CN115984185A - Paper towel package defect detection method, device and system and storage medium - Google Patents
Paper towel package defect detection method, device and system and storage medium Download PDFInfo
- Publication number
- CN115984185A CN115984185A CN202211556657.7A CN202211556657A CN115984185A CN 115984185 A CN115984185 A CN 115984185A CN 202211556657 A CN202211556657 A CN 202211556657A CN 115984185 A CN115984185 A CN 115984185A
- Authority
- CN
- China
- Prior art keywords
- image
- determining
- area
- target
- package
- 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
Images
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
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the disclosure relates to a method, a device and a system for detecting packaging defects of tissues and a storage medium. The paper towel package defect detection method mainly comprises the following steps: acquiring a first image comprising a first perspective image of the tissue package; determining the number of pixels of a plurality of target edges imaged at the first view angle according to the first image; and when the pixel number of any one target edge is out of a corresponding preset first qualified interval, determining that the first type of defect exists in the paper towel package. By adopting the method, the detection accuracy can be ensured, and the detection efficiency can be improved. In addition, because the first image does not need to be compared with the preset standard image globally, the defects are determined according to the number of pixels of the target edge, and a large amount of computing resources can be saved.
Description
Technical Field
The present disclosure relates to the field of paper towel product defect detection technologies, and in particular, to a paper towel package defect detection method, apparatus, system, and storage medium.
Background
During the production of tissue products, the corresponding tissue package may have a certain probability of defects, such as distortion of the outline of the tissue package, due to factors such as the precision of the production equipment, the operating precision of the production workers, and faults or errors occurring during the production process.
Such defects in tissue packaging can be detected by manual visual inspection, however, with less efficiency.
Disclosure of Invention
In view of the above, there is a need to provide a method, an apparatus, a system and a storage medium for detecting a package defect of a tissue, which can improve the efficiency of identifying the package defect of the tissue.
In a first aspect, the disclosed embodiments provide a method for detecting a package defect of a tissue, the method including:
acquiring a first image, wherein the first image comprises a first perspective image of the tissue package;
determining the number of pixels of a plurality of target edges imaged at a first view angle according to the first image;
and when the pixel number of any target edge is out of a corresponding preset first qualified interval, determining that the first type of defect exists in the paper towel package.
In some embodiments, the first image is a color image, and accordingly, determining the number of pixels of the plurality of target edges imaged at the first viewing angle based on the first image comprises:
converting the first image into a grayscale image or a black-and-white image;
and determining the number of pixels of the edges of the plurality of targets imaged at the first view angle in the gray-scale image or the black-and-white image.
In some embodiments, the tissue package defect detection method further comprises:
determining a characteristic region imaged by a first visual angle;
and when the difference value of the pixel number of any characteristic area and the pixel number of the corresponding area of the preset first standard imaging is out of a corresponding preset second qualified interval, determining that the second type of defects exist in the tissue package.
In some embodiments, the tissue package defect detection method further comprises:
comparing the first perspective imaging with a preset first standard imaging;
when a target area with the similarity of the corresponding area of the first standard imaging outside a corresponding preset third qualified interval exists in the first visual angle imaging, extracting the characteristics of the target area;
and determining the defect type corresponding to the target area according to the characteristics of the target area.
In some embodiments, determining the defect type corresponding to the target area according to the feature of the target area includes:
and when the difference value between the gray scale of the target area and the gray scale of the corresponding area in the first standard imaging is outside a preset gray scale difference allowable interval and the area of the target area is within a corresponding preset area interval, determining that the third type of defects exist in the tissue package.
In some embodiments, the tissue package defect detection method further comprises:
determining a target pattern in the first perspective imaging;
comparing the position of the target pattern with the position of a corresponding pattern of a preset first standard imaging to obtain a position deviation amount;
and when the position deviation amount exceeds a fourth corresponding preset qualified interval, determining that the tissue package has a fourth type of defects.
In some embodiments, the tissue package is a soft tissue package, the first perspective image comprises an imaging area of an opening of the tissue package;
the paper towel packaging defect detection method further comprises the following steps:
acquiring a second image, wherein the second image comprises a second visual angle image of the tissue package, and the second visual angle image comprises an imaging area of the seal ironing port;
comparing the second perspective imaging with a preset second standard imaging;
when a marked region with the similarity of the corresponding region of the second standard imaging outside a correspondingly preset fifth qualified interval exists in the second visual angle imaging, extracting the characteristics of the marked region;
and determining the defect type corresponding to the marking area according to the characteristics of the marking area.
In a second aspect, the disclosed embodiments provide a tissue package defect detecting device, including:
the first image acquisition module is used for acquiring a first image, and the first image comprises a first visual angle image of the tissue package;
the first pixel number determining module is used for determining the pixel numbers of a plurality of target edges imaged at a first visual angle according to the first image;
and the first defect detection module is used for determining that the first type of defects exist in the tissue package when the pixel number of any target edge is outside a corresponding preset first qualified interval.
In a third aspect, the disclosed embodiments provide a tissue package defect detection system, including a conveyor belt, a camera device, and a computer device; the conveyor belt is used for conveying the tissue product with the tissue package; the camera device is used for shooting the paper towel products conveyed by the conveyor belt and generating a first image comprising a first view angle image of the paper towel package; the computer device comprises a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the tissue package defect detection method in any embodiment when executing the computer program.
In a fourth aspect, the present disclosure provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the steps of the tissue package defect detection method in any embodiment.
When the method, the device, the system and the storage medium for detecting the paper towel package defects are implemented, the number of pixels of a plurality of target edges is determined by acquiring the first visual angle image of the paper towel package, whether the paper towel package has the first type of defects or not is judged according to the number of pixels, namely whether the outline of the paper towel package deforms beyond the allowable range or not is judged, and the detection efficiency can be improved while the detection accuracy is ensured. In addition, because the first image does not need to be compared with the preset standard image in the global mode, the defects are determined according to the number of pixels of the target edge, and a large amount of computing resources can be saved.
Drawings
FIG. 1 is a diagram of an exemplary application of the method for detecting defects in tissue packaging;
FIG. 2 is a schematic flow chart of a method for detecting defects in tissue packaging in some embodiments;
FIG. 3 is a schematic illustration of elements of a first image in some embodiments;
FIG. 4 is a schematic flow chart of steps involved in image conversion in some embodiments;
FIG. 5 is a block diagram of a tissue package defect detection apparatus according to some embodiments;
FIG. 6 is a schematic view of a tissue package defect detection system in accordance with certain embodiments;
FIG. 7 is yet another schematic diagram of a tissue package defect detection system in accordance with certain embodiments;
FIG. 8 is a diagram of the internal structure of some embodiments when the computer device is a server;
fig. 9 is an internal structural diagram of a computer device when the computer device is a terminal in some embodiments.
Detailed Description
In order to make the objects, technical solutions and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present disclosure and are not intended to limit the present disclosure.
The tissue package defect detection method provided by the embodiment of the disclosure can be applied to the application environment shown in fig. 1. The server 101 may communicate with the camera device 102 through a network, so as to obtain a first image generated by the camera device 102 shooting the tissue package from the camera device 102. The server 101 may be implemented by an independent server or a server cluster composed of a plurality of servers, and the camera device 102 may include one or more cameras, where at least one camera may capture the tissue package at a certain fixed viewing angle to generate the first image.
Of course, the method for detecting the package defect of the tissue can also be applied to other application environments, and is not limited herein. For example, there may be other storage or processing devices for signals or data between the server 101 and the camera device 102. The server 101 may read the first images from the camera device 102 stored by these storage devices or acquire the first images from the camera device 102 from these processing devices. For example, the server 101 may be replaced by a terminal, which may include, but is not limited to, a desktop computer, a notebook computer, or other detection device having a processor, and the processor may execute the tissue package defect detection method provided by the embodiment of the present disclosure.
Taking the application of the tissue package defect detection method to the server 101 in fig. 1 as an example, in some embodiments, as shown in fig. 2, the tissue package defect detection method includes steps S201, S202, and S203 that can be executed by the server 101, and the steps are explained below.
Step S201: a first image is acquired, the first image comprising a first perspective image of the tissue package.
As mentioned previously, the first image sent by the camera device 102 may be obtained directly, or may be obtained from a storage device or other data processing device. In general, the first image may be a photograph generated by the camera device 102 or may be a portion of the photograph, including at least the first perspective image of the tissue package, in any event.
The first view angle imaging refers to an image of the tissue package generated by shooting the tissue package at a certain view angle by one camera of the camera device 102.
In some alternative embodiments, when the camera captures a scene other than the tissue package while the tissue package is captured, the first image may further include an image of a scene other than the tissue package in addition to the first perspective image.
A tissue package is used to partially or fully wrap a tissue, typically in case the tissue product is a tissue, the corresponding tissue package is then the package of the tissue. Of course, in alternative embodiments, the tissue package may be other types of tissue products, and is not further described herein.
Typically, the first perspective imaging includes imaging of the first surface of the tissue package. The first surface may be any one of a plurality of surfaces of a tissue package. For example, the first surface may be a surface on which a brand identifier of the tissue package is located, a surface on which an opening of the tissue package is located, or a surface on which some patterns or characters of the tissue package are located.
Taking the tissue package as an example of a package of tissues in a rectangular parallelepiped shape, as shown in fig. 3, the first image 300 includes a first perspective image 310, and the first perspective image 310 includes a first edge 311, a second edge 312, a third edge 313, a fourth edge 314, an opening area 320, a mark area 330, and other areas in the first perspective image 310. The first edge 311, the second edge 312, the third edge 313 and the fourth edge 314 are four edges of the image 300 of the first surface, the opening area 320 is an imaging area of an opening of a tissue package, the identification area 330 is an imaging area of a brand identifier of the tissue package, and the other areas mentioned in this paragraph are imaging areas of other elements of the tissue package, including but not limited to appearances of various packaging patterns.
