CN117074433A - Spool PE film flaw off-line detection equipment based on penetrating light source and visual algorithm - Google Patents

Spool PE film flaw off-line detection equipment based on penetrating light source and visual algorithm Download PDF

Info

Publication number
CN117074433A
CN117074433A CN202311039854.6A CN202311039854A CN117074433A CN 117074433 A CN117074433 A CN 117074433A CN 202311039854 A CN202311039854 A CN 202311039854A CN 117074433 A CN117074433 A CN 117074433A
Authority
CN
China
Prior art keywords
light source
film
penetrating light
defects
detection device
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
Application number
CN202311039854.6A
Other languages
Chinese (zh)
Inventor
李伟超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Xunyi Technology Co ltd
Original Assignee
Shenzhen Xunyi Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Xunyi Technology Co ltd filed Critical Shenzhen Xunyi Technology Co ltd
Priority to CN202311039854.6A priority Critical patent/CN117074433A/en
Publication of CN117074433A publication Critical patent/CN117074433A/en
Pending legal-status Critical Current

Links

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
    • G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
    • G01N21/958—Inspecting transparent materials or objects, e.g. windscreens
    • 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
    • G01N21/01—Arrangements or apparatus for facilitating the optical investigation
    • 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
    • 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
    • G01N21/01—Arrangements or apparatus for facilitating the optical investigation
    • G01N2021/0106—General arrangement of respective parts
    • G01N2021/0112—Apparatus in one mechanical, optical or electronic block
    • 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
    • G01N2021/8883—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 involving the calculation of gauges, generating models

Landscapes

  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

The invention relates to the technical field of detection of flaws of reel transparent coiled materials, and discloses an offline detection device for flaws of reel PE (polyethylene) thin films based on a penetrating light source and a visual algorithm. The PE film clamping device A, the stepping motor or servo motor rotating platform B, the light source C, the plurality of camera systems D, the lens E, the rotating platform and system operation control system F, the display screen or the touch screen G, the mouse H, the keyboard I, the processor J, the starting button K, the pneumatic clamping device control system L, the pneumatic valve controller M, the dust removing device N, the distance moving device O, the stand P and the power switch knob Q are arranged in the equipment main body 111, so that the detection efficiency of defects such as PE protective film crystal points, foreign matters, black points, bubbles, scratches and dust points is improved, the labor cost is reduced, the detection accuracy is improved, PE films are graded in sections, and the factory benefit is improved.

Description

Spool PE film flaw off-line detection equipment based on penetrating light source and visual algorithm
Technical Field
The invention relates to the technical field of flaw detection of reel transparent coiled materials, in particular to offline detection equipment for flaws of reel PE (polyethylene) films based on a penetrating light source and a visual algorithm.
Background
The defect detection of the traditional scroll PE film (pet film) is to manually take an elongated lamp tube to plug into the center shaft of the scroll PE film, and detect defects such as crystal points, foreign matters, black points and bubbles by using eyes.
The online PE film detection device captures different types of defect images on the film by designing a light source and the position relation between the light source and a line scanning camera in front of a film reel, however, the detection mode is difficult to see clearly for the device which is not clear for the eyes, the detection precision is not high, and the reel film which is detected online and produced has several stages of storage, slitting and transportation, so that new defects can be caused, and the defect detection on the reel film is required.
Aiming at the defects in the prior art, the offline detection equipment for the defects of the scroll PE film based on the penetrating light source and the visual algorithm is provided, and is used for improving the detection efficiency of defects such as crystal points, foreign matters, black points, bubbles and the like of the PE protective film, reducing the labor cost, improving the detection accuracy, grading the PE film in sections and improving the factory benefit.
Disclosure of Invention
The invention aims to provide the offline detection equipment for the defects of the PE film on the reel based on the penetrating light source and the visual algorithm, so that the purposes of improving the detection efficiency of defects such as crystal points, foreign matters, black points and bubbles of the PE protective film, reducing the labor cost, improving the detection accuracy, grading the PE film in sections and improving the benefit of factories are achieved.
In order to achieve the above purpose, the present invention provides the following technical solutions: spool PE film flaw off-line measuring equipment based on penetrating light source and visual algorithm, including the equipment main part, and set up the removal subassembly of equipment bottom, the top of equipment main part is provided with the alarm lamp, the bottom fixed mounting of equipment main part has the foundation post, and every foundation post adaptation is a removal subassembly.
Preferably, the movable assembly comprises a connecting seat, a connecting bearing, a rotating shaft and an antifriction rotating shaft, wherein the connecting seat is fixedly arranged at the bottom of the equipment main body, the connecting bearing is contacted with the bottom of the connecting seat, and a side plate is fixedly arranged on the outer wall of the connecting bearing.
Preferably, the tail of the side plate is fixedly provided with a fixing seat, and the bottom end of the side plate is movably provided with a sliding wheel through an antifriction rotating shaft.
Preferably, the top of axis of rotation and the bottom fixed mounting of connecting seat, the bottom of axis of rotation is rotated with the curb plate through connecting bearing and is connected.
Preferably, the tail part of the fixing seat is movably provided with two groups of telescopic rods.
Preferably, the telescopic end part of the telescopic rod is movably provided with a buckling plate.
Preferably, a brake arc block is fixedly arranged on the inner side of the buckling plate.
Preferably, one end of the brake arc block is movably arranged between the side plates through a pin shaft, and a certain distance is reserved between the inner side of the brake arc block and the outer wall of the sliding wheel.
The invention provides an offline detection device for flaws of a scroll PE film based on a penetrating light source and a visual algorithm. The beneficial effects are as follows:
(1) The invention is characterized in that the connecting bearing is arranged, the bottom end of the rotating shaft is rotationally connected with the side plate through the connecting bearing, so that the movable pulley can rotate towards any direction, the convenience of equipment movement is improved, by arranging the telescopic rod, a user presses the buckling plate downwards by feet or hands when braking is needed, the telescopic rod is driven to extend, the braking arc block is driven to prop against the surface of the movable pulley, the friction force between the movable pulley and the braking arc block is increased, the equipment can be prevented from being damaged due to easy sliding, otherwise, the telescopic rod is driven to shrink by upwards snapping the buckling plate, the braking arc block is driven to release the propping effect on the surface of the movable pulley, the sliding state is recovered, and the movable pulley can be reused.
(2) The PE film clamping device is characterized in that a clamping scroll PE film device A, a stepping motor or servo motor rotating platform B, a light source C, a plurality of camera systems D, a lens E, a rotating platform, a system operation control system F, a display screen or a touch screen G, a mouse H, a keyboard I, a processor J, a starting button K, a pneumatic clamping device control system L, a pneumatic valve controller M, a dust removing device N, a distance moving device O, a rack P and a power switch knob Q are arranged in a device main body 111, so that the detection efficiency of defects such as PE protection film crystal points, foreign matters, black points and bubbles is improved, the labor cost is reduced, the detection accuracy is improved, PE films are graded in sections, and the factory benefit is improved.
Drawings
FIG. 1 is a perspective view of the structure of the present invention;
FIG. 2 is a top view of the structure of the present invention;
FIG. 3 is a bottom view of the structure of the present invention;
FIG. 4 is a side view of the structure of the present invention;
fig. 5 is an enlarged view of the invention with respect to fig. 3 a.
In the figure: 111 equipment main body, 112 alarm lamp, 113 bottom post, 2 moving assembly, 211 connecting seat, 212 connecting bearing, 213 axis of rotation, 214 curb plate, 215 fixing base, 216 antifriction axis, 217 movable pulley, 218 telescopic link, 219 buckle clamp plate, 220 brake arc piece.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Examples of the embodiments are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements throughout or elements having like or similar functionality. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.
In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communicated with the inside of two elements or the interaction relationship of the two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
Example 1
The preferred embodiment of the offline detection device for detecting defects of a PE film on a reel based on a penetrating light source and a visual algorithm is shown in fig. 1-5: the off-line detection equipment for the defects of the PE film of the scroll based on the penetrating light source and the visual algorithm comprises an equipment main body 111 and a moving assembly 2 arranged at the bottom of the equipment, wherein an alarm lamp 112 is arranged at the top of the equipment main body 111, bottom columns 113 are fixedly arranged at the bottom of the equipment main body 111, and each bottom column 113 is matched with one moving assembly 2;
