CN117764963A - Packaging bag defect detection method, device, terminal and medium based on machine vision - Google Patents
Packaging bag defect detection method, device, terminal and medium based on machine vision Download PDFInfo
- Publication number
- CN117764963A CN117764963A CN202311809235.0A CN202311809235A CN117764963A CN 117764963 A CN117764963 A CN 117764963A CN 202311809235 A CN202311809235 A CN 202311809235A CN 117764963 A CN117764963 A CN 117764963A
- Authority
- CN
- China
- Prior art keywords
- packaging bag
- defect detection
- image
- determining
- value
- 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.)
- Granted
Links
- 238000004806 packaging method and process Methods 0.000 title claims abstract description 302
- 238000001514 detection method Methods 0.000 title claims abstract description 230
- 230000007547 defect Effects 0.000 title claims abstract description 175
- 238000012545 processing Methods 0.000 claims abstract description 64
- 238000003860 storage Methods 0.000 claims abstract description 9
- 238000012544 monitoring process Methods 0.000 claims description 23
- 238000000034 method Methods 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims 2
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 239000000463 material Substances 0.000 description 4
- 238000012856 packing Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000011185 multilayer composite material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a packaging bag defect detection method, a packaging bag defect detection device, a packaging bag defect detection terminal and a packaging bag defect detection storage medium based on machine vision, wherein packaging bag images to be subjected to defect detection are obtained; processing the packaging bag image based on a preset image processing mode to extract defect detection characteristic data of the packaging bag image; and determining a defect detection result of the packaging bag based on the defect detection characteristic data. The machine vision technology is used for replacing manual detection of defects of the packaging bag, so that the detection quality and the detection efficiency can be remarkably improved, the labor cost is saved, the detection of various defects of the packaging bag is realized only through machine vision, the hardware use efficiency is high, and the realization of simplified hardware is possible.
Description
Technical Field
The invention relates to the technical field of packaging bag detection, in particular to a packaging bag defect detection method, device, terminal and storage medium based on machine vision.
Background
Packaging bags are widely used articles in industrial production and daily life, and they can provide important packaging and protection functions for various products. The manufacture of the packaging bag is a complex process, and many different processes and technologies are required, such as a printing process, various patterns, characters, trademarks and the like can be printed on the packaging bag, a cutting process, printed materials can be cut into a required shape and size, a splicing process, different materials can be spliced together to form a complete packaging bag, a coating process, a layer of material can be coated on the surface of the packaging bag to improve the strength, the water resistance, the moisture resistance and the like of the packaging bag, and a bonding process can bond the two materials together to manufacture the multi-layer composite material. However, during the manufacturing process, the package often suffers from various drawbacks, such as cut-out of the package, print color failure, print overprinting failure, etc. These defects can affect the quality and appearance of the package and, in severe cases, can lead to product damage and waste. Therefore, in actual production, it is necessary to detect defects in the package. At present, the defect detection of the packaging bag mostly depends on manual detection, and the defects of unstable standard, low detection quality, low detection efficiency, high labor cost and the like exist.
Disclosure of Invention
The invention aims to solve the technical problems that the defect detection of the existing packaging bag mostly depends on manual detection, and the existing packaging bag has unstable standard, low detection quality, low detection efficiency and high labor cost.
To solve at least one of the above technical problems, a first aspect of the present invention discloses a machine vision-based packaging bag defect detection method, which includes:
acquiring a packaging bag image to be subjected to defect detection;
processing the packaging bag image based on a preset image processing mode to extract defect detection characteristic data of the packaging bag image;
and determining a defect detection result of the packaging bag based on the defect detection characteristic data.
As an optional implementation manner, in the first aspect of the present invention, the defect detection feature data includes: an outer region length value and an outer region width value, wherein the outer region length value is a length value of a minimum bounding rectangle of an outer target region of the packaging bag image, and the outer region width value is a width value of the minimum bounding rectangle of the outer target region of the packaging bag image;
the processing the packaging bag image based on the preset image processing mode to extract the defect detection characteristic data of the packaging bag image comprises the following steps:
Performing binarization processing on the packaging bag image based on a predetermined first binarization threshold value to obtain a first binarization image corresponding to the packaging bag image;
determining the outer region length value and the outer region width value from the first binarized image;
the determining a defect detection result of the packaging bag based on the defect detection characteristic data comprises the following steps:
judging whether the length value of the external area is in a preset qualified length value interval or not;
judging whether the width value of the external area is in a preset qualified width value interval or not;
when the outer area length value is in the qualified length value interval and the outer area width value is in the qualified width value interval, determining that the size detection of the packaging bag is qualified;
and determining that the size detection of the packaging bag is unqualified when the external area length value is not in the qualified length value interval or the external area width value is not in the qualified width value interval.
As an optional implementation manner, in the first aspect of the present invention, the defect detection feature data further includes: the minimum circumscribed rectangle of the internal target area of the packaging bag image and the number of target pixel points of the internal target area of the packaging bag image;
The processing the packaging bag image based on the preset image processing mode to extract defect detection characteristic data of the packaging bag image further comprises:
performing binarization processing on the packaging bag image based on a second predetermined binarization threshold value to obtain a second binarization image corresponding to the packaging bag image;
determining a minimum circumscribed rectangle of an internal target area of the packaging bag image and the number of target pixel points of the internal target area of the packaging bag image from the second binarized image, wherein the number of target pixel points is the number of white pixels contained in the internal target area in the second binarized image;
the determining the defect detection result of the packaging bag based on the defect detection characteristic data further comprises:
calculating the ratio of the number of the target pixel points to the number of the pixel points contained in the minimum circumscribed rectangle of the internal target area of the packaging bag image;
when the ratio is larger than a preset ratio threshold, determining that the foreign matter detection of the packaging bag is qualified;
and when the ratio is not greater than the ratio threshold, determining that the foreign matter detection of the packaging bag is unqualified.
