CN111551552B - Appearance quality detection method for round hole punching net - Google Patents
Appearance quality detection method for round hole punching net Download PDFInfo
- Publication number
- CN111551552B CN111551552B CN202010419366.8A CN202010419366A CN111551552B CN 111551552 B CN111551552 B CN 111551552B CN 202010419366 A CN202010419366 A CN 202010419366A CN 111551552 B CN111551552 B CN 111551552B
- Authority
- CN
- China
- Prior art keywords
- circle
- line
- image
- hole punching
- row
- 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
- 238000004080 punching Methods 0.000 title claims abstract description 88
- 238000001514 detection method Methods 0.000 title abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 23
- 230000007547 defect Effects 0.000 claims abstract description 17
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 230000002950 deficient Effects 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 5
- 238000001914 filtration Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- PXHVJJICTQNCMI-UHFFFAOYSA-N Nickel Chemical compound [Ni] PXHVJJICTQNCMI-UHFFFAOYSA-N 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000030279 gene silencing Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000010409 ironing Methods 0.000 description 2
- 229910052751 metal Inorganic materials 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 229910001335 Galvanized steel Inorganic materials 0.000 description 1
- 241001124569 Lycaenidae Species 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 229910045601 alloy Inorganic materials 0.000 description 1
- 239000000956 alloy Substances 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 235000013361 beverage Nutrition 0.000 description 1
- 235000019504 cigarettes Nutrition 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005108 dry cleaning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000008397 galvanized steel Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 229910052759 nickel Inorganic materials 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000010935 stainless steel Substances 0.000 description 1
- 229910001220 stainless steel Inorganic materials 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
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
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/08—Measuring arrangements characterised by the use of optical techniques for measuring diameters
- G01B11/12—Measuring arrangements characterised by the use of optical techniques for measuring diameters internal diameters
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/14—Measuring arrangements characterised by the use of optical techniques for measuring distance or clearance between spaced objects or spaced apertures
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method for detecting the appearance quality of a round hole punching net. The invention mainly comprises four steps: firstly, preprocessing a hole punching net image to be detected; then virtually setting two horizontal lines in a hole punching net image to be detected to intersect with a first row of holes, intersecting two vertical lines with a first column of holes, and gradually adjusting and determining the final positions of the four lines; thirdly, virtual upper transverse lines, lower transverse lines, left vertical lines and right vertical lines are set in batches by using priori knowledge, and intersection points of all round holes and all virtual lines are obtained; finally, judging the appearance defect of the round hole punching net and calculating the center coordinates of all round holes, the radius of the round holes, the hole spacing and other parameters. The invention has the advantages of strong universality, suitability for appearance detection and parameter determination of various round hole punching nets, high detection speed and high precision.
Description
Technical Field
The invention relates to a technology for detecting appearance quality of a round hole punching net, in particular to a method for detecting round hole parameters and appearance defects in the round hole punching net.
Background
The round hole punching net is formed by using a metal plate as a raw material, and punching a plurality of round holes with the same radius, equal horizontal spacing and equal vertical spacing on the metal plate by a punching machine, wherein the round holes are regularly distributed. The round hole punching net usually takes galvanized steel plates, stainless steel plates, copper plates, aluminum plates, nickel plates and alloy plates as raw materials, and has the advantages of bending resistance, aging resistance, difficult rust, flat and smooth net surface, firmness, durability and the like. The product is mainly applied to various industries such as chemical machinery, pharmaceutical equipment, food and beverage machinery, cigarette machinery, harvesters, dry cleaners, ironing tables, silencing equipment, refrigerating equipment (central air conditioning) loudspeaker boxes, artware manufacturing, papermaking, hydraulic fittings, pharmaceutical equipment, filtering equipment and the like.
Due to the complexity of the round hole punching net structure and the precision limitation of the mechanical control system, various defects of the round hole punching net inevitably occur. The appearance defects of the round hole punching net mainly comprise uneven thickness distribution of the round hole punching net, nonstandard parameters such as punching hole diameter, transverse hole distance, longitudinal hole distance and the like, incomplete edges of the punching ring and the like. The surface characteristics of the product are reflected by important performance indexes, and the possible defects cause serious safety problems in subsequent use, so that the method has important practical significance for online detection of the surface appearance of the product.
The punching process is the main process in the manufacturing process of the round hole punching net. The punching aperture, the transverse pitch and the longitudinal pitch are key technical indexes. In the stamping process, defects such as uneven blind hole distance, connecting holes and the like appear due to various reasons. This will have a great impact on the performance and quality of the product. Currently, parameter measurement and defect detection of round hole punching networks are heavily dependent on manual sampling. This will have a number of negative effects and inconveniences on production. First, more labor is required and labor intensity is high. Secondly, whether each product has defects is very time-consuming to check, and the false detection rate and the omission rate are higher. In recent years, with the rapid development of machine vision technology, a detection method based on machine vision has been well developed and applied in the field of surface defect detection. The method is characterized in that Hough transformation and a least square method are widely adopted in circle parameter detection to obtain information such as the radius, the circle center and the like of each circle (namely punching) in an image, on the basis, parameters such as the transverse hole distance and the longitudinal hole distance between punching are calculated one by one, and because of the fact that the circles and the edge points of the circles are numerous, all circles in the image are analyzed, the calculated amount is large, the time consumption is long, and the requirement of monitoring instantaneity is difficult to meet. In the method of subtracting the standard template from the image to be measured by adopting the customized template, the standard template cannot be obtained in practice because of the unavoidable deviation within the tolerance allowable range in the mechanical stamping process, and a certain difficulty is brought to the implementation of the method.
