CN118688121B - Lens detection system and detection method - Google Patents
Lens detection system and detection method Download PDFInfo
- Publication number
- CN118688121B CN118688121B CN202411160379.2A CN202411160379A CN118688121B CN 118688121 B CN118688121 B CN 118688121B CN 202411160379 A CN202411160379 A CN 202411160379A CN 118688121 B CN118688121 B CN 118688121B
- Authority
- CN
- China
- Prior art keywords
- image
- defect
- lens
- defects
- film surface
- 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 80
- 230000007547 defect Effects 0.000 claims abstract description 269
- 239000000428 dust Substances 0.000 claims abstract description 81
- 239000007788 liquid Substances 0.000 claims abstract description 75
- 238000005507 spraying Methods 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 33
- 238000010191 image analysis Methods 0.000 claims abstract description 28
- 239000003595 mist Substances 0.000 claims abstract description 26
- 238000012546 transfer Methods 0.000 claims abstract description 6
- 230000007246 mechanism Effects 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 81
- 238000009826 distribution Methods 0.000 claims description 17
- 238000007689 inspection Methods 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 12
- 238000005516 engineering process Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 7
- 238000003706 image smoothing Methods 0.000 claims description 7
- 230000003287 optical effect Effects 0.000 claims description 7
- 239000007921 spray Substances 0.000 claims description 7
- 238000009833 condensation Methods 0.000 claims description 5
- 230000005494 condensation Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 238000012850 discrimination method Methods 0.000 claims description 2
- 238000009828 non-uniform distribution Methods 0.000 claims description 2
- 239000013589 supplement Substances 0.000 claims 2
- 230000004069 differentiation Effects 0.000 claims 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 15
- 230000008569 process Effects 0.000 description 14
- 230000011218 segmentation Effects 0.000 description 11
- 238000000605 extraction Methods 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 230000002950 deficient Effects 0.000 description 4
- 230000010339 dilation Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 230000001502 supplementing effect Effects 0.000 description 4
- 208000027418 Wounds and injury Diseases 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000003709 image segmentation Methods 0.000 description 3
- 239000012535 impurity Substances 0.000 description 3
- 206010052428 Wound Diseases 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000003908 quality control method Methods 0.000 description 2
- 239000011347 resin Substances 0.000 description 2
- 229920005989 resin Polymers 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000001931 thermography Methods 0.000 description 2
- 235000002566 Capsicum Nutrition 0.000 description 1
- 239000006002 Pepper Substances 0.000 description 1
- 235000016761 Piper aduncum Nutrition 0.000 description 1
- 235000017804 Piper guineense Nutrition 0.000 description 1
- 244000203593 Piper nigrum Species 0.000 description 1
- 235000008184 Piper nigrum Nutrition 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000000861 blow drying Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000015271 coagulation Effects 0.000 description 1
- 238000005345 coagulation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000012780 transparent material Substances 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
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
- G01N21/01—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
- G01N21/95—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
- G01N21/84—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
- G01N2021/9583—Lenses
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)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Testing Of Optical Devices Or Fibers (AREA)
Abstract
The invention discloses a lens detection system and a detection method, which belong to the technical field of defect detection and comprise a single-sided spraying station, an image acquisition station, a lens transfer mechanism, an image processing system, a defect position detection module and/or a defect type distinguishing module, wherein the single-sided spraying station is used for spraying mist liquid on a single surface of a lens to form a mist film surface, the image acquisition station is used for acquiring images of the mist film surface, the lens transfer mechanism is used for grabbing the lens and transferring the lens from the single-sided spraying station to the image acquisition station, the image processing system is used for receiving the images of the mist film surface and detecting defects of the mist film surface, the defect position detection module is used for carrying out image analysis on the images of the mist film surface to judge whether defects exist on the mist film surface or not, and the defect type distinguishing module is used for carrying out image analysis on the images of the mist film surface to judge the types of the defects, wherein the defect types comprise point dust and point defects. The invention can detect which surface of the lens the defect is positioned on, and can rapidly and accurately distinguish point-shaped defects from dust.
Description
Technical Field
The invention belongs to the technical field of defect detection, and particularly relates to a lens detection system and a lens detection method.
Background
As is well known, lenses are optical products made of transparent materials, and can be classified into five types, resin lenses, special lenses, space lenses, glass lenses, PVC lenses, and the like, depending on the materials. The lenses have high sensitivity to light during production and use, that is, when the lenses have small defects, the lenses may have a significant effect on light, so that the quality of the lenses directly determines the stability of the light path. In order to ensure the quality of the lens, high precision detection of the quality of the lens is required. At present, the lens detection modes are various, but the following two technical difficulties still exist:
1. The detection of the location of the defect, i.e. on which face of the lens the defect is located. In conventional lens defect detection methods, the camera is only able to capture one image of the lens. Because the lens has two sides, defects may occur on either side. In the image, the difference of the concave and convex surfaces of the lens cannot be considered, and whether the defect is concave or convex cannot be judged by the image. That is, since the lens has two surfaces and the lens is made of a light-transmitting material, when the lens image is acquired, the images of the two surfaces of the lens overlap, and thus the image detection result can only determine whether a defect exists, but cannot determine which surface of the lens the defect is located.
2. Dot dust and dot defect are distinguished. Since the similarity of point defects and point dust on an image is high, such as shape, size, and gradation, it is difficult to quickly and accurately distinguish. This requires extensive processing and analysis of the image to distinguish between point dust and point defects.
