A1 (en) * | 2015-06-16 | 2016-12-22 | 华南理工大学 | Method for automated detection of defects in cast wheel products |
| CN107895362A (en) * | 2017-10-30 | 2018-04-10 | 华中师范大学 | A kind of machine vision method of miniature binding post quality testing |
| CN108734709A (en) * | 2018-05-29 | 2018-11-02 | 西安工程大学 | A kind of identification of insulator flange shape parameter and destructive test method |
| CN109447977A (en) * | 2018-11-02 | 2019-03-08 | 河北工业大学 | A kind of defects of vision detection method based on multispectral depth convolutional neural networks |
| CN109816644A (en) * | 2019-01-16 | 2019-05-28 | 大连理工大学 | A kind of bearing defect automatic checkout system based on multi-angle light source image |
| CN109978875A (en) * | 2019-04-03 | 2019-07-05 | 无锡立赫智能科技有限公司 | A kind of capacitor open defect recognition methods and identification device |
| CN110542689A (en) * | 2019-10-10 | 2019-12-06 | 韦士肯(厦门)智能科技有限公司 | Bearing ring image detection device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5174535B2 (en) * | 2008-05-23 | 2013-04-03 | 株式会社日立ハイテクノロジーズ | Defect inspection method and apparatus |
-
2019
- 2019-12-12 CN CN201911270154.1A patent/CN111062919B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2761476A1 (en) * | 1997-03-28 | 1998-10-02 | Lorraine Laminage | METHOD FOR INSPECTING THE SURFACE OF A TRAVELING STRIP BY PRIOR CLASSIFICATION OF DETECTED SURFACE IRREGULARITY |
| JP2006292593A (en) * | 2005-04-12 | 2006-10-26 | Nippon Steel Corp | Flaw detector, flaw detecting method, computer program and recording medium |
| CN101799434A (en) * | 2010-03-15 | 2010-08-11 | 深圳市中钞科信金融科技有限公司 | Printing image defect detection method |
| CN102074031A (en) * | 2011-01-13 | 2011-05-25 | 广东正业科技股份有限公司 | Standard establishment method for observational check machine of printed circuit board |
| CN102157024A (en) * | 2011-05-03 | 2011-08-17 | 西安印钞有限公司 | System and method for on-line secondary detection checking of checking data of large-sheet checking machine |
| WO2016201947A1 (en) * | 2015-06-16 | 2016-12-22 | 华南理工大学 | Method for automated detection of defects in cast wheel products |
| CN107895362A (en) * | 2017-10-30 | 2018-04-10 | 华中师范大学 | A kind of machine vision method of miniature binding post quality testing |
| CN108734709A (en) * | 2018-05-29 | 2018-11-02 | 西安工程大学 | A kind of identification of insulator flange shape parameter and destructive test method |
| CN109447977A (en) * | 2018-11-02 | 2019-03-08 | 河北工业大学 | A kind of defects of vision detection method based on multispectral depth convolutional neural networks |
| CN109816644A (en) * | 2019-01-16 | 2019-05-28 | 大连理工大学 | A kind of bearing defect automatic checkout system based on multi-angle light source image |
| CN109978875A (en) * | 2019-04-03 | 2019-07-05 | 无锡立赫智能科技有限公司 | A kind of capacitor open defect recognition methods and identification device |
| CN110542689A (en) * | 2019-10-10 | 2019-12-06 | 韦士肯(厦门)智能科技有限公司 | Bearing ring image detection device |
Non-Patent Citations (2)
| Title |
|---|
| Component surface defect detection based on image segmentation method;Renwei L, Dong Y.;2016 Chinese Control and Decision Conference (CCDC);第5093-5096页 * |
| 基于改进Niblack算法的轴承滚子表面缺陷检测;陈金贵, 陈昊, 张奔;组合机床与自动化加工技术(第12期);第82-85+97页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111062919A (en) | 2020-04-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6879431B2 (en) | Image processing equipment, image processing method and image processing program | |
| CN111062919B (en) | Bearing ring appearance defect detection method | |
| CN114937055A (en) | Image self-adaptive segmentation method and system based on artificial intelligence | |
| CN113344857B (en) | Defect detection network training method, defect detection method and storage medium | |
| JP5337563B2 (en) | Form recognition method and apparatus | |
| JP2013167596A (en) | Defect inspection device, defect inspection method, and program | |
| CN111667475B (en) | Machine vision-based Chinese date grading detection method | |
| CN108921160B (en) | Book identification method, electronic equipment and storage medium | |
| JP2016099126A (en) | Steel material component identification apparatus and program of the same | |
| CN115100191A (en) | Metal casting defect identification method based on industrial detection | |
| CN117798087B (en) | Visual sorting system and terminal for lithium battery based on appearance defect detection | |
| CN115272350A (en) | Method for detecting production quality of computer PCB mainboard | |
| CN109063708B (en) | Industrial image feature identification method and system based on contour extraction | |
| US20050271260A1 (en) | Device, method and program for removing pores | |
| KR102602167B1 (en) | Deep learning-based MLCC stacked alignment inspection system and method | |
| JP4459945B2 (en) | Extraction color range setting method | |
| CN111898605A (en) | Set top box information detection method and system based on image OCR recognition | |
| JP7209278B2 (en) | Steel component identification device, steel component identification method, and steel component identification program | |
| JP7058009B2 (en) | Steel component identification device and its program | |
| JP4494424B2 (en) | Program and inspection device | |
| JP7058008B2 (en) | Steel component identification device and its program | |
| CN118115503B (en) | Method for detecting surface defects of miniature bearing ball based on computer vision | |
| CN118501177B (en) | Appearance defect detection method and system for formed foil | |
| CN113255657B (en) | Method and device for detecting scratch on bill surface, electronic equipment and machine-readable medium | |
| CN117474916B (en) | Image detection method, electronic equipment and storage medium |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230626 Address after: 215000 North 2nd Floor, Building 3, Listing Science and Technology Innovation Park, No. 19 Yong'an Road, High tech Zone, Suzhou City, Jiangsu Province Applicant after: Suzhou weishiken Testing Technology Co.,Ltd. Address before: 361000 room 3011, Xuanye building, Pioneer Park, torch hi tech Zone, Xiamen City, Fujian Province Applicant before: VSCAN (XIAMEN) INTELLIGENT TECHNOLOGY CO.,LTD. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |