A method, system and equipment for measuring the orientation of nonwoven fibers

Abstract

This invention discloses a method, system, and device for measuring the orientation of nonwoven fibers, belonging to the field of nonwoven fabrics. The method binarizes a color image of the nonwoven fabric to extract the fiber skeleton. Based on this, a T-shaped corner detection algorithm is used to determine the intersection points of the fiber skeleton. A fiber length constraint algorithm is used to limit the length of the skeleton segments, and a fiber projection algorithm is used to calculate the projected length of the skeleton segments, thereby determining the orientation of each length-constrained skeleton segment. The T-shaped corner detection algorithm used in this invention can accurately handle fiber skeleton intersection points, the fiber length constraint algorithm can effectively avoid interference from long fibers on orientation measurement, and the fiber projection algorithm can accurately calculate the projected length of the fibers. These three algorithms together make the measurement of nonwoven fiber orientation more accurate and efficient, and are applicable to various types of nonwoven materials.

Description

Technical Field

[0001] This invention relates to the field of nonwoven fabrics, and in particular to a method, system and device for measuring the orientation of nonwoven fibers. Background Technology

[0002] Nonwoven fabrics have wide applications in many fields, and fiber orientation is a key structural indicator that determines their performance. It reflects the anisotropy of the mechanical properties of nonwoven fabrics and partially determines their performance, production process, and applications. Therefore, accurately measuring the fiber orientation of nonwoven fabrics is essential for understanding and improving their performance.

[0003] Existing methods for measuring nonwoven fiber orientation include string tracing, fast Fourier transform, and Hough transform. These methods can automatically extract fiber orientation information from nonwoven fabrics and accurately calculate and analyze fiber orientation. However, these techniques are mainly suitable for analyzing thin nonwoven fabrics. For images containing a large number of fibers or multi-layer images, they may lead to underfocusing and thus introduce errors.

[0004] In addition, some researchers have used imaging techniques such as X-ray computed tomography and optical microscopy to obtain three-dimensional information of fibers in nonwoven fabrics, and employed image fusion algorithms to obtain clear images for further analysis of fiber orientation and arrangement. However, these methods may lead to increased computational complexity and slower processing speeds.

[0005] Especially regarding the handling of fiber crossings, while existing methods offer some solutions, such as those based on Bezier curve fitting, the accuracy of these methods still needs improvement. Fiber crossings and entanglements are very common in nonwovens, and these crossings can complicate fiber orientation measurements. Therefore, a method is needed that can more accurately handle fiber skeleton crossings and measure fiber orientation more precisely. Summary of the Invention

[0006] The purpose of this invention is to provide a method, system, and device for measuring the orientation of nonwoven fibers, which is applicable to various types of nonwoven materials, can effectively handle fiber skeleton intersections, and improve the measurement accuracy of fiber orientation.

[0007] To achieve the above objectives, the present invention provides the following solution:

[0008] A method for measuring the orientation of nonwoven fibers, comprising:

[0009] Acquire color images of nonwoven fabrics;

[0010] The color image is binarized to obtain a binary image of the nonwoven fabric;

[0011] Extract the fiber skeleton from the binary image;

[0012] The T-shaped corner detection algorithm is used to calculate the pixel value in the 8-neighborhood of each pixel in the fiber skeleton and determine the intersection point of the fiber skeleton.

[0013] All intersections are removed from the fiber skeleton, the fiber skeleton is decomposed into multiple skeleton segments, and the length of the skeleton segments is limited using a fiber length limiting algorithm;

[0014] The fiber projection algorithm is used to calculate the projected lengths of each length-limited skeleton segment in the X and Y directions;

[0015] The orientation of each length-limited skeleton segment is determined based on its projected length in the X and Y directions, thereby obtaining the fiber orientation of the nonwoven fabric.