As an optional implementation manner, in the first aspect of the present invention, the defect detection feature data further includes: the monitoring frame of the packaging bag image;
the processing the packaging bag image based on the preset image processing mode to extract defect detection characteristic data of the packaging bag image further comprises:
determining a monitoring frame of the packaging bag image according to the minimum circumscribed rectangle of the external target area of the packaging bag image;
the determining the defect detection result of the packaging bag based on the defect detection characteristic data further comprises:
when the monitoring frame comprises the minimum circumscribed rectangle of the internal target area of the packaging bag image, determining that the layout of the packaging bag is qualified;
and when the monitoring frame does not contain the minimum circumscribed rectangle of the internal target area of the packaging bag image, determining that the layout detection of the packaging bag is unqualified.
As an optional implementation manner, in the first aspect of the present invention, the defect detection feature data further includes: the number of overprinting mark pixels is the number of pixels occupied by overprinting marks of the packaging bag image;
the processing the packaging bag image based on the preset image processing mode to extract defect detection characteristic data of the packaging bag image further comprises:
Identifying overprinting marks from the packaging bag image, and calculating the number of pixel points occupied by the overprinting marks in the packaging bag image;
the determining the defect detection result of the packaging bag based on the defect detection characteristic data further comprises:
when the number of the overprinting mark pixel points is smaller than a preset pixel point number threshold value, determining that the overprinting detection of the packaging bag is qualified;
and when the number of the overprinting marked pixel points is not smaller than the threshold value of the number of the pixel points, determining that the overprinting detection of the packaging bag is unqualified.
As an optional implementation manner, in the first aspect of the present invention, the defect detection feature data further includes: a color histogram of the package bag image;
the processing the packaging bag image based on the preset image processing mode to extract defect detection characteristic data of the packaging bag image further comprises:
calculating a color histogram of the packaging bag image;
the determining the defect detection result of the packaging bag based on the defect detection characteristic data further comprises:
calculating a histogram difference value of the color histogram of the packaging bag image and the color histogram of the standard packaging bag image;
When the histogram difference value is smaller than a preset histogram difference value threshold value, determining that the color detection of the packaging bag is qualified;
and when the histogram difference is not smaller than the histogram difference threshold, determining that the color detection of the packaging bag is unqualified.
As an optional implementation manner, in the first aspect of the present invention, the defect detection feature data further includes: the deformation value of the packaging bag image;
the processing the packaging bag image based on the preset image processing mode to extract defect detection characteristic data of the packaging bag image further comprises:
comparing the external area length value and the external area width value with a preset standard external area length value and a standard external area width value respectively to obtain a deformation value of the packaging bag image;
the determining the defect detection result of the packaging bag based on the defect detection characteristic data further comprises:
when the deformation value is in a preset deformation value interval, determining that the filling detection of the packaging bag is qualified;
and when the deformation value is not in the deformation value interval, determining that the filling detection of the packaging bag is unqualified.
The second aspect of the invention discloses a packaging bag defect detection device based on machine vision, which comprises:
The acquisition module is used for acquiring the packaging bag image to be subjected to defect detection;
the extraction module is used for processing the packaging bag image based on a preset image processing mode so as to extract defect detection characteristic data of the packaging bag image;
and the determining module is used for determining the defect detection result of the packaging bag based on the defect detection characteristic data.
The third aspect of the invention discloses a packaging bag defect detection terminal based on machine vision, which comprises:
a memory storing executable program code;
a processor coupled to the memory;
the processor invokes the executable program code stored in the memory to perform some or all of the steps in the machine vision-based packaging bag defect detection method disclosed in the first aspect of the present invention.
A fourth aspect of the present invention discloses a computer storage medium storing computer instructions which, when invoked, are used to perform part or all of the steps of the machine vision-based packaging bag defect detection method disclosed in the first aspect of the present invention.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
In the embodiment of the invention, a packaging bag image to be subjected to defect detection is obtained; processing the packaging bag image based on a preset image processing mode to extract defect detection characteristic data of the packaging bag image; and determining a defect detection result of the packaging bag based on the defect detection characteristic data. The machine vision technology is used for replacing manual detection of defects of the packaging bag, so that the detection quality and the detection efficiency can be remarkably improved, the labor cost is saved, the detection of various defects of the packaging bag is realized only through machine vision, the hardware use efficiency is high, and the realization of simplified hardware is possible.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a machine vision-based packaging bag defect detection method according to an embodiment of the present invention;
FIG. 2 is a first binarized image corresponding to a package bag image according to an embodiment of the present invention;
FIG. 3 is a schematic view of a bag image showing a long side attached bag in an embodiment of the present invention;
FIG. 4 is a schematic illustration of a bag image showing a broadside bag in accordance with an embodiment of the present invention;
FIG. 5 is a second binarized image corresponding to a package bag image according to an embodiment of the present invention;
FIG. 6 is a schematic view showing a bag image with shielding of foreign matter in an embodiment of the invention;
FIG. 7 is a schematic diagram showing a package image showing a layout misalignment in an embodiment of the present invention;
FIG. 8 is a schematic view of a monitoring frame for a package image in an embodiment of the present invention;
FIG. 9 is a color histogram of two color channels of a standard bag image in an embodiment of the invention;
FIG. 10 is a color histogram of two color channels of a color difference package image in an embodiment of the present invention;
FIG. 11 is a schematic structural diagram of a packaging bag defect detecting device based on machine vision according to an embodiment of the present invention;
fig. 12 is a schematic structural diagram of a packaging bag defect detecting terminal based on machine vision according to an embodiment of the present invention;
fig. 13 is a schematic diagram of a computer storage medium according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms first, second and the like in the description and in the claims and in the above-described figures are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, apparatus, article, or article that comprises a list of steps or elements is not limited to only those listed but may optionally include other steps or elements not listed or inherent to such process, method, article, or article.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The invention discloses a packaging bag defect detection method, a packaging bag defect detection device, a packaging bag defect detection terminal and a packaging bag defect detection storage medium based on machine vision, wherein packaging bag images to be subjected to defect detection are obtained; processing the packaging bag image based on a preset image processing mode to extract defect detection characteristic data of the packaging bag image; and determining a defect detection result of the packaging bag based on the defect detection characteristic data. The machine vision technology is used for replacing manual detection of defects of the packaging bag, so that the detection quality and the detection efficiency can be remarkably improved, the labor cost is saved, the detection of various defects of the packaging bag is realized only through machine vision, the hardware use efficiency is high, and the realization of simplified hardware is possible. The following will describe in detail.
