CN115760696A - Surface scratch detection method - Google Patents
Surface scratch detection method Download PDFInfo
- Publication number
- CN115760696A CN115760696A CN202211275552.4A CN202211275552A CN115760696A CN 115760696 A CN115760696 A CN 115760696A CN 202211275552 A CN202211275552 A CN 202211275552A CN 115760696 A CN115760696 A CN 115760696A
- Authority
- CN
- China
- Prior art keywords
- image
- detected
- edge
- area
- edge detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- 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
- Image Analysis (AREA)
Abstract
The invention provides a surface scratch detection method, which relates to the technical field of machine vision defect detection and comprises the following steps: collecting a product surface image by using image collection equipment, and carrying out image processing on the collected surface image to obtain a to-be-detected area; preprocessing the image of the area to be detected; carrying out edge detection on the preprocessed image of the region to be detected, and carrying out image fusion on the obtained different edge detection image results to obtain a fused edge detection image; processing the fused edge detection image to obtain an image for marking the edge; the image of the marked edge is subjected to scratch screening to obtain a surface scratch detection result, so that the problem that the clear and continuous edge profile of the scratch cannot be detected by the traditional surface scratch detection method is solved, interference information and noise in the image are effectively removed, and the clear and continuous edge profile of the surface scratch is quickly detected.
Description
Technical Field
The invention relates to the technical field of machine vision defect detection, in particular to a surface scratch detection method.
Background
The surface scratch is a common defect in industrial production and manufacturing, the surface scratch detection is a very important step in the quality inspection process of modern industrial products, the appearance of the products is particularly emphasized in many industries, such as electronic assembly, automobile processing, screen production, furniture production and the like, the product appearance directly influences the product income, and the technical application of the product defect detection through computer vision is more and more extensive in the modern industrial detection process.
In the quality inspection process of actual industrial products, due to the fact that the noise and interference conditions of the detected target background are complex, and scratches are quite variable in the aspects of gray level, continuity, directionality and the like, the traditional surface scratch detection method cannot detect the edge profile with clear and continuous scratches.
Disclosure of Invention
The invention discloses a surface scratch detection method, which solves the problem that the traditional surface scratch detection method cannot detect the clear and continuous edge profile of scratches, effectively removes interference information and noise in an image, and quickly detects the clear and continuous edge profile of the surface scratches.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
the invention discloses a surface scratch detection method, which comprises the following steps:
acquiring a product surface image by using image acquisition equipment, and carrying out image processing on the acquired surface image to obtain a region to be detected;
preprocessing the image of the region to be detected;
carrying out edge detection on the preprocessed image of the region to be detected, and carrying out image fusion on the obtained different edge detection image results to obtain a fused edge detection image;
processing the fused edge detection image to obtain an image for marking the edge;
and carrying out scratch screening on the image of the marked edge to obtain a surface scratch detection result.
Further, the step of preprocessing the image of the region to be detected includes:
graying the image of the area to be detected;
filtering the grayed image of the area to be detected by adopting a filter;
and carrying out image enhancement on the filtered image of the region to be detected.
Further, the image enhancement is carried out on the filtered image of the area to be detected by adopting a piecewise linear transformation method, and the method comprises the following steps:
obtaining an image threshold value t by using an ostu binarization algorithm;
using image threshold t to adopt piecewise linear transformation;
wherein f (i, j) represents the gray value of the pixel point of the ith row and the jth column on the piecewise linear transformation input image; e (i, j) represents the gray value of the pixel point of the ith row and the jth column on the piecewise linear transformation output image; t is an image threshold; e is a gray scale adjustment value; b is a mixture of 1 Is the intercept of the first straight-line formula, b 2 Is the intercept, k, of the second linear formula 1 Is the slope, k, of the first straight-line equation 2 Is the slope in the first straight line formula, where b1=0, b2= e-k2 t,
and e is a gray scale adjustment value.
Further, the step of obtaining the fused edge detection image comprises:
performing edge detection on the preprocessed to-be-detected region image by using a laplace operator;
performing edge detection on the preprocessed to-be-detected region image by using a sobel operator;
and carrying out image fusion on a result image subjected to edge detection by using a laplace operator and a result image subjected to edge detection by using a sobel operator according to a certain weight ratio.