the moving assembly 2 comprises a connecting seat 211, a connecting bearing 212, a rotating shaft 213 and an anti-friction rotating shaft 216, wherein the connecting seat 211 is fixedly arranged at the bottom of the equipment main body 111, the bottom of the connecting seat 211 is contacted with the connecting bearing 212, and a side plate 214 is fixedly arranged on the outer wall of the connecting bearing 212; the tail part of the side plate 214 is fixedly provided with a fixed seat 215, and the bottom end of the side plate 214 is movably provided with a sliding wheel 217 through an antifriction rotating shaft 216; the top end of the rotating shaft 213 is fixedly arranged at the bottom of the connecting seat 211, and the bottom end of the rotating shaft 213 is rotationally connected with the side plate 214 through the connecting bearing 212; two groups of telescopic rods 218 are movably arranged at the tail part of the fixed seat 215, a buckling plate 219 is movably arranged at the telescopic end part of the telescopic rod 218, and a brake arc block 220 is fixedly arranged at the inner side of the buckling plate 219; one end of the brake arc block 220 is movably mounted between the side plates 214 through a pin shaft, and a certain interval is reserved between the inner side of the brake arc block 220 and the outer wall of the sliding wheel 217.
Example 2
On the basis of embodiment 1, a preferred embodiment of the offline detection device for defects of a spool PE film based on a penetrating light source and a visual algorithm provided by the invention is shown in fig. 1-5: the device main body 111 comprises a clamping scroll PE film device A, a stepping motor or servo motor rotating platform B, a light source C, a plurality of camera systems D, a lens E, a rotating platform and system operation control system F, a display screen or touch screen G, a mouse H, a keyboard I, a processor J, a starting button K, a pneumatic clamping device control system L, a pneumatic valve controller M, a dust removing device N, a distance moving device O, a stand P and a power switch knob Q; marking device AA (composed of xyz three-axis moving platform, x-axis about 50cm travel, y-axis about 1.4m travel, z-axis 20cm travel, marking is in the form of fountain pen or laser or nozzle)
The coordinate system R of the scroll PE film is defined as an intersection point of an intersection line of a coordinate origin of the scroll PE film edge-sealing line and a round surface of the bottom end (an inner supporting shaft) of the scroll PE film, wherein an x-axis is a straight line perpendicular to the scroll PE film edge-sealing line, and a y-axis is the scroll PE film edge-sealing line.
The scroll PE film temporary global image coordinate system S is defined as the origin of coordinates that are the upper left corner origins of the image taken by the lowermost camera of the multiple camera system D (camera x-axis vertical direction, y-axis horizontal direction installed), the x-axis being parallel to the image x-axis, the y-axis being parallel to the image y-axis. The X-axis and y-axis positive directions coincide with the X-axis and y-axis positive directions of the image.
The temporary global physical coordinate system T of the scroll PE film is defined as that the coordinate origin is converted to the coordinate origin of the physical coordinate system by the camera aperture imaging model, and the x-axis and the y-axis are converted to the x-axis and the y-axis under the physical coordinate system by the camera aperture imaging model.
Example 3
On the basis of embodiment 1, a preferred embodiment of the offline detection device for defects of a spool PE film based on a penetrating light source and a visual algorithm provided by the invention is shown in fig. 1-5: the offline detection device for the defects of the PE film of the scroll based on the penetrating light source and the visual algorithm has the following use process:
s0, powering up the system, powering up the light source, the camera and the like
S1, holding the scroll PE film on a rotary platform B for vertical placement
S2, starting the pneumatic valve controller M, so that the pneumatic clamping device control system L controls the clamping scroll PE film device A to clamp the scroll PE film.
S3, setting the length of the film through a software interface, so as to configure the exposure value of the camera and the moving distance from the moving device O.
And S4, pressing a start button K to enable the rotary platform and the system operation control system F to transmit signals to software running on the processor J.
S5, the software controls the stepping motor or the servo motor to rotate the platform B for one circle, and dust and foreign matters on the surface of the film are removed under the condition that the surface of the film is not damaged.
S6, controlling the cameras to take pictures sequentially by software, and processing the captured images by the detection algorithm module U to obtain flaw types and sizes. The marking device AA is then moved to the corresponding position for marking (z-coordinate estimated from the diameter of the PE reel and the xy-coordinate position of the flaw) based on the calculated flaw coordinates. The marking device moves from one end in the vertical direction to the other end according to the flaw coordinate sequence, and the marking is completed.
S7, after the processing of S5 is finished, the software controls the stepping motor or the servo motor rotating platform B to rotate by an angle, and then S5 is executed again
S8, repeatedly executing S5 for a plurality of times to enable the camera to shoot images of the full-scroll PE film, calculating a result, displaying a multi-grid image (an image obtained by displaying an enhanced original image) on a display screen or a touch screen G, and detecting a flaw distribution map, wherein the flaw distribution map displays flaw distribution coordinates of the scroll PE film.
S9, clicking the flaw distribution map can correspondingly see the flaw amplified image. The software interface with large flaws is more remarkable, and the problematic areas are selected to be checked according to flaw density.
S10, obtaining a picture through a stitching algorithm V, and checking a coordinate PP on a coordinate system R of the PE film of the flaw scroll R And the subsequent treatment is convenient.
Example 4
On the basis of embodiment 1, a preferred embodiment of the offline detection device for defects of a spool PE film based on a penetrating light source and a visual algorithm provided by the invention is shown in fig. 1-5: spool PE film flaw off-line detection equipment based on penetrating light source and visual algorithm, detection algorithm module U flow is as follows:
u0 and IMG for reading film flaw image BiBj (IMG BiBj An image obtained by taking a picture of the frame image at the Bi-th camera of the multi-camera system D
U1, dividing the film flaw image into a plurality of Zhang Xiaotu according to grids, wherein each image has a resolution of M x N (M and N are comprehensively considered according to hardware efficiency and algorithm precision, and the value is about hundreds, and the image is represented to have M rows and N columns)
U2, IMG one of the small images Sisj (IMG Sisj The method comprises the steps of performing deep learning detection and segmentation on a si-th image of a sj-th row of a grid cut from a large image, and obtaining flaw types, image coordinates and sizes according to confidence level and flaw size threshold value set by software
U3, carrying out U2 step by detecting and dividing through different deep learning networks for multiple times
And U4, regarding the multiple detection results as flaws by using multiple networks, or adjusting the false alarm rate of the system by a method which is considered as flaws only by one method, wherein the method is considered as flaws, and corresponds to the sensitivity and reliability in actual use. Finally obtaining flaw class and IMG in small graph Sisj Image coordinates PP in (a) Sisj And size (sum)
U5, image coordinate PP of flaw in small graph according to the following formula Sisj Converting into the large graph to obtain image coordinate PP of flaw in the large graph B
(N is changed to M)
Example 5
On the basis of embodiment 1, a preferred embodiment of the offline detection device for defects of a spool PE film based on a penetrating light source and a visual algorithm provided by the invention is shown in fig. 1-5: the spool PE film flaw off-line detection equipment based on the penetrating light source and the visual algorithm comprises the following steps of:
v0, reading one image IMG of the film to be detected currently BiBj Calculating flaw coordinates PP according to an algorithm module U B ，IMG BiBj Upper left angular position of (2)The origin is in a temporary global image coordinate system S of the scroll PE film, and the coordinate is S cBiBj
V1, detecting the reel PE film in the image IMG through a deep learning detection algorithm BiBj One side of the imaging target surface of all cameras is parallel to the long axis direction of the scroll PE film, and the other side of the imaging target surface of the lowermost camera is aligned with the two end point lines of the short axis direction of the scroll PE film.
V2, obtaining an image IMG of the edge sealing line of the spool PE film through a deep learning detection algorithm BiBj Is provided. The edge sealing line is positioned at the connecting line position of the short side center point of the detection frame.
And V3, reading all images of the film to be detected currently, and executing steps V1 and V2.
V4, analyzing the edge banding line detection results of the scroll PE film of all the images, wherein the edge banding line LB of the scroll PE film is detected by the images acquired by the Bn camera in Bm times BmBn
V5, edge banding line LB of spool PE film BmBn IMG at one of the endpoints of (c) BmBn Is PP in the coordinates of (2) BmBmLB0 ，
Converting it into a temporary global image coordinate system S of the reel PE film according to the following formula to obtain a coordinate S BmLB0 。
S BmLB0x ＝S cBmBnx +PP BmBnLB0x
S BmLB0y ＝S cBmBny +PP BmBnLB0y
V6, detecting the V0 to obtain a flaw coordinate PP B Converting into a temporary global image coordinate system S of the scroll PE film to obtain a coordinate S Bi
S Bix ＝S cBiBjx +PP Bx
S Biy ＝S cBiBjy +PP By
V7, coordinates S of flaws obtained by V0 detection under a temporary global image coordinate system S of the scroll PE film Bi Converting into a temporary global physical coordinate system T of the spool PE film to obtain a coordinate T Bi Wherein per is the unit pixel under the small hole imaging model estimationRepresentative of the actual size.
T Bix ＝per*S Bix
T Biy ＝per*S Biy
V8, edge banding line LB obtained by V5 BmBn Coordinates S in the temporary global image coordinate System S of the scroll PE film BmLB0 Converting into a temporary global physical coordinate system T of the spool PE film to obtain a coordinate T BmLB0 Where per is the actual size represented by the unit pixel under the small bore imaging model estimate.
T BmLB0x ＝per*S BmLB0x
T BmLB0y ＝per*S BmLB0y
V8, coordinates T of flaws obtained by V0 detection under a temporary global physical coordinate system T of the spool PE film B The following formula is converted into a reel PE film coordinate system R to obtain a coordinate R B
R Bx ＝-T BmLB0 +T Bix ++ (i-m) L (m is changed to Bm)
R Bx ＝-T BmLB0 +T Bix +(i-Bm)*L
T By ＝T Biy
Wherein L is the moving distance of a certain point on the film rotated each time, and is calculated according to the rotating radian of the motor and the radius R of the film of the reel.
L＝∝*R
Example 6
On the basis of embodiment 1, a preferred embodiment of the offline detection device for defects of a spool PE film based on a penetrating light source and a visual algorithm provided by the invention is shown in fig. 1-5: the offline detection equipment for the defects of the PE film of the scroll based on the penetrating light source and the visual algorithm comprises the following labeling flow of a detection algorithm module V:
a0, reading film flaw image
A1, dividing the film flaw image into a plurality of Zhang Xiaotu according to grids, wherein each image has a resolution of hundreds of times (depending on hardware efficiency and algorithm precision comprehensive consideration)
A2, enhancing the film flaw image by using an image enhancement algorithm, so that the flaw contrast is stronger and is easier to be seen by human eyes
A3, marking the positions and the categories of the flaws in the image by using a marking tool.
Spool PE film flaw off-line detection equipment based on penetrating light source and visual algorithm, concatenation algorithm module V training flow is as follows:
b0, reading film flaw image
B1, scaling the whole film flaw image to hundreds of resolutions
B2, marking four edges of the scroll PE film and edge sealing lines of the scroll PE film in the image by using marking tools
B1, when the film flaw image mosaics are enhanced, new diagonal lines are recalculated according to the diagonal lines of the detection frame and the size of the intercepted image block, and a new detection frame is formed to serve as a true value.
Example 7
On the basis of embodiment 1, a preferred embodiment of the offline detection device for defects of a spool PE film based on a penetrating light source and a visual algorithm provided by the invention is shown in fig. 1-5: spool PE film flaw off-line detection equipment based on penetrating light source and visual algorithm, the algorithm flow is as follows:
a0, reading film flaw image
A1, dividing a film flaw image into a plurality of Zhang Xiaotu according to grids, wherein each image has a resolution of hundreds of
A2, performing deep learning detection and segmentation on the small images, and obtaining flaw types, coordinates and sizes according to confidence coefficient and flaw size threshold value set by software
A3, detecting and dividing the multiple times by using different deep learning networks to carry out the step A2
A4, regarding the multiple detection results as flaws by using multiple networks, or regarding the flaws as flaws by only one method to adjust the false alarm rate of the system, wherein the false alarm rate corresponds to the sensitivity and reliability in actual use.
Spool PE film flaw off-line detection equipment based on penetrating light source and visual algorithm, the labeling flow is as follows:
b0, reading film flaw image
B1, enhancing the film flaw image by using an image enhancement algorithm, so that the flaw contrast is stronger and is more easily seen by human eyes
And B2, marking positions and categories of flaws in the image by using marking tools.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (8)