Example 1
Referring to fig. 1, fig. 1 is a flow chart of a machine vision-based method for detecting defects of a packaging bag according to an embodiment of the invention. As shown in fig. 1, the machine vision-based packaging bag defect detection method may include the following operations:
101. and acquiring an image of the packaging bag to be subjected to defect detection.
102. And processing the packaging bag image based on a preset image processing mode to extract defect detection characteristic data of the packaging bag image.
103. And determining a defect detection result of the packaging bag based on the defect detection characteristic data.
In the embodiment of the invention, the packaging bags to be subjected to defect detection can be transported on a production line in sequence and sequentially pass through the part of the production line provided with the high-speed camera. The high-speed camera captures each passing package bag, and thus an image of each package bag is obtained. Then, defect detection features of each package bag image are extracted, and defect detection of the package bag is performed using the extracted defect detection features.
In an alternative embodiment, the defect detection characteristic data includes: an outer region length value and an outer region width value, wherein the outer region length value is a length value of a minimum bounding rectangle of an outer target region of the packaging bag image, and the outer region width value is a width value of the minimum bounding rectangle of the outer target region of the packaging bag image;
the processing the packaging bag image based on the preset image processing mode to extract the defect detection characteristic data of the packaging bag image comprises the following steps:
performing binarization processing on the packaging bag image based on a predetermined first binarization threshold value to obtain a first binarization image corresponding to the packaging bag image;
Determining the outer region length value and the outer region width value from the first binarized image;
the determining a defect detection result of the packaging bag based on the defect detection characteristic data comprises the following steps:
judging whether the length value of the external area is in a preset qualified length value interval or not;
judging whether the width value of the external area is in a preset qualified width value interval or not;
when the outer area length value is in the qualified length value interval and the outer area width value is in the qualified width value interval, determining that the size detection of the packaging bag is qualified;
and determining that the size detection of the packaging bag is unqualified when the external area length value is not in the qualified length value interval or the external area width value is not in the qualified width value interval.
In this alternative embodiment, the inspection of the package for acceptable size may be accomplished. Specifically, as shown in fig. 2, the separation of the package from the background in the image is achieved by performing image binarization on the package image. The image binarization is a technology of converting an image into a picture composed of black and white pixel points, a binarization threshold is set, if the pixel value of a certain point in the image is larger than the binarization threshold, the point is set as a black pixel point, and if the pixel value of the certain point in the image is not larger than the binarization threshold, the point is set as a white pixel point, so that the binarization of the image can be realized. Since the content of the package images is usually fixed, that is, the content of the package images of the same batch of products is the same, a technician can determine an accurate binarization threshold according to his own experience and actual situations on site, so as to separate the package from the background in the image. After image binarization, the area of the white pixel point is the packaging bag, and then the minimum circumscribed rectangle P of the external target area can be determined according to the area of the white pixel point out And further determining an outer region length value and an outer region width value as defect detection characteristic data. It can be seen that the outside area length value and outside area width value characterize the length and width of the package. Finally, a qualified length value interval and a qualified width value interval are set, and whether the size of the packaging bag is qualified can be judged by judging whether the length value of the outer area and the width value of the outer area are in the qualified interval or not.
Therefore, according to the alternative embodiment, the length characteristic and the width characteristic of the packaging bag are extracted by binarizing the packaging bag image, and the qualified detection of the packaging bag size can be realized according to the extracted length characteristic and width characteristic, so that the actual situation of the packaging bag image can be fully considered, the image binarization is selected to extract the characteristics, the accurate extraction of the size characteristic of the packaging bag can be realized with less image processing information, and the size of the packaging bag can be accurately detected.
In an alternative embodiment, when determining that the size detection of the packaging bag is not qualified, the packaging bag may be further classified according to the extent that the external area length value and the external area width value exceed the qualified length value interval and the qualified width value interval. If the outer area length value and the outer area width value exceed the qualified length value interval and the qualified width value interval by 0% -10%, the dimension failure at the moment can be considered to be caused by normal production deviation; as shown in fig. 3, the length value of the outer area exceeds the interval of the qualified length value by more than 10%, namely that the dimension failure at this time is considered to be caused by the long-side bag connection of the packaging bag; as shown in fig. 4, the outside area width value exceeds the pass width value interval by 10% or more, and it is considered that the dimensional failure at this time is caused by the wide edge of the package bag.
Therefore, by implementing the optional embodiment, the common size error types of the packaging bag can be identified according to the extracted external area length value and external area width value, and the long-side bag connection and the wide-side bag connection of the packaging bag can be accurately identified.