Fig. 3 shows a case where the first-view-angle imaging is imaging of the first surface. While for some distorted appearance tissue packages, the first perspective imaging may include imaging of portions of other surfaces of the tissue package in addition to the first surface. For example, after the tissue package is squeezed to cause distortion in appearance, a portion of the edge imaged at a first viewing angle may be an image of a boundary of a certain surface, and another portion of the edge may be an image of a boundary of another surface, which are captured by a camera at the same time under the shooting viewing angle of the camera.
In some alternative embodiments, after the camera of the camera device 102 takes a picture of the tissue package, the picture may be preprocessed, and the preprocessed picture is used as the first image. The preprocessing method includes, but is not limited to, translation, rotation, image enhancement, smoothing or denoising.
Step S202: and determining the number of pixels of the plurality of target edges imaged at the first view angle according to the first image.
The edge imaged at the first perspective can be obtained using various edge detection algorithms. In general, the edge imaged by the first viewing angle may be a closed curve, or may include a plurality of open curves or straight lines, depending on the type of edge detection method.
The object edge may be part or all of the edge imaged at the first viewing angle. As shown in fig. 3, the target edge may be any one of the first edge 311, the second edge 312, the third edge 313, and the fourth edge 314, and if all four edges in fig. 3 are target edges, the number of the target edges is 4. The number of target edges can be selected according to actual requirements.
Determining the number of pixels of the plurality of target edges imaged in the first view refers to determining the number of pixels of each target edge respectively.
Step S203: and when the pixel number of any target edge is out of a corresponding preset first qualified interval, determining that the first type of defect exists in the paper towel package.
The first qualified interval is a type of preset numerical interval, when the number of pixels of the target edge is within the numerical interval, the length of the target edge is reflected to accord with a preset length standard, and the length standard can be formulated according to actual needs. For example, a tissue package determined as being free of defects may be determined, a first surface of the tissue package may be photographed by the camera device 102, a corresponding first surface image, i.e., a first standard image, may be obtained, the number of pixels of each edge of the first standard image may be determined, and a first pass interval corresponding to each item mark edge may be determined based on the determined number of pixels. For example, if the number of pixels of an edge of the first standard imaging is 1000, the first qualified interval may be [980, 1020] or [950, 1050] or other value intervals including the value of 1000.
Since the number of pixels of the edge can reflect the length of the edge, the first qualified interval corresponding to the target edge is determined according to the number of pixels of the edge imaged by the first standard, and the length standard is essentially established. For the tissue package of the tissue product of the same model, if the number of pixels of the target edge of a certain tissue package is outside the corresponding first qualified interval, it means that the difference between the length of the target edge of the tissue package and the length of the corresponding edge of the first standard imaging is large, and at this time, it can be determined that the tissue package has a defect. Typically, such defects may be caused by the tissue package being squeezed to deform such that the first perspective imaging includes imaging of surfaces other than the first surface.
The corresponding first qualified interval may be the same or different for target edges located at different positions in the first image. Taking fig. 3 as an example, the first qualified interval corresponding to the first edge 311 and the first qualified interval corresponding to the second edge 312 may be different; the first pass interval corresponding to the first edge 311 and the first pass interval corresponding to the third edge 313 may be the same.
The first type of defect mentioned above refers to deformation or breakage of the contour of the tissue package beyond an acceptable range. Such deformation or breakage can sometimes be manifested in collapse, bulge, twist or tear of the tissue package beyond acceptable limits.
In some optional embodiments, after determining that the first type of defect exists in the tissue package, relevant prompt information can be output.
The first visual angle imaging of the tissue package is obtained, the pixel numbers of the edges of the multiple targets are determined, whether the tissue package has the first type of defects or not is judged according to the pixel numbers, namely whether the outline of the tissue package deforms beyond the allowable range or not is judged, and the detection efficiency can be improved while the detection accuracy is guaranteed. In addition, because the first image does not need to be compared with the preset standard image globally, the defects are determined according to the number of pixels of the target edge, and a large amount of computing resources can be saved.
In some embodiments, the first image is a color image, and accordingly, as shown in fig. 4, the step S202 may include the steps of:
step S401, converting the first image into a gray scale image or a black and white image;
in step S402, the number of pixels of the plurality of target edges imaged at the first viewing angle in the gray image or the black-and-white image is determined.
When the photo generated by the paper towel package and taken by the camera of the camera device 102 is a color photo, the first image is a color image, and the color image can provide rich features for feature extraction, recognition or similarity calculation, which is beneficial to improving the recognition accuracy of related defects. However, when the number of pixels is calculated, the first image is converted into a gray image or a black-and-white image, and then the number of pixels of the target edge is recognized, so that the accuracy of recognizing the number of pixels can be improved, and the accuracy of recognizing the first type of defects can be improved. Of course, in other embodiments, the camera of the camera device 102 may take a photograph of the tissue package that is not a color photograph, and may be a grayscale or black and white photograph, for example.
In some embodiments, the tissue package defect detection method may further include the steps of:
determining a characteristic region imaged by a first visual angle;
and when the difference value of the pixel number of any characteristic area and the pixel number of the corresponding area of the preset first standard imaging is out of a corresponding preset second qualified interval, determining that the second type of defects exist in the tissue package.
The aforementioned feature region refers to an imaging region in which the range of the region can be determined by feature extraction and feature recognition. For the first perspective image, features that may be extracted and identified include, but are not limited to, corner features, pattern features, or character features.
The characteristic region may be a corner region, the corner region refers to an included angle region formed by intersection of a target edge and the target edge, and a range of the included angle region may be specifically set according to requirements, for example, the included angle region may be a region where a pixel point whose distance from a terminal of a certain target edge is smaller than a certain set value is located within the included angle range. When the angle of the angle is changed, the number of pixels in the corresponding angle area is also changed. Whether the paper towel package has the defect of the starting angle can be determined by judging whether the difference value between the pixel number of the corner area and the pixel number of the corresponding area of the preset first standard imaging is in the corresponding preset second qualified interval, namely the second defect is the defect of the starting angle. In general, the reason for the defective corner is that the temperature at which the tissue package is sealed is outside a reasonable range.
Of course, the aforementioned characteristic region may also be other regions besides the corner region, for example, the characteristic region may be an imaging region of an opening of a tissue package, or an imaging region of a certain pattern or character on the tissue package, and when the difference between the pixel count of these regions and the pixel count of the corresponding region imaged by the preset first standard is outside the corresponding preset second qualified interval, the corresponding second type of defect is that the opening, the pattern or the character does not meet the preset standard in terms of size or position.
The different locations of the feature regions, or different types of feature regions, may correspond to different second qualifying intervals. The second qualified interval is another type of preset numerical interval, when the number of pixels of the characteristic area is within the numerical interval, the part of the tissue package corresponding to the characteristic area is reflected to meet a preset standard, and the preset standard can be formulated according to actual needs.
The difference between the number of pixels in the feature region and the number of pixels in the corresponding region of the preset first standard imaging may be an absolute difference or an absolute value, and is not particularly limited herein. The corresponding region of the first standard imaging has the same standard of feature extraction and recognition as the feature region, and for example, feature extraction and recognition may be performed on the first perspective image according to a feature extraction and recognition algorithm of the corner region of the first standard imaging, thereby determining the corner region of the first perspective image.
In some embodiments, a tissue package defect detection method may include the steps of:
comparing the first perspective imaging with a preset first standard imaging;
when a target area with the similarity of the corresponding area of the first standard imaging outside a corresponding preset third qualified interval exists in the first visual angle imaging, extracting the characteristics of the target area;
and determining the defect type corresponding to the target area according to the characteristics of the target area.
In general, the first perspective image may be divided into a plurality of regions, and specifically, features in the first visual image may be extracted, and the first perspective image may be divided into a plurality of regions according to a preset region division rule based on the extracted features. The specific region division rule can be designed according to actual requirements. For example, for a paper extraction, the divisible areas include, but are not limited to, an imaged area of an opening, an imaged area of a brand logo, an imaged area of several patterns, an imaged area of several characters, etc., which may have features of a different visual level than other areas. Similarly, the first standard imaging may be area-divided according to an area division rule so that the first standard imaging has an area corresponding to the first angle-of-view imaging.
It follows that the first perspective imaging may have multiple target regions. Different target areas may correspond to different third qualifying intervals.
The third qualified interval is another preset numerical value interval, and in the first visual angle imaging, if the similarity between the target area and the corresponding area of the first standard imaging is outside the corresponding preset third qualified interval, the defect exists in the part of the tissue package corresponding to the target area. The corresponding defect types of different types of target areas can be different, and the third qualified area can be flexibly set according to the defect types. For example, for a portion of the opening of the tissue package, for which a similarity of the imaging area (i.e., the target area) of the opening in the first-view-angle imaging to the imaging area of the opening in the first standard imaging of not less than 85% is regarded as passing, the third pass interval may be set to [85%,100% ]. For example, for a portion of the brand identifier of the tissue package, if it is considered that the similarity between the imaging area (i.e., the target area) of the brand identifier in the first viewing angle imaging and the imaging area of the brand identifier in the first standard imaging is not less than 90%, the third satisfactory interval may be set to [90%,100% ]. Different target areas correspond to different parts of the tissue package, and the different parts of the tissue package may be manufactured by different processes, so that different parts of the tissue package may have different defect types, for example, the defect type corresponding to the target area may be poor opening, unclear brand identification, unclear certain patterns or characters, presence of a foreign matter or a stain on a certain tissue package part, and the like, which may be judged by the similarity.
The aforementioned features of the target area are used to distinguish objects corresponding to the target area, where the objects may be stains, mosquitoes, burrs, exposed tissues, and the like, and specifically, the features of the sample of the related object may be extracted in a machine learning manner, so as to determine different features corresponding to the imaging of different types of objects.
In some optional embodiments, for the case that there is dirt, foreign matter or white spots at the packaged part of the tissue, the aforementioned manner of determining the defect type corresponding to the target area according to the characteristics of the target area may include the following steps:
and determining that the third type of defects exist in the tissue package when the difference value between the gray level of the target area and the gray level of the corresponding area in the first standard imaging is outside the preset gray level difference allowable interval and the area of the target area is within the corresponding preset area interval.
