CN111272768B - Ceramic tube detection method - Google Patents
Ceramic tube detection method Download PDFInfo
- Publication number
- CN111272768B CN111272768B CN202010126330.0A CN202010126330A CN111272768B CN 111272768 B CN111272768 B CN 111272768B CN 202010126330 A CN202010126330 A CN 202010126330A CN 111272768 B CN111272768 B CN 111272768B
- Authority
- CN
- China
- Prior art keywords
- image
- original image
- area
- detection
- ceramic tube
- 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
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
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8867—Grading and classifying of flaws using sequentially two or more inspection runs, e.g. coarse and fine, or detecting then analysing
- G01N2021/887—Grading and classifying of flaws using sequentially two or more inspection runs, e.g. coarse and fine, or detecting then analysing the measurements made in two or more directions, angles, positions
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- 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
Abstract
The invention discloses a ceramic tube detection method, which comprises the following steps: s1, a camera collects an original image of a ceramic tube, and ROI area setting is carried out on the collected original image; s2, defect feature extraction is carried out in the ROI, and the bulge detection specifically comprises the following steps: acquiring a high-frequency part of the edge of an original image by using a Derivative Filter of a Derivative in a frequency domain; performing difference processing on the original image and the image obtained after frequency domain filtering to eliminate image edge interference and obtain an image without edge interference; smoothing the image without the edge interference in the spatial domain by using mean value filtering to obtain a smoothed image; setting a dynamic threshold offset, extracting a dark area, taking the difference value of the gray value g (t) of any pixel of the original image and the gray value f (x) of the corresponding pixel of the image after smoothing processing, and if the difference value is more than or equal to the pixel point of the dynamic threshold offset, judging the image to be convex. The ceramic capacitor detection device can effectively detect the defects of the ceramic capacitor such as the bulge and the like, and is high in detection precision, high in speed and good in effect.
Description
Technical Field
The invention relates to the technical field of visual detection, in particular to a detection method of a ceramic tube.
Background
The annular ceramic capacitor electronic components are easily affected with damp and abraded, and some electronic components are not qualified in the production process. At present, the ceramic capacitors are manually placed in a mold for manual sorting, the ceramic capacitors are manually screened, then the mold is turned over, and the back is detected. In the industrial mass production process, the product quality is checked manually, and the problems of low efficiency and low precision exist.
Disclosure of Invention
The invention aims to provide a method for detecting a ceramic tube, which can effectively detect the defects of bulges and the like of a ceramic capacitor and has the advantages of high detection precision, high speed and good effect.
In order to solve the technical problem, the invention provides a method for detecting a ceramic tube, which comprises the following steps:
s1, a camera collects an original image of a ceramic tube, and ROI area setting is carried out on the collected original image;
s2, extracting defect features in the ROI, wherein the defect feature extraction comprises bulge detection, and the bulge detection specifically comprises the following steps:
acquiring a high-frequency part of the edge of an original image by using a Derivative Filter of a Derivative in a frequency domain;
performing difference processing on the original image and the image obtained after frequency domain filtering to eliminate image edge interference and obtain an image without edge interference;
smoothing the image without the edge interference by using mean value filtering in a spatial domain to obtain a smoothed image;
setting a dynamic threshold offset, extracting a dark area, taking the difference value between the gray value g (t) of any pixel of the original image and the gray value f (x) of the corresponding pixel of the image after the smoothing processing, and if the difference value is more than or equal to the pixel point of the set dynamic threshold offset, judging the image to be convex, namely: g (t) is less than or equal to f (x) -offset.
Preferably, the defect feature extraction further comprises imprint defect detection, the imprint defect detection comprising;
and extracting a dark color region of the ROI region by utilizing threshold segmentation, and performing closed operation on the dark color region to obtain an imprinting region.
Preferably, the defect feature extraction further includes paste break and defect detection, and the paste break and defect detection is obtained by threshold extraction.
Preferably, the defect feature extraction further includes notch defect detection, and the notch defect detection includes:
scaling the gray scale of the image to increase the gray scale contrast, obtaining an image with enhanced contrast;
extracting a bright region R of the image with enhanced contrast, and performing an expansion algorithm on the bright region R to obtain a region A;
and taking a difference set between the area A and the annular surface area B of the ceramic tube to obtain an expansion area D exceeding the annular surface area B, namely A-B = D, wherein an area R' in the bright area R corresponding to the area D is a notch.