Aiming at the two technical difficulties, a more effective lens detection system and a detection method are needed to be found so as to improve the detection precision of the lens quality.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a lens detection system and a detection method, wherein a fog film surface is formed by spraying fog liquid on a single surface of a lens, and then the fog film surface is analyzed and processed by utilizing an image processing technology, so that the purpose of lens detection is finally realized.
A first object of the present invention is to provide a lens inspection system comprising:
a single-sided spraying station for spraying mist liquid to only a single surface of the lens to form a mist film surface;
the image acquisition station is used for acquiring images of the fog film surface;
The lens transfer mechanism is used for grabbing lenses and transferring the lenses from the single-sided spraying station to the image acquisition station;
The image processing system is used for receiving the image of the fog film surface and carrying out defect detection on the image of the fog film surface, wherein the defect detection comprises a defect position detection module and/or a defect type distinguishing module, and the defect detection comprises the following steps:
The defect position detection module is used for judging whether defects exist on the fog film surface according to image analysis on the image of the fog film surface;
And the defect type distinguishing module is used for judging the types of defects according to image analysis of the image of the fog film surface, wherein the types of defects comprise point dust and point defects.
Preferably, the single-sided spray station comprises:
the spraying device converts the liquid in the liquid storage bin into vaporific liquid and sprays the vaporific liquid onto a single surface of the lens;
and the temperature adjusting device is used for adjusting the temperature of the liquid in the liquid storage bin according to the detection requirement.
Preferably, the lens inspection system further comprises a blow-drying station for removing the fog of liquid from the lens.
Preferably, the image acquisition station comprises image acquisition equipment, a light supplementing lamp and a light absorbing plate, wherein the image acquisition equipment and the light supplementing lamp are positioned on one side of a fog film surface of the lens, and the light absorbing plate is positioned on the other side of the fog film surface of the lens during operation.
A second object of the present invention is to provide a lens inspection method, comprising:
s1, spraying mist liquid on a single surface of a lens to form a mist film surface;
S2, collecting an image of a fog film surface;
S3, receiving the image of the fog film surface, and carrying out defect detection on the image of the fog film surface, wherein the defect detection comprises defect position detection and/or defect type distinction, and the method comprises the following steps:
The defect position detection judges whether defects exist on the fog film surface according to image analysis on the image of the fog film surface;
and the defect type distinction judges the defect type according to image analysis of the image of the fog film surface, wherein the defect type comprises point dust and point defects.
Preferably, S1 is specifically:
s101, adjusting the temperature of liquid in a liquid storage bin according to detection requirements;
S102, converting the liquid meeting the temperature requirement into vaporific liquid, and spraying the vaporific liquid onto a single surface of the lens.
Preferably, the defect position detection comprises a first method and/or a second method, wherein:
The method comprises the steps of firstly, carrying out image analysis on an image of a fog film surface to obtain the distribution condition of the fog and/or the defect mode, and obtaining the position of the defect according to the distribution condition of the fog and/or the defect mode, wherein when the fog film is in a non-uniform distribution state, judging that the defect exists on one surface of the sprayed fog liquid;
the method comprises the steps of S1, obtaining an infrared image of a fog film surface by an infrared camera in S2, obtaining the position of a defect by analyzing the infrared image in S3, and finally, repeatedly detecting the position of the defect by changing the temperature of the liquid in S1.
Preferably, the defect type distinguishing comprises a method A and/or a method B, wherein:
The method A carries out defect type distinction based on the difference of optical effects, namely, carrying out image analysis on the image of the fog film surface to obtain refraction, scattering and reflection modes of defects on light rays, and carrying out defect type distinction according to the refraction, scattering and reflection modes;
And B, distinguishing defect types based on temperature and condensation speed, namely obtaining the distribution condition of the fog liquid at the defect position according to image analysis of the image of the fog film surface, wherein the distribution condition is punctiform defect or scratch defect when the fog liquid is gathered at the defect position, and is punctiform dust when the fog liquid is scattered.
Preferably, in the image analysis for defect type discrimination, the method for identifying point dust includes:
Image preprocessing, namely performing median filtering, image smoothing and image enhancement on the image of the foggy film surface to obtain a preprocessed image;
Expanding the image, and performing expansion processing on the preprocessed image;
image target recognition, namely recognizing a target area in the inflated image;
the method for distinguishing the point dust and the point defect divides the target area into the point dust or the point defect, and specifically comprises the following steps:
When the center gray level of the target area is higher than the lens gray level and the edge gray level of the target area is lower than the lens gray level, the identification result is point dust, otherwise, the identification result is point defect;
or extracting the edge of the target area based on the bright and dark boundary, and when the center distance between the two defects is smaller than the threshold value, identifying the two defects as point dust, otherwise, identifying the two defects as point defects.
Preferably, in the image analysis for defect type discrimination, the discrimination method of the point defect, the bubble defect and the scratch defect includes:
Image preprocessing, namely performing median filtering, image smoothing and image enhancement on the image of the foggy film surface to obtain a preprocessed image;
eliminating point dust on the preprocessed image, firstly identifying the point dust by using an identification method of the point dust, and then eliminating the point dust to obtain a defect image;
Dividing and extracting a defect image, namely dividing the defect image into a plurality of areas, and extracting a target object from the images of different areas by adopting an image threshold dividing technology;
Performing defect identification according to the characteristics of the defects, wherein:
when the extracted target objects are mutually isolated connected domains, identifying the extracted target objects as point defects;
when the extracted target object is a similar circular connected domain and appears at the edge of the lens, identifying whether the target object is a bubble or not by a Hough detection circle method;
And when the extracted target object is a gray abrupt change line with continuous coordinates, identifying the scratch defect by judging the continuity of the gray coordinates of the edges in the connected domain.