In an alternative embodiment, the defect detection feature data further includes: the minimum circumscribed rectangle of the internal target area of the packaging bag image and the number of target pixel points of the internal target area of the packaging bag image;
the processing the packaging bag image based on the preset image processing mode to extract defect detection characteristic data of the packaging bag image further comprises:
performing binarization processing on the packaging bag image based on a second predetermined binarization threshold value to obtain a second binarization image corresponding to the packaging bag image;
determining a minimum circumscribed rectangle of an internal target area of the packaging bag image and the number of target pixel points of the internal target area of the packaging bag image from the second binarized image, wherein the number of target pixel points is the number of white pixels contained in the internal target area in the second binarized image;
The determining the defect detection result of the packaging bag based on the defect detection characteristic data further comprises:
calculating the ratio of the number of the target pixel points to the number of the pixel points contained in the minimum circumscribed rectangle of the internal target area of the packaging bag image;
when the ratio is larger than a preset ratio threshold, determining that the foreign matter detection of the packaging bag is qualified;
and when the ratio is not greater than the ratio threshold, determining that the foreign matter detection of the packaging bag is unqualified.
In this alternative embodiment, the printed contents of the package can be separated by performing a second binarization process on the package image using a second binarization threshold value, as shown in fig. 5. Similarly, since the content of the package images is generally fixed, that is, the content of the package images of the same batch of products is the same, it is completely possible for a technician to determine another accurate binarization threshold value according to his own experience and on-site practical conditions to separate the printed contents of the package in the image. After the second binarization, the minimum circumscribed rectangle P of the internal target area can be determined according to the distribution of the white pixel points in The area where the white pixels are distributed is the printing content of the packaging bag, namely the internal target area. Then, the number of white pixels in the internal target area is counted, and whether the printed content of the packaging bag has foreign matters or not is judged according to the duty ratio of the number of the white pixels in the internal target area. As shown in fig. 6, when the printed contents of the package bag have foreign matter, a large part of the printed contents are blocked by the foreign matter, and the blocked part becomes black pixels after the image binarization is completed, it can be seen that the number of white pixels in the internal target area is significantly reduced in the internal target area ratio when the printed contents have no foreign matter, compared with the case where the printed contents have no foreign matter, and therefore, whether the printed contents of the package bag have foreign matter can be completely judged by the number of white pixels in the internal target area ratio. In particular, the skilled person can follow the test in the fieldAnd setting a proper ratio threshold, when the ratio is larger than the ratio threshold, the printed content is not blocked by the foreign matters, the foreign matters are detected to be qualified, and when the ratio is not larger than the ratio threshold, the black pixels are too many, the printed content is blocked by the foreign matters, and the foreign matters are detected to be unqualified.
Therefore, according to the alternative embodiment, the second binarization threshold value is used for performing the second binarization processing on the packaging bag image, the printed content in the packaging bag is separated, then the proportion of the white pixel points in the internal target area to the internal target area is used for judging whether the printed content of the packaging bag has foreign matters or not, the actual situation of the packaging bag image can be fully considered, the image binarization is selected for carrying out the feature extraction of the foreign matter detection, the accurate feature extraction of the foreign matter detection can be realized with less image processing information, and the foreign matter detection of the printed content of the packaging bag can be accurately realized.
In an alternative embodiment, the defect detection feature data further includes: the monitoring frame of the packaging bag image;
the processing the packaging bag image based on the preset image processing mode to extract defect detection characteristic data of the packaging bag image further comprises:
determining a monitoring frame of the packaging bag image according to the minimum circumscribed rectangle of the external target area of the packaging bag image;
the determining the defect detection result of the packaging bag based on the defect detection characteristic data further comprises:
When the monitoring frame comprises the minimum circumscribed rectangle of the internal target area of the packaging bag image, determining that the layout of the packaging bag is qualified;
and when the monitoring frame does not contain the minimum circumscribed rectangle of the internal target area of the packaging bag image, determining that the layout detection of the packaging bag is unqualified.
In this alternative embodiment, as shown in fig. 7, the printing of the package sometimes results in a misplacement. Aiming at the situation of misplacement of the layout, the method can firstly calculate the image of the packaging bag according to the outside of the image of the packaging bagAnd determining a monitoring frame of the packaging bag image by the minimum circumscribed rectangle of the part target area, wherein the long side and the wide side of the monitoring frame can be respectively parallel to the long side and the wide side of the minimum circumscribed rectangle of the external target area, and the lengths of the long side and the wide side of the monitoring frame can be also obtained according to the percentages. As shown in fig. 8, the minimum bounding rectangle P of the monitor frame M and the external target area out Parallel, length and width are taken from the length and width of the smallest bounding rectangle of the outer target area by a predetermined percentage. And then judging whether the layout of the packaging bag is misplaced or not by judging whether the monitoring frame contains the minimum circumscribed rectangle of the internal target area of the packaging bag or not. In fig. 7, the monitoring frame intersects with the minimum circumscribed rectangle, and the monitoring frame does not include the minimum circumscribed rectangle of the internal target area, so that it can be determined that the layout of the packaging bag is dislocated, and the layout detection is not qualified. In the same way, as the image content of the packaging bag is relatively fixed, for the setting of the monitoring frame M, a technician can debug the proper monitoring frame M in a field debugging mode, so that a proper layout detection effect can be achieved.
Therefore, according to the implementation of the alternative embodiment, the monitoring frame of the packaging bag image is determined according to the minimum circumscribed rectangle of the external target area of the packaging bag image, and then whether the layout of the packaging bag is misplaced is judged by judging whether the monitoring frame contains the minimum circumscribed rectangle of the internal target area of the packaging bag or not, so that the layout detection of the packaging bag can be realized.
In an alternative embodiment, the defect detection feature data further includes: the number of overprinting mark pixels is the number of pixels occupied by overprinting marks of the packaging bag image;
the processing the packaging bag image based on the preset image processing mode to extract defect detection characteristic data of the packaging bag image further comprises:
identifying overprinting marks from the packaging bag image, and calculating the number of pixel points occupied by the overprinting marks in the packaging bag image;
the determining the defect detection result of the packaging bag based on the defect detection characteristic data further comprises:
when the number of the overprinting mark pixel points is smaller than a preset pixel point number threshold value, determining that the overprinting detection of the packaging bag is qualified;
And when the number of the overprinting marked pixel points is not smaller than the threshold value of the number of the pixel points, determining that the overprinting detection of the packaging bag is unqualified.