Further, the step of acquiring an image of the marked edge comprises:
performing threshold segmentation and morphological processing on the fused edge detection image to obtain a processed edge detection image;
superposing the edge information of the processed edge detection image to the image of the pre-processed area to be detected to obtain an image for marking the edge;
the edge information overlay is implemented as follows:
wherein, I A (i, j) representing the gray value of a pixel point in the ith row and the jth column on the output image; i is B (i, j) representing the gray value of pixel points in the ith row and the jth column on the preprocessed image of the region to be detected; i is b (i, j) representing the gray value of the pixel point in the ith row and the jth column on the edge detection image after threshold segmentation and morphological processing are carried out on the fused edge detection image; u is the screening threshold.
Further, the step of performing scratch screening on the image of the marked edge comprises:
establishing an image corresponding relation, establishing a corresponding relation by using pixel coordinates of the fused edge detection image, the preprocessed image of the area to be detected and the blank gray level image, taking the fused edge detection image as a search image of suspicious pixel points, taking the preprocessed image of the area to be detected as a sampling image, and taking the blank gray level image as an output object;
searching suspicious pixel points, setting a suspicious threshold value R, sequentially traversing each pixel point on the fused edge detection image, and if the gray value of a certain pixel point is greater than R, regarding the pixel point as a non-suspicious edge point; if the gray value of a certain pixel point is smaller than R, the pixel point is regarded as a suspicious edge point;
local sampling and statistics, wherein a square sampling area K =1,2,3 and is 2K +1 in side length is constructed on an image of a to-be-detected area after preprocessing by taking a pixel coordinate corresponding to a suspicious pixel point as a center, and pixel points on the edge of the square sampling area are uniformly sampled, wherein the number of the sampling points is G; calculating a gray threshold S of the image of the pre-processed to-be-detected region by using an ostu binarization algorithm, taking the threshold as a boundary value of a bright gray value and a dark gray value on a sampling point of the image of the pre-processed to-be-detected region, and counting the occurrence times of the bright gray value and the dark gray value of the sampling point, wherein the occurrence times of the bright gray value is g 1 The number of occurrences of the dark gradation value is g 2 And g is 1 、g 2 Satisfy G = G 1 +g 2 ；
Identifying suspicious pixel points, setting a screening threshold value U, wherein U is more than 0 and less than 1, and when g 1 When the gray value is greater than UXG, the pixel point is determined as a surface scratch edge point, and the gray value of the pixel point is assigned to be 255 on the blank gray image; when g is 1 When the gray value is less than or equal to U multiplied by G, the pixel point is determined to be a non-surface scratch edge point, and the gray value of the pixel point is assigned to be 0 on the blank gray image;
and (3) screening the area of the connected domain, forming the connected domain by using the pixels with the gray value of 255, solving the connected domain with the largest area, setting a proportional value, multiplying the area of the largest connected domain by the proportional value to obtain an area screening value, and removing the connected domain with the area smaller than the area screening value, so that a noise area is removed, and the scratch edge profile is obtained.
The beneficial technical effects are as follows:
the invention discloses a surface scratch detection method, which comprises the following steps: acquiring a product surface image by using image acquisition equipment, and carrying out image processing on the acquired surface image to obtain a region to be detected; preprocessing the image of the region to be detected; carrying out edge detection on the preprocessed image of the region to be detected, and carrying out image fusion on the obtained different edge detection image results to obtain a fused edge detection image; processing the fused edge detection image to obtain an image for marking the edge; the image of the marked edge is subjected to scratch screening to obtain a surface scratch detection result, so that the problem that the clear and continuous edge profile of the scratch cannot be detected by the traditional surface scratch detection method is solved, interference information and noise in the image are effectively removed, and the clear and continuous edge profile of the surface scratch is quickly detected.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings used in the description of the embodiments will be briefly described below.
FIG. 1 is a flow chart illustrating the steps of a method for detecting scratches according to the present invention;
fig. 2 is an image of a region to be detected acquired in the embodiment of the present invention;
FIG. 3 is an image of the pre-processed region to be detected according to an embodiment of the present invention;
FIG. 4 is a fused edge detection image according to an embodiment of the present invention;
FIG. 5 is an image of a marked edge in an embodiment of the invention;
fig. 6 is an image of a surface scratch detection result in an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention and are not to be construed as limiting the present invention.
