Defect detection method and system based on color gradient high-speed nonwoven fabric production line

Abstract

The present invention discloses a defect detection method and system for a high-speed nonwoven fabric production line based on color gradients, belonging to the field of quality inspection technology. The method comprises: obtaining an upper surface image and a lower surface image of the same area of ​​nonwoven fabric on the nonwoven fabric production line; calculating the color gradient of the upper surface image to obtain an upper surface color gradient image; calculating the color gradient of the lower surface image to obtain a lower surface color gradient image; and using a connected domain analysis method to perform defect identification on each of the upper and lower surface color gradient images, thereby obtaining the upper surface position, upper surface area, lower surface position, and lower surface area of ​​each defect on the nonwoven fabric. By calculating the color gradient and extracting color change information, the embodiments of the present invention can accurately identify defects.

Description

Technical Field

[0001] The present invention relates to the technical field of quality inspection, and in particular to a defect detection method and system based on a color gradient high-speed nonwoven fabric production line. Background Art

[0002] In nonwoven fabric production lines, detecting defects such as color spots, oil stains, and damage is a critical step in ensuring product quality. Traditionally, manual inspection has dominated defect detection methods. However, manual inspection is inefficient, limited by human resources, and susceptible to factors such as fatigue and subjective judgment, leading to errors in test results.

[0003] With the development of computer vision technology, automated defect detection methods based on image processing have begun to be widely researched and applied. These methods typically include steps such as image preprocessing, feature extraction, and classifier design. Although image processing-based methods offer higher efficiency and better consistency than manual inspection, they still face several challenges.

[0004] First, many existing methods rely primarily on grayscale or texture features to detect defects. These features work well in some scenarios, such as for defects with distinct shapes and uniform sizes. However, for defects with significant color variations, such as spots and oil stains, using only grayscale or texture features often fails to achieve satisfactory detection results.

[0005] Secondly, many existing methods rely on fixed thresholds or rules to identify defects. These thresholds or rules often require manual adjustment based on specific application scenarios. This requires extensive manual intervention and adjustment when dealing with defects of different types or in different environments, reducing their versatility and scalability.

[0006] Therefore, developing a defect detection method that can accurately identify defects without requiring extensive human intervention is an important technical challenge in the nonwovens production industry. Summary of the Invention

[0007] The purpose of the present invention is to provide a defect detection method and system for a color gradient high-speed nonwoven fabric production line, so as to achieve accurate identification of defects without requiring a large amount of manual participation.

[0008] To achieve the above object, the present invention provides the following solutions:

[0009] The present invention provides a defect detection method for a high-speed nonwoven fabric production line based on a color gradient, the method comprising the following steps:

[0010] Acquire upper surface images and lower surface images of the same area of ​​nonwoven fabric on a nonwoven fabric production line;

[0011] Calculating the color gradient of the upper surface image to obtain an upper surface color gradient image;

[0012] Calculating the color gradient of the lower surface image to obtain a lower surface color gradient image;

[0013] The connected domain analysis method is used to identify defects in the upper surface color gradient image and the lower surface color gradient image respectively, and the upper surface position, upper surface area, lower surface position and lower surface area of ​​each defect on the nonwoven fabric are obtained.

[0014] Optionally, a surface image group of nonwoven fabrics on a nonwoven fabric production line is obtained, and then the method further includes:

[0015] preprocessing the upper surface image to obtain a preprocessed upper surface image;

[0016] The lower surface image is preprocessed to obtain a preprocessed lower surface image.

[0017] Optionally, preprocessing the upper surface image to obtain a preprocessed upper surface image specifically includes:

[0018] Perform color space conversion on the upper surface image to obtain the HSV image of the upper surface;

[0019] The HSV image of the upper surface is smoothed and normalized to obtain a preprocessed upper surface image.