In this alternative embodiment, the package is printed in a four-color printing mode, the package needs to be printed for 4 times sequentially through the 4 parts, the Cyan part is printed first, the Magenta, yellow and blacK parts are printed sequentially, and finally the printing of four color channels of C (Cyan ), M (Magenta), Y (Yellow) and K (blacK) is overlapped to obtain the final package printing. However, in the printing process, the packaging bag may not be accurately aligned with the printing positions of each color due to thermal expansion and contraction, mechanical errors and other reasons, and the printing positions of each color may deviate, so that the superposition effect of the final printing of each color is affected, and the quality of the final packaging bag printed product is affected. In order to detect overprinting deviation of packaging bag printing, a overprinting detection mark, such as a "+" mark, can be printed at the same blank position of the packaging bag during each overprinting, if the overprinting deviation is qualified, the "+" marks of four overprinting are strictly overlapped, and only a clear "+" mark appears in the final packaging bag printing finished product; if the overprinting deviation is not qualified, the "+" sign in the final packaging bag printed finished product may be blurred or double-image, and even a plurality of "+" signs can appear, so that whether the overprinting deviation of the packaging bag is qualified can be judged by detecting the printing condition of the "+" signs. Specifically, the machine vision can detect the overprinting mark "+" of the packaging bag image at a pixel level, firstly, an image area of the "+" mark is extracted, and then the number of pixel points occupied by the "+" mark in the image is calculated. If the overprinting deviation is qualified, the "+" sign can be clear, and the number of the pixels occupied by the "+" sign cannot be excessive, so that the overprinting detection of the packaging bag can be determined to be qualified; if the overprinting deviation is not qualified, the "+" sign may be blurred or ghost, and the number of the pixels occupied by the "+" sign is usually more, so that the overprinting detection of the packaging bag can be determined to be unqualified. Similarly, during overprinting detection, the threshold value of the number of the pixel points can be determined by technicians through field debugging, so that a good overprinting detection effect can be ensured.
It can be seen that by implementing this alternative embodiment, the overprinting of the package can be detected using machine vision by providing overprinting marks in the package printing and then detecting whether the overprinting of the package is acceptable by detecting the number of pixels of the overprinting marks in the package image.
In an alternative embodiment, the defect detection feature data further includes: a color histogram of the package bag image;
the processing the packaging bag image based on the preset image processing mode to extract defect detection characteristic data of the packaging bag image further comprises:
calculating a color histogram of the packaging bag image;
the determining the defect detection result of the packaging bag based on the defect detection characteristic data further comprises:
calculating a histogram difference value of the color histogram of the packaging bag image and the color histogram of the standard packaging bag image;
when the histogram difference value is smaller than a preset histogram difference value threshold value, determining that the color detection of the packaging bag is qualified;
and when the histogram difference is not smaller than the histogram difference threshold, determining that the color detection of the packaging bag is unqualified.
In this alternative embodiment, the color of the package is determined to be acceptable by comparing the color histogram of the package image with the color histogram of the standard package image to effect detection of the color difference of the package. Color histograms are widely used color features in many image retrieval systems that describe the proportions of different colors in an entire image without regard to the spatial location of each color. The color histogram is a function of gray levels and represents the number of pixels having each gray level in the color channel of the image, reflecting the frequency of occurrence of each gray level in the color channel of the image. The abscissa of the color histogram is the gray level, and the ordinate is the frequency at which the gray level appears. As described above, the printed image of the package can be generally divided into C, M, Y, K four color channels, and thus, color histograms of the four color channels can be extracted for detection of color differences. As shown in fig. 9, fig. 9 is a color histogram of a certain two color channels of a standard packing bag image, and it can be seen from the figure that the pixels of the a channel are mainly distributed in gray scales of 0-50. As shown in fig. 10, fig. 10 is a color histogram of the two color channels of a package image having color differences. As can be seen from a comparison of the two figures, there is a large difference in pixel distribution of the two color histograms due to the color difference of the two package images. In particular, differences between color histograms may be quantitatively represented using histogram differences. The histogram difference calculating method may be as follows, calculating the difference of the pixel numbers of the two color histograms at each gray level, and then superposing the absolute values of all the differences to obtain the histogram difference. Alternatively, the difference value of each gray level may be filtered, a certain threshold value is set, and only the gray level difference value greater than the threshold value is finally superimposed into the histogram difference value, so that the filtering of the minor difference can be realized. Likewise, the histogram difference threshold may also be determined by a technician through field debugging, so that the effect of color detection can be ensured.
It can be seen that this alternative embodiment is implemented by comparing the color histogram of the package image with the color histogram of the standard package image, thereby enabling detection of the color difference of the package, and detecting whether the color of the package is acceptable.
In an alternative embodiment, the defect detection feature data further includes: the deformation value of the packaging bag image;
the processing the packaging bag image based on the preset image processing mode to extract defect detection characteristic data of the packaging bag image further comprises:
comparing the external area length value and the external area width value with a preset standard external area length value and a standard external area width value respectively to obtain a deformation value of the packaging bag image;
the determining the defect detection result of the packaging bag based on the defect detection characteristic data further comprises:
when the deformation value is in a preset deformation value interval, determining that the filling detection of the packaging bag is qualified;
and when the deformation value is not in the deformation value interval, determining that the filling detection of the packaging bag is unqualified.