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
In order to test the surface scratch detection method disclosed by the invention, the to-be-detected area should contain background and other interference information, such as the edge of the detected object and the pattern.
The invention discloses a surface scratch detection method, which specifically comprises the following steps of:
s1: collecting a product surface image by using image collection equipment, and carrying out image processing on the collected surface image to obtain a to-be-detected area;
specifically, in the embodiment of the present invention, a camera is used to collect a surface image of the metal shell of the electronic product, and the camera uploads the collected image to a computer for image processing to obtain a to-be-detected area of the metal shell of the electronic product, which is shown in fig. 2;
s2: preprocessing the image of the area to be detected;
specifically, the step of preprocessing the image of the region to be detected includes:
s21: graying an image of a region to be detected;
s22: filtering the grayed image of the area to be detected by adopting a filter;
specifically, a Gaussian filter is adopted to perform low-pass filtering on the grayed image of the area to be detected, and partial noise is removed;
s23: and carrying out image enhancement on the filtered image of the region to be detected.
Specifically, the image enhancement is carried out on the filtered image of the area to be detected by adopting a piecewise linear transformation method, and the image enhancement comprises the following steps:
obtaining an image threshold value t by using an ostu binarization algorithm;
using image threshold t to adopt piecewise linear transformation;
wherein f (i, j) represents the gray value of the pixel point of the ith row and the jth column on the piecewise linear transformation input image; e (i, j) represents the gray value of the pixel point of the ith row and the jth column on the piecewise linear transformation output image; t is an image threshold; e is a gray scale adjustment value; b 1 Is the intercept of the first straight-line formula, b 2 Is as followsIntercept, k, of two linear formulae 1 Is the slope, k, of the first straight-line equation 2 Is the slope in the first straight line formula, where b1=0, b2= e-k2 t,
e is a gray level adjustment value, and different enhancement effects can be achieved by changing the e value.
If a proper e value can be selected, so that k1 is less than 1, and k2 is greater than 1, the transformation compresses the pixel value with the gray value of [0, t ], expands the pixel value with the gray value of [ t,255], compresses the pixel in the dark part, expands the pixel in the bright part, and accordingly achieves the effect of enhancing the image contrast, and provides a precondition for subsequent edge detection and scratch identification, in this embodiment, the image threshold value t =151 found by the ostu binarization method is used, the e value selects e =100 according to the empirical value, and the finally obtained piecewise linear transformation result is shown in fig. 3;
s3: carrying out edge detection on the preprocessed image of the region to be detected, and carrying out image fusion on the obtained different edge detection image results to obtain a fused edge detection image;
specifically, the step of acquiring the fused edge detection image includes:
performing edge detection on the preprocessed to-be-detected region image by using a laplace operator;
performing edge detection on the preprocessed to-be-detected region image by using a sobel operator;
the result image after the edge detection is performed by using the laplace operator and the result image after the edge detection is performed by using the sobel operator are subjected to image fusion through a certain weight ratio, in the embodiment, the fused image is shown in fig. 4, as can be seen from fig. 4, a large amount of noise points and a large amount of non-edge information exist in the result image after the edge detection is performed, including the edge information of the electronic product shell and the edge of the product mark, and the interference information often brings great difficulty to the detection and screening of scratches.
S4: processing the fused edge detection image to obtain an image for marking the edge;
specifically, threshold segmentation and morphological processing are carried out on the fused edge detection image to obtain a processed edge detection image;
superimposing the edge information of the processed edge detection image to the image of the pre-processed to-be-detected area to obtain an image of a marked edge, where the image of the marked edge in this embodiment is shown in fig. 5;
the edge information superposition is implemented as follows:
wherein, I A (i, j) represents the gray value of the pixel point of the ith row and the jth column on the output image; i is B (i, j) representing the gray value of pixel points in the ith row and the jth column on the preprocessed image of the to-be-detected region; i is b (i, j) representing the gray value of the pixel point in the ith row and the jth column on the edge detection image after threshold segmentation and morphological processing are carried out on the fused edge detection image; u is a screening threshold;
s5: and carrying out scratch screening on the image of the marked edge to obtain a surface scratch detection result.