[0020] Optionally, the formula for calculating the color gradient of the upper surface image is:

[0021] G=sqrt[(dH / dx)^2+(dH / dy)^2+(dS / dx)^2+(dS / dy)^2+(dV / dx)^2+(dV / dy)^2];

[0022] Where G is the color gradient, dH / dx and dH / dy represent the color gradients of the hue of the upper surface image in the horizontal and vertical directions, respectively, dS / dx and dS / dy represent the color gradients of the saturation of the upper surface image in the horizontal and vertical directions, respectively, and dV / dx and dV / dy represent the color gradients of the brightness of the upper surface image in the horizontal and vertical directions, respectively.

[0023] Optionally, a connected domain analysis method is used to identify defects on the upper surface color gradient image and the lower surface color gradient image respectively to obtain the upper surface position, upper surface area, lower surface position and lower surface area of ​​each defect on the nonwoven fabric, and then further includes:

[0024] Calculate the contamination degree of each defect on the nonwoven fabric based on the upper surface position, upper surface area, lower surface position and lower surface area of ​​each defect;

[0025] Determine whether the contamination degree of the defect is greater than the contamination degree threshold and obtain the judgment result;

[0026] If the judgment result indicates yes, then it is determined to use cutting to process the defect;

[0027] If the judgment result indicates no, it is determined to use a cleaning method to treat the defect.

[0028] Optionally, the degree of contamination of a defect is calculated as:

[0029]

[0030] Among them, r i is the damage degree of the i-th defect, S p,i and S d,i are the upper and lower surface areas of the i-th defect, S p,i ∩S d,i represents the intersection of the upper and lower surface areas of the i-th defect, S p,i ∪S d,i represents the union of the upper and lower surface areas of the i-th defect.

[0031] A defect detection system based on a color gradient high-speed nonwoven fabric production line, the system is applied to the above method, and the system comprises:

[0032] An image acquisition module, used for acquiring an upper surface image and a lower surface image of the same area of ​​a nonwoven fabric on a nonwoven fabric production line;

[0033] A first color gradient calculation module is used to calculate the color gradient of the upper surface image to obtain an upper surface color gradient image;

[0034] A second color gradient calculation module is used to calculate the color gradient of the lower surface image to obtain a lower surface color gradient image;

[0035] The defect recognition module is used to identify defects on the upper surface color gradient image and the lower surface color gradient image respectively using the connected domain analysis method, and obtain the upper surface position, upper surface area, lower surface position and lower surface area of ​​each defect on the nonwoven fabric.

[0036] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above method when executing the computer program.

[0037] A computer-readable storage medium stores a computer program, which implements the above method when executed.

[0038] A defect detection device based on a color gradient high-speed nonwoven fabric production line, the device comprising: a first camera, a second camera and a controller;

[0039] The first camera and the second camera are respectively arranged on the upper part and the lower part of the nonwoven fabric of the nonwoven fabric production line;

[0040] The first camera and the second camera are both connected to the controller;

[0041] The controller is used to perform defect identification using the above method.

[0042] Optionally, the device further comprises a marking mechanism;

[0043] The marking mechanism is arranged on the upper part of the rewinding machine of the nonwoven fabric production line, and the control end of the marking mechanism is connected to the controller;

[0044] The controller is further configured to mark defects based on the identified positions and areas of the upper surface defects and the positions and areas of the lower surface defects.

[0045] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0046] Embodiments of the present invention provide a defect detection method and system for a high-speed nonwoven fabric production line based on color gradients. The method comprises: obtaining an upper surface image and a lower surface image of the same area of ​​nonwoven fabric on the nonwoven fabric production line; calculating the color gradient of the upper surface image to obtain an upper surface color gradient image; calculating the color gradient of the lower surface image to obtain a lower surface color gradient image; and using a connected domain analysis method to perform defect identification on each of the upper and lower surface color gradient images to obtain the upper surface position, upper surface area, lower surface position, and lower surface area of ​​each defect on the nonwoven fabric. By calculating the color gradient and extracting color change information, the embodiment of the present invention can accurately identify defects.

[0047] Furthermore, the embodiment of the present invention calculates the overlap rate of defects on the upper and lower surfaces to detect the degree of contamination, thereby providing effective guidance for defect treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 A flow chart of a defect detection method for a color gradient high-speed nonwoven fabric production line provided by an embodiment of the present invention;

[0050] Figure 2 A schematic structural diagram of a defect detection device based on a color gradient high-speed nonwoven fabric production line provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0052] The purpose of the present invention is to provide a defect detection method and system for a color gradient high-speed nonwoven fabric production line, so as to achieve accurate identification of defects without requiring a large amount of manual participation.

[0053] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0054] Example 1

[0055] Embodiment 1 of the present invention provides a defect detection method for a high-speed nonwoven fabric production line based on a color gradient, such as Figure 1 As shown, the method includes the following steps:

[0056] Step 101: Acquire an upper surface image and a lower surface image of the same area of ​​a nonwoven fabric on a nonwoven fabric production line.

[0057] In the embodiment of the present invention, a high-speed camera is provided at the upper and lower positions of the non-woven fabric in the non-woven fabric production line to capture the upper surface image and the lower surface image of the non-woven fabric in real time.

[0058] The embodiment of the present invention also uses a computer device to perform a series of preprocessing steps on the upper surface image and the lower surface image captured by the high-speed camera to better perform subsequent color gradient calculation and defect detection. The preprocessing steps include the following parts:

[0059] a. Color space conversion: Convert the RGB color space image to the HSV color space. The HSV color space's color representation method can better express color variations, especially when dealing with color-related issues such as stains, oil stains, and damage. Using the HSV color space can produce better results than using the RGB color space.

[0060] b. Image smoothing: To eliminate image noise and maintain color trends, image smoothing methods such as Gaussian filtering and median filtering can be used to process the image. These methods can effectively remove noise while preserving edge information, providing clearer and more accurate input for subsequent color gradient calculations.

[0061] c. Normalization: To ensure that the processed image data is within a uniform range, the image data can be normalized. This can eliminate the dimensional effects between the image data and avoid excessively large values ​​in subsequent calculations, which can affect the accuracy of the calculation results.

[0062] Step 102: Calculate the color gradient of the upper surface image to obtain an upper surface color gradient image.

[0063] The formula for calculating the color gradient of the surface image is:

[0064] G=sqrt[(dH / dx)^2+(dH / dy)^2+(dS / dx)^2+(dS / dy)^2+(dV / dx)^2+(dV / dy)^2];

[0065] Where G is the color gradient, dH / dx and dH / dy represent the color gradients of the hue of the upper surface image in the horizontal and vertical directions, respectively, dS / dx and dS / dy represent the color gradients of the saturation of the upper surface image in the horizontal and vertical directions, respectively, and dV / dx and dV / dy represent the color gradients of the brightness of the upper surface image in the horizontal and vertical directions, respectively.

[0066] Step 103: Calculate the color gradient of the lower surface image to obtain a lower surface color gradient image.

[0067] The formula for calculating the color gradient of the lower surface image in the embodiment of the present invention is consistent with the formula for calculating the color gradient of the upper surface image, and will not be repeated here.

[0068] Step 104 : Using the connected domain analysis method to identify defects on the upper surface color gradient image and the lower surface color gradient image, respectively, to obtain the upper surface position, upper surface area, lower surface position, and lower surface area of ​​each defect on the nonwoven fabric.

[0069] In the color gradient images (upper and lower surface color gradient images), areas with large color changes (i.e., defects) are highlighted. Defects are detected based on the color gradient images, and their location and area can be determined using methods such as connected domain analysis.

[0070] The embodiment of the present invention also calculates and distinguishes the pollution degree, as follows:

[0071] The contamination degree is calculated for the images of the same defect on the upper and lower surfaces of the nonwoven fabric. The specific method is to calculate the area of ​​the defect on the upper and lower surfaces, and then calculate the overlap rate as the contamination degree:

[0072] Contamination degree = (intersection of the upper surface area and the lower surface area of ​​the defect) / (union of the upper surface area and the lower surface area of ​​the defect) * 100%.

[0073] Specifically, the calculation formula for the contamination degree of the defect is:

[0074]

[0075] Among them, r i is the damage degree of the i-th defect, S p,i and S d,i are the upper and lower surface areas of the i-th defect, S p,i ∩S d,i represents the intersection of the upper and lower surface areas of the i-th defect, S p,i ∪S d,i represents the union of the upper and lower surface areas of the i-th defect.