The third type of defect includes defects that the portion of the tissue package has stains, foreign matter or white spots outside the acceptable range. The preset gray difference allowable interval and the preset area interval are two numerical value intervals, and can be set according to the type of the target area and the specific actual requirement, for example, the defect that the part packaged by the paper towel is stained is caused, the gray difference allowable interval can be set to be not less than 30, and the corresponding area interval can be set to be not more than 1 square millimeter, so that the defect in the aspect of the stained can be identified. The foregoing difference in gray scales may refer to an absolute difference between two gray scales in some cases, and may also refer to an absolute value of a difference between two gray scales in other cases.
In some embodiments, the tissue package defect detection method may further include the steps of:
determining a target pattern in the first perspective imaging;
comparing the position of the target pattern with the position of a corresponding pattern of a preset first standard imaging to obtain a position deviation amount;
and when the position deviation amount exceeds a fourth corresponding preset qualified interval, determining that the tissue package has a fourth type of defects.
The fourth type of defect is a defect of layout deviation, that is, the pattern and the characters on the tissue package are deviated from the preset positions, and the deviation amount exceeds the acceptable range. The fourth qualified interval is another numerical interval, and can be specifically set according to actual requirements. For example, when the target pattern is an image of an opening, the fourth pass interval may be less than 2 mm, but may take other values.
In some optional embodiments, the coordinates of the pixel points on the edge of the target pattern may be used to represent the position of the target pattern, or the coordinates of the reference points such as the center point and the edge point of the target pattern may be used to represent the position of the target pattern.
The position deviation amount may be a distance between a coordinate point representing the target pattern position and a coordinate point representing the corresponding pattern position of the first standard imaging, when the coordinate point representing the target pattern position is plural, a distance between the coordinate point representing each target pattern position and the coordinate point representing the corresponding pattern position of the first standard imaging may be determined respectively, distances between the plural coordinate points may be obtained, and a maximum value or an average value or the like among the plural distances may be taken as the position deviation amount.
In some embodiments, the tissue package is a soft tissue package and the first perspective image comprises an imaging area of an opening of the tissue package. Correspondingly, the paper towel packaging defect detection method can further comprise the following steps:
acquiring a second image, wherein the second image comprises a second perspective image of the tissue package, and the second perspective image comprises an imaging area of the seal opening;
comparing the second perspective imaging with a preset second standard imaging;
when a marked region with the similarity of the corresponding region of the second standard imaging outside a correspondingly preset fifth qualified interval exists in the second visual angle imaging, extracting the characteristics of the marked region;
and determining the defect type corresponding to the marking area according to the characteristics of the marking area.
The principle of the second image acquisition is the same as that of the first image acquisition, and the second image is also derived from a camera of the camera device 102, and in some cases, the second image may be a color image, and in other cases, the second image may also be a non-color image. The difference lies in that the camera for shooting the first image and the camera for shooting the second image are different cameras, and the shooting angles of the two cameras are different.
The second perspective imaging includes imaging of a second surface of the tissue package. The second surface may be a surface of the tissue package other than the first surface where the seal is located.
The principle and manner of comparing the first perspective image with the preset first standard image to determine the defect type corresponding to the target region are described above, and the principle and manner of comparing the second perspective image with the preset second standard image to determine the mark region are also similar. The difference is that the portion of the tissue package corresponding to the marking area is distinguished from the portion of the tissue package corresponding to the target area in terms of location and visual characteristics. It follows that the second perspective imaging may have a plurality of marker regions. Different marking regions may correspond to different fifth qualifying intervals. And the fifth qualified interval is another preset numerical value interval, and in the second visual angle imaging, if the similarity between the marked area and the corresponding area of the second standard imaging is outside the corresponding preset fifth qualified interval, the paper towel packaging part corresponding to the marked area is indicated to have a defect. The corresponding defect types of the mark areas of different types can be different, and the fifth qualified area can be flexibly arranged according to the defect types. For example, for the location of the seal of the tissue package, if it is deemed to be acceptable that the imaged area of the seal (i.e., the label area) in the second perspective image is not less than 90% similar to the imaged area of the seal in the second standard image, then the fifth acceptable interval may be set to [90%,100% ].
The aforementioned characteristics of the mark region are used to distinguish objects corresponding to the mark region, where the objects may be envelopes, wrinkle parts, seal openings, and the like, and specifically, the characteristics of the sample of the related object may be extracted in a machine learning manner, so as to determine different characteristics corresponding to imaging of different types of objects.
Because the different portions of the tissue package corresponding to the different marking regions may be manufactured by different processes, different defect types may exist in the different portions of the tissue package, for example, the defect types corresponding to the marking regions may be a defective seal, a defective fold, a defective side seal, and the like, which may all be determined by similarity.
On the basis of judging whether the tissue package has defects according to the first image, the second visual angle imaging is compared with the preset second standard imaging, and whether the tissue package has defects can be judged more comprehensively.
Of course, in addition to the first image and the second image, in the case that the camera device 102 has more cameras, the tissue package may be photographed by more cameras from more different viewing angles, so as to obtain more images with different viewing angles, and the images with different viewing angles are compared with the preset standard image, so as to judge whether the tissue package has defects under multiple viewing angles more comprehensively.