Compared with the prior art, the application has the advantages and positive effects that:
The first step of the invention is to uniformly spray a layer of fog liquid on one side surface of the lens to form a uniform fog film. This step is achieved by fine spray techniques to ensure uniformity of the foggy surface. After the spraying is finished, the image capturing is carried out on the fog film surface by using high-precision image acquisition equipment. These images may be conventional RGB color images, or gray scale images, or even infrared images for thermal imaging to accommodate different detection requirements.
Then, the collected image (image of the foggy film surface) is input into an image processing system, and the image is subjected to deep analysis and processing by using an advanced data processing algorithm.
If the analysis and processing result shows that the defect exists, the defect is positioned on the fog film surface, then the defect positioning can be rapidly performed through an image processing technology, namely, the specific position parameters of the defect positioned on the fog film surface are determined, and the high efficiency and the accuracy of the process ensure that the defect positioned on the surface of the lens can be identified in the shortest time.
The present invention also classifies the detected defects in detail. For example, it can distinguish whether it is spot dust caused by dust or a truly existing spot defect. The fine-granularity defect classification capability not only improves the detection accuracy, but also enables the subsequent lens quality control work to be more efficient. In general, the invention can greatly improve the quality detection speed and accuracy of the lens production line and ensure that the outgoing lenses meet the high-standard optical quality requirements.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic system diagram of a preferred embodiment of the present invention;
FIG. 2 is a lens image acquired in an embodiment of the present application;
FIG. 3 is a partial view of a lens showing dust on the lens according to an embodiment of the present application;
FIG. 4 is a partial view of a lens showing dust after image processing on the lens according to an embodiment of the present application;
FIG. 5 is a partial view of a lens showing a spot defect on the lens according to an embodiment of the present application;
FIG. 6 is a partial view of a lens showing a spot defect on the lens after image processing on the lens according to an embodiment of the present application;
FIG. 7 is a partial view of a lens showing a detection zone on the lens according to an embodiment of the present application;
FIG. 8 is a partial view of a lens showing Otsu screening of areas in accordance with an embodiment of the present application;
FIG. 9 is a partial view of a lens according to an embodiment of the present application, showing the results of the detection of the Otsu area fitting circle;
FIG. 10 is a partial view of a lens showing the result of screening the region for histogram threshold in accordance with an embodiment of the present application;
FIG. 11 is a partial view of a lens for displaying detection results taken by a fitted circle of a histogram area in an embodiment of the present application;
Fig. 12 is a partial view of a lens for displaying an image after identification marking in an embodiment of the present application.
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. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present invention.
Referring to fig. 1, a lens inspection system includes:
A single-sided spraying station 1 for spraying mist liquid to only a single surface of the lens to form a mist film surface;
The single-sided spraying station is one of the cores of the application, and has the main functions of spraying mist liquid on a single surface of a lens, wherein the spraying uniformity needs to be ensured when spraying, and the liquid can be water or other liquid with color;
the image acquisition station 2 is used for acquiring images of the fog film surface;
The image acquisition station is another core of the application, the quality of image acquisition directly determines the accuracy of an image analysis processing result, therefore, in the image acquisition process, the fog film surface is positioned on the focal plane of the image acquisition device, the other surface of the lens is far away from the focal plane, the relative rest between the fog film surface and the image acquisition device is ensured, the image acquisition station can acquire common images such as RGB images or gray images and infrared images, when the common images are required to be acquired, the image acquisition station comprises a common image acquisition part 4, the common image acquisition part 4 comprises a camera, a light supplementing lamp and a light absorbing plate, when the common image acquisition part is in operation, the camera and the light supplementing lamp are positioned on one side of the fog film surface of the lens, the light absorbing plate is positioned on the other side of the fog film surface of the lens, and when the infrared images are required to be acquired, the image acquisition station comprises an infrared camera, the lens can be hung in air, and a colored light absorbing flannelette is arranged at a position of 100mm below the lens in order to eliminate the influence of reflected light.
The lens transfer mechanism is used for grabbing lenses and transferring the lenses from the single-sided spraying station to the image acquisition station;
in order to meet the high-efficiency detection requirement of a large number of lenses and avoid pollution to the lenses caused by manual operation, an automatic or intelligent manipulator is preferred in the lens transferring process;
the image processing system receives the image of the fog film surface and detects defects of the image of the fog film surface, wherein the defects comprise a defect position detection module and/or a defect type distinguishing module;
the image processing system is another core of the application, and mainly comprises various image processing software modules, in particular:
The defect position detection module is used for judging whether defects exist on the fog film surface according to image analysis on the image of the fog film surface;
And the defect type distinguishing module is used for judging the types of defects according to image analysis of the image of the fog film surface, wherein the types of defects comprise point dust and point defects.