Preferably, the "scaling the gray scale of the image to increase the gray scale contrast to obtain the contrast-enhanced image" specifically includes:
g '= g multi + Add, where Mult = 255/(maxgay-MinGray), add = -Mult multi MinGray, maxgay is the maximum gray value of the original image, minGray is the minimum gray value of the original image, g is the gray value of the original image, and g' is the gray value of the image after contrast enhancement.
Preferably, the defect feature extraction further includes inner ring size detection, and the inner ring size detection includes:
extracting an inner ring area on an original image;
acquiring a maximum inscribed circle of the inner ring area;
and judging whether the size of the maximum inscribed circle is in a preset range.
Preferably, the defect feature extraction further includes outer ring size detection, and the outer ring size detection includes:
extracting an outer ring area on an original image;
fitting the circular wheel gallery of the outer ring area according to a least square fitting circle method to obtain a fitted excircle;
and judging whether the size of the excircle is in a preset range.
Preferably, the "fitting a circular contour of the outer ring region according to a least square fitting circle method to obtain a fitted outer circle" specifically includes:
determining a circle on the plane according to the circle centers (A, B) and the radius R, wherein the circle has a general formula of x 2 +y 2 + ax + by + c =0, wherein a =0.5 a, b = -0.5 b,
extracting N point coordinates (xi, yi) on a circular wheel gallery of an outer ring area, wherein N is more than or equal to 3;
objective function
And respectively solving the partial derivatives of the F (a, B, c) for a, B and c, and making the partial derivatives equal to 0 to obtain the values of a, B and c, and then solving the circle centers (a, B) and the radius R of the excircle.
Preferably, the "acquiring an original image of the ceramic tube by the camera" specifically includes: and collecting the original image of the ceramic tube by two times of different illumination, wherein the two times of different illumination are 60-degree annular light and 90-degree annular light.
The invention has the beneficial effects that:
1. according to the invention, manual detection is replaced by machine vision, so that the production efficiency and quality are greatly improved, the detection speed can reach 220/min, and the production automation degree is improved; the size measurement precision can reach 0.02mm, and the accuracy of the detection precision is improved.
2. In the invention, for bulge detection, the bulge defect can be effectively detected by locally setting the threshold value for segmentation and extraction, and the detection precision is high.
Drawings
FIG. 1 is a schematic view of the structure of a ceramic tube according to the present invention;
FIG. 2 is a schematic structural diagram of the annular region B of the present invention;
FIG. 3 is a schematic flow chart of the present invention.
Detailed Description
The present invention is further described below in conjunction with the drawings and the embodiments so that those skilled in the art can better understand the present invention and can carry out the present invention, but the embodiments are not to be construed as limiting the present invention.
Referring to fig. 1, the invention discloses a ceramic tube detection method, which comprises the following steps:
firstly, a camera collects an original image of a ceramic tube, and ROI (region of interest) region setting is carried out on the collected original image;
the method for acquiring the original image of the ceramic tube by the camera specifically comprises the following steps: acquiring original images of the ceramic tube by two times of different illumination, wherein the two times of different illumination are 60-degree annular light and 90-degree annular light, and the 60-degree annular light source is used for acquiring gaps and bulges of products; the 90-degree annular light is used for collecting product marks and paste cracks. When image acquisition is carried out, image acquisition is carried out on two end faces of the ceramic tube respectively, each end face is respectively polished by a 60-degree annular light source and a 90-degree annular light source and images are acquired, and therefore four original images are obtained.
In addition, the camera in the invention is a black-and-white camera, and the acquired image is a gray scale image, so that the algorithm steps can be reduced, and the detection efficiency is improved.
In the present invention, as shown in fig. 1, a schematic structural view of a ceramic tube is shown. The ceramic tube is a cylinder or flat cylinder capacitor, and the two end surfaces of the ceramic tube are the upper bottom surface and the lower bottom surface of the cylinder or flat cylinder capacitor.
And step two, extracting defect characteristics in the ROI.
1. The defect feature extraction comprises protrusion detection, protrusion features are dark areas, but a global threshold cannot be determined due to nonuniform backgrounds, and the method for segmentation and extraction by locally setting the threshold comprises the following steps:
(1) Acquiring a high-frequency part of the edge of an original image by using a Derivative Filter of a Derivative in a frequency domain;
(2) Performing difference processing on the original image and the image obtained after frequency domain filtering to eliminate image edge interference and obtain an image without edge interference;
(3) Smoothing the image without the edge interference by using mean value filtering in a spatial domain to obtain a smoothed image;
(4) Setting a dynamic threshold offset, extracting a dark area, taking the difference value between the gray value g (t) of any pixel of the original image and the gray value f (x) of the corresponding pixel of the image after the smoothing processing, and if the difference value is more than or equal to the pixel point of the set dynamic threshold offset, judging the image to be convex, namely: g (t) is less than or equal to f (x) -offset.