It should be understood that although the steps in the flowcharts of fig. 2 and 4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps shown in fig. 2 and 4, as well as other embodiments, relate to steps that are not performed in the exact order in which they are performed unless explicitly stated herein, and may be performed in other orders. Moreover, at least a part of the steps of the foregoing embodiments may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or the stages is not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a part of the sub-steps or the stages of other steps.
The embodiment of the present disclosure further provides a paper towel package defect detecting device, as shown in fig. 5, the paper towel package defect detecting device 500 includes:
a first image obtaining module 501, configured to obtain a first image, where the first image includes a first perspective image of a tissue package;
a first pixel number determining module 502, configured to determine, according to the first image, pixel numbers of a plurality of target edges imaged at a first viewing angle;
the first defect detecting module 503 is configured to determine that the tissue package has a first type of defect when the number of pixels of any one target edge is outside a corresponding preset first qualified interval.
In some embodiments, the first image is a color image, and accordingly, the first pixel count determining module 502 may include:
a conversion unit (not shown) for converting the first image into a grayscale image or a black-and-white image;
and a pixel determining unit (not shown) for determining the number of pixels of the plurality of target edges imaged at the first viewing angle in the gray-scale image or the black-and-white image.
In some embodiments, the tissue package defect detecting apparatus 500 may further include:
a feature region determination module (not shown) for determining a feature region imaged from the first perspective;
and a second defect detection module (not shown) for determining that the second type of defect exists in the tissue package when the difference value between the pixel number of any characteristic area and the pixel number of the corresponding area of the preset first standard imaging is out of the corresponding preset second qualified interval.
In some embodiments, the tissue package defect detecting apparatus 500 may further include:
a first comparing module (not shown) for comparing the first perspective imaging with a preset first standard imaging;
a first feature extraction module (not shown) for extracting features of the target region when the target region exists in the first perspective imaging, wherein the similarity of the target region to the corresponding region of the first standard imaging is outside a corresponding preset third qualified interval;
and a third defect detection module (not shown) for determining a defect type corresponding to the target area according to the characteristics of the target area.
In some embodiments, the first defect type determining module determines that the tissue package has the third type of defect when the difference between the gray level of the target region and the gray level of the corresponding region in the first standard imaging is outside a preset gray level difference allowable interval and the area of the target region is within a preset area interval.
In some embodiments, the tissue package defect detecting device 500 may further include:
a target pattern determination module (not shown) for determining a target pattern in the first perspective imaging;
a position comparison module (not shown) for comparing the position of the target pattern with the position of the corresponding pattern imaged by the preset first standard to obtain a position deviation amount;
and a fourth defect detecting module (not shown) for determining that the tissue package has a fourth type of defect when the position deviation exceeds a fourth qualified interval corresponding to the preset value.
In some embodiments, the tissue package is a soft tissue package, the first viewing angle images an imaging area including an opening of the tissue package, and accordingly, the tissue package defect detecting apparatus 500 may further include:
a second image acquisition module (not shown) for acquiring a second image, the second image comprising a second perspective image of the tissue package, the second perspective image comprising an imaged area of the seal seam;
a second comparing module (not shown) for comparing the second perspective image with a second standard image;
a second feature extraction module (not shown) for extracting features of the marked region when the marked region exists in the second perspective imaging, and the similarity of the marked region and the corresponding region of the second standard imaging is outside a corresponding preset fifth qualified interval;
and a fifth defect detecting module (not shown) for determining the defect type corresponding to the marked region according to the characteristics of the marked region.
For specific limitations of the tissue package defect detecting device 500, reference may be made to the above limitations of the tissue package defect detecting method, which will not be described herein again. All or part of the modules in the tissue package defect detecting device 500 can be implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
The embodiment of the present disclosure further provides a tissue package defect detecting system, as shown in fig. 6, the system includes a conveyor belt 601, a camera device 602, and a computer device 603. Wherein the conveyor belt 601 is adapted to transport a tissue product 604 having a tissue package and the camera device 602 is adapted to capture the tissue product 604 transported by the conveyor belt 601 and to generate a first image comprising a first perspective image of the tissue package. The computer device 603 comprises a memory, a processor and a computer program stored on the memory and executable on the processor, the processor when executing the computer program implementing the steps of the method for detecting a package defect of a tissue as in any of the previous embodiments.
In other embodiments, the camera device 602 may also include other cameras, not shown in fig. 6, that may capture the tissue package of the tissue product 604 to generate images at a second image or even other further perspectives.