Disclosure of Invention
Aiming at the problems, the invention provides an automatic detection method for appearance defects of a round hole punching net, which utilizes four lines (two transverse lines and two vertical lines) to obtain eight edge points on each circle, and calculates the center coordinates of the round holes, the radius thereof, the hole spacing and other parameters by using a small number of intersection points. The method can replace manual spot check, realize high-speed and high-precision quality detection of the round hole punching plate, and enable the round hole punching net to meet the appearance qualification standard. The invention obtains the hole punching net region image by a high-precision industrial CCD camera, and the specific contents are as follows:
s100, preprocessing a hole punching net image with the size of (m, n);
s200, virtually setting an initial transverse line H 11 、H 21 And vertical line Z 11 、Z 21 Gradually adjusting the initial virtual line position and obtaining the final intersection point of the round holes and the virtual lines in the round hole punching net image;
s300, setting virtual upper transverse lines H in batches 1p Lower transverse line H 2p Left vertical line Z 1q And right vertical line Z 2q And obtaining round holes and batch setting virtual lines H in the round hole punching net image 1p 、H 2p 、Z 1q 、Z 2q Wherein p is the p-th row circle in the hole punching net image, q is the q-th column circle in the hole punching net image, H 1p Represents the upper horizontal line of the p row, H 2p Represents the p-th row lower transverse line, Z 1q Represents the left vertical line of the q-th column, Z 2q Represents the right vertical line of the q-th column;
s400, judging appearance defects of the round holes, and calculating the circle center coordinates, the radius, the transverse hole distance, the longitudinal hole distance and other dimensional parameters of each round hole by using a small number of intersection points. The invention has the following advantages:
1. the invention has strong universality and is suitable for appearance detection of various round hole punching nets;
2. the invention is not limited to the independent detection of each circle, but calculates the radius of each round hole, the circle center thereof, the distance between the round holes and other parameters by using a small number of points on the round holes, and the invention is applicable even if the machining has tolerance within the allowable range, and has high speed and high precision.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is an explanatory diagram of hole punching mesh spacing;
FIG. 3 is a cross hole pitch illustration of a round hole punch screen;
FIG. 4 is a longitudinal pitch illustration of a round hole punch screen;
FIG. 5 is an illustration of the left width of a round hole punch screen;
FIG. 6 is an illustration of the right side width of a round hole punch screen;
FIG. 7 is an initial landscape-portrait positioning chart;
FIG. 8 is a diagram of virtual horizontal and vertical lines intersecting circles;
fig. 9 is a graph of virtual horizontal and vertical lines intersecting circles.
Detailed Description
The invention is described by taking the quality detection of a round hole punching net produced by Haohui precision instruments limited company as an example. The round hole punching net is mainly applied to equipment such as dry cleaning machines, ironing tables, silencing equipment, sound boxes and the like; the appearance detection mainly comprises parameters (radius, circle center and the like) of each round hole, transverse hole distance, longitudinal hole distance and the like; before the detection starts, the model CX161 of the round hole punching net to be detected and related prior parameters thereof are input, wherein the model CX161 comprises the total width d 6 = 160.003mm, right side width d 4 11.171mm, left side width d 5 24.099mm, transverse pitch d 2 2.597mm, longitudinal pitch d 3 =1.493 mm, pore diameter d 1 =1.965 mm, as shown in fig. 2, 3, 4, 5, 6.
And converting the parameters in the world coordinate system into an image coordinate system, wherein the aim of calibration is to determine the quantitative corresponding relation between the actual size of the measured object and the number of pixels in the image acquired by the camera so as to correspond the image distance to the actual distance of the measured object, thereby realizing the actual test requirement of the parameters. When the method is implemented, the standard component imaging method is adopted to calibrate the transformation of the coordinate system. The specific calibration process is as follows:
(1) placing the calibration plate on a measuring system object stage in a horizontal manner with the accuracy of 1um by 5.6mm, and ensuring that the edges of the calibration plate are parallel to the coordinate axes of the camera imaging screen;
(2) collecting an image of a calibration plate, identifying left and right marking circles on the calibration plate, and obtaining pixel values between the left and right marking circles and the left and right marking circle centers by using the upper and lower marking circles;
(3) the actual distance of the upper, lower, left and right marking circles is divided by the pixel value between the two to obtain the pixel equivalent under the condition of fixed focal length and fixed object distance. To improve the detection accuracy, the pixel equivalent is reserved by 12 bits, the equivalent in the X-axis pixel direction of the camera is 0.003826796100mm, and the pixel equivalent in the Y-axis direction is 0.003827779593mm.
