CN114332066B - Pinhole alignment detection method and device based on image difference - Google Patents
Pinhole alignment detection method and device based on image difference Download PDFInfo
- Publication number
- CN114332066B CN114332066B CN202210005075.3A CN202210005075A CN114332066B CN 114332066 B CN114332066 B CN 114332066B CN 202210005075 A CN202210005075 A CN 202210005075A CN 114332066 B CN114332066 B CN 114332066B
- Authority
- CN
- China
- Prior art keywords
- image
- positioning
- pixel
- needle
- detected
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 39
- 239000000758 substrate Substances 0.000 claims abstract description 30
- 238000000034 method Methods 0.000 claims abstract description 7
- 238000005457 optimization Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 7
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims description 6
- 230000000877 morphologic effect Effects 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 5
- 230000002146 bilateral effect Effects 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 3
- 230000003993 interaction Effects 0.000 description 4
- 238000003708 edge detection Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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 Processing (AREA)
- Image Analysis (AREA)
- Container, Conveyance, Adherence, Positioning, Of Wafer (AREA)
Abstract
The invention discloses a pinhole alignment detection method and device based on image difference, wherein the method comprises the steps of firstly, under the condition that an element to be detected is not placed, continuously updating a substrate image to obtain a pixel set of a positioning needle area of the substrate image in real time, after obtaining the image to be detected, carrying out difference between the image to be detected and the substrate image to obtain a difference image, determining the pixel set of a positioning hole area according to the difference image, and further calculating a difference value of center distances of the two through least square elliptic fit or counting the pixel number ratio of the positioning needle in the positioning hole to judge whether pinholes are aligned. The invention can accurately detect the relative position of the element positioning hole to be detected and the substrate positioning needle, has higher real-time performance and can greatly improve the production efficiency.
Description
Technical Field
The invention relates to the field of visual detection, in particular to a pinhole alignment detection method and device based on image difference.
Background
In precision machining processes, workpiece alignment is critical. Along with the continuous accumulation of mechanical motion errors, inaccurate positioning is caused; a workpiece alignment detection method and device with high reliability and good real-time performance are needed;
the existing machine vision-based workpiece alignment detection method has poor adaptability to illumination and environmental changes, and has the defects of high false detection rate, low reliability and poor instantaneity;
disclosure of Invention
In order to solve the technical problems, the invention provides a pinhole alignment detection method and device based on image difference, which can accurately detect the relative positions of a component positioning hole to be detected and a substrate positioning needle so as to realize reliable detection of whether two workpieces are aligned or not, thereby improving the real-time performance of detection and greatly improving the production efficiency.
In order to achieve the above object, the present invention adopts the following technical measures:
the invention discloses a pinhole alignment detection method based on image difference, which is characterized by comprising the following steps:
s1: acquiring a substrate gray image B and a gray image F to be detected, and calculating a difference image D of the substrate gray image B and the gray image F to be detected according to the formula (1); determining a set of pixel coordinates u= { (U) of a positioning hole region in the differential image D r1 ,u c1 ),(u r2 ,u c2 )…(u rk ,u ck ) Edge pixel coordinate set c= { (C) of the positioning hole r1 ,c c1 ),(c r2 ,c c2 )…(c rt ,c ct )…(c rm ,c cm ) (u) rk ,u ck ) Representing the coordinates of the kth pixel of location Kong Ouyu, (c) rt ,c ct ) Representing the coordinates of the t pixel points at the edge of the positioning round hole, wherein k is the number of the pixel points in the positioning hole area, and m is the number of the pixel points at the edge of the positioning round hole; t is E [1, m]；
In the formula (1), F (x, y) represents a pixel point at (x, y) in the gray image F to be detected, B (x, y) represents a pixel point at (x, y) in the substrate gray image B, D (x, y) represents a pixel point at (x, y) in the differential image D, and T isNon-negative threshold, t 1 Is the gray value of foreground point pixel in the differential image D, t 2 The gray value of the background point pixel in the differential image D;
s2: sequentially performing morphological opening operation, morphological closing operation, gaussian filtering and bilateral filtering on the substrate gray image B, and determining a pixel coordinate set A= { (a) of a positioning needle region through OTSU global threshold segmentation r1 ,a c1 ),(a r2 ,a c2 )…(a ri ,a ci ) Edge pixel coordinate set n= { (N) for pin r1 ,n c1 ),(n r2 ,n c2 )…(n rs ,n cs )…(n rj ,n cj ) And (b) wherein (a) ri ,a ci ) Coordinates of a pixel point representing the i-th positioning needle region, (n) rs ,n cs ) Representing coordinates of the s-th pixel point of the edge of the positioning needle, wherein i is the number of the pixel points of the positioning needle area, and j is the number of the pixel points of the edge of the positioning needle; s epsilon [1, j ]]；
S3: judging whether the positioning needle is aligned with the positioning hole or not according to the pixel coordinate set U, C, A, N;
s31: according to a pixel coordinate set C of the positioning hole, establishing a positioning hole target optimization function H by using a formula (2);
in the formula (2), X 1 ,X 2 ,X 3 ,X 4 ,X 5 Five parameters of the positioning hole set according to an elliptic general equation;
according to the pixel coordinate set N of the positioning needle, establishing a positioning needle target optimization function G by utilizing a formula (3);
in the formula (3), Y 1 ,Y 2 ,Y 3 ,Y 4 ,Y 5 Five parameters of the positioning needle set according to an elliptic general equation;
solving an optimal solution X when the target optimization functions H and G take the minimum value 1 * 、X 2 * 、X 3 * 、X 4 * X 5 * And the optimal solution Y 1 * 、Y 2 * 、Y 3 * 、Y 4 * 、Y 5 * ；
S32: the center coordinates (X) of the positioning holes are obtained by using the formulas (4) to (6) C ,Y C ) And a long and a short axis a c ,b c ；
The center coordinates (X) of the positioning needle are obtained by using the formulas (7) to (9) N ,Y N ) And a long and a short axis a n ,b n ；
S33: calculating a distance threshold R between the positioning needle and the positioning hole by using the formula (10), judging whether the formula (11) is satisfied, if so, indicating that the positioning needle and the positioning hole are aligned, otherwise, indicating that the positioning needle and the positioning hole are not aligned:
R＝K c (β 1 a c +β 2 b c )+K n (β 3 a n +β 4 b n ) (10)
(X N -X C ) 2 +(Y N -Y C ) 2 ＜R 2 (11)
in the formula (10), K c ,K n Representing the coefficient of calculating the distance threshold value between the locating hole and the locating needle, beta 1 ,β 2 ,β 3 ,β 4 And (5) representing the weight coefficient for calculating the radius of the positioning needle and the radius of the positioning hole.
The pinhole alignment detection method based on image difference is also characterized in that the method for judging whether the positioning needle is aligned with the positioning hole in the step S3 is replaced by:
counting the number P of the same pixel coordinates in the pixel coordinate set U and the pixel coordinate set A; if P > T b If so, determining that the positioning needle is aligned with the positioning hole; otherwise, determining that the positioning needle is not aligned with the positioning hole, wherein T b Indicating a preset threshold.
The invention relates to a pinhole alignment detection device based on image difference, which is characterized by comprising the following components: the device comprises an image acquisition unit, a controller unit and an in-place detection unit;
the image acquisition unit acquires a current image on the detection area and sends the current image to the controller unit;
the in-place detection unit judges whether an element to be detected exists or not and whether the element to be detected is placed in place or not by using a sensor; if no element to be detected exists, a signal Sig1 without the element to be detected is sent to the controller unit; if the element to be detected is available and the element to be detected is placed, sending a placement signal Sig2 to the controller unit;
the controller unit takes the current image as a substrate gray image B after graying if receiving the signal Sig1, and controls the image acquisition unit to acquire the image and graying to obtain a gray image F to be detected if receiving the signal Sig2, and obtains a differential image D, a pixel coordinate set U of a locating hole area and an edge pixel coordinate set C of the locating hole according to the substrate gray image B and the gray image F to be detected, and then sequentially carries out pretreatment on the substrate image B and then carries out global threshold segmentation through OTSU to obtain a pixel coordinate set A of the locating needle area and an edge pixel coordinate set N of the locating needle, so as to judge whether the locating needle is aligned with the locating hole according to the pixel coordinate set U, C, A, N.
Compared with the prior art, the invention has the beneficial effects that:
1) The invention combines with the actual production process, and avoids the influence caused by illumination or environmental change by continuously updating the substrate image in real time; when the element to be detected covers the substrate, an image difference method is adopted, and the outline of the positioning round hole of the element to be detected is effectively segmented, so that the detection precision is improved.
2) According to the noise condition and gray scale characteristics of the image of the element to be detected which are not placed, the invention adopts a combination of a plurality of filtering modes, thereby effectively eliminating the influence of fine scratches and light reflection spots on the surface of the image of the substrate, effectively extracting the outline of the positioning needle and further improving the detection precision.
3) The device comprises an image acquisition unit, a controller unit, an in-place detection unit, a display unit and an input unit, and the pinhole alignment detection is completed based on an image difference method.
Drawings
FIG. 1 is a schematic diagram of the overall structure of a detection device according to the present invention;
FIG. 2 is a flow chart of the detection method of the present invention;
reference numerals in the drawings: 1 a controller unit; 2 a man-machine interaction unit; 3, an image acquisition unit; and 4 to a detection unit.
Detailed Description
In this embodiment, as shown in fig. 1, a pinhole alignment detection device based on image difference includes: the device comprises a controller unit 1, a man-machine interaction unit 2, an image acquisition unit 3 and an in-place detection unit 4;
the image acquisition unit 3 mainly comprises an imaging element, wherein the imaging element is an industrial camera of a Michaelv VCGE-503C; the communication bus of Ethernet communication is connected with the controller unit 1, the camera element is fixed right above the area to be detected, and the acquired current image on the acquisition detection substrate is sent to the controller unit 1 and the in-place detection unit 4 frame by frame;
the controller unit 1 comprises an ARM chip based on a Linux system, the model of the ARM chip is BCM2711, and an OPENCV vision open source library and a QT application program are installed in the Linux system;
the in-place detection unit 4 comprises a first photoelectric sensor 41 and a second photoelectric sensor 42, wherein the first photoelectric sensor 41 is used for detecting whether an element to be detected exists, and if the element to be detected does not exist, a signal Sig1 without the element to be detected is sent to the controller unit 1; the second photoelectric sensor 42 is configured to detect whether the element to be detected is in place, and if the element to be detected is in place, send a place signal Sig2 to the controller unit 1;
the controller unit 1 takes the current image as a substrate gray image B after graying when receiving the signal Sig1, and takes the image as a to-be-detected gray image F after controlling the image acquisition unit to acquire the image and graying when receiving the signal Sig2, and obtains a differential image D, a pixel coordinate set U of a locating hole area and an edge pixel coordinate set C of the locating hole according to the substrate gray image B and the to-be-detected gray image F, and then sequentially carries out pretreatment on the substrate image B and then carries out global threshold segmentation through OTSU to obtain a pixel coordinate set A of the locating needle area and an edge pixel coordinate set N of the locating needle, so as to judge whether the locating needle is aligned with the locating hole according to the pixel coordinate set U, C, A, N.
The man-machine interaction unit 2 comprises input devices such as a keyboard and a mouse and a display supporting an HDMI interface, is used for setting the acquisition frame rate of the image acquisition unit, selecting a detection area, setting parameters such as a detection threshold value and the like, displaying an acquired image sequence, and writing man-machine interaction programs based on a QT open source library, wherein the deviation of the distance between the center of a currently detected positioning needle and a positioning round hole, the detection result and the like.
In this embodiment, a pinhole alignment detection method based on image difference, as shown in fig. 2, includes the following steps:
s1: acquiring a substrate gray image B and a gray image F to be detected, and calculating a difference image D of the substrate gray image B and the gray image F to be detected according to the formula (1);
in the formula (1), F (x, y) represents a pixel point at (x, y) in the gray image F to be detected, B (x, y) represents a pixel point at (x, y) in the substrate gray image B, D (x, y) represents a pixel point at (x, y) in the differential image D, T is a non-negative threshold value, T 1 Is the gray value of foreground point pixel in the differential image D, t 2 The gray value of the background point pixel in the differential image D; d (x, y) after calculation is a binary image, and the pixel value of the positioning round hole area of the image to be detected is changed into t 1 The method comprises the steps of carrying out a first treatment on the surface of the In this embodiment, t 1 Taking 255, t 2 Taking 0 and taking 50;
determining a set of pixel coordinates u= { (U) of a positioning hole region in the differential image D r1 ,u c1 ),(u r2 ,u c2 )…(u rk ,u ck ) Performing channel edge detection on the differential image D, searching the peripheral outline of the positioning hole by utilizing FindContours function based on OPENCV vision open source library, and determining an edge pixel coordinate set C= { (C) of the positioning hole r1 ,c c1 ),(c r2 ,c c2 )…(c rt ,c ct )…(c rm ,c cm ) (u) rk ,u ck ) Representing the kth pixel point coordinates of the positioning Kong Ouyu; (c) rt ,c ct ) Representing the coordinates of the t pixel points at the edge of the positioning hole, wherein k is the number of the pixel points in the positioning hole area, and m is the number of the pixel points at the edge of the positioning hole; t is E [1, m]；
S2: sequentially performing morphological opening operation, morphological closing operation, gaussian filtering and bilateral filtering on the substrate gray image B, removing the influence of noise such as scratches, light spots and the like, and determining a positioning needle through OTSU global threshold segmentationPixel coordinate set a= { (a) of region r1 ,a c1 ),(a r2 ,a c2 )…(a ri ,a ci ) Finally, through CANNY edge detection, based on OPENCV vision open source library, the peripheral outline of the positioning needle is searched by utilizing FindContours function, and the edge pixel coordinate set N= { (N) of the positioning needle is determined r1 ,n c1 ),(n r2 ,n c2 )…(n rs ,n cs )…(n rj ,n cj ) And (b) wherein (a) ri ,a ci ) Pixel coordinates representing the i-th pointer region, (n) rs ,n cs ) Representing the coordinates of the s-th pixel point of the edge of the positioning needle, wherein i is the number of pixel points of the positioning needle area, and j is the number of pixel points of the edge of the positioning needle; s epsilon [1, j ]]；
S3: respectively carrying out least square ellipse fitting on the pixel coordinate sets C and N to obtain the center coordinates and the radius of the positioning hole and the positioning needle, and judging whether the positioning hole and the positioning needle are aligned according to the relative positions of the positioning hole and the positioning needle;
s31: establishing a locating hole target optimization function H according to a formula (2) by using a pixel coordinate set C of the locating hole;
in the formula (2), X 1 ,X 2 ,X 3 ,X 4 ,X 5 Five parameters of the positioning hole set according to an elliptic general equation;
establishing a positioning needle target optimization function G according to a formula (3) by utilizing a pixel coordinate set N of the positioning needle;
in the formula (3), Y 1 ,Y 2 ,Y 3 ,Y 4 ,Y 5 Five parameters of the positioning needle set according to an elliptic general equation;
solving an optimal solution X when the target optimization functions H and G take the minimum value 1 * 、X 2 * 、X 3 * 、X 4 * 、X 5 * And the optimal solution Y 1 * 、Y 2 * 、Y 3 * 、Y 4 * 、Y 5 * ；
S32: the center coordinates (X) of the positioning holes are obtained by using the formulas (4) to (6) C ,Y C ) And a long and a short axis a c ,b c ；
The center coordinates (X) of the positioning needle are obtained by using the formulas (7) to (9) N ,Y N ) And a long and a short axis a n ,b n ；
S33: calculating a distance threshold R between the positioning needle and the positioning hole by using the formula (10), judging whether the formula (11) is satisfied, if so, indicating that the positioning needle and the positioning hole are aligned, otherwise, indicating that the positioning needle and the positioning hole are not aligned:
R＝K c (β 1 a c +β 2 b c )+K n (β 3 a n +β 4 b n ) (10)
(X N -X C ) 2 +(Y N -Y C ) 2 ＜R 2 (11)
in the formula (10), K c ,K n Representing the coefficient of calculating the distance threshold value between the locating hole and the locating needle, beta 1 ,β 2 ,β 3 ,β 4 And (5) representing the weight coefficient for calculating the radius of the positioning needle and the radius of the positioning hole. In the present embodiment, K c 1, K is taken n Taking 0, beta 1 ,β 2 ,β 3 ,β 4 0.5 is taken;
in this embodiment, there is another method for determining whether the positioning needle is aligned with the positioning hole: counting the number P of the same pixel coordinates in the pixel coordinate set U and the pixel coordinate set A; if P > T b If so, determining that the positioning needle is aligned with the positioning hole; otherwise, determining that the positioning needle is not aligned with the positioning hole, wherein T b Indicating a preset threshold.
Claims (3)
1. The pinhole alignment detection method based on image difference is characterized by comprising the following steps:
s1: acquiring a substrate gray image B and a gray image F to be detected, and calculating a difference image D of the substrate gray image B and the gray image F to be detected according to the formula (1); determining a set of pixel coordinates u= { (U) of a positioning hole region in the differential image D r1 ,u c1 ),(u r2 ,u c2 )…(u rk ,u ck ) Edge pixel coordinate set c= { (C) of the positioning hole r1 ,c c1 ),(c r2 ,c c2 )…(c rt ,c ct )…(c rm ,c cm ) (u) rk ,u ck ) Representing the coordinates of the kth pixel of location Kong Ouyu, (c) rt ,c ct ) Representing the coordinates of the t pixel points at the edge of the positioning round hole, wherein k is the number of the pixel points in the positioning hole area, and m is the number of the pixel points at the edge of the positioning round hole; t is E [1, m]；
In the formula (1), F (x, y) represents a pixel point at (x, y) in the gray image F to be detected, B (x, y) represents a pixel point at (x, y) in the substrate gray image B, D (x, y) represents a pixel point at (x, y) in the differential image D, T is a non-negative threshold value, T 1 Is the gray value of foreground point pixel in the differential image D, t 2 The gray value of the background point pixel in the differential image D;
s2: sequentially performing morphological opening operation, morphological closing operation, gaussian filtering and bilateral filtering on the substrate gray image B, and determining a pixel coordinate set A= { (a) of a positioning needle region through OTSU global threshold segmentation r1 ,a c1 ),(a r2 ,a c2 )…(a ri ,a ci ) Edge pixel coordinate set n= { (N) for pin r1 ,n c1 ),(n r2 ,n c2 )…(n rs ,n cs )…(n rj ,n cj ) And (b) wherein (a) ri ,a ci ) Coordinates of a pixel point representing the i-th positioning needle region, (n) rs ,n cs ) Representing coordinates of the s-th pixel point of the edge of the positioning needle, wherein i is the number of the pixel points of the positioning needle area, and j is the number of the pixel points of the edge of the positioning needle; s epsilon [1, j ]]；
S3: judging whether the positioning needle is aligned with the positioning hole or not according to the pixel coordinate set U, C, A, N;
s31: according to a pixel coordinate set C of the positioning hole, establishing a positioning hole target optimization function H by using a formula (2);
in the formula (2), X 1 ,X 2 ,X 3 ,X 4 ,X 5 Five parameters of the positioning hole set according to an elliptic general equation;
according to the pixel coordinate set N of the positioning needle, establishing a positioning needle target optimization function G by utilizing a formula (3);
in the formula (3), Y 1 ,Y 2 ,Y 3 ,Y 4 ,Y 5 Five parameters of the positioning needle set according to an elliptic general equation;