Some of the details of the above embodiments are set forth in detail below:
The single-sided spray station comprises:
The spraying device is used for converting the liquid in the liquid storage bin into vaporous liquid and spraying the vaporous liquid onto a single surface of the lens, and mainly comprises the liquid storage bin and an atomizing nozzle, wherein the liquid storage bin 9 and the atomizing nozzle are connected through a pipeline with a pump;
And the temperature adjusting device is used for adjusting the temperature of the liquid in the liquid storage bin according to the detection requirement. The temperature regulating device can comprise a warmer and a cooler and can be arranged in the liquid storage bin or the atomizing nozzle or the pipeline;
The temperature sensor is used for detecting the temperature of the vaporific liquid and can select an infrared temperature sensor;
The lens inspection system may also include a blow-dry station 3 for removing the hazy liquid from the lens. After the cleaning is finished, if the other surface of the lens needs to be detected, the manipulator can be used for grabbing the lens, spraying atomized liquid on the other surface, and then detecting the other surface.
Preferred embodiment 2A lens inspection method includes:
s1, spraying mist liquid on a single surface of a lens to form a mist film surface;
The single-sided spraying is one of the core procedures of the application, and has the main functions of spraying mist liquid on a single surface of a lens, wherein the spraying uniformity needs to be ensured when spraying, and the liquid can be water or other liquid with color;
S2, collecting an image of a fog film surface;
The image acquisition is another core process of the application, and the accuracy of an image analysis processing result is directly determined by the quality of the image acquisition, so that in the image acquisition process, the foggy film surface is positioned on the focal plane of the image acquisition equipment, and the relative stillness between the foggy film surface and the image acquisition equipment is ensured;
S3, receiving the image of the fog film surface, and carrying out defect detection on the image of the fog film surface, wherein the defect detection comprises defect position detection and/or defect type distinction;
the image processing is another core process of the application, which is mainly finished by image processing software or visual inspection, and the specific steps are as follows:
The defect position detection judges whether defects exist on the fog film surface according to image analysis on the image of the fog film surface;
Compared with the prior art, the application firstly utilizes liquid (such as water vapor) to form fog on a single surface of the lens, and can effectively distinguish whether the defect is on the convex surface or the concave surface of the lens. This is because the fog acts on only one face of the lens, so the location of the defect can be determined from the area covered by the fog, principally due to the interaction of the vapor with the lens and the specific effect of the vapor on the lens surface. If there is no dust and defect on the surface of the lens, the uniformly distributed atomized liquid is formed on the single surface of the lens, and if there is dust and/or defect on the surface of the lens, the distribution of the atomized liquid is changed;
First, when steam contacts one surface of the lens, a layer of mist, also known as a fog film, is formed on that surface of the lens. The fog film can cover one surface of the lens, and the other surface is clear without fog film. By analysing the area covered by the mist, it can be quickly determined on which face of the lens the defect is present. If a defect occurs on the surface in contact with the haze, the haze distribution on that surface may be affected by the defect, assuming a particular pattern or shape. While the unaffected side remains clear, contrast. By analyzing the distribution of the fog film and the defect mode, the defect on which surface of the lens can be accurately judged.
Second, the interaction of the fog film with the lens surface can lead to temperature changes and condensation. These physical effects may further help to distinguish on which face the defect is. For example, when the fog film contacts the lens surface, the fog film will rapidly transfer heat to the lens, resulting in an increase in the temperature of the lens surface. Since the defective portion and the non-defective portion may differ in heat conduction performance, the defective portion and the non-defective portion also differ in reaction to temperature change. This temperature difference can be detected and analyzed by infrared thermal imaging techniques to further determine on which face the defect is. That is, different vapor temperatures have different effects on defect detection, different temperatures may result in different responses of defects in the material or product, some defects being more pronounced at high temperatures, and others being more detectable at low temperatures. Therefore, by adjusting the temperature of the steam, the position of the defect can be more precisely located, and the size or type thereof can be judged.
On the other hand, a combination of a plurality of temperatures is adopted. Two methods are proposed, namely, the defect type and size are distinguished by gradually changing the temperature in one detection process and observing the defect performance at different temperatures, and secondly, the defect type and size are detected by using one temperature and then verified or deeply detected by using the other temperature. The defect detection method fully utilizes the advantages of different temperatures on defect detection, and improves the accuracy and reliability of detection.
The defect type distinction judges the defect type according to image analysis of the image of the fog film surface, wherein the defect type comprises point dust, point defects, scratch defects and the like;
The application uses different manifestations of steam on point defects and dust to distinguish;
Interaction of the vapor with the lens, the vapor forms a fog film when it contacts the lens surface. The fog film can cover the entire lens surface, including those areas of potential defects.
The difference in optical effects is that dust and point defects may have different refraction, scattering and reflection patterns on light under the action of steam. Defects of different nature may exhibit different optical effects due to the steam altering the way light passes through the lens surface.
Temperature and condensation rate-due to the nature of dust and punctiform defects, they may also differ in their heat exchange behaviour with steam. For example, point defects may cause a different coagulation rate from surrounding areas due to their internal structure or material characteristics.
When the lens to be inspected is placed in a vapor environment, the vapor will contact the lens surface. If spot defects and scratch defects are present on the steam-affected surface, water vapor may accumulate more easily at these defects. This is because point defects and scratch defects typically form grooves or cracks that allow water vapor to more easily enter and remain in these areas.
Conversely, if dust is present on the surface of the object, the dust reduces the surface tension of the water, making it easier for the water vapor to spread out and distribute over other areas of the object. Dust is usually attached only to the surface of the object, and grooves or cracks are not formed, so that water vapor is not particularly accumulated at the dust. By observing the distribution condition of the water vapor on the surface of the object, whether point defects and scratch defects exist can be primarily judged.