The bulge defect can be effectively detected by locally setting a threshold value for segmentation and extraction, and the detection precision is high.
2. The defect feature extraction further comprises imprinting defect detection and paste breaking defect detection.
The gray value of the mark is greater than the paste fracture gray value, and the mark defect detection comprises the following steps; the marking is that yellow punctate dark spots are appeared due to surface process frosting, a dark area of the ROI area is extracted by utilizing threshold segmentation, and the dark area is subjected to closed operation to obtain a marking area. Under a black-and-white camera, the contrast of the black and white of the cream fracture imaging color is obvious, and the direct threshold value extraction is the cream fracture area.
3. Defect feature extraction also includes gap defect detection, which includes:
(1) Scaling the gray scale of the image to increase the gray scale contrast, obtaining an image with enhanced contrast;
(2) Extracting a bright region R of the image with enhanced contrast, and performing an expansion algorithm on the bright region R to obtain a region A, wherein the method specifically comprises the following steps:
g '= g × Mult + Add, where Mult = 255/(maxgay-MinGray), add = -Mult × MinGray, maxgay is the maximum gray value of the original image, minGray is the minimum gray value of the original image, g is the gray value of the original image, and g' is the gray value of the image after contrast enhancement;
(3) And taking a difference set between the area A and the annular surface area B of the ceramic tube to obtain an expansion area D exceeding the annular surface area B, namely A-B = D, wherein an area R' in the bright area R corresponding to the area D is a notch. The annular region is a circular ring region of the end of the ceramic tube, as illustrated in fig. 2.
2. The defect feature extraction further comprises inner ring size detection and outer ring size detection.
The inner ring size detection comprises:
(1) Extracting an inner ring area on an original image;
(2) Acquiring a maximum inscribed circle of the inner ring area;
(3) And judging whether the size of the maximum inscribed circle is in a preset range.
The outer ring size detection comprises:
(1) Extracting an outer ring area on an original image;
(2) Fitting the circular wheel gallery of the outer ring area according to a least square fitting circle method to obtain a fitted excircle, and specifically comprising:
determining a circle on the plane according to the circle centers (A, B) and the radius R, wherein the circle has a general formula of x 2 +y 2 + ax + by + c =0, wherein a =0.5 a, b = -0.5 b,
extracting N point coordinates (xi, yi) on a circular wheel gallery of an outer ring area, wherein N is more than or equal to 3;
objective function
Respectively calculating partial derivatives of a, b and c by F (a, b and c) to make the partial derivatives equal to 0 to obtainAnd (4) obtaining the circle centers (A, B) and the radius R of the excircle when the values of a, B and c are reached.
(3) And judging whether the size of the excircle is in a preset range.
In the invention, a captured target is converted into an image signal through the acquisition device, and the image signal is converted into a digital signal according to information such as pixel distribution, brightness and color. The image detection system performs various operations on the digital models, extracts interesting features, and judges whether the product is qualified or not according to judgment conditions, so that the good products and the defective products are detected to be separated independently. By detecting the defects of marks, paste cracks (ceramic falls off), bulges and gaps on the surface of the ceramic tube and measuring the internal and external dimensions of the ceramic tube, the invention separates good products from defective products by the capacitor of the ceramic tube, and improves the detection accuracy and the production efficiency.
In the invention, the mark is a product process problem to form a light yellow point on the surface; the ceramic layer falls off or is broken when the paste is broken; the convex features adopt a processing method of combining frequency domain derivative filtering to eliminate edge interference and spatial domain mean filtering to smooth the image; and (3) extracting a bright light area by notch detection and image contrast enhancement, making a difference set after the area expands, and taking the intra-ring bright light area corresponding to the corrosion area exceeding the ring surface as the notch area.
In the invention, the operation judgment is carried out according to the parallel processing judgment of the mark, the paste break, the inside and outside dimensions, the bulge and the notch, and if one item is unqualified, the product is judged to be a defective product. And the defect judgment size can be flexibly set according to the requirements of customers. The ceramic tube detection method provided by the invention replaces manual detection, the detection speed can reach 220/min, and the production automation degree is improved. The size measurement precision can reach 0.02mm, and the accuracy of the detection precision is improved.