1. Spool PE film flaw off-line measuring equipment based on penetrating light source and vision algorithm, including equipment main part (111) to and set up mobile component (2) in the equipment bottom, its characterized in that: the top of equipment main part (111) is provided with alarm lamp (112), the bottom fixed mounting of equipment main part (111) has foundation column (113), and every foundation column (113) adaptation is remove subassembly (2).
2. The offline detection device for defects of a scroll PE film based on a penetrating light source and a visual algorithm according to claim 1, wherein: the movable assembly (2) comprises a connecting seat (211), a connecting bearing (212), a rotating shaft (213) and an anti-friction rotating shaft (216), wherein the connecting seat (211) is fixedly arranged at the bottom of the equipment main body (111), the bottom of the connecting seat (211) is contacted with the connecting bearing (212), and a side plate (214) is fixedly arranged on the outer wall of the connecting bearing (212).
3. The offline detection device for defects of a scroll PE film based on a penetrating light source and a visual algorithm according to claim 2, wherein: the tail of the side plate (214) is fixedly provided with a fixed seat (215), and the bottom end of the side plate (214) is movably provided with a sliding wheel (217) through an antifriction rotating shaft (216).
4. The offline detection device for defects of a scroll PE film based on a penetrating light source and a visual algorithm according to claim 2, wherein: the top of the rotating shaft (213) is fixedly arranged at the bottom of the connecting seat (211), and the bottom of the rotating shaft (213) is rotationally connected with the side plate (214) through the connecting bearing (212).
5. The offline detection device for defects of a scroll PE film based on a penetrating light source and a visual algorithm according to claim 3, wherein: two groups of telescopic rods (218) are movably arranged at the tail part of the fixed seat (215).
6. The offline detection device for defects of a spool PE film based on a penetrating light source and a visual algorithm according to claim 5, wherein the offline detection device is characterized in that: the telescopic end part of the telescopic rod (218) is movably provided with a buckling plate (219).
7. The offline detection device for defects of a spool PE film based on a penetrating light source and a visual algorithm of claim 6, wherein the offline detection device comprises: the inner side of the buckling plate (219) is fixedly provided with a brake arc block (220).
8. The offline detection device for defects of a spool PE film based on a penetrating light source and a visual algorithm according to claim 7, wherein: one end of the brake arc block (220) is movably arranged between the side plates (214) through a pin shaft, and a certain distance is reserved between the inner side of the brake arc block (220) and the outer wall of the sliding wheel (217).
CN202311039854.6A 2023-08-17 2023-08-17 Spool PE film flaw off-line detection equipment based on penetrating light source and visual algorithm Pending CN117074433A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311039854.6A CN117074433A (en) 2023-08-17 2023-08-17 Spool PE film flaw off-line detection equipment based on penetrating light source and visual algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311039854.6A CN117074433A (en) 2023-08-17 2023-08-17 Spool PE film flaw off-line detection equipment based on penetrating light source and visual algorithm

Publications (1)

Publication Number Publication Date
CN117074433A true CN117074433A (en) 2023-11-17

Family

ID=88718970

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311039854.6A Pending CN117074433A (en) 2023-08-17 2023-08-17 Spool PE film flaw off-line detection equipment based on penetrating light source and visual algorithm

Country Status (1)

Country Link
CN (1) CN117074433A (en)

Similar Documents

Publication Publication Date Title
CN107356608B (en) Rapid dark field detection method for surface microdefects of large-caliber fused quartz optical element
Herráez et al. 3D modeling by means of videogrammetry and laser scanners for reverse engineering
CN110142785A (en) A kind of crusing robot visual servo method based on target detection
EP3285131A1 (en) Parallel connection platform tracking control device and method using visual equipment as sensor
CN102519400B (en) Large slenderness ratio shaft part straightness error detection method based on machine vision
CN108562250B (en) Keyboard keycap flatness rapid measurement method and device based on structured light imaging
CN107121093A (en) A kind of gear measurement device and measuring method based on active vision
CN111398172A (en) 3D visual detection equipment and method
CN101458072A (en) Three-dimensional contour outline measuring set based on multi sensors and measuring method thereof
CN112540089B (en) Application method of digital imaging system in concrete bridge crack detection and analysis
US9726151B2 (en) Assessment of rotor blades
US11562478B2 (en) Method and system for testing field of view
CN104050446A (en) Meter pointer image identification method based on pointer width character
CN104700395A (en) Method and system for detecting appearance crack of structure
CN108981607A (en) A kind of object color three dimension profile scan device based on dual laser device
JP6938107B1 (en) How to measure road surface damage
CN113554667B (en) Three-dimensional displacement detection method and device based on image recognition
CN110986834A (en) Automatic assembly pipe penetration monitoring method
CN104748792A (en) Operating method for water environment monitoring device
CN103593663A (en) Image positioning method of banknote printing plate
CN111627070B (en) Method, device and storage medium for calibrating rotation shaft
CN115014248B (en) Laser projection line identification and flatness judgment method
CN205427436U (en) Display device's counterpoint check out test set and exposure process systems
CN104297256B (en) Apparent flaws detecting system and method
CN117074433A (en) Spool PE film flaw off-line detection equipment based on penetrating light source and visual algorithm

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