In some embodiments, as shown in fig. 7, the tissue package defect detection system 600 may further include an optical sensor 701 and a defective product rejection device 702. The optical sensor 601 is configured to detect whether a tissue product to be detected exists in the designated area 703, if yes, send a signal to the computer device 603, and after receiving the signal, the computer device 603 controls the camera device 602 to capture the tissue product to be detected, so as to obtain a first image or a group of images at multiple viewing angles, where the group of images includes the first image and a second image. After the paper towel package defect detection method is executed, the computer device 603 detects the paper towel package of the paper towel product to be detected, and if it is determined that the paper towel package has defects (for example, a first type of defect, a second type of defect, a third type of defect, or a fourth type of defect), determines the detected paper towel product as a defective product, and controls the defective product removing device 702 to remove the detected paper towel product. The defective product rejection device 702 may include a push rod and a motor, and the processor of the computer device 603 may control the motor to drive the push rod to impact the detected tissue product so that it is pushed away from the conveyor belt 601. The defective product rejection device 702 may also comprise an air pump and a nozzle, and the processor of the computer device 603 may control the air pump to operate such that an air flow is blown out of the nozzle, by which the detected tissue product is pushed away from the conveyor belt 601. Of course, the defective product rejection device 702 may also take other configurations that push the detected tissue product off of the conveyor belt 601. Therefore, the method for detecting the packaging defect of the paper towel can further comprise the following steps: acquiring a signal sent by the optical sensor 603, and controlling the camera device 602 to photograph the detected tissue product according to the signal; acquiring a first image, a second image or even more images generated by photographing with the camera device 602; after determining that the tissue package is defective, the defective product rejection device 702 is controlled to push the detected tissue product off the conveyor belt 601.
In some embodiments, the computer device 603 may be a server, the internal structure of which may be as shown in FIG. 8. The computer device 603 includes a processor, memory, network interface connected by a system bus. Wherein the processor of the computer device 603 is used to provide computing and control capabilities. The memory of the computer device 603 comprises a non-volatile storage medium, internal memory. The nonvolatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external camera device 602 via a network connection. The computer program is executed by a processor to implement the method for detecting a package defect of a tissue in any of the embodiments herein.
In some alternative embodiments, the processor may be implemented in the form of at least one of a Programmable Logic Array (PLA), a Field Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a general purpose processor, or other programmable logic device.
In some embodiments, the computer device 603 may be a terminal, the internal structure of which may be as shown in FIG. 9. The computer device 603 includes a processor, memory, network interface, display screen, and input means connected by a system bus. Wherein the processor of the computer device 603 is used to provide computing and control capabilities. The memory of the computer device 603 comprises a non-volatile storage medium, internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device 603 is used for communication with an external terminal through a network connection. The computer program is executed by a processor to implement the method for detecting a package defect of a tissue in any of the embodiments herein. The display screen of the computer device 603 may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device 603 may be a touch layer covered on the display screen, a key, a trackball or a touch pad arranged on a housing of the computer device 603, or an external keyboard, a touch pad or a mouse.
Those skilled in the art will appreciate that the configurations shown in fig. 8 or 9 are merely block diagrams of portions of configurations associated with embodiments of the present disclosure, and do not constitute limitations on the computing devices to which embodiments of the present disclosure may be applied, as a particular computing device may include more or less components than shown, or combine certain components, or have a different arrangement of components.
Embodiments of the present disclosure also provide a computer-readable storage medium having a computer program stored thereon, where the computer program, when executed by a processor, implements the following steps:
acquiring a first image, wherein the first image comprises a first perspective image of the tissue package;
determining the number of pixels of a plurality of target edges imaged at a first view angle according to the first image;
and when the pixel number of any target edge is out of a corresponding preset first qualified interval, determining that the first type of defect exists in the paper towel package.
In other embodiments, the computer program, when executed by the processor, further implements the other steps of the method for detecting a defect in a tissue package in any of the above embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by a computer program, which may be stored in a non-volatile computer-readable storage medium, and the computer program may include the processes of the embodiments of the methods described above when executed. Any reference to memory, storage, databases, or other media used in the embodiments provided in the disclosure may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present disclosure, and the description thereof is more specific and detailed, but not to be construed as limiting the scope of the present disclosure. It should be noted that various changes and modifications can be made by one skilled in the art without departing from the spirit of the disclosure, and these changes and modifications are all within the scope of the disclosure. Therefore, the protection scope of the present disclosure should be subject to the appended claims.
Claims (10)
1. A method for detecting a packaging defect of a tissue, the method comprising:
acquiring a first image comprising a first perspective image of the tissue package;
determining the number of pixels of a plurality of target edges imaged at the first view angle according to the first image;
and when the pixel number of any one target edge is out of a corresponding preset first qualified interval, determining that the first type of defect exists in the paper towel package.
2. The detection method according to claim 1, wherein the first image is a color image;
determining the number of pixels of a plurality of target edges imaged at the first view angle according to the first image, comprising:
converting the first image into a grayscale image or a black-and-white image;
and determining the number of pixels of a plurality of target edges imaged at a first visual angle in the gray-scale image or the black-and-white image.
3. The detection method according to claim 1, further comprising:
determining a characteristic region imaged by the first view angle;
and when the difference value of the pixel number of any one characteristic area and the pixel number of the corresponding area of the preset first standard imaging is out of a corresponding preset second qualified interval, determining that the second type of defects exist in the paper towel package.
4. The method of detecting according to claim 1, further comprising:
comparing the first perspective imaging with a preset first standard imaging;
when a target area with the similarity of the corresponding area of the first standard imaging outside a corresponding preset third qualified interval exists in the first visual angle imaging, extracting the characteristics of the target area;
and determining the defect type corresponding to the target area according to the characteristics of the target area.