According to the transformation relation between the world coordinate system and the image coordinate system, converting the parameters under the world coordinate system into the image coordinate system to obtain the total width d 6 ' right side width d 5 ' left side width d 4 ' transverse pitch d 2 ' longitudinal pitch d 3 ' aperture d 1 ′。
The round hole punching net is horizontally arranged on the belt conveyer belt and enters the detection workstation from left to right at a fixed speed. In the detection workstation, a high-precision industrial CCD camera is vertically downward, and a top annular light source is adopted for illumination to obtain a hole punching net image. With reference to fig. 2, the specific implementation steps of the present invention are as follows:
s100, preprocessing a hole punching net image with the size of (m, n):
s110, filtering noise by using median filtering, acquiring a threshold value by using an Otsu algorithm, and performing binarization processing on the image.
S200, virtually setting initial transverse lines and vertical lines in a round hole punching net image, gradually adjusting initial virtual line positions and obtaining final intersecting points of round holes and virtual lines in the round hole punching net image:
s210, virtually setting two horizontal lines and two vertical lines in an image, and respectively recordingIs an upper transverse line H 11 And a lower transverse line H 21 Left vertical line Z 11 And right vertical line Z 21, wherein ,H11 and H21 Intersecting with the first row circle, Z 11 and Z21 Intersecting the first row of circles, an upper transverse line H 11 Is yy 01 Lower transverse line H 21 Is yy 11 Left vertical line Z 11 Is xx 01 Right vertical line Z 21 Is xx 11 As shown in fig. 7;
s220. let t=1, k=1, g=0, h=0, e=0, yy for the ordinate 01 Upper transverse line H of (2) 11 Execute S230 to determine the final position yy 01last ;
S230, searching a horizontal line with the y-axis in the image from left to right, and acquiring a pixel coordinate point where the horizontal line intersects with a circle:
f 1 =I(i+1,yy)-I(i,yy) i∈[1,m) (1)
wherein I (I, yy) is a pixel value of the image at the position (I, yy), p is a p-th row circle in the hole punching net image, and q is a q-th column circle in the hole punching net image; h t (x tpq ) Satisfy f for horizontal line 1 >The abscissa value of row q at 0; h t (y tpq ) Satisfy f for horizontal line 1 >The ordinate value of row q at 0; c (C) k (x kpq ) Satisfy f for horizontal line 1 <The abscissa value of row q at 0; c (C) k (y kpq ) Satisfy f for horizontal line 1 <The ordinate value of row q at 0;
if h=0 and g=0, S231 is performed;
if h=0 and g=1, g=g+1, S231 is performed;
if h=0 and g=3, S231 is performed;
if h=1, execute S322;
if h=2, S323 is executed;
s231 calculating H t -C k The average value of (2), namely:wherein N is the number of the rows of circles;
if g=0, then step S232 is performed;
if g=2, then step S233 is performed;
if g=3, then step S234 is performed;
s232. g=g+1, yy=yy+1, if g=1, then S230 is performed, otherwise S233 is performed;
S233.c t =b t2 -b t0 ,g=g+1,b t3 =b t2 ;
s234. if t=1 and c t >0 indicates that the horizontal line is in the upper half of the p-th row circle, the following operations are performed:
if t=1 and c t <0, yy 01 =yy 01 -10, performing S220;
if t=2 and c t <0 indicates that the horizontal line is in the lower half of the p-th row circle, then the following operations are performed:
if t=2 and c t >0, yy 11 =yy 11 +10, executing S240;
if t=1 and k=1, yy 01last =yy last The method comprises the steps of carrying out a first treatment on the surface of the If t=2 and k=2, yy 11last =yy last ;
If t=2 and k=2, then S250 is performed, otherwise S240 is performed;
s240. let t=2, k=2, g=0, h=0, e=0, yy for the ordinate 11 Lower transverse line H of (2) 21 Execute S230 to determine the final position yy 11last ;
S250. let t=3, k=3, g=0, h=0, e=0, xx for the abscissa 01 Left vertical line Z of (2) 11 Execution S260 determines its final position xx 01last ;
S260, searching from top to bottom for a vertical line with an abscissa xx in the image, and acquiring a pixel coordinate point where the vertical line intersects with a circle:
f 2 =I(xx,j+1)-I(xx,j) j∈[1,n) (3)
wherein I (xx, j) is a pixel value of an image at a position (xx, j), p is a p-th row circle in the hole punching net image, and q is a q-th column circle in the hole punching net image; h t (x tpq ) Satisfy f for vertical line 2 >The abscissa value of row q at 0; h t (y tpq ) Satisfy f for vertical line 2 >The ordinate value of row q at 0; c (C) k (x kpq ) Satisfy f for vertical line 2 <The abscissa value of row q at 0; c (C) k (y kpq ) Satisfy f for vertical line 2 <The ordinate value of row q at 0;