solving an optimal solution X when the target optimization functions H and G take the minimum value 1 * 、X 2 * 、X 3 * 、X 4 * 、X 5 * And the optimal solution Y 1 * 、Y 2 * 、Y 3 * 、Y 4 * 、Y 5 * ；
S32: the center coordinates (X) of the positioning holes are obtained by using the formulas (4) to (6) C ,Y C ) And a long and a short axis a c ,b c ；
The center coordinates (X) of the positioning needle are obtained by using the formulas (7) to (9) N ,Y N ) And a long and a short axis a n ,b n ；
S33: calculating a distance threshold R between the positioning needle and the positioning hole by using the formula (10), judging whether the formula (11) is satisfied, if so, indicating that the positioning needle and the positioning hole are aligned, otherwise, indicating that the positioning needle and the positioning hole are not aligned:
R＝K c (β 1 a c +β 2 b c )+K n (β 3 a n +β 4 b n ) (10)
(X N -X C ) 2 +(Y N -Y C ) 2 ＜R 2 (11)
in the formula (10), K c ,K n Representing the coefficient of calculating the distance threshold value between the locating hole and the locating needle, beta 1 ,β 2 ,β 3 ,β 4 And (5) representing the weight coefficient for calculating the radius of the positioning needle and the radius of the positioning hole.
2. The pinhole alignment detection method based on image difference as claimed in claim 1, wherein the method of determining whether the positioning needle is aligned with the positioning hole in step S3 is replaced with:
counting the number P of the same pixel coordinates in the pixel coordinate set U and the pixel coordinate set A; if P > T b If so, determining that the positioning needle is aligned with the positioning hole; otherwise, determining that the positioning needle is not aligned with the positioning hole, wherein T b Indicating a preset threshold.
3. A pinhole alignment detection device based on image difference, characterized by comprising: the device comprises an image acquisition unit, a controller unit and an in-place detection unit;
the image acquisition unit acquires a current image on the detection area and sends the current image to the controller unit;
the in-place detection unit judges whether an element to be detected exists or not and whether the element to be detected is placed in place or not by using a sensor; if no element to be detected exists, a signal Sig1 without the element to be detected is sent to the controller unit; if the element to be detected is available and the element to be detected is placed, sending a placement signal Sig2 to the controller unit;
the controller unit takes the current image as a substrate gray image B after graying if receiving the signal Sig1, and controls the image acquisition unit to acquire the image and graying to obtain a gray image F to be detected if receiving the signal Sig2, and obtains a differential image D, a pixel coordinate set U of a locating hole area and an edge pixel coordinate set C of the locating hole according to the substrate gray image B and the gray image F to be detected, and then sequentially carries out pretreatment on the substrate image B and then carries out global threshold segmentation through OTSU to obtain a pixel coordinate set A of the locating needle area and an edge pixel coordinate set N of the locating needle, so as to judge whether the locating needle is aligned with the locating hole according to the pixel coordinate set U, C, A, N.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210005075.3A CN114332066B (en) | 2022-01-05 | 2022-01-05 | Pinhole alignment detection method and device based on image difference |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210005075.3A CN114332066B (en) | 2022-01-05 | 2022-01-05 | Pinhole alignment detection method and device based on image difference |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114332066A CN114332066A (en) | 2022-04-12 |
| CN114332066B true CN114332066B (en) | 2024-02-13 |
Family
ID=81024752
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210005075.3A Active CN114332066B (en) | 2022-01-05 | 2022-01-05 | Pinhole alignment detection method and device based on image difference |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114332066B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0930499A1 (en) * | 1998-01-16 | 1999-07-21 | NEC Corporation | Automatic visual inspection apparatus, automatic visual inspection method, and recording medium having recorded an automatic visual inspection program |
