CN116026861A - Glass bottle detection method and system - Google Patents
Glass bottle detection method and system Download PDFInfo
- Publication number
- CN116026861A CN116026861A CN202310163758.6A CN202310163758A CN116026861A CN 116026861 A CN116026861 A CN 116026861A CN 202310163758 A CN202310163758 A CN 202310163758A CN 116026861 A CN116026861 A CN 116026861A
- Authority
- CN
- China
- Prior art keywords
- image
- glass bottle
- sub
- judging
- size
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000011521 glass Substances 0.000 title claims abstract description 179
- 238000001514 detection method Methods 0.000 title claims abstract description 72
- 230000007547 defect Effects 0.000 claims abstract description 39
- 230000002950 deficient Effects 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 16
- 238000007689 inspection Methods 0.000 claims abstract description 5
- 238000012216 screening Methods 0.000 claims description 41
- 238000005457 optimization Methods 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000013361 beverage Nutrition 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002834 transmittance Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
A method and a system for detecting a glass bottle comprise the following steps: shooting glass bottles passing through a conveyor belt to obtain a glass bottle detection image; positioning the detection image, acquiring the region of the glass bottle in the detection image, and rotating the detection frame to the region of the glass bottle; and analyzing the image in the detection frame to judge whether the glass bottle in the detection frame has defects, marking the glass as defective products if the glass bottle has the defects, detecting the size of the glass bottle if the glass bottle has the defects, judging whether the size threshold is met, and marking the glass bottle as defective products if the size threshold is not met. And the identification model is used for identifying the glass bottle and acquiring the area where the glass bottle is located, and then the identification frame is moved to the area where the glass bottle is located through an algorithm, so that background images are reduced, and the success rate of defect judgment of the glass bottle is improved. According to the invention, intelligent quality inspection is performed on the glass bottle through the identification technology, so that the cost of manual detection is reduced, and the detection efficiency is improved.
Description
Technical Field
The invention relates to the technical field of glass bottle detection, in particular to a glass bottle detection method and a glass bottle detection system.
Background
With the development of society, glass bottles are widely used in beverage industry, pharmaceutical industry and the like. In order to ensure the production quality of the glass bottle, quality detection is required before delivery of the glass bottle, and unqualified products are removed.
In the current related production links, a manual detection mode is adopted to detect the quality of the glass bottles, and the detected unqualified products are removed from the production line. However, the glass bottle is a product with high demand and high production capacity, and the manual detection mode has low efficiency and high cost, so that the production development is restricted to a certain extent.
Disclosure of Invention
Aiming at the defects, the invention aims to provide a method and a system for detecting the glass bottle, which are used for intelligently inspecting the quality of the glass bottle through an identification technology, so that the cost of manual detection is reduced, and meanwhile, the detection efficiency is improved.
To achieve the purpose, the invention adopts the following technical scheme: the method for detecting the glass bottle comprises the following steps:
step S1: shooting glass bottles passing through a conveyor belt to obtain a glass bottle detection image;
step S2: positioning the detection image, acquiring the region of the glass bottle in the detection image, and rotating the detection frame to the region of the glass bottle;
step S3: and analyzing the image in the detection frame to judge whether the glass bottle in the detection frame has defects, marking the glass as defective products if the glass bottle has the defects, detecting the size of the glass bottle if the glass bottle has the defects, judging whether the size threshold is met, and marking the glass bottle as defective products if the size threshold is not met.
Preferably, the specific step of determining whether the glass bottle in the detection frame has a defect in the step S3 is as follows:
step S31: dividing the image in the detection frame by using a gray threshold dividing algorithm to obtain at least two first sub-images, acquiring first sub-images with gray levels larger than a gray threshold, judging the first sub-images by using a first judging parameter to obtain a first screening result, and if the first screening result meets the requirement, performing step S32;
step S32: dividing the screened first sub-image by using a dynamic threshold dividing algorithm to obtain a plurality of second sub-images, obtaining the second sub-image with the largest brightness change, judging the second sub-image by using a second judging parameter to obtain a second screening result, and if the second screening result meets the requirement, performing step S33;
step S33: and searching the screened first sub-image by using a linear feature searching algorithm to obtain an in-doubt region in the first sub-image, judging the in-doubt region by a third judging parameter to obtain a third screening result, and if the third screening result meets the requirement, judging that the current glass bottle has no defect.