[0076] The intersection in the embodiment of the present invention is the intersection of the area of ​​the i-th defect on the upper surface and the area of ​​the lower surface, and the union is the union of the area of ​​the i-th defect on the upper surface and the area of ​​the lower surface.

[0077] If the contamination level is greater than 50%, it is considered to be severely contaminated and requires cutting; if it is less than 50%, it is considered to be lightly contaminated and can be manually cleaned.

[0078] Example 2

[0079] Embodiment 2 of the present invention provides a defect detection system based on a color gradient high-speed nonwoven fabric production line, the system being applied to the above-mentioned method, the system comprising:

[0080] The image acquisition module is used to acquire the upper surface image and the lower surface image of the same area of ​​the nonwoven fabric on the nonwoven fabric production line.

[0081] The first color gradient calculation module is used to calculate the color gradient of the upper surface image to obtain the upper surface color gradient image.

[0082] The second color gradient calculation module is used to calculate the color gradient of the lower surface image to obtain the lower surface color gradient image.

[0083] The defect recognition module is used to identify defects on the upper surface color gradient image and the lower surface color gradient image respectively using the connected domain analysis method, and obtain the upper surface position, upper surface area, lower surface position and lower surface area of ​​each defect on the nonwoven fabric.

[0084] Example 3

[0085] Embodiment 3 of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method when executing the computer program.

[0086] Example 4

[0087] Embodiment 4 of the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the above method when the computer program is executed.

[0088] Example 5

[0089] Embodiment 5 of the present invention provides a defect detection device based on a color gradient high-speed non-woven fabric production line, the device comprising: a first camera, a second camera and a controller; the first camera and the second camera are respectively arranged on the upper and lower parts of the non-woven fabric of the non-woven fabric production line; the first camera and the second camera are both connected to the controller; the controller is used to use the above-mentioned method to identify defects.

[0090] As a preferred embodiment, the device in the embodiment of the present invention also includes a marking mechanism; the marking mechanism is arranged on the upper part of the rewinding machine of the non-woven fabric production line, and the control end of the marking mechanism is connected to the controller; the controller is also used to mark defects based on the identified position and area of ​​the upper surface defects and the position and area of ​​the lower surface defects.

[0091] For example, in the embodiment of the present invention, the first camera and the second camera are both high-speed cameras, such as Figure 2 As shown, the steps of color gradient calculation and pollution degree calculation are all implemented in the controller. The controller in the embodiment of the present invention can be a computer, a single chip microcomputer, a portable device, etc. The above-mentioned marking mechanism is used to mark defects.

[0092] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0093] High Accuracy: By leveraging color gradient information, the present invention can accurately identify defects such as color spots, oil stains, and damage. Traditional inspection methods typically rely solely on grayscale or texture information, but color information is crucial in some cases, especially for defects like color spots and oil stains. By utilizing color gradient information, these defects can be captured through color changes, thereby improving inspection accuracy.

[0094] High efficiency: The embodiments of the present invention utilize computer-automated processing, significantly improving efficiency compared to manual inspection. On a nonwovens production line, the number of defects can be enormous, making manual inspection inefficient and error-prone. Computer vision technology, however, can process and analyze large numbers of images in a fraction of the time.

[0095] Strong versatility and scalability: This embodiment of the present invention does not rely on manually set thresholds or rules, but instead automatically detects defects based on color gradient information. This makes the method widely applicable to defect detection in different types and environments, and it is highly versatile and scalable.

[0096] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0097] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only intended to help understand the method and core concept of the present invention. At the same time, those skilled in the art will find that the specific implementation methods and application scopes may vary based on the concept of the present invention. In summary, the contents of this specification should not be construed as limiting the present invention.