| CN111080582A (en) * | 2019-12-02 | 2020-04-28 | 易思维（杭州）科技有限公司 | Method for detecting defects on inner surface and outer surface of workpiece |
| CN111562260A (en) * | 2020-04-14 | 2020-08-21 | 江苏大学 | Lotus root mud hole detection method and device based on machine vision |
| CN113344990A (en) * | 2021-04-27 | 2021-09-03 | 成都飞机工业（集团）有限责任公司 | Hole site representation projection system and hole site alignment method of self-adaptive fitting |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101540040B (en) * | 2008-03-21 | 2012-12-12 | 深圳迈瑞生物医疗电子股份有限公司 | Method and device for automatically detecting boundary of beam-limiting device |
-
2022
- 2022-01-05 CN CN202210005075.3A patent/CN114332066B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0930499A1 (en) * | 1998-01-16 | 1999-07-21 | NEC Corporation | Automatic visual inspection apparatus, automatic visual inspection method, and recording medium having recorded an automatic visual inspection program |
| CN111080582A (en) * | 2019-12-02 | 2020-04-28 | 易思维（杭州）科技有限公司 | Method for detecting defects on inner surface and outer surface of workpiece |
| CN111562260A (en) * | 2020-04-14 | 2020-08-21 | 江苏大学 | Lotus root mud hole detection method and device based on machine vision |
| CN113344990A (en) * | 2021-04-27 | 2021-09-03 | 成都飞机工业（集团）有限责任公司 | Hole site representation projection system and hole site alignment method of self-adaptive fitting |
Non-Patent Citations (2)
| Title |
|---|
| 钢球表面缺陷的图像差分检测算法;王义文;屈冠彤;刘献礼;付鹏强;李博;;计算机辅助设计与图形学学报;20161015(10);全文 * |
| 面向PCB圆形基准点的权重式椭圆拟合定位方法;岑誉;高健;曾友;简川霞;;组合机床与自动化加工技术;20150420(04);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114332066A (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10664992B2 (en) | Non-contact visual detection method for mark positioning of mobile phone touch screen | |
| CN110501342B (en) | Cheese yarn rod positioning visual detection method | |
| CN109900711A (en) | Workpiece, defect detection method based on machine vision | |
| CN105783723B (en) | Precision die surface processing accuracy detection device and method based on machine vision | |
| CN109584239B (en) | High-light object surface defect detection system and method based on reflected light | |
| CN113724193B (en) | PCBA part size and clearance high-precision visual measurement method | |
| CN107345789A (en) | A kind of pcb board hole location detecting device and method | |
| CN108871185B (en) | Method, device and equipment for detecting parts and computer readable storage medium | |
| CN110991360B (en) | Robot inspection point position intelligent configuration method based on visual algorithm | |
| CN205643192U (en) | Check out test set of SMT masterplate quality | |
| CN107891012B (en) | Pearl size and circularity sorting device based on equivalent algorithm | |
| CN109444172A (en) | A kind of automatic optical detection device and its method suitable for artificial intelligence detection PCB | |
| CN110146017A (en) | Industrial robot repetitive positioning accuracy measurement method | |
| CN103630544A (en) | Online visual detection system | |
| CN108000239A (en) | Digital control processing on-line detecting system | |
| CN109448059A (en) | A kind of quick X angular-point sub-pixel detection method | |
| Fu et al. | Medicine glass bottle defect detection based on machine vision | |
| CN111624203A (en) | Relay contact alignment non-contact measurement method based on machine vision | |
| CN104613869A (en) | Method and system for detecting elliptical hole group based on maximum inscribed circle | |
| CN105023018A (en) | Jet code detection method and system | |
| CN109622404B (en) | Automatic sorting system and method for micro-workpieces based on machine vision | |
| CN113705564B (en) | Pointer type instrument identification reading method | |
| CN114332066B (en) | Pinhole alignment detection method and device based on image difference | |
| CN206281468U (en) | A kind of contactless detection device of columnar object perpendicularity | |
| CN108363958B (en) | Oil tank detection method based on high-resolution optical remote sensing image |
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 |