S1 specifically comprises the following steps:
s101, adjusting the temperature of liquid in a liquid storage bin according to detection requirements;
S102, converting the liquid meeting the temperature requirement into vaporific liquid, and spraying the vaporific liquid onto a single surface of the lens.
In the above-mentioned scheme of the lens detection method, the defect position detection includes a first method and/or a second method, wherein:
the method comprises the steps of firstly, carrying out image analysis on an image of a fog film surface to obtain the distribution condition of the fog and/or the defect mode, and obtaining the position of the defect according to the distribution condition of the fog and/or the defect mode;
the method comprises the steps of firstly spraying mist liquid to a single surface of a lens in S1, wherein the temperature of the liquid is higher than that of the surface of the lens, then acquiring an infrared image of a mist film surface by an infrared camera in S2, and finally acquiring the position of a defect through analysis of the infrared image in S3.
In the above-described embodiment of the lens inspection method, in the second method, the defect position inspection is repeatedly performed by changing the liquid temperature in S1.
In the above-mentioned scheme of the lens detection method, the defect type distinction includes method A and/or method B, wherein:
The method A carries out defect type distinction based on the difference of optical effects, namely, carrying out image analysis on the image of the fog film surface to obtain refraction, scattering and reflection modes of defects on light rays, and carrying out defect type distinction according to the refraction, scattering and reflection modes;
And B, distinguishing defect types based on temperature and condensation speed, namely obtaining the distribution condition of the fog liquid at the defect position according to image analysis of the image of the fog film surface, wherein the distribution condition is punctiform defect or scratch defect when the fog liquid is gathered at the defect position, and is punctiform dust when the fog liquid is scattered.
The lens defect image processing is shown in fig. 1, in which a camera acquires a complete lens gray image, the visible impurities and the defects have uniform gray values as a whole, the difference between the defect gray and the background gray is large, and the uniformity of the background gray is determined by the uniformity of water vapor acting on the lens. For the defect feature, the following processing is performed on the image:
Image input, fig. 2 shows that the camera collects a complete lens gray image, in which the impurities and defects are seen to have uniform gray values throughout, and the difference between the defect gray and the background gray is large, and the uniformity of the background gray is determined by the uniformity of steam acting on the lens. For the defect feature, the following processing is performed on the image.
Morphology may highlight or inhibit specific shape features:
the spot dust appears to be present on the lens in a protruding manner, and the spot dust has a diffusion effect on steam, and cannot condense in the vicinity thereof, and the effect of approximate expansion in imaging is obtained. The use of dilation in morphology makes its characteristics more pronounced.
The point dust presents a center gray level higher than the lens gray level, the edge gray is lower than the lens gray.
The edge extraction and the line detection are aimed at the extraction of bright and dark boundaries, two defects are formed by frames when dust is taken out, the centers of the defects are close, and the dust can be judged by judging the coordinates of the two areas.
In this embodiment, the method for identifying dust spots includes:
The image preprocessing, the preprocessing is carried out on the original image to ensure that the image quality meets the requirement of subsequent processing, the main purpose is to eliminate irrelevant information in the image of the defogging film surface and recover useful real information, thereby improving the reliability of feature extraction, image segmentation and identification. In determining the image segmentation threshold, the selection of the threshold is sensitive to noise. In the application, the main noise is random salt and pepper noise introduced by a CCD circuit and dust noise on the surface of the lens, and the gray level of the noise is darker relative to the defects (mainly bubbles, particles and scratches) of the lens. Aiming at the characteristics, the application carries out the treatments of median filtering, image smoothing, image enhancement and the like on the image of the fog film surface, eliminates partial noise introduced, enhances defect information, can not completely remove noise, especially dust noise, through pretreatment, and needs to further remove the influence of dust later.
Next, the preprocessed image is subjected to a dilation operation to enhance the target region in the image so that it is more easily identified and analyzed. The dilation process may be implemented by a specific algorithm, such as morphological dilation, which will help fill small voids in the target region and enlarge its boundaries.
After the inflation process is completed, an image target recognition step is performed. This process involves the use of computer vision and image processing techniques to identify and locate target areas in the inflated image. The target area may include defects of various shapes and sizes, such as point dust and point defects.
In order to distinguish between point dust and point defects, further analysis and division of the target area is required. In particular, the distinction can be made by analyzing the gray scale characteristics of the target region. When the center gray value of the target area is higher than the gray value of the surrounding lenses and the edge gray value of the target area is lower than the gray value of the lenses, the target area can be judged to be point dust. In contrast, if the gray scale characteristics of the target region do not meet the above conditions, they are recognized as point defects.
Another differentiating method is based on the extraction of bright and dark boundaries. By extracting the edge information of the target area, it can be analyzed whether the center distance between two defects is smaller than a preset threshold value. If there is a case where the centers of the two defects are closer, it is possible to judge the two defects as point dust, otherwise, it is recognized as point defect. This method relies on accurate extraction of image edges and accurate calculation of defect center distance.
Through the steps, point dust and point defects in the image can be effectively identified and distinguished, so that accurate data support is provided for further image processing and quality control.