In this alternative embodiment, it is also possible to determine whether the number, volume, etc. of the filled articles are acceptable or not based on the degree of deformation of the package after the package is filled with the articles. In order to further improve the content of the detection, the embodiment of the invention provides that whether the filled article is qualified or not after the packaging bag is filled with the article. Specifically, after the package is filled with the product, the package will generally change in size due to the filling of the package with the product, e.g., the length and width of the package will be reduced relative to the length and width of the package when the package is flat-laid due to the bulge in the middle of the package. And the degree of deformation of the package bag will also vary with the volume of the filled article. It is therefore entirely feasible to determine whether the volume of the filled item matches by detecting the degree of deformation of the package. The ratio of the outer region length value detected by the image to the standard outer region length value and the ratio of the outer region width value to the standard outer region width value can be used as deformation values of the packaging bag image. The deformation value interval can also be determined by technicians through field debugging, so that the filling detection effect can be ensured.
It can be seen that this alternative embodiment is implemented to judge whether the number, volume, etc. of the filled articles are acceptable according to the degree of deformation of the package bag, so that the filling detection of the package bag can be realized by using machine vision.
As can be seen, the machine vision-based method for detecting defects of packaging bags described in fig. 1 is implemented to obtain images of packaging bags to be subjected to defect detection; processing the packaging bag image based on a preset image processing mode to extract defect detection characteristic data of the packaging bag image; and determining a defect detection result of the packaging bag based on the defect detection characteristic data. The machine vision technology is used for replacing manual detection of defects of the packaging bag, so that the detection quality and the detection efficiency can be remarkably improved, the labor cost is saved, the detection of various defects of the packaging bag is realized only through machine vision, the hardware use efficiency is high, and the realization of simplified hardware is possible.
Example two
Referring to fig. 11, fig. 11 is a schematic structural diagram of a packaging bag defect detecting device based on machine vision according to an embodiment of the present invention. As shown in fig. 11, the machine vision-based packing bag defect detecting apparatus may include:
An acquisition module 1101, configured to acquire a package image to be subjected to defect detection;
an extracting module 1102, configured to process the package bag image based on a preset image processing manner, so as to extract defect detection feature data of the package bag image;
a determining module 1103, configured to determine a defect detection result of the packaging bag based on the defect detection feature data.
For the specific description of the above-mentioned machine vision-based packaging bag defect detecting device, reference may be made to the specific description of the above-mentioned machine vision-based packaging bag defect detecting method, which is not described in detail herein.
Example III
Referring to fig. 12, fig. 12 is a schematic structural diagram of a packaging bag defect detecting terminal based on machine vision according to an embodiment of the present invention. As shown in fig. 12, the machine vision-based packing bag defect detecting terminal may include:
a memory 1201 in which executable program codes are stored;
a processor 1202 coupled to the memory 1201;
the processor 1202 invokes executable program code stored in the memory 1201 to perform steps in the machine vision based bag defect detection method disclosed in the embodiment of the present invention.
Example IV
The embodiment of the invention discloses a computer storage medium which stores computer instructions for executing the steps in the packaging bag defect detection method based on machine vision disclosed in the embodiment of the invention when the computer instructions are called.
The apparatus embodiments described above are merely illustrative, wherein the modules illustrated as separate components may or may not be physically separate, and the components shown as modules may or may not be physical, i.e., may be located in one place, or may be distributed over a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above detailed description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product that may be stored in a computer-readable storage medium including Read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), one-time programmable Read-Only Memory (OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM) or other optical disc Memory, magnetic disc Memory, tape Memory, or any other medium that can be used for computer-readable carrying or storing data.
Finally, it should be noted that: the embodiment of the invention discloses a packaging bag defect detection method, a packaging bag defect detection device, a packaging bag defect detection terminal and a packaging bag defect detection storage medium based on machine vision, which are disclosed as preferred embodiments of the invention, and are only used for illustrating the technical scheme of the invention, but not limiting the technical scheme; although the invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that; the technical scheme recorded in the various embodiments can be modified or part of technical features in the technical scheme can be replaced equivalently; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (10)
1. A machine vision-based packaging bag defect detection method, the method comprising:
acquiring a packaging bag image to be subjected to defect detection;
processing the packaging bag image based on a preset image processing mode to extract defect detection characteristic data of the packaging bag image;
and determining a defect detection result of the packaging bag based on the defect detection characteristic data.
2. The machine vision-based packaging bag defect detection method of claim 1, wherein the defect detection feature data comprises: an outer region length value and an outer region width value, wherein the outer region length value is a length value of a minimum bounding rectangle of an outer target region of the packaging bag image, and the outer region width value is a width value of the minimum bounding rectangle of the outer target region of the packaging bag image;
The processing the packaging bag image based on the preset image processing mode to extract the defect detection characteristic data of the packaging bag image comprises the following steps:
performing binarization processing on the packaging bag image based on a predetermined first binarization threshold value to obtain a first binarization image corresponding to the packaging bag image;
determining the outer region length value and the outer region width value from the first binarized image;
the determining a defect detection result of the packaging bag based on the defect detection characteristic data comprises the following steps:
judging whether the length value of the external area is in a preset qualified length value interval or not;
judging whether the width value of the external area is in a preset qualified width value interval or not;
when the outer area length value is in the qualified length value interval and the outer area width value is in the qualified width value interval, determining that the size detection of the packaging bag is qualified;
and determining that the size detection of the packaging bag is unqualified when the external area length value is not in the qualified length value interval or the external area width value is not in the qualified width value interval.