Preferably, before step S3 is performed, image optimization is further required for the detected image;
wherein the image optimization includes one or more of image filtering, enhancement algorithms, and denoising operations.
Preferably, the step of detecting the size of the glass bottle is as follows:
obtaining the pixel size of a photo of the model glass bottle at different distances from a camera, and obtaining the pixel distance ratio of the model glass bottle in the camera through a plurality of groups of pixel sizes, wherein the pixel distance ratio comprises the pixel distance ratio in the horizontal direction and the pixel distance ratio in the vertical direction;
obtaining the pixel size of the length and width of the screened first sub-image on the picture, obtaining the real size of the first sub-image through the pixel distance ratio and the pixel size of the length and width of the first sub-image on the picture, and judging whether the real size meets the size threshold of the glass bottle.
A glass bottle detection system uses a glass bottle detection method, which comprises a shooting module, a positioning module and a judging module;
the shooting module is used for shooting glass bottles passing through the conveyor belt to obtain a glass bottle detection image;
the positioning module is used for positioning the detection image, acquiring the region of the glass bottle in the detection image, and rotating the detection frame to the region of the glass bottle;
the judging module is used for analyzing the image in the detecting frame to judge whether the glass bottle in the detecting frame has defects, if so, marking the glass as defective products, if not, detecting the size of the glass bottle, judging whether the size threshold is met, and if not, marking the glass as defective products.
Preferably, the judging module comprises a defect judging sub-module;
the defect judging submodule comprises a first judging unit, a second judging unit and a third judging unit;
the first judging unit is used for dividing the image in the detection frame by using a gray threshold dividing algorithm to obtain at least two first sub-images, acquiring first sub-images with gray levels larger than a gray threshold, judging the first sub-images through first judging parameters to obtain a first screening result, and calling the second judging unit if the first screening result meets the requirement;
the second judging unit is used for dividing the screened first sub-image by using a dynamic threshold dividing algorithm, obtaining a plurality of second sub-images, obtaining a second sub-image with the largest brightness change, judging the second sub-image through a second judging parameter to obtain a second screening result, and calling a third judging unit if the second screening result meets the requirement;
the third judging unit is used for searching the screened first sub-image by using a linear feature searching algorithm, acquiring an in-doubt region in the first sub-image, judging the in-doubt region through a third judging parameter to obtain a third screening result, and if the third screening result meets the requirement, the current glass bottle has no defect.
Preferably, the system further comprises an image preprocessing module, wherein the image preprocessing module is used for optimizing the detected image;
wherein the image optimization includes one or more of image filtering, enhancement algorithms, and denoising operations.
Preferably, the judging module comprises a size judging sub-module, wherein the size judging sub-module is used for acquiring the pixel sizes of the photographs of the model glass bottle at different distances from the camera, and acquiring the pixel distance ratio of the model glass bottle in the camera through a plurality of groups of pixel sizes, wherein the pixel distance ratio comprises the pixel distance ratio in the horizontal direction and the pixel distance ratio in the vertical direction;
obtaining the pixel size of the length and width of the screened first sub-image on the picture, obtaining the real size of the first sub-image through the pixel distance ratio and the pixel size of the length and width of the first sub-image on the picture, and judging whether the real size meets the size threshold of the glass bottle.