The distinguishing method of the punctiform defect, the bubble defect and the scratch defect comprises the following steps:
In the image preprocessing stage, median filtering processing is firstly carried out on an original image so as to remove noise and miscellaneous points in the image. Then, the high-frequency noise in the image is further eliminated by an image smoothing technique, so that the image becomes smoother. And finally, enhancing the contrast and detail of the image by adopting an image enhancement technology, thereby obtaining a clearer preprocessed image.
Next, in order to eliminate point dust on the preprocessed image, the influence of the point dust on the lens to be detected is eliminated, and in a common detection mode, the point dust is similar to the point defect in shape, and the application distinguishes the point defect and the point dust by utilizing different performances of steam on the point defect and the point dust. The interaction of the vapor with the lens forms a fog film when the vapor contacts the lens surface. The fog film can cover the entire lens surface, including those areas of potential defects. In this embodiment, an efficient method for recognizing point dust is first used, and the position of the point dust is recognized by analyzing the local features of the image. Once the point dust is identified, it is eliminated by a corresponding algorithm, resulting in a purer defect image.
In the stage of dividing and extracting the defect image, the defect image is divided into a plurality of areas so as to facilitate the subsequent processing. Then, an image threshold segmentation technology is adopted, and a target object is extracted from each region according to different region image characteristics. This process ensures accurate extraction of the target object, providing a basis for further defect identification.
When defect identification is carried out according to the characteristics of the defects, the following strategies are adopted:
1. When the target objects extracted by image segmentation are connected domains isolated from each other, these connected domains are identified as point defects. This is because point defects often appear as isolated points or small spots in the image.
2. When the extracted target objects are connected domains like circles and the connected domains like circles appear at the edge of the lens, whether the target objects are bubbles or not is identified by a Hough detection circle method. The Hough detection rounding method is an effective image processing technology and can accurately detect round objects in images.
3. When the extracted target object is a gray scale abrupt change line with continuous coordinates, the continuity of the gray scale coordinates of the edges in the connected domain is judged to identify the scratch defect. The method can effectively identify scratch defects in the image and ensure the accuracy and the reliability of the scratch defects.
Through the steps, the image can be effectively preprocessed, point dust eliminated, segmentation extracted and defect identified, so that a solid foundation is provided for subsequent image processing and analysis.
The application makes the imaging of point dust and point defect inconsistent by acting on the lens through the fog film. Fig. 3 and 4 are spot dust images and algorithmic process images on a lens. Fig. 5 and 6 are spot images and algorithmically processed images on a lens. If spot dust is present on the surface of the object, the spot dust reduces the surface tension of the water, so that the water vapor is more easily dispersed and distributed in other areas of the object. Spot dust usually adheres only to the surface of the object and does not form grooves or cracks, so that water vapor does not particularly collect at the dust. The dust can be primarily judged as spot dust by observing the distribution of the water vapor on the surface of the object and dispersing a certain vapor in a center spot shape.
The method comprises the steps of dividing and extracting a defect image, dividing the defect image into a plurality of areas, extracting a target object from a background image by adopting an image threshold dividing technology, dividing the image into key meaningful areas by the image dividing, extracting the target object from the background image, and preparing for subsequent image recognition and other operations. The image threshold segmentation is a quite mature segmentation technology, and the image is regarded as the combination of two types of areas (target area and background area) with different gray levels by utilizing the difference of the target area to be extracted in the image and the background thereof in gray characteristics, so that the most reasonable segmentation threshold is determined, and the corresponding binary image is finally generated.
The detection area is extracted, the lens area is acted by water vapor, the background is black light-absorbing flannelette, so the lens area is extracted by binarization, and the accuracy of the lens area is judged. Fig. 7 is a detection area image.
Referring to fig. 8 to 11, since the threshold segmentation method is suitable for the situation of strong contrast between the target and the background gray level, the present application can select the threshold segmentation method to perform the image detection segmentation process. The selection of the threshold value is the key of successful segmentation, wherein the criterion function method which can be selected is Otsu method, histogram threshold value method and the like. The optimal threshold is determined by simulating the two image threshold segmentation algorithms, and the optimal threshold segmentation image binarization is applied.
It can be seen from fig. 9 that the best threshold determined by using the Otsu method has better effect, low image distortion, and is more suitable for the subsequent image recognition and automation, while fig. 11 shows that the image distortion of the lens image after passing through the histogram threshold method is related to the manually selected threshold, and in the application, the histogram threshold method needs to manually determine a proper threshold, which is not suitable for the automation requirement of the application, so that the Otsu method is designed and selected to divide the threshold.
Image defect impurity feature extraction and identification, and digital image feature extraction and identification are all the time important points and difficulties in the field of machine vision. In actual image processing, there is no fixed algorithm for feature extraction recognition. The design is mainly aimed at non-film defects, which are mainly point injuries, scratches and bubbles. Basic algorithms matched with the characteristics are compiled according to the characteristics. The point damage is mainly formed by small isolated connected domains, bubbles are all arranged at the edge of the lens and determined by the processing process of the resin lens, then the bubble defect is in a circular connected domain, the defect is identified by a Hough detection circle method, and the scratch is characterized in that the coordinates of the defect gray mutation points are approximately continuous, and the continuity of the edge gray coordinates in the connected domain can be identified. FIG. 12 is an image after identifying marks, wherein scratches and point wounds are marked in the image, and the order from left to right is 1-4, wherein 1,2 and 4 are point wounds, and 3 is a scratch.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.