Claims

1. A defect detection method for a high-speed nonwoven fabric production line based on color gradient, characterized in that: The method comprises the following steps: Acquire upper surface images and lower surface images of the same area of ​​nonwoven fabric on a nonwoven fabric production line; Calculating the color gradient of the upper surface image to obtain an upper surface color gradient image; Calculating the color gradient of the lower surface image to obtain a lower surface color gradient image; Connected domain analysis is used to identify defects on the upper surface color gradient image and the lower surface color gradient image respectively, and the upper surface position, upper surface area, lower surface position and lower surface area of ​​each defect on the nonwoven fabric are obtained; Calculate the contamination degree of each defect on the nonwoven fabric based on the upper surface position, upper surface area, lower surface position and lower surface area of ​​each defect; Determine whether the contamination degree of the defect is greater than the contamination degree threshold and obtain the judgment result; If the judgment result indicates yes, then it is determined to use cutting to process the defect; If the judgment result indicates no, then determining to treat the defect in a cleaning manner; The calculation formula for the contamination degree of defects is: Among them, r i is the damage degree of the i-th defect, S p,i and S d,i are the upper and lower surface areas of the i-th defect, S p,i ∩S d,i represents the intersection of the upper and lower surface areas of the i-th defect, S p,i ∪S d,i represents the union of the upper and lower surface areas of the i-th defect.

2. The defect detection method based on the color gradient high-speed nonwoven fabric production line according to claim 1, characterized in that: Acquire a set of surface images of nonwoven fabrics on a nonwoven fabric production line, followed by: preprocessing the upper surface image to obtain a preprocessed upper surface image; The lower surface image is preprocessed to obtain a preprocessed lower surface image.

3. The defect detection method based on the color gradient high-speed nonwoven fabric production line according to claim 2, characterized in that, Preprocessing the upper surface image to obtain a preprocessed upper surface image specifically includes: Perform color space conversion on the upper surface image to obtain the HSV image of the upper surface; The HSV image of the upper surface is smoothed and normalized to obtain a preprocessed upper surface image.

4. The defect detection method based on the color gradient high-speed nonwoven fabric production line according to claim 1 is characterized in that, The formula for calculating the color gradient of the surface image is: G=sqrt[(dH / dx)^2+(dH / dy)^2+(dS / dx)^2+(dS / dy)^2+(dV / dx)^2+(dV / dy)^2]; Where G is the color gradient, dH / dx and dH / dy represent the color gradients of the hue of the upper surface image in the horizontal and vertical directions, respectively, dS / dx and dS / dy represent the color gradients of the saturation of the upper surface image in the horizontal and vertical directions, respectively, and dV / dx and dV / dy represent the color gradients of the brightness of the upper surface image in the horizontal and vertical directions, respectively.

5. A defect detection system based on a color gradient high-speed nonwoven fabric production line, characterized in that: The system is applied to the method according to any one of claims 1 to 4, and the system includes: An image acquisition module, used for acquiring an upper surface image and a lower surface image of the same area of ​​a nonwoven fabric on a nonwoven fabric production line; A first color gradient calculation module is used to calculate the color gradient of the upper surface image to obtain an upper surface color gradient image; A second color gradient calculation module is used to calculate the color gradient of the lower surface image to obtain a lower surface color gradient image; The defect recognition module is used to identify defects on the upper surface color gradient image and the lower surface color gradient image respectively using the connected domain analysis method, and obtain the upper surface position, upper surface area, lower surface position and lower surface area of ​​each defect on the nonwoven fabric.

6. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 4 when executing the computer program.

7. A defect detection device based on a color gradient high-speed nonwoven fabric production line, characterized in that: The device includes: a first camera, a second camera and a controller; The first camera and the second camera are respectively arranged on the upper part and the lower part of the nonwoven fabric of the nonwoven fabric production line; The first camera and the second camera are both connected to the controller; The controller is used to perform defect identification using the method according to any one of claims 1 to 4.

8. The defect detection device based on the color gradient high-speed nonwoven fabric production line according to claim 7 is characterized in that: The device also includes a marking mechanism; The marking mechanism is arranged on the upper part of the rewinding machine of the nonwoven fabric production line, and the control end of the marking mechanism is connected to the controller; The controller is further configured to mark defects based on the identified positions and areas of the upper surface defects and the positions and areas of the lower surface defects.

Images