if h=0 and g=0, S261 is executed;
if h=0 and g=1, g=g+1, S261 is performed;
if h=0 and g=3, S261 is performed;
if h=1, S324 is performed;
if h=2, S400 is performed;
s261, calculating H t -C k The average value of (2), namely:where M is the number of circles in the column,
if g=0, then step S262 is performed;
if g=2; step S263 is performed;
if g=3, then step S264 is performed;
s262.g=g+1, xx=xx+1, if g=1, S260 is performed, otherwise S263 is performed;
S263.c t =b t2 -b t0 ,g=g+1,b t3 =b t2 ;
s264. if t=3 and c t >0 indicates that the horizontal line is in the left half of the q-th column circle, the following operations are performed:
if t=3 and c t <0, xx 01 =xx 01 -10, performing S250;
if t=4 and c t <0 indicates that the horizontal line is in the right half of the q-th column circle, then the following is performed:
if t=4 and c t >0, xx 11 =xx 11 +10, execution S270;
if t=3 and k=3, xx 01last =xx last The method comprises the steps of carrying out a first treatment on the surface of the If t=4 and k=4, xx 11last =xx last ;
If t=4 and k=4, then S300 is performed, otherwise S270 is performed;
s270. let t=4, k=4, g=0, h=0, e=0, xx for the abscissa 11 Right vertical line Z of (2) 21 Execution S260 determines its final position xx 11last 。
S300, setting virtual upper transverse lines H in batches 1p Lower transverse line H 2p Left vertical line Z 1q And right vertical line Z 2q And obtain round hole punchVirtual line H is set for round holes and batches in hole network image 1p 、H 2p 、Z 1q 、Z 2q Wherein p is the p-th row circle in the hole punching net image, q is the q-th column circle in the hole punching net image, H 1p Represents the upper horizontal line of the p row, H 2p Represents the p-th row lower transverse line, Z 1q Represents the left vertical line of the q-th column, Z 2q The right vertical line of the q-th column is shown in fig. 8, and the specific method is as follows:
s310 upper transverse line H 11 To finally determine yy 01last For the start ordinate, every interval d 3 ' set virtual upper horizontal lines in batch, namely:
yy 0p =yy 01last +(p-1)*d′ 3 ; (5)
lower transverse line H 21 To finally determine yy 11last For the start ordinate, every interval d 3 ' virtual lower horizontal lines are set in batch, namely:
yy 1p =yy 11last +(p-1)*d′ 3 ; (6)
left vertical line Z 11 To finally determine xx 01last For starting abscissa, every interval d 2 ' batch setting virtual left vertical lines, namely:
xx 0q =xx 01last +(q-1)*d′ 2 ; (7)
right vertical line Z 21 To finally determine xx 11last For starting abscissa, every interval d 2 ' batch setting of virtual right vertical lines, namely:
xx 1q =xx 11last +(q-1)*d′ 2 ; (8)
wherein p is the p-th row circle in the hole punching net image, and q is the q-th column circle in the hole punching net image;
s320, calculating virtual lines H set in batches 1p 、H 2p 、Z 1q 、Z 2q The specific method of the intersection point with the round hole in the round hole punching net image is as follows:
s321, for any upper transverse line H 1p Let t=1, k=1, yy=yy 0p H=1, executing S230, and obtaining the hole punching pattern and the round hole in the round hole punching net imageIntersection point H 1 (x 1pq ,y 1pq )、C 1 (x 1pq ,y 1pq );
S322 for any lower transverse line H 2p Let t=2, k=2, yy=yy 1p H=2, executing S230, and obtaining the intersection point H of the hole punching screen image and the round hole in the round hole punching screen image 2 (x 2pq ,y 2pq )、C 2 (x 2pq ,y 2pq );
S323 for any left vertical line Z 1q Let t=3, k=3, xx=xx 0q H=1, executing S260, and obtaining the intersection point H of the hole punched net image and the round hole 3 (x 3pq ,y 3pq )、C 3 (x 3pq ,y 3pq );
S324 for any right vertical line Z 2q Let t=4, k=4, xx=xx 1q H=2, executing S260, and obtaining the intersection point H of the hole punching screen image and the round hole in the round hole punching screen image 4 (x 4pq ,y 4pq )、C 4 (x 4pq ,y 4pq )。
S400, judging appearance defects of the round holes, and calculating the circle center coordinates, the radius, the transverse hole distance, the longitudinal hole distance and other dimensional parameters of each round hole by using a small number of intersection points:
s410, calculating a coordinate difference value, wherein the specific operation is as follows:
u 1 =H 1 (x 1pq )-H 1 (x 1p(q-1) );v 1 =H 3 (y 3pq )-H 3 (y 3(p-1)q ); (9)
u 2 =C 1 (x 1pq )-C 1 (x 1p(q-1) );v 2 =C 3 (y 3pq )-C 3 (y 3(p-1)q ); (10)
u 3 =H 2 (x 2pq )-H 2 (x 2p(q-1) );v 3 =H 4 (y 4pq )-H 4 (y 4(p-1)q ); (11)
u 4 =C 2 (x 2pq )-C 2 (x 2p(q-1) );v 4 =C 4 (y 4pq )-C 4 (y 4(p-1)q ); (12)
u 5 =H 1 (x 1pq )-C 1 (x 1p(q-1) );v 5 =H 3 (y 3pq )-C 3 (y 3(p-1)q );(13)
u 6 =H 2 (x 2pq )-C 2 (x 2p(q-1) );v 6 =H 4 (y 4pq )-C 4 (y 4(p-1)q ); (14)