One of the above technical solutions has the following advantages or beneficial effects: and detecting the glass bottle in the image through the identification model, acquiring the region where the glass bottle is located, and then moving the identification frame to the region where the glass bottle is located through an algorithm so as to reduce background images and improve the success rate of defect judgment of the glass bottle. And then judging the defects of the glass bottle, judging the size of the glass bottle further when the defects are not found after judging the glass bottle, if the size also meets the requirement, judging the glass bottle as a good product, and if one of the sizes does not meet the requirement, judging the glass bottle as a defective product. According to the invention, intelligent quality inspection is performed on the glass bottle through the identification technology, so that the cost of manual detection is reduced, and the detection efficiency is improved.
Drawings
FIG. 1 is a flow chart of one embodiment of the method of the present invention.
Fig. 2 is a schematic diagram of the architecture of one embodiment of the system of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for explaining the present invention and are not to be construed as limiting the present invention.
In the description of embodiments of the present invention, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the embodiments of the present invention, the meaning of "plurality" is two or more, unless explicitly defined otherwise.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present invention, unless otherwise indicated, the meaning of "a plurality" is two or more. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
As shown in fig. 1-2, a method for detecting a glass bottle comprises the following steps:
step S1: shooting glass bottles passing through a conveyor belt to obtain a glass bottle detection image;
step S2: positioning the detection image, acquiring the region of the glass bottle in the detection image, and rotating the detection frame to the region of the glass bottle;
step S3: and analyzing the image in the detection frame to judge whether the glass bottle in the detection frame has defects, marking the glass as defective products if the glass bottle has the defects, detecting the size of the glass bottle if the glass bottle has the defects, judging whether the size threshold is met, and marking the glass bottle as defective products if the size threshold is not met.
In the invention, the glass bottle is placed on the conveyor belt, the glass bottle is conveyed by the conveyor belt, the photoelectric sensor is arranged on the glass bottle in the conveying process, the camera is controlled by the photoelectric sensor, and at the moment, the glass bottle is shot by the camera, so that a detection image with glass is obtained. And then training an identification model of the glass bottle through the existing model training, detecting the glass bottle in the image through the identification model, acquiring the area where the glass bottle is located, and then moving the identification frame to the area where the glass bottle is located through an algorithm so as to reduce the background image and improve the defect judging success rate of the glass bottle. And then judging the defects of the glass bottle, judging the size of the glass bottle further when the defects are not found after judging the glass bottle, if the size also meets the requirement, judging the glass bottle as a good product, and if one of the sizes does not meet the requirement, judging the glass bottle as a defective product. According to the invention, intelligent quality inspection is performed on the glass bottle through the identification technology, so that the cost of manual detection is reduced, and the detection efficiency is improved.
Preferably, the specific step of determining whether the glass bottle in the detection frame has a defect in the step S3 is as follows:
step S31: dividing the image in the detection frame by using a gray threshold dividing algorithm to obtain at least two first sub-images, acquiring first sub-images with gray levels larger than a gray threshold, judging the first sub-images by using a first judging parameter to obtain a first screening result, and if the first screening result meets the requirement, performing step S32;
in the method, firstly, a detection image is segmented by using a gray threshold segmentation algorithm to obtain a first sub-image, a background part and a glass bottle entity part exist in the first sub-image, and in order to distinguish clear glass bottles and background parts, screening is carried out according to gray threshold values after the first sub-image is obtained, different gray threshold values are selected for different glass bottles, for example, when a non-transparent glass bottle is judged, the gray level of the glass bottle is smaller than that of the surrounding environment in the natural environment because the glass bottle is non-transparent, and at the moment, the entity of the glass bottle in the detection image can be judged only by selecting the first sub-image with a large gray level value. After the first sub-image is screened, the entity of the glass bottle is clarified, and then the entity of the glass bottle is further judged, wherein the first judging parameter can be the shape integrity of the glass bottle of the first sub-image, when the shape of the glass bottle of the first sub-image is incomplete, the fact that a gap can appear at the edge of the current shooting angle of the current glass bottle is indicated, at the moment, the first screening result does not meet the requirement, and the glass bottle is a defective product.