[0016] Optionally, a T-shaped corner detection algorithm is used to calculate the pixel value in the 8-neighborhood of each pixel in the fiber skeleton to determine the intersection point of the fiber skeleton, specifically including:

[0017] For a pixel with a value of P1, if pixel value P1 satisfies any of the following 8 conditions, then the pixel with a value of P1 is determined to be an intersection point of the fiber skeleton:

[0018] Condition 1: P1×P2×P3×P5×P8=255^5 and P4×P6×P7×P9=0;

[0019] Condition 2: P3×P4×P5×P6×P9=255^5 and P1×P2×P7×P8=0;

[0020] Condition 3: P2×P5×P7×P8×P9=255^5 and P1×P3×P4×P6=0;

[0021] Condition 4: P1×P4×P5×P6×P7=255^5 and P2×P3×P8×P9=0;

[0022] Condition 5: P2×P5×P6×P7=255^4 and P1×P3×P4×P8×P9=0;

[0023] Condition 6: P1×P5×P6×P8=255^4 and P2×P3×P4×P7×P9=0;

[0024] Condition 7: P3×P4×P5×P8=255^4 and P1×P2×P6×P7×P9=0;

[0025] Condition 8: P2×P4×P5×P9=255^4 and P1×P3×P6×P7×P8=0;

[0026] Where P2, P3, P4, P5, P6, P7, P8, and P9 represent the pixel values ​​in the 8-neighborhood of the pixel with pixel value P1.

[0027] Optionally, a fiber length constraint algorithm is used to constrain the length of the skeleton segment, specifically including:

[0028] Traverse all skeleton pixels in the skeleton fragment and identify pixels that have only one neighboring point that is a skeleton pixel in 8-connectivity as endpoints;

[0029] Select an unvisited endpoint and mark it as visited;

[0030] Iterate from the selected endpoint, apply the connectivity principle to visit the neighboring points of the endpoint to accumulate length, and mark the neighboring points as visited;

[0031] When the accumulated length reaches the threshold T, the iteration stops, and the grayscale value of the current access point is set to 0 to delete the current access point;

[0032] Set the two neighboring points before and after the current visited point as new endpoints, and return to the step "Select an unvisited endpoint and mark it as visited" until all endpoints are marked as visited.

[0033] Optionally, the formula for calculating the orientation of the skeleton segment after length limitation is:

[0034] θ = arctan(L) y / L x );

[0035] Where θ represents the orientation angle of the skeleton segment after length constraint, and L x and L y These represent the projected lengths of the skeleton segment in the X and Y directions, respectively, after length constraints.

[0036] Optionally, acquiring a color image of the nonwoven fabric includes:

[0037] Color sub-images of nonwoven fabrics at different depths were obtained using an optical microscope;

[0038] By fusing color sub-images of different depths, a color image of the entire nonwoven fabric is obtained.

[0039] Optionally, in the binary image of the nonwoven fabric, the background pixel value is 0 and the fiber pixel value is 255.

[0040] Optionally, the color image is binarized to obtain a binary image of the nonwoven fabric, and then the process further includes:

[0041] Morphological filtering is applied to remove small black holes within the fibrous tissue in the binary image, and the structures adjacent to the two ends of the small black holes are connected.

[0042] Optionally, extracting the fiber skeleton from the binary image specifically includes:

[0043] A thinning algorithm is used to gradually remove the boundary pixels of the fibers in the binary image, extract the fiber skeleton, and represent it with a center line with a width of 1 pixel.

[0044] A nonwoven fiber orientation measurement system, comprising:

[0045] The image acquisition module is used to acquire color images of nonwoven fabrics;

[0046] The binarization module is used to perform binarization processing on the color image to obtain a binary image of the nonwoven fabric.

[0047] A skeleton extraction module is used to extract the fibrous skeleton from the binary image;

[0048] The corner detection module is used to calculate the pixel value in the 8-neighborhood of each pixel in the fiber skeleton using a T-shaped corner detection algorithm to determine the intersection point of the fiber skeleton.

[0049] The length limiting module is used to delete all intersections in the fiber skeleton, decompose the fiber skeleton into multiple skeleton segments, and limit the length of the skeleton segments using a fiber length limiting algorithm.

[0050] The projection module is used to calculate the projected length of each length-limited skeleton segment in the X and Y directions using a fiber projection algorithm.

[0051] The orientation determination module is used to determine the orientation of each length-limited skeleton segment based on the projected lengths of each length-limited skeleton segment in the X and Y directions, thereby obtaining the fiber orientation of the nonwoven fabric.

[0052] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the nonwoven fiber orientation measurement method as described above.