s420, judging appearance defects of the round hole, wherein the specific operation is as follows:
setting a threshold t=15, performing the following operations:
u′ 1 =u 1 (w 1 +1)-u 1 (w 1 );v′ 1 =v 1 (s 1 +1)-v 1 (s 1 ); (15)
u′ 2 =u 2 (w 1 +1)-u 1 (w 1 );v′ 2 =v 2 (s 1 +1)-v 2 (s 1 ); (16)
u′ 3 =u 3 (w 1 +1)-u 3 (w 1 );v′ 3 =v 3 (s 1 +1)-v 3 (s 1 ); (17)
u′ 4 =u 4 (w 1 +1)-u 4 (w 1 );v′ 4 =v 4 (s 1 +1)-v 4 (s 1 ); (18)
u′ 5 =u 5 (w 2 +1)-u 5 (w 2 );v′ 5 =v 5 (s 2 +1)-v 5 (s 2 ); (19)
u′ 6 =u 6 (w 2 +1)-u 6 (w 2 );v′ 6 =v 6 (s 2 +1)-v 6 (s 2 ); (20)
wherein ,w1 ∈[1,max(q)-1),w 2 ∈[1,max(q)-2),s 1 ∈[1,max(p)-1),s 2 E [1, max (p) -2); p is a hole punching net pictureThe p-th row circle in the image, q is the q-th column circle in the hole punching net image;
s430, calculating a circle center coordinate and a radius, wherein the specific operation is as follows:
at H 1 、H 2 、H 3 、H 4 、C 1 、C 2 、C 3 、C 4 Three points H are selected from eight points 3 (x 3pq ,y 3pq )、H 4 (x 4pq ,y 4pq )、C 1 (x 1pq ,y 1pq );
Let A (x) 0 ,y 0 )=H 3 (x 3pq ,y 3pq )、B(x 1 ,y 1 )=H 4 (x 4pq ,y 4pq )、C(x 2 ,y 2 )=C 1 (x 1pq ,y 1pq )
The center of circle is marked as (x) c ,y c ) The radius is r, the diameter is equal to r,
wherein ,
s440, calculating the transverse hole distance and the longitudinal hole distance,
the (p, q) is the p-th row and q-th column circle in the hole punching net image, namely the q-th circle from left to right on the p-th row or the p-th circle from top to bottom on the q-th column;
s450, converting parameters calculated under the image coordinate system into the world coordinate system according to the calibrated transformation relation between the world coordinate system and the image coordinate system, and obtaining the dimensional parameters such as the center coordinates, the radius, the transverse hole pitch, the longitudinal hole pitch and the like of all the round holes in the round hole punching net image under the world coordinate system;
s460, comparing the circle center coordinates, the radius, the transverse hole distance and the longitudinal hole distance of each round hole in the round hole punching net image under the world coordinate system with the circle center coordinates, the radius, the transverse hole distance and the longitudinal hole distance of factory standards, and detecting whether the round hole meets the standards.
Claims (1)
1. A method for detecting the appearance quality of a round hole punching net at least comprises the following steps:
s100, preprocessing a hole punching net image with the size of (m, n);
s200, virtually setting an initial transverse line H 11 、H 21 And vertical line Z 11 、Z 21 Gradually adjusting the initial virtual line position and obtaining the final intersection point of the round holes and the virtual line in the round hole punching net image, wherein the step S200 further comprises the steps S210-S270:
s210, virtually arranging two horizontal lines and two vertical lines in the image, respectively marked as upper transverse lines H 11 And a lower transverse line H 21 Left vertical line Z 11 And right vertical line Z 21, wherein ,H11 and H21 And the first line circleIntersection, Z 11 and Z21 Intersecting the first row of circles, an upper transverse line H 11 Is yy 01 Lower transverse line H 21 Is yy 11 Left vertical line Z 11 Is xx 01 Right vertical line Z 21 Is xx 11 ;
S220. let t=1, k=1, g=0, h=0, e=0, yy for the ordinate 01 Upper transverse line H of (2) 11 Execute S230 to determine the final position yy 01last ;
S230, searching a horizontal line with the y-axis in the image from left to right, and acquiring a pixel coordinate point where the horizontal line intersects with a circle:
f 1 =I(i+1,yy)-I(i,yy) i∈[1,m) (1)
wherein I (I, yy) is a pixel value of the image at the position (I, yy), p is a p-th row circle in the hole punching net image, and q is a q-th column circle in the hole punching net image; h t (x tpq ) Satisfy f for horizontal line 1 >The abscissa value of row q at 0; h t (y tpq ) Satisfy f for horizontal line 1 >The ordinate value of row q at 0; c (C) k (x kpq ) Satisfy f for horizontal line 1 <The abscissa value of row q at 0; c (C) k (y kpq ) Satisfy f for horizontal line 1 <The ordinate value of row q at 0;
if h=0 and g=0, S231 is performed;
if h=0 and g=1, g=g+1, S231 is performed;
if h=0 and g=3, S231 is performed;
if h=1, execute S322;
if h=2, S323 is executed;
s231 calculating H t -C k The average value of (2), namely:where N is the number of such rows of circles,
if g=0, then step S232 is performed;
if g=2, then step S233 is performed;
if g=3, then step S234 is performed;
s232. g=g+1, yy=yy+1, if g=1, then S230 is performed, otherwise S233 is performed;
S233.c t =b t2 -b t0 ,g=g+1,b t3 =b t2 ;