The image to mark edge utilizes the local textural feature of mar to carry out the mar screening, gets rid of most interference information and noise point, recycles the less noise zone of area of the area removal of connected domain, reachs mar information, specifically includes following step:
s51: establishing an image corresponding relation, establishing a corresponding relation by using pixel coordinates of the fused edge detection image, the preprocessed image of the area to be detected and the blank gray level image, operating according to the corresponding relation of the pixel coordinates of the three images, taking the fused edge detection image as a search image of suspicious pixel points, taking the preprocessed image of the area to be detected as a sampling image, and taking the blank gray level image as an output object;
s52: searching suspicious pixel points, setting a suspicious threshold value R, sequentially traversing each pixel point on the fused edge detection image, and if the gray value of a certain pixel point is greater than R, regarding the pixel point as a non-suspicious edge point; if the gray value of a certain pixel point is smaller than R, the pixel point is regarded as a suspicious edge point, and the process can be expressed by a formula as follows:
wherein, I A (i, j) representing the gray value of the pixel point in the ith row and the jth column on the fused edge detection image; i is C (i, j) is the gray value of the pixel point of the ith row and the jth column on the blank gray image; suspended point indicates that the pixel is considered as a suspicious pixel;
s53: local sampling and statistics, wherein a square sampling area K =1,2,3 and is 2K +1 in side length is constructed on an image of a to-be-detected area after preprocessing by taking a pixel coordinate corresponding to a suspicious pixel point as a center, and pixel points on the edge of the square sampling area are uniformly sampled, wherein the number of the sampling points is G; calculating a gray threshold S of the image of the pre-processed to-be-detected area by using an ostu binarization algorithm, taking the threshold as a boundary value of a bright gray value and a dark gray value on a sampling point of the image of the pre-processed to-be-detected area, and counting the occurrence times of the bright gray value and the dark gray value of the sampling point, wherein the occurrence times of the bright gray value is counted as g 1 The number of occurrences of the dark gradation value is g 2 And g is a radical of 1 、g 2 Satisfy G = G 1 +g 2 ；
S54: identifying suspicious pixel points, setting a screening threshold value U, wherein U is more than 0 and less than 1, and when g 1 When the gray value is greater than UXG, the pixel point is determined as a surface scratch edge point, and the gray value of the pixel point is assigned to be 255 on the blank gray image; when g is 1 When the gray value is less than or equal to UXG, the pixel point is determined to be a non-surface scratch edge point, and the gray value of the pixel point is assigned to be 0 on the blank gray image;
the process can be formulated as follows:
wherein, I C (i, j) representing the gray value of the pixel point of the ith row and j column on the blank gray image;
s55: and (3) screening the area of the connected domain, forming the connected domain by using the pixels with the gray value of 255, solving the connected domain with the largest area, setting a proportional value, multiplying the area of the largest connected domain by the proportional value to obtain an area screening value, and removing the connected domain with the area smaller than the area screening value, so that a noise area is removed, and the scratch edge profile is obtained.
According to the size of the image and the characteristics of the scratch in this embodiment, the suspicious threshold R =1, the gray threshold S =190, the screening threshold U =0.6, K =9, and G =16 are respectively taken, and the finally obtained scratch detection result is shown in fig. 6.
The surface scratch detection method disclosed by the invention can detect the surface scratches under the background of high noise and multiple interferences and can effectively remove the interference information and the noise, and the surface scratch detection method disclosed by the invention has wide applicability and can effectively detect the surface scratches of different materials such as metal, glass, paper and the like.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The above examples are only for describing the preferred embodiments of the present invention, and are not intended to limit the scope of the present invention, and various modifications and improvements made to the technical solution of the present invention by those skilled in the art without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.
Claims (6)
1. A surface scratch detection method is characterized by comprising the following steps:
collecting a product surface image by using image collection equipment, and carrying out image processing on the collected surface image to obtain a to-be-detected area;
preprocessing the image of the region to be detected;
performing edge detection on the preprocessed image of the region to be detected, and performing image fusion on the obtained different edge detection image results to obtain a fused edge detection image;
processing the fused edge detection image to obtain an image for marking the edge;
and carrying out scratch screening on the image of the marked edge to obtain a surface scratch detection result.
2. The method according to claim 1, wherein the step of preprocessing the image of the region to be detected comprises:
graying an image of a region to be detected;
filtering the grayed image of the area to be detected by adopting a filter;
and carrying out image enhancement on the filtered image of the region to be detected.