3. The machine vision-based packaging bag defect detection method of claim 2, wherein the defect detection feature data further comprises: the minimum circumscribed rectangle of the internal target area of the packaging bag image and the number of target pixel points of the internal target area of the packaging bag image;
The processing the packaging bag image based on the preset image processing mode to extract defect detection characteristic data of the packaging bag image further comprises:
performing binarization processing on the packaging bag image based on a second predetermined binarization threshold value to obtain a second binarization image corresponding to the packaging bag image;
determining a minimum circumscribed rectangle of an internal target area of the packaging bag image and the number of target pixel points of the internal target area of the packaging bag image from the second binarized image, wherein the number of target pixel points is the number of white pixels contained in the internal target area in the second binarized image;
the determining the defect detection result of the packaging bag based on the defect detection characteristic data further comprises:
calculating the ratio of the number of the target pixel points to the number of the pixel points contained in the minimum circumscribed rectangle of the internal target area of the packaging bag image;
when the ratio is larger than a preset ratio threshold, determining that the foreign matter detection of the packaging bag is qualified;
and when the ratio is not greater than the ratio threshold, determining that the foreign matter detection of the packaging bag is unqualified.
4. The machine vision-based packaging bag defect detection method of claim 3, wherein the defect detection feature data further comprises: the monitoring frame of the packaging bag image;
the processing the packaging bag image based on the preset image processing mode to extract defect detection characteristic data of the packaging bag image further comprises:
determining a monitoring frame of the packaging bag image according to the minimum circumscribed rectangle of the external target area of the packaging bag image;
the determining the defect detection result of the packaging bag based on the defect detection characteristic data further comprises:
when the monitoring frame comprises the minimum circumscribed rectangle of the internal target area of the packaging bag image, determining that the layout of the packaging bag is qualified;
and when the monitoring frame does not contain the minimum circumscribed rectangle of the internal target area of the packaging bag image, determining that the layout detection of the packaging bag is unqualified.
5. The machine vision-based packaging bag defect detection method of claim 4, wherein the defect detection feature data further comprises: the number of overprinting mark pixels is the number of pixels occupied by overprinting marks of the packaging bag image;
The processing the packaging bag image based on the preset image processing mode to extract defect detection characteristic data of the packaging bag image further comprises:
identifying overprinting marks from the packaging bag image, and calculating the number of pixel points occupied by the overprinting marks in the packaging bag image;
the determining the defect detection result of the packaging bag based on the defect detection characteristic data further comprises:
when the number of the overprinting mark pixel points is smaller than a preset pixel point number threshold value, determining that the overprinting detection of the packaging bag is qualified;
and when the number of the overprinting marked pixel points is not smaller than the threshold value of the number of the pixel points, determining that the overprinting detection of the packaging bag is unqualified.
6. The machine vision-based packaging bag defect detection method of claim 5, wherein the defect detection feature data further comprises: a color histogram of the package bag image;
the processing the packaging bag image based on the preset image processing mode to extract defect detection characteristic data of the packaging bag image further comprises:
calculating a color histogram of the packaging bag image;
the determining the defect detection result of the packaging bag based on the defect detection characteristic data further comprises:
Calculating a histogram difference value of the color histogram of the packaging bag image and the color histogram of the standard packaging bag image;
when the histogram difference value is smaller than a preset histogram difference value threshold value, determining that the color detection of the packaging bag is qualified;
and when the histogram difference is not smaller than the histogram difference threshold, determining that the color detection of the packaging bag is unqualified.
7. The machine vision-based packaging bag defect detection method of claim 6, wherein the defect detection feature data further comprises: the deformation value of the packaging bag image;
the processing the packaging bag image based on the preset image processing mode to extract defect detection characteristic data of the packaging bag image further comprises:
comparing the external area length value and the external area width value with a preset standard external area length value and a standard external area width value respectively to obtain a deformation value of the packaging bag image;
the determining the defect detection result of the packaging bag based on the defect detection characteristic data further comprises:
when the deformation value is in a preset deformation value interval, determining that the filling detection of the packaging bag is qualified;
And when the deformation value is not in the deformation value interval, determining that the filling detection of the packaging bag is unqualified.
8. A machine vision-based packaging bag defect detection device, the device comprising:
the acquisition module is used for acquiring the packaging bag image to be subjected to defect detection;
the extraction module is used for processing the packaging bag image based on a preset image processing mode so as to extract defect detection characteristic data of the packaging bag image;
and the determining module is used for determining the defect detection result of the packaging bag based on the defect detection characteristic data.
9. A machine vision-based package bag defect detection terminal, the terminal comprising:
a memory storing executable program code;
a processor coupled to the memory;
the processor invokes the executable program code stored in the memory to perform the machine vision based bag defect detection method of any one of claims 1-7.
10. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the machine vision-based bag defect detection method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311809235.0A CN117764963B (en) | 2023-12-25 | 2023-12-25 | Packaging bag defect detection method, device, terminal and medium based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311809235.0A CN117764963B (en) | 2023-12-25 | 2023-12-25 | Packaging bag defect detection method, device, terminal and medium based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117764963A true CN117764963A (en) | 2024-03-26 |
| CN117764963B CN117764963B (en) | 2024-08-13 |
Family
ID=90310230
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311809235.0A Active CN117764963B (en) | 2023-12-25 | 2023-12-25 | Packaging bag defect detection method, device, terminal and medium based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117764963B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103072718A (en) * | 2012-12-27 | 2013-05-01 | 天津普达软件技术有限公司 | Machine vision detection system and method for food packaging production line |
| CN105675614A (en) * | 2016-02-19 | 2016-06-15 | 清华大学 | Packaging bag sealing quality detection device and method |
| CN106204618A (en) * | 2016-07-20 | 2016-12-07 | 南京文采科技有限责任公司 | Product surface of package defects detection based on machine vision and sorting technique |
| CN106770372A (en) * | 2016-11-29 | 2017-05-31 | 中国科学院自动化研究所 | White glass detection method of surface flaw based on micro-vision |
| CN107014821A (en) * | 2017-02-28 | 2017-08-04 | 深圳市维图视技术有限公司 | A kind of plastics valve bag detecting system and method |
| CN107966454A (en) * | 2017-12-25 | 2018-04-27 | 陕西科技大学 | A kind of end plug defect detecting device and detection method based on FPGA |
| CN109724990A (en) * | 2019-01-08 | 2019-05-07 | 上海大学 | The quick positioning and detection method in coding region in a kind of packing box label |
| CN111524120A (en) * | 2020-04-22 | 2020-08-11 | 征图新视(江苏)科技股份有限公司 | Printed matter tiny scratch and overprint deviation detection method based on deep learning |
| CN111968082A (en) * | 2020-07-30 | 2020-11-20 | 陕西科技大学 | Product packaging defect detection and identification method based on machine vision |
| CN114092375A (en) * | 2020-07-30 | 2022-02-25 | 四川卡库机器人科技有限公司 | Automatic detection system and method for printing defects of packaging bag cover |
| CN114882037A (en) * | 2022-07-11 | 2022-08-09 | 北京中科慧眼科技有限公司 | Image defect detection method and system based on dynamic printing mask |
| CN116703899A (en) * | 2023-08-03 | 2023-09-05 | 青岛义龙包装机械有限公司 | Bag type packaging machine product quality detection method based on image data |
| CN117011304A (en) * | 2023-10-08 | 2023-11-07 | 深圳思谋信息科技有限公司 | Defect detection method, defect detection device, computer equipment and computer readable storage medium |
-
2023
- 2023-12-25 CN CN202311809235.0A patent/CN117764963B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103072718A (en) * | 2012-12-27 | 2013-05-01 | 天津普达软件技术有限公司 | Machine vision detection system and method for food packaging production line |
| CN105675614A (en) * | 2016-02-19 | 2016-06-15 | 清华大学 | Packaging bag sealing quality detection device and method |
| CN106204618A (en) * | 2016-07-20 | 2016-12-07 | 南京文采科技有限责任公司 | Product surface of package defects detection based on machine vision and sorting technique |
| CN106770372A (en) * | 2016-11-29 | 2017-05-31 | 中国科学院自动化研究所 | White glass detection method of surface flaw based on micro-vision |
| CN107014821A (en) * | 2017-02-28 | 2017-08-04 | 深圳市维图视技术有限公司 | A kind of plastics valve bag detecting system and method |
| CN107966454A (en) * | 2017-12-25 | 2018-04-27 | 陕西科技大学 | A kind of end plug defect detecting device and detection method based on FPGA |
| CN109724990A (en) * | 2019-01-08 | 2019-05-07 | 上海大学 | The quick positioning and detection method in coding region in a kind of packing box label |
| CN111524120A (en) * | 2020-04-22 | 2020-08-11 | 征图新视(江苏)科技股份有限公司 | Printed matter tiny scratch and overprint deviation detection method based on deep learning |
| CN111968082A (en) * | 2020-07-30 | 2020-11-20 | 陕西科技大学 | Product packaging defect detection and identification method based on machine vision |
| CN114092375A (en) * | 2020-07-30 | 2022-02-25 | 四川卡库机器人科技有限公司 | Automatic detection system and method for printing defects of packaging bag cover |
| CN114882037A (en) * | 2022-07-11 | 2022-08-09 | 北京中科慧眼科技有限公司 | Image defect detection method and system based on dynamic printing mask |
| CN116703899A (en) * | 2023-08-03 | 2023-09-05 | 青岛义龙包装机械有限公司 | Bag type packaging machine product quality detection method based on image data |
| CN117011304A (en) * | 2023-10-08 | 2023-11-07 | 深圳思谋信息科技有限公司 | Defect detection method, defect detection device, computer equipment and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 李丹等: "基于机器视觉的包装袋缺陷检测算法研究与应用", 《激光与光电子学进展》, vol. 56, no. 9, 31 May 2019 (2019-05-31), pages 3 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117764963B (en) | 2024-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6771807B2 (en) | Method and system for detecting defects on a printed circuit board | |
| CN109752392B (en) | PCB defect type detection system and method | |
| CN113034488B (en) | Visual inspection method for ink-jet printed matter | |
| JP2013122455A (en) | Method and device for optically testing object to be tested during production and/or packing of cigarette | |
| CN116573307A (en) | Automatic garbage classification and recycling intelligent equipment and intelligent garbage classification system thereof | |
| CN117664991A (en) | Defect detection system | |
| CN117764963B (en) | Packaging bag defect detection method, device, terminal and medium based on machine vision | |
| CN115861161A (en) | Machine learning system, learning data collection method, and storage medium | |
| CN114708247A (en) | Cigarette case packaging defect identification method and device based on deep learning | |
| CN112465910B (en) | Target shooting distance obtaining method and device, storage medium and electronic equipment | |
| CN110516375B (en) | Abnormal board card detection method and device, electronic equipment and storage medium | |
| CN111460198B (en) | Picture timestamp auditing method and device | |
| CN117475233A (en) | Method, device, equipment and computer storage medium for detecting abnormal state of gland | |
| CN112165853A (en) | PCB solder paste printing quality inspection method, device and system | |
| EP4358020A1 (en) | Method of detecting errors in the placement of elements in the pcb | |
| KR102691280B1 (en) | Printing inspection device inspecting date printing and operating method of thereof | |
| CN117115114B (en) | YOLO-based power electronic device production process target identification and defect detection method | |
| US20230360194A1 (en) | Quality inspection method and quality inspection arrangement | |
| JP3190173B2 (en) | Semiconductor device appearance inspection method and appearance inspection device | |
| CN111445458B (en) | Method for detecting printing quality of mobile phone battery label | |
| CN113780074A (en) | Method and device for detecting quality of wrapping paper and storage medium | |
| JPH04133500A (en) | Polarity difference detection method | |
| JP2004318488A (en) | Product inspection method and product inspection device | |
| CN116848400A (en) | Method for evaluating transverse sealing quality of food package | |
| CN118858292A (en) | Mainboard detection method and device, equipment and storage medium |
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 |