5. The detection method according to claim 4, wherein determining the defect type corresponding to the target area according to the feature of the target area comprises:
and determining that the third type of defects exist in the tissue package when the difference value between the gray level of the target area and the gray level of the corresponding area in the first standard imaging is outside a preset gray level difference allowed interval and the area of the target area is within a corresponding preset area interval.
6. The detection method according to claim 1, further comprising:
determining a target pattern in the first perspective imaging;
comparing the position of the target pattern with the position of a corresponding pattern of a preset first standard imaging to obtain a position deviation amount;
and when the position deviation amount exceeds a corresponding preset fourth qualified interval, determining that the tissue package has a fourth type of defects.
7. The inspection method of claim 1, wherein the tissue package is a soft tissue package, the first perspective image comprises an imaged area of an opening of the tissue package;
the method further comprises the following steps:
acquiring a second image comprising a second perspective image of the tissue package, the second perspective image comprising an imaged area of a seal;
comparing the second perspective imaging with a preset second standard imaging;
when a marked region with the similarity of the corresponding region of the second standard imaging outside a correspondingly preset fifth qualified interval exists in the second perspective imaging, extracting the feature of the marked region;
and determining the defect type corresponding to the marking area according to the characteristics of the marking area.
8. A tissue package defect detection apparatus, the apparatus comprising:
a first image acquisition module for acquiring a first image comprising a first perspective image of the tissue package;
the first pixel number determining module is used for determining the pixel numbers of a plurality of target edges imaged at the first visual angle according to the first image;
and the first defect detection module is used for determining that the first type of defects exist in the paper towel package when the pixel number of any one target edge is outside a corresponding preset first qualified interval.
9. A facial tissue packaging defect detection system is characterized by comprising a conveyor belt, camera equipment and computer equipment;
the conveyor belt is used for conveying the tissue product with the tissue package;
the camera device is used for shooting the paper towel products conveyed by the conveyor belt and generating a first image comprising a first visual angle image of the paper towel package;
the computer device comprises a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211556657.7A CN115984185A (en) | 2022-12-06 | 2022-12-06 | Paper towel package defect detection method, device and system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211556657.7A CN115984185A (en) | 2022-12-06 | 2022-12-06 | Paper towel package defect detection method, device and system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115984185A true CN115984185A (en) | 2023-04-18 |
Family
ID=85971364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211556657.7A Pending CN115984185A (en) | 2022-12-06 | 2022-12-06 | Paper towel package defect detection method, device and system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115984185A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117147587A (en) * | 2023-10-31 | 2023-12-01 | 维达纸业（中国）有限公司 | Defect detection system and detection method based on soft-drawing packaging |
-
2022
- 2022-12-06 CN CN202211556657.7A patent/CN115984185A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117147587A (en) * | 2023-10-31 | 2023-12-01 | 维达纸业（中国）有限公司 | Defect detection system and detection method based on soft-drawing packaging |
| CN117147587B (en) * | 2023-10-31 | 2024-01-16 | 维达纸业（中国）有限公司 | Defect detection system and detection method based on soft-drawing packaging |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111179243A (en) | Small-size chip crack detection method and system based on computer vision | |
| JP5061543B2 (en) | Printed matter inspection device, printed matter inspection method | |
| TWI608422B (en) | Optical character recognition device, optical character recognition method, and recording medium | |
| CN110596120A (en) | Glass boundary defect detection method, device, terminal and storage medium | |
| JPH07141463A (en) | Detection of mechanically printed amount of money in binary-coded image | |
| CN116228678A (en) | Automatic identification and processing method for chip packaging defects | |
| CN114266764A (en) | Character integrity detection method and device for printed label | |
| CN115984185A (en) | Paper towel package defect detection method, device and system and storage medium | |
| CN109584237A (en) | Chip detection method and device, computer equipment and storage medium | |
| CN110288040B (en) | Image similarity judging method and device based on topology verification | |
| CN115512381A (en) | Text recognition method, text recognition device, text recognition equipment, storage medium and working machine | |
| CN113283439B (en) | Intelligent counting method, device and system based on image recognition | |
| US20150117769A1 (en) | Blob-Encoding | |
| CN115619783B (en) | Method and device for detecting product processing defects, storage medium and terminal | |
| CN115631198B (en) | Crack detection method and device for glass display screen and computer equipment | |
| CN115984197A (en) | Defect detection method based on standard PCB image and related device | |
| CN111935480B (en) | Detection method for image acquisition device and related device | |
| JP2010091525A (en) | Pattern matching method of electronic component | |
| CN111882572B (en) | One-dimensional code detection method and device, storage medium and electronic equipment | |
| CN110852994B (en) | Visual detection method and system for jet printing card | |
| JP2006035505A (en) | Method and device for inspecting printed matter | |
| US20240078658A1 (en) | Inspection apparatus and storage medium storing computer program | |
| JP7300155B2 (en) | Teaching device in solid preparation appearance inspection, and teaching method in solid preparation appearance inspection | |
| JP2020003452A (en) | Inspection device, method for inspection, and program for inspection device | |
| JP2022184098A (en) | Image processing device, image processing method and program |
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 |