Step S32: dividing the screened first sub-image by using a dynamic threshold dividing algorithm to obtain a plurality of second sub-images, obtaining the second sub-image with the largest brightness change, judging the second sub-image by using a second judging parameter to obtain a second screening result, and if the second screening result meets the requirement, performing step S33;
when the shape of the glass bottle is complete, the next step of judgment is performed, and because the judgment in the step S31 is that the shape of the edge of the glass bottle is complete under the current visual angle, if a notch or irregular deformation appears in the middle part of the glass bottle, the judgment cannot be performed through the step S31, so in the invention, the screened first sub-image is segmented through a dynamic threshold segmentation algorithm, wherein the dynamic threshold in the dynamic threshold segmentation method can be brightness. When the glass bottle is defective or split, the light transmission under normal light is different from that of normal glass, so after the plurality of second sub-images are divided, the plurality of second sub-images are compared with each other, a second sub-image with large brightness variation is obtained, and whether the brightness in the second sub-image meets the requirement of a second judgment parameter or not is judged, wherein the second judgment parameter is a brightness parameter. When the brightness in the second sub-image does not meet the brightness parameter, the second screening result does not meet the requirement, and the glass bottle is a defective product.
Step S33: and searching the screened first sub-image by using a linear feature searching algorithm to obtain an in-doubt region in the first sub-image, judging the in-doubt region by a third judging parameter to obtain a third screening result, and if the third screening result meets the requirement, judging that the current glass bottle has no defect.
If the glass bottle has a fine crack, the effect on the light transmittance of the glass bottle is very small, so that the method in step S32 cannot identify whether the glass bottle has a crack or a scratch, and in step S33, the first sub-image after screening is identified and searched by using a linear feature searching algorithm, and a linear image existing in the first sub-image is found and marked as a suspicious region. Since the line image of the suspicious region is not necessarily a crack or a scratch. In the invention, the suspicious region is judged by a third judging parameter, wherein the third judging parameter is a model parameter of a crack or a scratch, and whether the crack or the scratch is judged by comparing the model parameter with a linear image in the suspicious region. If the third screening result meets the requirement, the current glass bottle has no defect.
Preferably, before step S3 is performed, image optimization is further required for the detected image;
wherein the image optimization includes one or more of image filtering, enhancement algorithms, and denoising operations.
Preferably, the step of detecting the size of the glass bottle is as follows:
obtaining the pixel size of a photo of the model glass bottle at different distances from a camera, and obtaining the pixel distance ratio of the model glass bottle in the camera through a plurality of groups of pixel sizes, wherein the pixel distance ratio comprises the pixel distance ratio in the horizontal direction and the pixel distance ratio in the vertical direction;
obtaining the pixel size of the length and width of the screened first sub-image on the picture, obtaining the real size of the first sub-image through the pixel distance ratio and the pixel size of the length and width of the first sub-image on the picture, and judging whether the real size meets the size threshold of the glass bottle.
The method for confirming the pixel distance of the model glass bottle comprises the following steps: using a model glass bottle of known size, photographing the calibration object when the camera is at a distance d=1, 2,3,4,5m, respectively, and calculating the pixel distances of the width x and the height y in the image by using a picture tool. For example, the actual width and height of the calibration object are respectively 0.284 m and 0.289m, when the camera is away from the calibration object d=1m, the pixel distance x=200pixels and y=300pixels; when the camera is at a distance d=2m, the pixel distance x=100pixels, and y=150pixels. Since there is a linear relationship between the pixel distance and the actual distance, when d=3m can be calculated afterwards, x=66pix, y=100deg.pix; when d=4m, x=50pix, y=75pix; when d=5m, x=40pix, y=60deg.pix. At a vertical distance of one meter, 1 pixel represents the actual distance: x=0.285 m/200, y=0.289 m/300. At a vertical distance of two meters, 1 pixel represents the actual distance: x=0.285 m/100=0.285 × (200/d), y=0.289 m/150=0.289/300/d. At a vertical distance of n meters, the pixel distance ratio of 1 pixel in the horizontal direction is: x=0.285++200/n, the pixel distance ratio in the vertical direction for 1 pixel is: y=0.289 ≡ (300/n). Because each camera has a different pixel distance, the pixel distance needs to be measured using the method described above before use.