Claims (9)
1. A lens inspection system, comprising:
a single-sided spraying station for spraying mist liquid to only a single surface of the lens to form a mist film surface;
the image acquisition station is used for acquiring images of the fog film surface;
The lens transfer mechanism is used for grabbing lenses and transferring the lenses from the single-sided spraying station to the image acquisition station;
The image processing system is used for receiving the image of the fog film surface and carrying out defect detection on the image of the fog film surface, wherein the defect detection comprises a defect position detection module and/or a defect type distinguishing module, and the defect detection comprises the following steps:
The defect position detection module is used for judging whether defects exist on the fog film surface according to image analysis on the image of the fog film surface;
the defect type distinguishing module is used for judging the types of defects according to image analysis of the image of the fog film surface, wherein the types of defects comprise point dust and point defects;
the dust spot identification method comprises the following steps:
Image preprocessing, namely performing median filtering, image smoothing and image enhancement on the image of the foggy film surface to obtain a preprocessed image;
Expanding the image, and performing expansion processing on the preprocessed image;
image target recognition, namely recognizing a target area in the inflated image;
the method for distinguishing the point dust and the point defect divides the target area into the point dust or the point defect, and specifically comprises the following steps:
When the center gray level of the target area is higher than the lens gray level and the edge gray level of the target area is lower than the lens gray level, the identification result is point dust, otherwise, the identification result is point defect;
or extracting the edge of the target area based on the bright and dark boundary, and when the center distance between the two defects is smaller than the threshold value, identifying the two defects as point dust, otherwise, identifying the two defects as point defects.
2. The lens inspection system of claim 1, wherein the single-sided spray station comprises:
the spraying device converts the liquid in the liquid storage bin into vaporific liquid and sprays the vaporific liquid onto a single surface of the lens;
and the temperature adjusting device is used for adjusting the temperature of the liquid in the liquid storage bin according to the detection requirement.
3. The lens inspection system of claim 1 further comprising a blow-dry station for removing misting liquid from the lens.
4. The lens inspection system of claim 1 wherein the image capture station comprises an image capture device, a light supplement lamp and a light absorbing plate, the image capture device and the light supplement lamp being positioned on one side of the foggy surface of the lens and the light absorbing plate being positioned on the other side of the foggy surface of the lens in operation.
5. A method for inspecting a lens, comprising:
s1, spraying mist liquid on a single surface of a lens to form a mist film surface;
S2, collecting an image of a fog film surface;
S3, receiving the image of the fog film surface, and carrying out defect detection on the image of the fog film surface, wherein the defect detection comprises defect position detection and/or defect type distinction, and the method comprises the following steps:
The defect position detection judges whether defects exist on the fog film surface according to image analysis on the image of the fog film surface;
the defect type distinction judges the defect type according to image analysis of the image of the fog film surface, wherein the defect type comprises point dust and point defects;
the dust spot identification method comprises the following steps:
Image preprocessing, namely performing median filtering, image smoothing and image enhancement on the image of the foggy film surface to obtain a preprocessed image;
Expanding the image, and performing expansion processing on the preprocessed image;
image target recognition, namely recognizing a target area in the inflated image;
the method for distinguishing the point dust and the point defect divides the target area into the point dust or the point defect, and specifically comprises the following steps:
When the center gray level of the target area is higher than the lens gray level and the edge gray level of the target area is lower than the lens gray level, the identification result is point dust, otherwise, the identification result is point defect;
or extracting the edge of the target area based on the bright and dark boundary, and when the center distance between the two defects is smaller than the threshold value, identifying the two defects as point dust, otherwise, identifying the two defects as point defects.
6. The method for detecting lenses according to claim 5, wherein S1 is specifically:
s101, adjusting the temperature of liquid in a liquid storage bin according to detection requirements;
S102, converting the liquid meeting the temperature requirement into vaporific liquid, and spraying the vaporific liquid onto a single surface of the lens.
7. The method of claim 5, wherein the defect location detection comprises method one and/or method two, wherein:
The method comprises the steps of firstly, carrying out image analysis on an image of a fog film surface to obtain the distribution condition of the fog and/or the defect mode, and obtaining the position of the defect according to the distribution condition of the fog and/or the defect mode, wherein when the fog film is in a non-uniform distribution state, judging that the defect exists on one surface of the sprayed fog liquid;
the method comprises the steps of S1, obtaining an infrared image of a fog film surface by an infrared camera in S2, obtaining the position of a defect by analyzing the infrared image in S3, and finally, repeatedly detecting the position of the defect by changing the temperature of the liquid in S1.
8. The method of claim 5, wherein the defect type differentiation comprises method a and/or method B, wherein:
The method A carries out defect type distinction based on the difference of optical effects, namely, carrying out image analysis on the image of the fog film surface to obtain refraction, scattering and reflection modes of defects on light rays, and carrying out defect type distinction according to the refraction, scattering and reflection modes;
And B, distinguishing defect types based on temperature and condensation speed, namely obtaining the distribution condition of the fog liquid at the defect position according to image analysis of the image of the fog film surface, wherein the distribution condition is punctiform defect or scratch defect when the fog liquid is gathered at the defect position, and is punctiform dust when the fog liquid is scattered.