The above-mentioned embodiments are merely preferred embodiments for fully illustrating the present invention, and the scope of the present invention is not limited thereto. The equivalent substitution or change made by the technical personnel in the technical field on the basis of the invention is all within the protection scope of the invention. The protection scope of the invention is subject to the claims.
Claims (4)
1. The ceramic tube detection method is characterized by comprising the following steps:
s1, a camera collects an original image of a ceramic tube, and ROI (region of interest) region setting is carried out on the collected original image;
s2, extracting defect features in the ROI, wherein the defect feature extraction comprises bulge detection, and the bulge detection specifically comprises the following steps:
acquiring a high-frequency part of the edge of an original image by using a Derivative Filter of a Derivative Filter in a frequency domain;
performing difference processing on the original image and the image obtained after frequency domain filtering to eliminate image edge interference and obtain an image without edge interference;
smoothing the image without the edge interference by using mean filtering in a spatial domain to obtain a smoothed image;
setting a dynamic threshold offset, extracting a dark area, taking the difference value between the gray value g (t) of any pixel of the original image and the gray value f (x) of the corresponding pixel of the image after the smoothing processing, and if the difference value is more than or equal to the pixel point of the set dynamic threshold offset, judging the image to be convex, namely: g (t) is less than or equal to f (x) -offset;
the defect feature extraction further comprises imprinted defect detection, the imprinted defect detection comprising;
extracting a dark color region of the ROI region by utilizing threshold segmentation, and performing closed operation on the dark color region to obtain a mark region;
the defect feature extraction further comprises paste break defect detection, wherein the paste break defect detection is obtained by threshold extraction;
defect feature extraction still includes breach defect detection, breach defect detection includes:
scaling the gray scale of the image to increase the gray scale contrast, obtaining an image with enhanced contrast;
extracting a bright region R of the image with enhanced contrast, and performing an expansion algorithm on the bright region R to obtain a region A;
taking a difference value between the area A and the ring surface area B of the ceramic tube to obtain an expansion area D exceeding the ring surface area B, namely A-B = D, wherein an area R' in the bright area R corresponding to the area D is a notch;
the defect feature extraction further comprises inner ring size detection, which comprises:
extracting an inner ring area on an original image;
acquiring a maximum inscribed circle of the inner ring area;
judging whether the size of the maximum inscribed circle is in a preset range;
the defect feature extraction further comprises outer ring size detection, which comprises:
extracting an outer ring area on an original image;
fitting the circular wheel gallery of the outer ring area according to a least square fitting circle method to obtain a fitted excircle;
judging whether the size of the excircle is in a preset range;
wherein, the 'camera collects the original image of the ceramic tube' specifically comprises: and collecting the original image of the ceramic tube by two times of different illumination, wherein the two times of different illumination are 60-degree annular light and 90-degree annular light.
2. The method for inspecting a ceramic tube according to claim 1, wherein the scaling the gray scale of the image to increase the gray scale contrast and obtain the contrast-enhanced image specifically comprises:
g '= g × Mult + Add, where Mult = 255/(maxgay-MinGray), add = -Mult × MinGray, maxgay is the maximum gray value of the original image, minGray is the minimum gray value of the original image, g is the gray value of the original image, and g' is the gray value of the image after contrast enhancement.
3. The method for detecting the ceramic tube according to claim 1, wherein the step of fitting the circular contour of the outer ring region according to a least square fitting circle method to obtain a fitted outer circle comprises the following specific steps:
determining a circle on the plane according to the circle centers (A, B) and the radius R, wherein the circle has a general formula of x 2 +y 2 + ax + by + c =0, wherein a =0.5 a, b = -0.5 b,
extracting N point coordinates (xi, yi) on a circular wheel gallery in an outer ring area, wherein N is more than or equal to 3;
objective function
And respectively solving the partial derivatives of the F (a, B and c) to a, B and c, making the partial derivatives equal to 0 to obtain the values of a, B and c, and then solving the circle centers (A and B) and the radius R of the excircle.
4. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 3 are implemented when the program is executed by the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010126330.0A CN111272768B (en) | 2020-02-28 | 2020-02-28 | Ceramic tube detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010126330.0A CN111272768B (en) | 2020-02-28 | 2020-02-28 | Ceramic tube detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111272768A CN111272768A (en) | 2020-06-12 |
| CN111272768B true CN111272768B (en) | 2022-12-27 |
Family
ID=71000486
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010126330.0A Active CN111272768B (en) | 2020-02-28 | 2020-02-28 | Ceramic tube detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111272768B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111696106A (en) * | 2020-07-31 | 2020-09-22 | 上海帆声图像科技有限公司 | Screen quality detection method, device and system of display equipment |
| CN112034676B (en) * | 2020-09-25 | 2024-03-08 | 上海华力微电子有限公司 | Pretreatment method of pixel graph |
| CN113808087A (en) * | 2021-09-02 | 2021-12-17 | 上汽通用五菱汽车股份有限公司 | Defect management and control method and device for surface of steel plate and computer readable storage medium |
| CN115205291B (en) * | 2022-09-15 | 2023-02-24 | 广州镭晨智能装备科技有限公司 | Circuit board detection method, device, equipment and medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005249415A (en) * | 2004-03-01 | 2005-09-15 | Seiko Epson Corp | Stain defect detecting method and stain defect detector |
| CN106204614B (en) * | 2016-07-21 | 2019-01-08 | 湘潭大学 | A kind of workpiece appearance defects detection method based on machine vision |
| CN107525467B (en) * | 2017-08-16 | 2020-03-24 | 浙江清华长三角研究院台州创新中心 | Method and device for detecting mounting defect combination of magnetic steel sheets of motor rotor |
| CN109934839A (en) * | 2019-03-08 | 2019-06-25 | 北京工业大学 | A kind of workpiece inspection method of view-based access control model |
| CN110296997B (en) * | 2019-07-03 | 2022-06-03 | 三峡大学 | Method and device for detecting defects of ceramic tiles based on machine vision |
| CN110807763A (en) * | 2019-09-19 | 2020-02-18 | 湖北三江航天万峰科技发展有限公司 | Method and system for detecting ceramic tile surface bulge |
| CN113658092A (en) * | 2021-05-13 | 2021-11-16 | 湖南莱塞智能装备有限公司 | Aluminum electrolytic capacitor defect detection method based on image processing |
-
2020
- 2020-02-28 CN CN202010126330.0A patent/CN111272768B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111272768A (en) | 2020-06-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111272768B (en) | Ceramic tube detection method | |
| CN109141232B (en) | Online detection method for disc castings based on machine vision | |
| CN108460757B (en) | Mobile phone TFT-LCD screen Mura defect online automatic detection method | |
| US9230318B2 (en) | Analysis of the digital image of the external surface of a tyre and processing of false measurement points | |
| CN110261410A (en) | A kind of detection device and method of glass lens defect | |
| CN103954634A (en) | Online quality detection system for printed matter | |
| CN109816627B (en) | Method for detecting weak and small defect target in ink area of plane glass element | |
| CN113034488A (en) | Visual detection method of ink-jet printed matter | |
| CN112782179A (en) | Method and system for detecting defects of light-reflecting surface of product | |
| KR101677070B1 (en) | System and Method for Automatically Detecting a Mura Defect using Morphological Image Processing and Labeling | |
| JP2019168388A (en) | Image inspection method and image inspection device | |
| CN111426693A (en) | Quality defect detection system and detection method thereof | |
| CN110021012B (en) | Mobile phone lens window glass defect detection method based on machine vision technology | |
| US11255798B1 (en) | Method of detecting lens cleanliness using out-of-focus differential flat field correction | |
| CN109785290A (en) | Normalized steel plate defect detection method is shone based on local light | |
| CN115330770B (en) | Cloth area type defect identification method | |
| CN117233158A (en) | Chip surface defect detection method and related device | |
| CN115294119B (en) | Machine vision-based method for detecting stains in inner grooves of heads of plum-blossom-shaped threads | |
| CN115829981A (en) | Visual detection method for end face damage of retired bearing | |
| JP5727709B2 (en) | Residue measuring method and residue measuring apparatus | |
| Mishra et al. | Surface defects detection for ceramic tiles using image processing and morphological techniques | |
| CN108280825A (en) | A kind of liquid crystal display emargintion detection method | |
| ChaoJie et al. | Intelligent bearing quality checking system based on visual inspection | |
| JP4036048B2 (en) | Defect identification method | |
| CN110624853A (en) | Online magic stick visual detection system |
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 |