3. The method for detecting the surface scratches as claimed in claim 2, wherein the image enhancement is performed on the filtered image of the region to be detected by using a piecewise linear transformation method, comprising the following steps:
obtaining an image threshold value t by using an ostu binarization algorithm;
using image threshold t to adopt piecewise linear transformation;
the expression of the piecewise linear transformation is as follows:
wherein f (i, j) represents the gray value of the pixel point of the ith row and the jth column on the piecewise linear transformation input image; e (i, j) represents the gray value of the pixel point of the ith row and the jth column on the piecewise linear transformation output image; t is an image threshold; e is a gray scale adjustment value; b 1 Is the intercept of the first straight-line formula, b 2 Is the intercept, k, of the second linear formula 1 Is the slope, k, of the first straight-line equation 2 Is the slope in the first straight line formula, where b1=0, b2= e-k2 t,
and e is a gray scale adjustment value.
4. The method according to claim 1, wherein the step of obtaining the fused edge detection image comprises:
performing edge detection on the preprocessed to-be-detected region image by using a laplace operator;
performing edge detection on the preprocessed to-be-detected region image by using a sobel operator;
and carrying out image fusion on a result image subjected to edge detection by using a laplace operator and a result image subjected to edge detection by using a sobel operator according to a certain weight ratio.
5. The method according to claim 1, wherein the step of obtaining an image of the marked edge comprises:
performing threshold segmentation and morphological processing on the fused edge detection image to obtain a processed edge detection image;
superposing the edge information of the processed edge detection image to the image of the pre-processed area to be detected to obtain an image for marking the edge;
the edge information superposition is implemented as follows:
wherein, I A (i, j) represents the gray value of the pixel point of the ith row and the jth column on the output image; i is B (i, j) representing the gray value of pixel points in the ith row and the jth column on the preprocessed image of the region to be detected; i is b (i, j) represents the gray value of the pixel point in the ith row and the jth column on the edge detection image after the fused edge detection image is subjected to threshold segmentation and morphological processing.
6. The method according to claim 1, wherein the step of screening the image of the marked edge for scratches comprises:
establishing an image corresponding relation, establishing a corresponding relation by using pixel coordinates of the fused edge detection image, the preprocessed image of the area to be detected and the blank gray level image, taking the fused edge detection image as a search image of the suspicious pixel point, taking the preprocessed image of the area to be detected as a sampling image, and taking the blank gray level image as an output object;
searching suspicious pixel points, setting a suspicious threshold value R, sequentially traversing each pixel point on the fused edge detection image, and if the gray value of a certain pixel point is greater than R, regarding the pixel point as a non-suspicious edge point; if the gray value of a certain pixel point is smaller than R, the pixel point is regarded as a suspicious edge point;
local sampling and statistics, wherein a square sampling area K =1,2,3,.. The side length of which is 2K +1 is constructed on an image of a to-be-detected area after pretreatment by taking a pixel coordinate corresponding to a suspicious pixel point as a center, and pixel points on the edge of the square sampling area are uniformly sampled, wherein the number of sampling points is G; calculating a gray threshold S of the image of the pre-processed to-be-detected region by using an ostu binarization algorithm, taking the threshold as a boundary value of a bright gray value and a dark gray value on a sampling point of the image of the pre-processed to-be-detected region, and counting the occurrence times of the bright gray value and the dark gray value of the sampling point, wherein the occurrence times of the bright gray value is g 1 The number of occurrences of the dark gradation value is g 2 And g is 1 、g 2 Satisfy G = G 1 +g 2 ；
Identifying suspicious pixel points, setting a screening threshold value U, wherein U is more than 0 and less than 1, and when g 1 When the gray value is greater than UXG, the pixel point is determined as a surface scratch edge point, and the gray value of the pixel point is assigned to be 255 on the blank gray image; when g is 1 When the gray value is less than or equal to UXG, the pixel point is determined to be a non-surface scratch edge point, and the gray value of the pixel point is assigned to be 0 on the blank gray image;