s234. if t=1 and c t >0 indicates that the horizontal line is in the upper half of the p-th row circle, the following operations are performed:
if t=1 and c t <0, yy 01 =yy 01 -10, performing S220;
if t=2 and c t <0 indicates that the horizontal line is in the lower half of the p-th row circle, then the following operations are performed:
if t=2 and c t >0, yy 11 =yy 11 +10, executing S240;
if t=1 and k=1, yy 01last =yy last The method comprises the steps of carrying out a first treatment on the surface of the If t=2 and k=2, yy 11last =yy last ;
If t=2 and k=2, then S250 is performed, otherwise S240 is performed;
s240. let t=2, k=2, g=0, h=0, e=0, yy for the ordinate 11 Lower transverse line H of (2) 21 Execute S230 to determine the final position yy 11last ;
S250. let t=3, k=3, g=0, h=0, e=0, xx for the abscissa 01 Left vertical line Z of (2) 11 Execution S260 determines its final position xx 01last ;
S260, searching from top to bottom for a vertical line with an abscissa xx in the image, and acquiring a pixel coordinate point where the vertical line intersects with a circle:
f 2 =I(xx,j+1)-I(xx,j) j∈[1,n) (3)
wherein I (xx, j) is a pixel value of an image at a position (xx, j), p is a p-th row circle in the hole punching net image, and q is a q-th column circle in the hole punching net image; h t (x tpq ) Satisfy f for vertical line 2 >The abscissa value of row q at 0; h t (y tpq ) Satisfy f for vertical line 2 >The ordinate value of row q at 0; c (C) k (x kpq ) Satisfy f for vertical line 2 <The abscissa value of row q at 0; c (C) k (y kpq ) Satisfy f for vertical line 2 <The ordinate value of row q at 0;
if h=0 and g=0, S261 is executed;
if h=0 and g=1, g=g+1, S261 is performed;
if h=0 and g=3, S261 is performed;
if h=1, S324 is performed;
if h=2, S400 is performed;
s261, calculating H t -C k The average value of (2), namely:where M is the number of circles in the column,
if g=0, then step S262 is performed;
if g=2, then step S263 is performed;
if g=3, then step S264 is performed;
s262.g=g+1, xx=xx+1, if g=1, S260 is performed, otherwise S263 is performed;
S263.c t =b t2 -b t0 ,g=g+1,b t3 =b t2 ;
s264. if t=3 and c t >0 indicates that the horizontal line is in the left half of the q-th column circle, the following operations are performed:
if t=3 and c t <0, xx 01 =xx 01 -10, performing S250;
if t=4 and c t <0 indicates that the horizontal line is in the right half of the q-th column circle, then the following is performed:
if t=4 and c t >0, xx 11 =xx 11 +10, execution S270;
if t=3 and k=3, xx 01last =xx last The method comprises the steps of carrying out a first treatment on the surface of the If t=4 and k=4, xx 11last =xx last ;
If t=4 and k=4, then S300 is performed, otherwise S270 is performed;
s270. let t=4, k=4, g=0, h=0, e=0, xx for the abscissa 11 Right vertical line Z of (2) 21 Execution S260 determines its final position xx 11last ;
S300, setting virtual upper transverse lines H in batches 1p Lower transverse line H 2p Left vertical line Z 1q And right sideVertical line Z 2q And obtaining round holes and batch setting virtual lines H in the round hole punching net image 1p 、H 2p 、Z 1q 、Z 2q Wherein p is the p-th row circle in the hole punching net image, q is the q-th column circle in the hole punching net image, H 1p Represents the upper horizontal line of the p row, H 2p Represents the p-th row lower transverse line, Z 1q Represents the left vertical line of the q-th column, Z 2q Representing the q-th column right vertical line, S300 further includes steps S310-S324:
s310 upper transverse line H 11 To finally determine yy 01last For the start ordinate, every interval d 3 ' set virtual upper horizontal lines in batch, namely:
yy 0p =yy 01last +(p-1)*d′ 3 ; (5)
lower transverse line H 21 To finally determine yy 11last For the start ordinate, every interval d 3 ' virtual lower horizontal lines are set in batch, namely:
yy 1p =yy 11last +(p-1)*d′ 3 ; (6)
left vertical line Z 11 To finally determine xx 01last For starting abscissa, every interval d 2 ' batch setting virtual left vertical lines, namely:
xx 0q =xx 01last +(q-1)*d′ 2 ; (7)
right vertical line Z 21 To finally determine xx 11last For starting abscissa, every interval d 2 ' batch setting of virtual right vertical lines, namely:
xx 1q =xx 11last +(q-1)*d′ 2 ; (8)
wherein p is the p-th row circle in the hole punching net image, and q is the q-th column circle in the hole punching net image;
s320, calculating virtual lines H set in batches 1p 、H 2p 、Z 1q 、Z 2q The specific method of the intersection point with the round hole in the round hole punching net image is as follows:
s321, for any upper transverse line H 1p Let t=1, k=1, yy=yy 0p H=1, executing S230, and obtaining an image of the hole punching net and the hole punching netIntersection point H of middle round hole 1 (x 1pq ,y 1pq )、C 1 (x 1pq ,y 1pq );