In the detection process, as the glass bottle is already intercepted in the step S31, the real size of the glass bottle currently shot can be judged through the pixel size and the pixel distance ratio in the horizontal direction and the vertical direction in the screened first sub-image, and the size detection is realized.
A glass bottle detection system uses a glass bottle detection method, which comprises a shooting module, a positioning module and a judging module;
the shooting module is used for shooting glass bottles passing through the conveyor belt to obtain a glass bottle detection image;
the positioning module is used for positioning the detection image, acquiring the region of the glass bottle in the detection image, and rotating the detection frame to the region of the glass bottle;
the judging module is used for analyzing the image in the detecting frame to judge whether the glass bottle in the detecting frame has defects, if so, marking the glass as defective products, if not, detecting the size of the glass bottle, judging whether the size threshold is met, and if not, marking the glass as defective products.
Preferably, the judging module comprises a defect judging sub-module;
the defect judging submodule comprises a first judging unit, a second judging unit and a third judging unit;
the first judging unit is used for dividing the image in the detection frame by using a gray threshold dividing algorithm to obtain at least two first sub-images, acquiring first sub-images with gray levels larger than a gray threshold, judging the first sub-images through first judging parameters to obtain a first screening result, and calling the second judging unit if the first screening result meets the requirement;
the second judging unit is used for dividing the screened first sub-image by using a dynamic threshold dividing algorithm, obtaining a plurality of second sub-images, obtaining a second sub-image with the largest brightness change, judging the second sub-image through a second judging parameter to obtain a second screening result, and calling a third judging unit if the second screening result meets the requirement;
the third judging unit is used for searching the screened first sub-image by using a linear feature searching algorithm, acquiring an in-doubt region in the first sub-image, judging the in-doubt region through a third judging parameter to obtain a third screening result, and if the third screening result meets the requirement, the current glass bottle has no defect.
Preferably, the system further comprises an image preprocessing module, wherein the image preprocessing module is used for optimizing the detected image;
wherein the image optimization includes one or more of image filtering, enhancement algorithms, and denoising operations.
Preferably, the judging module comprises a size judging sub-module, wherein the size judging sub-module is used for acquiring the pixel sizes of the photographs of the model glass bottle at different distances from the camera, and acquiring the pixel distance ratio of the model glass bottle in the camera through a plurality of groups of pixel sizes, wherein the pixel distance ratio comprises the pixel distance ratio in the horizontal direction and the pixel distance ratio in the vertical direction;
obtaining the pixel size of the length and width of the screened first sub-image on the picture, obtaining the real size of the first sub-image through the pixel distance ratio and the pixel size of the length and width of the first sub-image on the picture, and judging whether the real size meets the size threshold of the glass bottle.
In the description of the present specification, reference to the terms "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives, and variations of the above embodiments may be made by those of ordinary skill in the art within the scope of the invention.
Claims (8)
1. The method for detecting the glass bottle is characterized by comprising the following steps of:
step S1: shooting glass bottles passing through a conveyor belt to obtain a glass bottle detection image;
step S2: positioning the detection image, acquiring the region of the glass bottle in the detection image, and rotating the detection frame to the region of the glass bottle;
step S3: and analyzing the image in the detection frame to judge whether the glass bottle in the detection frame has defects, marking the glass as defective products if the glass bottle has the defects, detecting the size of the glass bottle if the glass bottle has the defects, judging whether the size threshold is met, and marking the glass bottle as defective products if the size threshold is not met.