and (3) screening the area of the connected domain, forming the connected domain by using the pixels with the gray value of 255, solving the connected domain with the largest area, setting a proportional value, multiplying the area of the largest connected domain by the proportional value to obtain an area screening value, and removing the connected domain with the area smaller than the area screening value, so that a noise area is removed, and the scratch edge profile is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211275552.4A CN115760696A (en) | 2022-10-18 | 2022-10-18 | Surface scratch detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211275552.4A CN115760696A (en) | 2022-10-18 | 2022-10-18 | Surface scratch detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115760696A true CN115760696A (en) | 2023-03-07 |
Family
ID=85353739
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211275552.4A Pending CN115760696A (en) | 2022-10-18 | 2022-10-18 | Surface scratch detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115760696A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116703898A (en) * | 2023-08-03 | 2023-09-05 | 山东优奭趸泵业科技有限公司 | Quality detection method for end face of precision mechanical bearing |
| CN117455870A (en) * | 2023-10-30 | 2024-01-26 | 太康精密（中山）有限公司 | Connecting wire and connector quality visual detection method |
| CN118411367A (en) * | 2024-07-03 | 2024-07-30 | 浙江一鸣包装印刷有限公司 | Printed pattern defect detection method and system for plastic package |
| CN118628502A (en) * | 2024-08-15 | 2024-09-10 | 大连亚明汽车部件股份有限公司 | Die-casting clock surface identification method and system based on machine vision |
-
2022
- 2022-10-18 CN CN202211275552.4A patent/CN115760696A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116703898A (en) * | 2023-08-03 | 2023-09-05 | 山东优奭趸泵业科技有限公司 | Quality detection method for end face of precision mechanical bearing |
| CN116703898B (en) * | 2023-08-03 | 2023-10-20 | 山东优奭趸泵业科技有限公司 | Quality detection method for end face of precision mechanical bearing |
| CN117455870A (en) * | 2023-10-30 | 2024-01-26 | 太康精密（中山）有限公司 | Connecting wire and connector quality visual detection method |
| CN117455870B (en) * | 2023-10-30 | 2024-04-16 | 太康精密（中山）有限公司 | Connecting wire and connector quality visual detection method |
| CN118411367A (en) * | 2024-07-03 | 2024-07-30 | 浙江一鸣包装印刷有限公司 | Printed pattern defect detection method and system for plastic package |
| CN118411367B (en) * | 2024-07-03 | 2024-09-10 | 浙江一鸣包装印刷有限公司 | Printed pattern defect detection method and system for plastic package |
| CN118628502A (en) * | 2024-08-15 | 2024-09-10 | 大连亚明汽车部件股份有限公司 | Die-casting clock surface identification method and system based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115760696A (en) | Surface scratch detection method | |
| CN112630222B (en) | Mobile phone cover plate glass defect detection method based on machine vision | |
| CN114972357B (en) | Roller surface defect detection method and system based on image processing | |
| CN114937055B (en) | Image self-adaptive segmentation method and system based on artificial intelligence | |
| CN109829876B (en) | Chain plate defect online detection device and method based on machine vision | |
| CN109870461B (en) | Electronic components quality detection system | |
| CN108345881B (en) | Document quality detection method based on computer vision | |
| CN117437219B (en) | Magnetic glue inductance irregular appearance defect detection method based on computer vision | |
| CN117541588B (en) | Printing defect detection method for paper product | |
| CN107220649A (en) | A kind of plain color cloth defects detection and sorting technique | |
| CN109472788B (en) | Method for detecting flaw on surface of airplane rivet | |
| CN106934801A (en) | A kind of fluorescentmagnetic particle(powder) defect inspection method based on Laws texture filterings | |
| CN113034488A (en) | Visual detection method of ink-jet printed matter | |
| CN110687122A (en) | Method and system for detecting surface cracks of ceramic tile | |
| CN116309416A (en) | Visual inspection method for surface of part | |
| CN114841982A (en) | Air conditioner filter element quality monitoring method based on image processing | |
| CN114332081B (en) | Textile surface abnormity determination method based on image processing | |
| CN114862843B (en) | Rapid detection method for surface defects of metal strip based on filter fusion | |
| CN111753794A (en) | Fruit quality classification method and device, electronic equipment and readable storage medium | |
| Oni et al. | Patterned fabric defect detection and classification (FDDC) techniques: a review | |
| CN114612384B (en) | Method and system for detecting defects of appearance material of sport protector | |
| CN113706566A (en) | Perfuming spray performance detection method based on edge detection | |
| CN109001213B (en) | Reel-to-reel ultrathin flexible IC substrate appearance detection method | |
| Tang et al. | Surface inspection system of steel strip based on machine vision | |
| CN114693686B (en) | Method for detecting stains on bed sheet cloth |
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 |