S322 for any lower transverse line H 2p Let t=2, k=2, yy=yy 1p H=2, executing S230, and obtaining the intersection point H of the hole punching screen image and the round hole in the round hole punching screen image 2 (x 2pq ,y 2pq )、C 2 (x 2pq ,y 2pq );
S323 for any left vertical line Z 1q Let t=3, k=3, xx=xx 0q H=1, executing S260, and obtaining the intersection point H of the hole punched net image and the round hole 3 (x 3pq ,y 3pq )、C 3 (x 3pq ,y 3pq );
S324 for any right vertical line Z 2q Let t=4, k=4, xx=xx 1q H=2, executing S260, and obtaining the intersection point H of the hole punching screen image and the round hole in the round hole punching screen image 4 (x 4pq ,y 4pq )、C 4 (x 4pq ,y 4pq );
S400, judging appearance defects of the round holes, calculating the circle center coordinates, the radius, the transverse hole distance, the longitudinal hole distance and other dimensional parameters of each round hole by using a small number of intersection points, wherein the S400 further comprises the steps of S410-S460:
s410, calculating a coordinate difference value,
u 1 =H 1 (x 1pq )-H 1 (x 1p(q-1) );v 1 =H 3 (y 3pq )-H 3 (y 3(p-1)q ); (9)
u 2 =C 1 (x 1pq )-C 1 (x 1p(q-1) );v 2 =C 3 (y 3pq )-C 3 (y 3(p-1)q ); (10)
u 3 =H 2 (x 2pq )-H 2 (x 2p(q-1) );v 3 =H 4 (y 4pq )-H 4 (y 4(p-1)q ); (11)
u 4 =C 2 (x 2pq )-C 2 (x 2p(q-1) );v 4 =C 4 (y 4pq )-C 4 (y 4(p-1)q ); (12)
u 5 =H 1 (x 1pq )-C 1 (x 1p(q-1) );v 5 =H 3 (y 3pq )-C 3 (y 3(p-1)q ); (13)
u 6 =H 2 (x 2pq )-C 2 (x 2p(q-1) );v 6 =H 4 (y 4pq )-C 4 (y 4(p-1)q ); (14)
s420, judging the defect of the round hole,
u′ 1 =u 1 (w 1 +1)-u 1 (w 1 );v′ 1 =v 1 (s 1 +1)-v 1 (s 1 ); (15)
u′ 2 =u 2 (w 1 +1)-u 1 (w 1 );v′ 2 =v 2 (s 1 +1)-v 2 (s 1 ); (16)
u′ 3 =u 3 (w 1 +1)-u 3 (w 1 );v′ 3 =v 3 (s 1 +1)-v 3 (s 1 ); (17)
u′ 4 =u 4 (w 1 +1)-u 4 (w 1 );v′ 4 =v 4 (s 1 +1)-v 4 (s 1 ); (18)
u′ 5 =u 5 (w 2 +1)-u 5 (w 2 );v′ 5 =v 5 (s 2 +1)-v 5 (s 2 ); (19)
u′ 6 =u 6 (w 2 +1)-u 6 (w 2 );v′ 6 =v 6 (s 2 +1)-v 6 (s 2 ); (20)
wherein ,w1 ∈[1,max(q)-1),w 2 ∈[1,max(q)-2),s 1 ∈[1,max(p)-1),s 2 E [1, max (p) -2), p is the p-th row circle in the hole punching net image, and q is the q-th column circle in the hole punching net image;
s430, calculating the center coordinates and the radius,
at H 1 、H 2 、H 3 、H 4 、C 1 、C 2 、C 3 、C 4 Three points H are selected from eight points 3 (x 3pq ,y 3pq )、H 4 (x 4pq ,y 4pq )、C 1 (x 1pq ,y 1pq );
Let A (x) 0 ,y 0 )=H 3 (x 3pq ,y 3pq )、B(x 1 ,y 1 )=H 4 (x 4pq ,y 4pq )、C(x 2 ,y 2 )=C 1 (x 1pq ,y 1pq )
The center of circle is marked as (x) c ,y c ) The radius is r, the diameter is equal to r,
wherein ,
s440, calculating the transverse hole distance and the longitudinal hole distance,
the (p, q) is the p-th row and q-th column circle in the hole punching net image, namely the q-th circle from left to right on the p-th row or the p-th circle from top to bottom on the q-th column;
s450, converting parameters calculated under the image coordinate system into the world coordinate system according to the calibrated transformation relation between the world coordinate system and the image coordinate system, and obtaining the dimensional parameters such as the center coordinates, the radius, the transverse hole pitch, the longitudinal hole pitch and the like of all the round holes in the round hole punching net image under the world coordinate system;
s460, comparing the circle center coordinates, the radius, the transverse hole distance and the longitudinal hole distance of each round hole in the round hole punching net image under the world coordinate system with the circle center coordinates, the radius, the transverse hole distance and the longitudinal hole distance of factory standards, and detecting whether the round hole meets the standards.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010419366.8A CN111551552B (en) | 2020-05-18 | 2020-05-18 | Appearance quality detection method for round hole punching net |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010419366.8A CN111551552B (en) | 2020-05-18 | 2020-05-18 | Appearance quality detection method for round hole punching net |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111551552A CN111551552A (en) | 2020-08-18 |
CN111551552B true CN111551552B (en) | 2023-06-13 |
Family
ID=72002001
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010419366.8A Active CN111551552B (en) | 2020-05-18 | 2020-05-18 | Appearance quality detection method for round hole punching net |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111551552B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008015029A (en) * | 2006-07-03 | 2008-01-24 | Sharp Corp | Display device |
CN104122265A (en) * | 2013-04-28 | 2014-10-29 | 郑州大学 | Method and system for checking screw hole thread missing of metal plate |