9. The lens inspection method according to claim 5, wherein in the image analysis for defect type discrimination, the discrimination method of point-like defects, bubble defects and scratch defects includes:
Image preprocessing, namely performing median filtering, image smoothing and image enhancement on the image of the foggy film surface to obtain a preprocessed image;
eliminating point dust on the preprocessed image, firstly identifying the point dust by using an identification method of the point dust, and then eliminating the point dust to obtain a defect image;
Dividing and extracting a defect image, namely dividing the defect image into a plurality of areas, and extracting a target object from the images of different areas by adopting an image threshold dividing technology;
Performing defect identification according to the characteristics of the defects, wherein:
when the extracted target objects are mutually isolated connected domains, identifying the extracted target objects as point defects;
when the extracted target object is a similar circular connected domain and appears at the edge of the lens, identifying whether the target object is a bubble or not by a Hough detection circle method;
And when the extracted target object is a gray abrupt change line with continuous coordinates, identifying the scratch defect by judging the continuity of the gray coordinates of the edges in the connected domain.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411160379.2A CN118688121B (en) | 2024-08-22 | 2024-08-22 | Lens detection system and detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411160379.2A CN118688121B (en) | 2024-08-22 | 2024-08-22 | Lens detection system and detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118688121A CN118688121A (en) | 2024-09-24 |
| CN118688121B true CN118688121B (en) | 2024-12-13 |
Family
ID=92768181
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411160379.2A Active CN118688121B (en) | 2024-08-22 | 2024-08-22 | Lens detection system and detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118688121B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR200319553Y1 (en) * | 2003-04-07 | 2003-07-12 | 주식회사 심우 | The surface inspect apparatus of glass for display device |
| CN109030501A (en) * | 2018-07-31 | 2018-12-18 | 苏州天准科技股份有限公司 | A kind of mobile phone glass AF film surface Defect Detection device and detection method |
| CN117405683A (en) * | 2023-11-13 | 2024-01-16 | 苏州元瞰科技有限公司 | Cover plate glass AG processing uniformity detection method and detection device |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2500630A1 (en) * | 1981-02-25 | 1982-08-27 | Leser Jacques | METHOD FOR SEARCHING FOR DEFECTS IN GLASS SHEETS AND DEVICE USING SAID METHOD |
| JP2005249489A (en) * | 2004-03-02 | 2005-09-15 | Seiko Epson Corp | Defect detection method for eyeglass lenses |
| JP2010137663A (en) * | 2008-12-10 | 2010-06-24 | Toyota Motor Corp | Spectacles monitoring device |
| CN115393358B (en) * | 2022-10-28 | 2023-01-31 | 菲特（天津）检测技术有限公司 | Lens detection method and multi-station detection device |
-
2024
- 2024-08-22 CN CN202411160379.2A patent/CN118688121B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR200319553Y1 (en) * | 2003-04-07 | 2003-07-12 | 주식회사 심우 | The surface inspect apparatus of glass for display device |
| CN109030501A (en) * | 2018-07-31 | 2018-12-18 | 苏州天准科技股份有限公司 | A kind of mobile phone glass AF film surface Defect Detection device and detection method |
| CN117405683A (en) * | 2023-11-13 | 2024-01-16 | 苏州元瞰科技有限公司 | Cover plate glass AG processing uniformity detection method and detection device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118688121A (en) | 2024-09-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109816644B (en) | An automatic detection system for bearing defects based on multi-angle light source images | |
| KR101343901B1 (en) | Method and apparatus for eye detection in digital image | |
| JP3581314B2 (en) | Automatic lens inspection system | |
| CN103913468B (en) | Many defects of vision checkout equipment and the method for large-scale LCD glass substrate on production line | |
| US3988068A (en) | Method and apparatus for detecting cosmetic defects in opthalmic lenses | |
| EP0686842B1 (en) | Ophtalmic lens inspection with a double focus illumination | |
| US4876457A (en) | Method and apparatus for differentiating a planar textured surface from a surrounding background | |
| RU2764644C1 (en) | Method for detecting surface defects, device for detecting surface defects, method for producing steel materials, method for steel material quality control, steel materials production plant, method for generating models for determining surface defects and a model for determining surface defects | |
| CN109523541A (en) | A kind of metal surface fine defects detection method of view-based access control model | |
| CN106780473B (en) | A kind of magnet ring defect multi-vision visual detection method and system | |
| CN109001212A (en) | A kind of stainless steel soup ladle defect inspection method based on machine vision | |
| CN107610085A (en) | A kind of welding point defect detecting system based on computer vision | |
| CN109816627B (en) | Target detection method for weak and small defects in the ink area of flat glass components | |
| CN113252568A (en) | Lens surface defect detection method, system, product and terminal based on machine vision | |
| CN108320282A (en) | The ceramic wall and floor bricks surface defect detection apparatus and its method of multicharacteristic information fusion | |
| US20170045448A1 (en) | Apparatus of Detecting Transmittance of Trench on Infrared-Transmittable Material and Method Thereof | |
| Fu et al. | Medicine glass bottle defect detection based on machine vision | |
| CN110096980A (en) | Character machining identifying system | |
| CN111307819A (en) | Wafer edge defect detection system and method | |
| EP0686841A2 (en) | System and method for inspecting lenses | |
| CN118501177A (en) | Appearance defect detection method and system for formed foil | |
| CN106770372B (en) | Detection method of white glass surface defects based on microscopic vision | |
| CN118566248A (en) | Chip patch precision visual detection method | |
| CN115731228A (en) | Gold-plated chip defect detection system and method | |
| CN118688121B (en) | Lens detection system and detection method |
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 |