2. The method for inspecting glass bottles as claimed in claim 1, wherein,
the specific step of judging whether the glass bottle in the detection frame has defects in the step S3 is as follows:
step S31: dividing the image in the detection frame by using a gray threshold dividing algorithm to obtain at least two first sub-images, acquiring first sub-images with gray levels larger than a gray threshold, judging the first sub-images by using a first judging parameter to obtain a first screening result, and if the first screening result meets the requirement, performing step S32;
step S32: dividing the screened first sub-image by using a dynamic threshold dividing algorithm to obtain a plurality of second sub-images, obtaining the second sub-image with the largest brightness change, judging the second sub-image by using a second judging parameter to obtain a second screening result, and if the second screening result meets the requirement, performing step S33;
step S33: and searching the screened first sub-image by using a linear feature searching algorithm to obtain an in-doubt region in the first sub-image, judging the in-doubt region by a third judging parameter to obtain a third screening result, and if the third screening result meets the requirement, judging that the current glass bottle has no defect.
3. The method according to claim 2, wherein before step S3, the detected image is further subjected to image optimization;
wherein the image optimization includes one or more of image filtering, enhancement algorithms, and denoising operations.
4. The method for inspecting glass bottles as claimed in claim 2 wherein the step of inspecting the size of glass bottles comprises the steps of:
obtaining the pixel size of a photo of the model glass bottle at different distances from a camera, and obtaining the pixel distance ratio of the model glass bottle in the camera through a plurality of groups of pixel sizes, wherein the pixel distance ratio comprises the pixel distance ratio in the horizontal direction and the pixel distance ratio in the vertical direction;
obtaining the pixel size of the length and width of the screened first sub-image on the picture, obtaining the real size of the first sub-image through the pixel distance ratio and the pixel size of the length and width of the first sub-image on the picture, and judging whether the real size meets the size threshold of the glass bottle.
5. A glass bottle detection system, which uses the glass bottle detection method according to any one of claims 1 to 4, and is characterized by comprising a shooting module, a positioning module and a judging module;
the shooting module is used for shooting glass bottles passing through the conveyor belt to obtain a glass bottle detection image;
the positioning module is used for positioning the detection image, acquiring the region of the glass bottle in the detection image, and rotating the detection frame to the region of the glass bottle;
the judging module is used for analyzing the image in the detecting frame to judge whether the glass bottle in the detecting frame has defects, if so, marking the glass as defective products, if not, detecting the size of the glass bottle, judging whether the size threshold is met, and if not, marking the glass as defective products.
6. The system of claim 5, wherein the judging module comprises a defect judging sub-module;
the defect judging submodule comprises a first judging unit, a second judging unit and a third judging unit;
the first judging unit is used for dividing the image in the detection frame by using a gray threshold dividing algorithm to obtain at least two first sub-images, acquiring first sub-images with gray levels larger than a gray threshold, judging the first sub-images through first judging parameters to obtain a first screening result, and calling the second judging unit if the first screening result meets the requirement;
the second judging unit is used for dividing the screened first sub-image by using a dynamic threshold dividing algorithm, obtaining a plurality of second sub-images, obtaining a second sub-image with the largest brightness change, judging the second sub-image through a second judging parameter to obtain a second screening result, and calling a third judging unit if the second screening result meets the requirement;
the third judging unit is used for searching the screened first sub-image by using a linear feature searching algorithm, acquiring an in-doubt region in the first sub-image, judging the in-doubt region through a third judging parameter to obtain a third screening result, and if the third screening result meets the requirement, the current glass bottle has no defect.
7. The glass bottle inspection system of claim 5, further comprising an image pre-processing module for further requiring image optimization of the inspection image;
wherein the image optimization includes one or more of image filtering, enhancement algorithms, and denoising operations.