[0053] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0054] This invention discloses a method, system, and device for measuring the orientation of nonwoven fibers. The T-corner detection algorithm can accurately handle the intersection of fiber skeletons, the fiber length limitation algorithm can effectively avoid the interference of long fibers on orientation measurement, and the fiber projection algorithm can accurately calculate the projected length of the fiber. These three algorithms together make the measurement of nonwoven fiber orientation more accurate and efficient, and are applicable to various types of nonwoven materials. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 A flowchart of a nonwoven fiber orientation measurement method provided in an embodiment of the present invention;

[0057] Figure 2 A schematic diagram illustrating a nonwoven fiber orientation measurement method provided in an embodiment of the present invention;

[0058] Figure 3 This is a schematic diagram of a binary image of a nonwoven fabric provided in an embodiment of the present invention;

[0059] Figure 4 This is a schematic diagram of the skeleton extraction process provided in an embodiment of the present invention;

[0060] Figure 5 This is a schematic diagram of the length limiting algorithm process provided in an embodiment of the present invention;

[0061] Figure 6 This is a schematic diagram of the T-corner detection process provided in an embodiment of the present invention;

[0062] Figure 7 A comparison diagram of fiber distribution results and algorithms provided in the embodiments of the present invention. Detailed Implementation

[0063] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0064] This invention provides a method, system, and device for measuring the orientation of nonwoven fibers. It employs a novel T-shaped corner detection algorithm to achieve more accurate fiber orientation measurement. Furthermore, it introduces fiber length constraint and fiber projection algorithms, which are also key components and further improve the measurement accuracy. This invention is applicable to various types of nonwoven materials and can effectively handle fiber skeleton intersections, thereby improving the measurement accuracy of fiber orientation.

[0065] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0066] Example 1

[0067] like Figure 1 As shown, this embodiment of the invention provides a method for measuring the orientation of nonwoven fibers, including:

[0068] Step 1: Obtain a color image of the nonwoven fabric.

[0069] Color sub-images of the nonwoven fabric at different depths are acquired using an optical microscope; these sub-images are then fused to obtain a color image of the entire nonwoven fabric. Step 1 corresponds to... Figure 2 The image acquisition and image fusion sections.

[0070] Step 2: Binarize the color image to obtain a binary image of the nonwoven fabric.

[0071] In the binary image, the background has a pixel value of 0, and the fibers have a pixel value of 255. A binary image of a nonwoven fabric is shown below. Figure 3 As shown.

[0072] After binarization, morphological filtering is performed: morphological filtering is applied to remove small black holes within the fiber and connect adjacent structures.

[0073] Step 3: Extract the fiber skeleton from the binary image.

[0074] Based on existing thinning algorithms, the boundary pixels of the fibers are gradually removed to extract their skeleton. The fiber skeleton consists of a centerline with a width of 1 pixel, as shown below. Figure 4 As shown.

[0075] Step 4: Using the T-shaped corner detection algorithm, calculate the pixel value in the 8-neighborhood of each pixel in the fiber skeleton to determine the intersection point of the fiber skeleton.

[0076] T-corner detection: T-corner detection is performed on the skeleton to identify the intersections of the fiber skeleton. For example... Figure 6As shown, the specific method is to calculate the pixel values ​​in its 8-neighborhood for each pixel, and determine whether it is a T-corner point using the following formula:

[0077] First case: P1×P2×P3×P5×P8=255^5 and P4×P6×P7×P9=0

[0078] The second scenario: P3×P4×P5×P6×P9=255^5 and P1×P2×P7×P8=0

[0079] The third scenario: P2×P5×P7×P8×P9=255^5 and P1×P3×P4×P6=0

[0080] The fourth case: P1×P4×P5×P6×P7=255^5 and P2×P3×P8×P9=0

[0081] Fifth case: P2×P5×P6×P7=255^4 and P1×P3×P4×P8×P9=0

[0082] The sixth case: P1×P5×P6×P8=255^4 and P2×P3×P4×P7×P9=0

[0083] The seventh case: P3×P4×P5×P8=255^4 and P1×P2×P6×P7×P9=0

[0084] Eighth case: P2×P4×P5×P9=255^4 and P1×P3×P6×P7×P8=0

[0085] Where 255 is the pixel value of a white pixel and 0 is the pixel value of a black pixel. For a pixel with a value of P1, if any of the above conditions are met, the pixel with a value of P1 is considered to be a T-shaped corner point (intersection point). P2, P3, P4, P5, P6, P7, P8, and P9 represent the pixel values ​​in the 8-neighborhood of the pixel with a value of P1.

[0086] Step 5: Delete all intersections in the fiber skeleton, decompose the fiber skeleton into multiple skeleton segments, and use a fiber length limiting algorithm to limit the length of the skeleton segments.

[0087] Length Limitation Algorithm: A fiber length limitation algorithm is used to restrict the length of the fiber skeleton. For each skeleton segment, if its length is less than the threshold L (5 pixels), it is deleted. The specific steps are as follows:

[0088] Step 5-1: Traverse all skeleton pixels (P=255) in the skeleton fragment image and identify pixels with only one neighbor that is also a skeleton pixel in 8-connectivity. Mark each identified pixel as an endpoint by changing its grayscale value to 50 (P=50).

[0089] Step 5-2: Start length accumulation, select an unvisited endpoint and mark it as visited.

[0090] Step 5-3: Start iterating from the selected endpoint, visit its neighboring points by applying the connectivity principle, and mark the neighboring points as visited while accumulating the length.

[0091] Step 5-4: When the length reaches the threshold T, stop the iteration and delete the current point (current access point) by setting its grayscale value to 0 (P=0). Set the two neighboring points before and after the current point as the new endpoints and set their grayscale values ​​to 50 (P=50).

[0092] Step 5-5: Repeat steps 5-2, 5-3, and 5-4, calculating the length of each segment starting from 0, until all endpoints are marked as visited. The length of the result is limited as follows. Figure 5 As shown. Figure 5 The point inside the middle box is the current point to be deleted.

[0093] Step 6: Calculate the projected length of each length-limited skeleton segment in the X and Y directions using the fiber projection algorithm.

[0094] The fiber projection algorithm is used to calculate the projected length of the fibers, and then the fiber orientation is calculated. Specifically, for each skeleton segment, its projected lengths in the X and Y directions are calculated, denoted as L, respectively. x and L y .

[0095] Step 7: Determine the orientation of each length-limited skeleton segment based on its projected length in the X and Y directions, thereby obtaining the fiber orientation of the nonwoven fabric.

[0096] The formula for calculating the orientation of the skeleton segment after length restriction is as follows:

[0097] θ = arctan(L) y / L x )

[0098] Where θ represents the orientation angle of the skeleton segment after length constraint, and L x and L y These represent the projected lengths of the skeleton segment in the X and Y directions, respectively, after length constraints.

[0099] The present invention has the following beneficial effects:

[0100] 1. High precision: A new T-shaped corner detection algorithm is adopted. This algorithm, developed specifically for the characteristics of nonwoven fabric fibers, can more accurately locate the intersection points of the fiber skeleton, thereby more accurately measuring the fiber orientation. This is a major improvement compared to existing technologies, as existing methods lack sufficient precision when dealing with fiber skeleton intersection points.

[0101] 2. Wide Applicability: This method also incorporates fiber length constraint and fiber projection algorithms, which further improve the measurement accuracy of fiber orientation, making it applicable to various types of nonwoven materials. This is a significant advantage over existing technologies, as existing methods may not be suitable for all types of nonwoven materials.

[0102] The above advantages mainly stem from three key technologies: the T-corner detection algorithm, the fiber length constraint algorithm, and the fiber projection algorithm. The T-corner detection algorithm accurately handles fiber skeleton intersections, the fiber length constraint algorithm effectively avoids interference from long fibers in orientation measurements, and the fiber projection algorithm accurately calculates the projected length of the fiber. These three technologies together make the measurement of nonwoven fiber orientation more accurate and efficient. A comparison of fiber distribution results and algorithms is shown in the figure below. Figure 7 As shown. Figure 7 Part (a) represents the fiber strength orientation distribution; part (b) represents the orientation distribution after applying both the length constraint algorithm and the orientation algorithm, compared with the strength orientation distribution; part (c) represents the original orientation distribution without any optimization algorithm, compared with the strength orientation distribution; part (d) represents the orientation distribution after applying only the length constraint algorithm, compared with the strength orientation distribution; part (e) represents the orientation distribution after applying the CPDA corner detection algorithm, compared with the strength orientation distribution; and part (f) represents the orientation distribution after applying the CSS corner detection algorithm, compared with the strength orientation distribution.

[0103] Example 2

[0104] In order to perform the method corresponding to Embodiment 1 above and achieve the corresponding functions and technical effects, a nonwoven fiber orientation measurement system is provided below, including:

[0105] The image acquisition module is used to acquire color images of nonwoven fabrics.

[0106] The binarization module is used to perform binarization processing on the color image to obtain a binary image of the nonwoven fabric.

[0107] A skeleton extraction module is used to extract the fibrous skeleton from the binary image.

[0108] The corner detection module is used to calculate the pixel value in the 8-neighborhood of each pixel in the fiber skeleton using a T-shaped corner detection algorithm, and to determine the intersection point of the fiber skeleton.

[0109] The length limiting module is used to delete all intersections in the fiber skeleton, decompose the fiber skeleton into multiple skeleton segments, and limit the length of the skeleton segments using a fiber length limiting algorithm.

[0110] The projection module is used to calculate the projected length of each length-limited skeleton segment in the X and Y directions using a fiber projection algorithm.

[0111] The orientation determination module is used to determine the orientation of each length-limited skeleton segment based on the projected lengths of each length-limited skeleton segment in the X and Y directions, thereby obtaining the fiber orientation of the nonwoven fabric.

[0112] The nonwoven fiber orientation measurement system provided in this embodiment of the invention has a similar working principle and beneficial effects to the nonwoven fiber orientation measurement method described in the above embodiments, so it will not be described in detail here. For details, please refer to the introduction of the above method embodiments.

[0113] Example 3

[0114] This invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the nonwoven fiber orientation measurement method as described in Embodiment 1.

[0115] Furthermore, when the computer program in the aforementioned memory is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0116] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0117] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method of nonwoven fiber orientation measurement, characterized by, The method comprises the following steps: acquiring a color image of the non-woven fabric; performing a binaryzation process on the color image to obtain a binary image of the non-woven fabric; extracting a fiber skeleton from the binary image; calculating the pixel values in the 8-neighborhood of each pixel in the fiber skeleton to determine the intersection points of the fiber skeleton by using a T-shaped corner point detection algorithm; deleting all the intersection points in the fiber skeleton to decompose the fiber skeleton into a plurality of skeleton segments, and limiting the length of the skeleton segments by using a fiber length limiting algorithm; wherein the fiber length limiting algorithm comprises the following steps: traversing all the skeleton pixels in the skeleton segment, and identifying a pixel having only one adjacent point being a skeleton pixel in the 8-connectivity as an end point; selecting an unvisited end point and marking it as visited; starting iteration from the selected end point, and applying the connectivity principle to visit the adjacent points of the end point to accumulate the length, while marking the adjacent points as visited; when the length accumulation reaches a threshold T, stopping the iteration, and setting the gray value of the current visited point to 0 to delete the current visited point; setting the two adjacent points before and after the current visited point as new end points, and returning to the step of "selecting an unvisited end point and marking it as visited" until all the end points are marked as visited; calculating the projection lengths of each length-limited skeleton segment in the X direction and the Y direction by using a fiber projection algorithm; determining the orientation of each length-limited skeleton segment according to the projection lengths of each length-limited skeleton segment in the X direction and the Y direction, thereby obtaining the fiber orientation of the non-woven fabric.

2. The nonwoven fiber orientation measurement method according to claim 1, characterized by, The T-shaped corner point detection algorithm comprises the following steps: for a pixel having a pixel value P1, if the pixel value P1 satisfies any one of the following eight conditions, the pixel having the pixel value P1 is determined as an intersection point of the fiber skeleton: condition one: P1 × P2 × P3 × P5 × P8 = 255^5 and P4 × P6 × P7 × P9 = 0; condition two: P3 × P4 × P5 × P6 × P9 = 255^5 and P1 × P2 × P7 × P8 = 0; condition three: P2 × P5 × P7 × P8 × P9 = 255^5 and P1 × P3 × P4 × P6 = 0; condition four: P1 × P4 × P5 × P6 × P7 = 255^5 and P2 × P3 × P8 × P9 = 0; condition five: P2 × P5 × P6 × P7 = 255^4 and P1 × P3 × P4 × P8 × P9 = 0; condition six: P1 × P5 × P6 × P8 = 255^4 and P2 × P3 × P4 × P7 × P9 = 0; Condition seven: P3 x P4 x P5 x P8 = 255^4 and P1 x P2 x P6 x P7 x P9 = 0; Condition eight: P2 x P4 x P5 x P9 = 255^4 and P1 x P3 x P6 x P7 x P8 = 0; Wherein, P2, P3, P4, P5, P6, P7, P8, P9 represent pixel values in the 8-neighborhood of the pixel with pixel value P1.

3. The nonwoven fiber orientation measurement method according to claim 1, characterized by, The calculation formula of the orientation of the length-limited skeleton segment is: θ = arctan(L y / L x ) ; wherein θ represents an orientation angle of the skeleton segment after length restriction, L x and L y respectively represent the projection length of the skeleton segment in the X direction and the Y direction after length restriction.

4. The nonwoven fiber orientation measurement method according to claim 1, characterized by, The color image of the non-woven fabric is acquired, specifically comprising: The color sub-images of the non-woven fabric at different layer depths are acquired using an optical microscope; The color sub-images at different layer depths are fused to obtain the color image of the whole non-woven fabric.

5. The nonwoven fiber orientation measurement method according to claim 1, characterized by, In the binary image of the non-woven fabric, the pixel value of the background is 0, and the pixel value of the fiber is 255.

6. The nonwoven fiber orientation measurement method according to claim 1, characterized by, The color image is binarized to obtain a binary image of the non-woven fabric, and then further comprising: Morphological filtering is applied to remove small black holes in the fiber body in the binary image and connect the adjacent structures at both ends of the small black holes.

7. The nonwoven fiber orientation measurement method according to claim 1, characterized by, The fiber skeleton is extracted from the binary image, specifically comprising: A thinning algorithm is used to gradually remove the boundary pixels of the fiber in the binary image to extract the fiber skeleton, and the center line with a width of 1 pixel is used to represent the fiber skeleton.

8. A nonwoven fiber orientation measurement system characterized by, Comprise: An image acquisition module is configured to acquire a color image of the non-woven fabric; A binarization module is configured to binarize the color image to obtain a binary image of the non-woven fabric; A skeleton extraction module is configured to extract a fiber skeleton from the binary image; An angle point detection module is configured to use a T-type angle point detection algorithm to calculate the pixel values in the 8-neighborhood of each pixel in the fiber skeleton to determine the intersection points of the fiber skeleton; A length limitation module is configured to delete all intersection points in the fiber skeleton, decompose the fiber skeleton into multiple skeleton segments, and limit the length of the skeleton segments using a fiber length limitation algorithm; wherein the fiber length limitation algorithm is used to limit the length of the skeleton segments, specifically comprising: traversing all skeleton pixels in the skeleton segment, and identifying a pixel with only one adjacent point being a skeleton pixel in 8-connectivity as an end point; selecting an unvisited end point and marking it as visited; starting iteration from the selected end point, applying connectivity principle to visit the adjacent points of the end point to accumulate the length, and marking the adjacent points as visited; when the length accumulation reaches a threshold T, stopping iteration, and setting the gray value of the current visited point to 0 to delete the current visited point; setting the two adjacent points before and after the current visited point as new end points, and returning to the step of "selecting an unvisited end point and marking it as visited" until all end points are marked as visited; A projection module is configured to calculate the projection length of each length-limited skeleton segment in the X direction and the Y direction using a fiber projection algorithm; An orientation determination module is configured to determine the orientation of each length-limited skeleton segment according to the projection length of each length-limited skeleton segment in the X direction and the Y direction, thereby obtaining the fiber orientation of the non-woven fabric.

9. An electronic device, comprising: A computer program product comprising a memory, a processor, and a computer program stored on the memory and loadable on the processor, the processor implementing the nonwoven fiber orientation measurement method as claimed in any of claims 1 to 7 when executing the computer program.

Images