CN104457577A (en) * | 2014-12-19 | 2015-03-25 | 上海工业自动化仪表研究院 | Machine-vision-oriented non-contact type workpiece positioning and measuring method |
CN106623493A (en) * | 2016-12-31 | 2017-05-10 | 湖南文理学院 | Detection method for continuous punching of steel band |
CN107797517A (en) * | 2017-09-30 | 2018-03-13 | 湖南文理学院 | The method and system detected using realizing of Robot Vision steel band punching processing |
CN107907063A (en) * | 2017-11-14 | 2018-04-13 | 湖南文理学院 | A kind of the steel band punching processing detecting system and method for view-based access control model measurement |
CN109990711A (en) * | 2019-04-25 | 2019-07-09 | 湘潭大学 | A kind of appearance quality detection method of punched nickel-plated steel band |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010135642A (en) * | 2008-12-05 | 2010-06-17 | Tokyo Electron Ltd | Substrate inspection method and storage medium |
-
2020
- 2020-05-18 CN CN202010419366.8A patent/CN111551552B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008015029A (en) * | 2006-07-03 | 2008-01-24 | Sharp Corp | Display device |
CN104122265A (en) * | 2013-04-28 | 2014-10-29 | 郑州大学 | Method and system for checking screw hole thread missing of metal plate |
CN104457577A (en) * | 2014-12-19 | 2015-03-25 | 上海工业自动化仪表研究院 | Machine-vision-oriented non-contact type workpiece positioning and measuring method |
CN106623493A (en) * | 2016-12-31 | 2017-05-10 | 湖南文理学院 | Detection method for continuous punching of steel band |
CN107797517A (en) * | 2017-09-30 | 2018-03-13 | 湖南文理学院 | The method and system detected using realizing of Robot Vision steel band punching processing |
CN107907063A (en) * | 2017-11-14 | 2018-04-13 | 湖南文理学院 | A kind of the steel band punching processing detecting system and method for view-based access control model measurement |
CN109990711A (en) * | 2019-04-25 | 2019-07-09 | 湘潭大学 | A kind of appearance quality detection method of punched nickel-plated steel band |
Non-Patent Citations (2)
Title |
---|
基于亚像素边缘检测的高精度圆孔参数测量方法研究;钱斌等;《上海航天》;20171225(第06期);全文 * |
基于极坐标计盒维数的圆形通孔缺陷检测;周强等;《陕西科技大学学报(自然科学版)》;20170225(第01期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN111551552A (en) | 2020-08-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107657603B (en) | Industrial appearance detection method based on intelligent vision | |
CN111537517B (en) | Unmanned intelligent stamping defect identification method | |
US9582872B2 (en) | Optical film defect detection method and system thereof | |
CN107607554A (en) | A kind of Defect Detection and sorting technique of the zinc-plated stamping parts based on full convolutional neural networks | |
CN115294113B (en) | Quality detection method for wood veneer | |
CN109990711B (en) | Appearance quality detection method for punched nickel-plated steel strip | |
CN107063099A (en) | A kind of machinery manufacturing industry online quality monitoring method of view-based access control model system | |
CN116188475B (en) | Intelligent control method, system and medium for automatic optical detection of appearance defects | |
CN113793337B (en) | Locomotive accessory surface abnormal degree evaluation method based on artificial intelligence | |
CN115797354B (en) | Method for detecting appearance defects of laser welding seam | |
CN115018827B (en) | Automatic detection method for quality of building material weld joint | |
CN115345876B (en) | Bolt thread defect detection method based on ultrasonic image | |
CN111161237A (en) | Fruit and vegetable surface quality detection method, storage medium and sorting device thereof | |
CN114706358A (en) | Method and system for processing welding process information of straight welded pipe | |
IL263097B2 (en) | Optimizing a set-up stage in an automatic visual inspection process | |
CN115797361B (en) | Aluminum template surface defect detection method | |
CN115272305B (en) | Button hole defect detection method | |
CN115294109A (en) | Real wood board production defect identification system based on artificial intelligence, and electronic equipment | |
CN114187267B (en) | Stamping part defect detection method based on machine vision | |
CN112683166B (en) | Die-cutting product size detection method | |
CN110935646A (en) | Full-automatic crab grading system based on image recognition | |
CN117085969B (en) | Artificial intelligence industrial vision detection method, device, equipment and storage medium | |
CN111551552B (en) | Appearance quality detection method for round hole punching net | |
CN117649404A (en) | Medicine packaging box quality detection method and system based on image data analysis | |
CN116542910A (en) | Stamping part round hole positioning and deformation detection method based on sub-pixel edge extraction |
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 |