8. The system for detecting glass bottles according to claim 6, wherein the judging module comprises a size judging sub-module, the size judging sub-module is used for obtaining model glass bottles with known sizes and shooting at different distances of a camera, obtaining pixel sizes of pictures of the model glass bottles at different distances, and obtaining pixel distance ratios of the model glass bottles in the camera through a plurality of groups of pixel sizes, wherein the pixel distance ratios comprise pixel distance ratios in a horizontal direction and pixel distance ratios in a vertical direction;
obtaining the pixel size of the length and width of the screened first sub-image on the picture, obtaining the real size of the first sub-image through the pixel distance ratio and the pixel size of the length and width of the first sub-image on the picture, and judging whether the real size meets the size threshold of the glass bottle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310163758.6A CN116026861A (en) | 2023-02-24 | 2023-02-24 | Glass bottle detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310163758.6A CN116026861A (en) | 2023-02-24 | 2023-02-24 | Glass bottle detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116026861A true CN116026861A (en) | 2023-04-28 |
Family
ID=86077761
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310163758.6A Pending CN116026861A (en) | 2023-02-24 | 2023-02-24 | Glass bottle detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116026861A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118469518A (en) * | 2024-07-09 | 2024-08-09 | 齐鲁高速公路股份有限公司 | Safe use method and device of open fire air source, electronic equipment and program product |
| CN119737887A (en) * | 2024-12-23 | 2025-04-01 | 佛山市三力智能设备科技有限公司 | Method for detecting out-of-roundness and concave-convex defects of glass bottle body |
-
2023
- 2023-02-24 CN CN202310163758.6A patent/CN116026861A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118469518A (en) * | 2024-07-09 | 2024-08-09 | 齐鲁高速公路股份有限公司 | Safe use method and device of open fire air source, electronic equipment and program product |
| CN119737887A (en) * | 2024-12-23 | 2025-04-01 | 佛山市三力智能设备科技有限公司 | Method for detecting out-of-roundness and concave-convex defects of glass bottle body |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111047655B (en) | High-definition camera cloth defect detection method based on convolutional neural network | |
| CN116559183B (en) | Method and system for improving defect judging efficiency | |
| CN116026861A (en) | Glass bottle detection method and system | |
| TW201702586A (en) | Optical film defect detection method and system thereof | |
| CN113658131B (en) | Machine vision-based tour ring spinning broken yarn detection method | |
| CN104992446B (en) | The image split-joint method of non-linear illumination adaptive and its realize system | |
| CN113538603B (en) | Optical detection method and system based on array product and readable storage medium | |
| CN109932369B (en) | Method and device for detecting special-shaped display panel | |
| CN111551559A (en) | LCD (liquid Crystal display) liquid crystal screen defect detection method based on multi-view vision system | |
| CN115620061A (en) | Hardware part defect detection method and system based on image recognition technology | |
| CN112686890A (en) | Artificial board surface defect detection method based on singular value decomposition | |
| CN114119591A (en) | A kind of display screen picture quality detection method | |
| CN118096751B (en) | Injection molding appearance defect detection method and device, electronic equipment and storage medium | |
| CN110189297A (en) | A method for detecting appearance defects of magnetic materials based on gray level co-occurrence matrix | |
| CN111968082A (en) | Product packaging defect detection and identification method based on machine vision | |
| CN112819844A (en) | Image edge detection method and device | |
| CN112669272B (en) | AOI rapid detection method and rapid detection system | |
| CN113192061A (en) | LED package appearance detection image extraction method and device, electronic equipment and storage medium | |
| CN112561875A (en) | Photovoltaic cell panel coarse grid detection method based on artificial intelligence | |
| CN118644484B (en) | Intelligent defect detection method for household textile | |
| CN103175839A (en) | Processing method and system for detection of offset plate surface | |
| CN119444664B (en) | A visual inspection method for welding quality | |
| CN109387527A (en) | On a kind of film in film defect detection method | |
| CN114125435A (en) | Intelligent image defect detection method for network camera | |
| CN112837285A (en) | A method and device for edge detection of a panel image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |