Composite material reinforcement length calculation method and device based on image processing

Abstract

The application discloses a composite material reinforcing body length calculation method and device based on image processing, and the method comprises the following steps: obtaining a composite material organization image, processing the composite material organization image to obtain a reinforcing body image with a single composite material reinforcing body, processing the reinforcing body outer contour of the reinforcing body image by adopting a skeleton thinning algorithm to obtain a first reinforcing body skeleton, performing point-by-point detection based on the first reinforcing body skeleton, and removing redundant points to obtain a more accurate second reinforcing body skeleton. The front moving method is adopted to extract the reinforcing body axis in the second reinforcing body skeleton, and the longest one in the reinforcing body axis is found as a reinforcing body main axis for calculating the reinforcing body length. The method is simple, the calculation amount is small, the reinforcing body main axis obtained can better reflect the main part of the reinforcing body length, and the shortest distance between the reinforcing body main axis two end points and the reinforcing body outer contour makes the calculation of the reinforcing body length more accurate.

Description

Technical Field

[0001] This invention relates to the field of composite material microstructure characterization and image processing technology, specifically to a method and apparatus for calculating the length of composite material reinforcements based on image processing. Background Technology

[0002] Advanced materials science techniques allow for the combination of different materials to achieve properties that simultaneously belong to the composite material. For example, sintering technology can be used to create composites of ceramics and metals. These composites possess not only the high hardness and wear resistance of ceramics but also the electrical conductivity, thermal conductivity, and toughness of metals. This advantage of composite materials allows for the design and combination of different materials to meet specific needs. Consequently, composite materials are widely used in various forms across diverse industries.

[0003] Typically, composite materials consist of one material as the matrix and another as the reinforcement, combined through specific processes. The matrix is ​​generally a continuous phase, while the reinforcement can be continuous or discontinuous. In composite materials with discontinuous reinforcement, the content and shape of the reinforcement affect the composite's properties. For example, in conductivity tests of composite materials using a metal as the reinforcement and a ceramic as the matrix, the conductivity increases with increasing metal content. However, with a constant metal content, the shape of the metal reinforcement significantly influences the material's conductivity. Composite materials with high aspect ratio shapes (e.g., elongated strips) exhibit significantly higher conductivity than those with low aspect ratio shapes (e.g., near-circular, near-square, near-acute triangular, etc.).

[0004] Therefore, in the research and evaluation of composite material properties, the shape of the reinforcement, especially its aspect ratio, is widely focused on and measured. Traditional measurement methods are based on manual measurement. Technicians use rulers to measure the length of the reinforcement and visually select locations, and measure the thickness of the reinforcement. Manual measurement is time-consuming and labor-intensive, requiring a significant investment of time and energy from technicians. Therefore, in actual measurement processes, image processing methods are often relied upon to reduce labor intensity. Traditional image processing methods are difficult to directly calculate the length and thickness of the reinforcement, and indirect methods are often used to estimate these values. For example, the length and thickness of the reinforcement can be approximated by calculating the minimum bounding rectangle of the reinforcement. Furthermore, to avoid the hassle of calculating length and thickness, other parameters are used for calculation. For instance, after obtaining the perimeter and area of ​​the reinforcement, the shape factor is calculated: shape factor = perimeter² ÷ (4π × area), used to approximate the required parameters. These methods have a certain degree of accuracy and effectiveness when the reinforcement has a simple shape and clear outline, but they have a large error for reinforcements with complex shapes and many serrated outlines, and their applicability is limited. For example, the shape factor can only obtain accurate results in the calculation of near-circular or elliptical reinforcement phases. Summary of the Invention

[0005] In view of the aforementioned technical problems, the purpose of the embodiments of this application is to propose a method and apparatus for calculating the length of composite material reinforcements based on image processing, so as to solve the technical problems mentioned in the background section above.

[0006] In a first aspect, the present invention provides a method for calculating the length of a composite material reinforcement based on image processing, comprising the following steps:

[0007] S1, acquire composite material microstructure image, process composite material microstructure image to obtain reinforcement image with single composite material reinforcement;

[0008] S2, refine the augmentation image to obtain the first augmentation skeleton;

[0009] S3, Detect the first reinforcement skeleton point by point, remove the redundant points in the first reinforcement skeleton, and obtain the second reinforcement skeleton;

[0010] S4, the length of the composite reinforcement is calculated using the leading edge movement method based on the second reinforcement skeleton.

[0011] Preferably, step S1 involves processing the composite material tissue image, specifically including cropping and enlarging the composite material tissue image, wherein the cropped image contains a complete single composite material reinforcement.

[0012] Preferably, step S2 specifically includes:

[0013] Extract the outer contour of the augmented body from the augmented body image;

[0014] The outer contour of the augmented body image is skeletonized to obtain the first augmented body skeleton.

[0015] Preferably, step S3 involves removing redundant points from the first reinforcing skeleton, specifically including:

[0016] Determine the number of neighboring points around the current point. Based on the number of neighboring points and their positional relationships, decide whether to retain the current point. The positions of the neighboring points include the centers of the four vertices and four sides of the quadrilateral centered on the current point.

[0017] Preferably, the decision to retain the current point is based on the number of its neighboring points and the positional relationships between them. Specifically, this includes:

[0018] In response to the determination that there is one neighboring point around the current point, the current point is retained and marked as an endpoint;

[0019] In response to determining that there are two neighboring points around the current point, it is determined whether the positions of the two neighboring points on the four vertices and the center of the four sides of the quadrilateral are adjacent. If they are, the current point is deleted; otherwise, the current point is retained.

[0020] In response to determining that there are 3 neighboring points around the current point, it is determined whether the positions of the 3 neighboring points on the four vertices and the center of the four sides of the quadrilateral are continuous. If so, the current point is deleted; otherwise, the current point is retained.

[0021] In response to determining that there are 4 neighboring points around the current point, it is determined whether the positions of the 4 neighboring points on the four vertices and the centers of the four sides of the quadrilateral are continuous. If so, the current point is deleted; otherwise, the current point is retained.

[0022] In response to determining that there are 5 neighboring points around the current point, it is determined whether the positions of the 5 neighboring points on the four vertices and the center of the four sides of the quadrilateral are continuous. If so, the current point is deleted; otherwise, the current point is retained.

[0023] In response to determining that there are 6 neighboring points around the current point, it is determined whether the positions of the 6 neighboring points on the four vertices and the center of the four sides of the quadrilateral are continuous. If so, the current point is deleted; otherwise, the current point is retained.

[0024] If it is determined that there are 7 or more neighboring points around the current point, delete the current point.

[0025] Preferably, step S4 specifically includes:

[0026] S41, Select an endpoint as the leading edge point of the reinforcement axis, and determine the neighboring points around the leading edge point;

[0027] S42, Process the leading edge point or reinforcement axis according to the number and / or properties of the neighboring points around the leading edge point;

[0028] S43, using the other endpoints as leading edges, repeat steps S41-S42 to determine several reinforcing body axes;

[0029] S44, calculate the length of all reinforcement axes, and take the longest reinforcement axis as the main reinforcement axis. The main reinforcement axis has a first end point and a second end point.

[0030] S45, calculate the shortest distances from the first and second endpoints of the main axis of the enhancer to the outer contour of the enhancer in the enhancer image, and calculate the enhancer length according to the following formula:

[0031] Reinforcement length = length of the main axis of the reinforcement + shortest distance from the first endpoint of the main axis of the reinforcement to the outer contour of the reinforcement + shortest distance from the second endpoint of the main axis of the reinforcement to the outer contour of the reinforcement.

[0032] Preferably, step S42 specifically includes:

[0033] Determine whether the neighboring point is the leading edge point through which the reinforcement axis passes. If so, remove the neighboring point; otherwise, keep the neighboring point.

[0034] In response to the determination that the number of remaining neighboring points exceeds 1, the number of reinforcement axes is increased to n-1, where n is the number of neighboring points, and the corresponding neighboring points are stored as the leading edge points of the corresponding reinforcement axes;

[0035] In response to the determination that there is only one remaining neighboring point, the neighboring point is stored as the leading edge of the augmentation axis led by the leading edge point;

[0036] In response to determining that the remaining neighboring points are the leading edges of another reinforcement axis, the reinforcement axis and the other reinforcement axis and the leading edges they lead are deleted.

[0037] In response to determining that the remaining neighboring points are endpoints, the calculation of the axis led by the leading edge point is completed, and the calculation of other axes continues until the leading edge point is an endpoint.

[0038] In a second aspect, the present invention provides a composite material reinforcement length calculation device based on image processing, comprising:

[0039] The image acquisition module is configured to acquire composite material tissue images, process the composite material tissue images, and obtain reinforcement images with a single composite material reinforcement.

[0040] The thinning module is configured to thin the augmented volume image to obtain the first augmented volume skeleton;

[0041] The point-by-point detection module is configured to detect the first reinforcement skeleton point by point, remove the redundant points in the first reinforcement skeleton, and obtain the second reinforcement skeleton.

[0042] The leading edge movement module is configured to calculate the length of the composite reinforcement based on the second reinforcement skeleton using the leading edge movement method.

[0043] Thirdly, the present invention provides an electronic device including one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any implementation of the first aspect.

[0044] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in any of the implementations of the first aspect.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] (1) The composite material reinforcement length calculation method based on image processing proposed in this invention can be used to calculate the reinforcement length in the automatic processing of composite material microstructure images, thereby achieving accurate and efficient calculation of the reinforcement length.

[0047] (2) The composite material reinforcement length calculation method based on image processing proposed in this invention uses a skeleton thinning algorithm to process the outer contour of the reinforcement image to obtain the first reinforcement skeleton. Based on the first reinforcement skeleton, point-by-point detection is performed to remove redundant points in order to obtain a more accurate second reinforcement skeleton.

[0048] (3) The composite material reinforcement length calculation method based on image processing proposed in this invention uses the leading edge moving method to extract the reinforcement axis in the second reinforcement skeleton, and finds the longest one among the reinforcement axes as the main reinforcement axis to calculate the reinforcement length. This method is simple, requires less calculation, and the obtained main reinforcement axis can better reflect the main part of the reinforcement length. Combined with the shortest distance between the two ends of the main reinforcement axis and the outer contour of the reinforcement, the calculation of the reinforcement length is more accurate. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0050] Figure 1 This is an exemplary device architecture diagram in which an embodiment of this application can be applied;

[0051] Figure 2 This is a flowchart illustrating the image processing-based composite material reinforcement length calculation method according to an embodiment of this application.

[0052] Figure 3 This is a schematic diagram of the reinforcement image processing process in the composite material reinforcement length calculation method based on image processing, as described in an embodiment of this application.

[0053] Figure 4 This is a schematic diagram illustrating the positional relationship between the current point and adjacent points in the point-by-point detection of the image processing-based composite material reinforcement length calculation method according to an embodiment of this application.

[0054] Figure 5 This is a schematic diagram of the leading edge movement method of the composite material reinforcement length calculation method based on image processing, as an embodiment of this application.

[0055] Figure 6 This is a schematic diagram of an image processing-based composite material reinforcement length calculation device according to an embodiment of this application;

[0056] Figure 7 This is a schematic diagram of the structure of a computer device suitable for implementing the electronic device of the present application. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0058] Figure 1 An exemplary device architecture 100 is shown that can be applied to the image processing-based composite material reinforcement length calculation method or the image processing-based composite material reinforcement length calculation device according to the embodiments of this application.

[0059] like Figure 1As shown, the device architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, and 103 and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0060] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various applications, such as data processing applications and file processing applications, can be installed on terminal devices 101, 102, and 103.

[0061] Terminal devices 101, 102, and 103 can be either hardware or software. When terminal devices 101, 102, and 103 are hardware, they can be various electronic devices, including but not limited to smartphones, tablets, laptops, and desktop computers. When terminal devices 101, 102, and 103 are software, they can be installed in the electronic devices listed above. They can be implemented as multiple software programs or software modules (e.g., software programs or software modules used to provide distributed services) or as a single software program or software module. No specific limitations are imposed here.

[0062] Server 105 can be a server that provides various services, such as a background data processing server that processes files or data uploaded by terminal devices 101, 102, and 103. The background data processing server can process the acquired files or data and generate processing results.

[0063] It should be noted that the composite material reinforcement length calculation method based on image processing provided in this application embodiment can be executed by server 105 or by terminal devices 101, 102, and 103. Correspondingly, the composite material reinforcement length calculation device based on image processing can be set in server 105 or in terminal devices 101, 102, and 103.

[0064] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Any number of terminal devices, networks, and servers can be included depending on implementation needs. If the data being processed does not need to be retrieved remotely, the above architecture may not include a network, requiring only servers or terminal devices.

[0065] Figure 2 An embodiment of this application illustrates a method for calculating the length of a composite material reinforcement based on image processing, comprising the following steps:

[0066] S1, acquire composite material microstructure image, process composite material microstructure image to obtain reinforcement image with single composite material reinforcement.

[0067] In a specific embodiment, step S1 involves processing the composite material tissue image, specifically including cropping and enlarging the composite material tissue image, wherein the cropped image contains a complete single composite material reinforcement.

[0068] For details, please refer to Figure 3 The composite material microstructure images in this application use microstructure images of ceramic matrix metal composites as an example. From the microstructure images of the ceramic matrix metal composites, a reinforcement image containing the reinforcement to be measured is obtained. This reinforcement image includes the outer contour of the reinforcement, such as... Figure 3 (a) and Figure 3 As shown in (b). Preferably, the augmented body image can be obtained by taking a screenshot, and the augmented body image still has a certain degree of clarity after being enlarged. The screenshot is taken by extending a certain distance outward from the outer contour of the augmented body, so that the augmented body is located in the middle of the augmented body image and the outer contour of the augmented body is displayed, making subsequent processing more accurate and convenient.

[0069] S2, refine the augmentation image to obtain the first augmentation skeleton.

[0070] In a specific embodiment, step S2 specifically includes:

[0071] Extract the outer contour of the augmented body from the augmented body image;

[0072] The outer contour of the augmented body image is skeletonized to obtain the first augmented body skeleton.

[0073] Specifically, such as Figure 3 (c) Extract the outer contour of the augmentation body from the augmentation body image, and process the augmentation body image using existing skeleton thinning algorithms to obtain the first augmentation body skeleton, such as... Figure 3 As shown in (d), the specific skeleton refinement algorithm will not be described in detail here.

[0074] S3, Detect the first reinforcement skeleton point by point, remove the redundant points in the first reinforcement skeleton, and obtain the second reinforcement skeleton.

[0075] In a specific embodiment, step S3 involves removing redundant points from the first reinforcing skeleton, specifically including:

[0076] Determine the number of neighboring points around the current point. Based on the number of neighboring points and their positional relationships, decide whether to retain the current point. The positions of the neighboring points include the centers of the four vertices and four sides of the quadrilateral centered on the current point.

[0077] In a specific embodiment, determining whether to retain the current point based on the number of neighboring points around the current point and the positional relationship between the neighboring points specifically includes:

[0078] In response to the determination that there is one neighboring point around the current point, the current point is retained and marked as an endpoint;

[0079] In response to determining that there are two neighboring points around the current point, it is determined whether the positions of the two neighboring points on the four vertices and the center of the four sides of the quadrilateral are adjacent. If they are, the current point is deleted; otherwise, the current point is retained.

[0080] In response to determining that there are 3 neighboring points around the current point, it is determined whether the positions of the 3 neighboring points on the four vertices and the center of the four sides of the quadrilateral are continuous. If so, the current point is deleted; otherwise, the current point is retained.

[0081] In response to determining that there are 4 neighboring points around the current point, it is determined whether the positions of the 4 neighboring points on the four vertices and the centers of the four sides of the quadrilateral are continuous. If so, the current point is deleted; otherwise, the current point is retained.

[0082] In response to determining that there are 5 neighboring points around the current point, it is determined whether the positions of the 5 neighboring points on the four vertices and the center of the four sides of the quadrilateral are continuous. If so, the current point is deleted; otherwise, the current point is retained.

[0083] In response to determining that there are 6 neighboring points around the current point, it is determined whether the positions of the 6 neighboring points on the four vertices and the center of the four sides of the quadrilateral are continuous. If so, the current point is deleted; otherwise, the current point is retained.

[0084] If it is determined that there are 7 or more neighboring points around the current point, delete the current point.

[0085] For details, please refer to Figure 4 A quadrilateral is set around the current point, and the four vertices of the quadrilateral and the center points of the four sides form a grid. The first augmentation skeleton is then detected point by point based on the positional relationship of adjacent points on the grid around the current point, including the following cases:

[0086] (1)Reference Figure 4-1 and Figure 4-2 If there is one neighboring point around the current point, keep the current point and mark it as the endpoint;

[0087] (2)Reference Figure 4-3~ Figure 4-7 If the current point has two adjacent points, and these two adjacent points are not adjacent to each other (i.e., there is at least one point between the adjacent points that is separated by the center points of the four vertices and four sides of the quadrilateral), then the current point is retained. (Refer to...) Figure 4 -8, if the two adjacent points are adjacent, delete the current point;

[0088] (3)Reference Figure 4 -9~ Figure 4-1 7. If there are 3 adjacent points around the current point, and the positions of the 3 adjacent points are not consecutive, that is, at least 2 adjacent points are separated by at least one of the four vertices and the center points of the four sides of the quadrilateral, then keep the current point; if the positions of the 3 adjacent points are adjacent, then delete the current point.

[0089] (4)Reference Figure 4-1 8~ Figure 4-2 2. If there are 4 adjacent points around the current point, and the positions of the 4 adjacent points are not consecutive, that is, at least 2 adjacent points are separated by at least one of the four vertices and the center points of the four sides of the quadrilateral, then keep the current point; if the positions of the 4 adjacent points are adjacent, then delete the current point.

[0090] (6)Reference Figure 4-2 3~ Figure 4-2 7. If there are 5 adjacent points around the current point, and the positions of the 5 adjacent points are not consecutive, that is, at least 2 adjacent points are separated by at least one of the four vertices and four sides of the quadrilateral, then keep the current point; if the positions of the 5 adjacent points are adjacent, then delete the current point.

[0091] (7)Reference Figure 4-2 8. If there are 6 adjacent points around the current point, and the positions of the 6 adjacent points are not consecutive, that is, at least 2 adjacent points are separated by at least one of the four vertices and four sides of the quadrilateral, then keep the current point; if the positions of the 6 adjacent points are adjacent, delete the current point.

[0092] (8) If there are 7 or more adjacent points around the current point, delete the current point.

[0093] It should be pointed out that, Figure 4 The position of the midpoint only indicates the relative positional relationship between adjacent points. When the positions of each adjacent point rotate 90°, 180° or 270° around the current point (i.e. the center point), this step will be processed as if it were in the unrotated state.

[0094] S4, the length of the composite reinforcement is calculated using the leading edge movement method based on the second reinforcement skeleton.

[0095] In a specific embodiment, step S4 specifically includes:

[0096] S41, Select an endpoint as the leading edge point of the reinforcement axis, and determine the neighboring points around the leading edge point;

[0097] S42, Process the leading edge point or reinforcement axis according to the number and / or properties of the neighboring points around the leading edge point;

[0098] S43, using the other endpoints as leading edges, repeat steps S41-S42 to determine several reinforcing body axes;

[0099] S44, calculate the length of all reinforcement axes, and take the longest reinforcement axis as the main reinforcement axis. The main reinforcement axis has a first end point and a second end point.

[0100] S45, calculate the shortest distances from the first and second endpoints of the main axis of the enhancer to the outer contour of the enhancer in the enhancer image, and calculate the enhancer length according to the following formula:

[0101] Reinforcement length = length of the main axis of the reinforcement + shortest distance from the first endpoint of the main axis of the reinforcement to the outer contour of the reinforcement + shortest distance from the second endpoint of the main axis of the reinforcement to the outer contour of the reinforcement.

[0102] In a specific embodiment, step S42 specifically includes:

[0103] Determine whether the neighboring point is the leading edge point through which the reinforcement axis passes. If so, remove the neighboring point; otherwise, keep the neighboring point.

[0104] In response to the determination that the number of remaining neighboring points exceeds 1, the number of reinforcement axes is increased to n-1, where n is the number of neighboring points, and the corresponding neighboring points are stored as the leading edge points of the corresponding reinforcement axes;

[0105] In response to the determination that there is only one remaining neighboring point, the neighboring point is stored as the leading edge of the augmentation axis led by the leading edge point;

[0106] In response to determining that the remaining neighboring points are the leading edges of another reinforcement axis, the reinforcement axis and the other reinforcement axis and the leading edges they lead are deleted.

[0107] In response to determining that the remaining neighboring points are endpoints, the calculation of the axis led by the leading edge point is completed, and the calculation of other axes continues until the leading edge point is an endpoint.

[0108] Specifically, with Figure 5 Using the second reinforced skeleton shown as an example, the specific steps of the leading-edge movement method are as follows:

[0109] (1) Set endpoint 1 as the leading edge point of the reinforcing body axis 1. Point 1 has only one neighboring point, point 2, around it. Therefore, point 1 is the endpoint.

[0110] (2) Find the nearest point to the front edge (endpoint 1), which is point 2, and make the following judgment:

[0111] (a) If point 2 is not an old front point, then point 2 is retained. The front points through which the axis of the reinforcement passes during the front movement can be set as old front points.

[0112] (b) Since there is only one neighboring point, point 2 is stored as the leading edge point of the reinforcement axis 1 led by endpoint 1, and point 1 is set as the old leading edge point.

[0113] (c) Point 2 is not the leading edge of another reinforcement axis, so the reinforcement axis 1 it leads is retained;

[0114] (d) Point 2 is not an endpoint, and the reinforcement axis 1 still needs to continue to find the next leading edge point.

[0115] (3) Find the neighboring points of the new frontier point (point 2), which are points 1 and 3, and make the following judgments:

[0116] (a) If point 1 is the old frontier point, then point 1 is removed;

[0117] (b) If point 3 is not an old frontier point, then point 3 is retained;

[0118] (c) Since there is only one neighboring point, point 3 is stored as the leading edge point of the reinforcement axis 1 led by point 2, and point 2 is set as the old leading edge point;

[0119] (e) Point 3 is not the leading edge of another axis, so retain the reinforcing axis 1 that it leads.

[0120] (f) Point 3 is not an endpoint, and the axis still needs to continue searching for the next leading edge point of the reinforcing axis 1.

[0121] (4) By analogy, continue to search for the leading edge point of the reinforcing body axis 1. When point 7 is the leading edge point, the neighboring points 6, 8', and 8 can be obtained, and the following judgments can be made:

[0122] (a) If point 6 is an old frontier point, then remove point 6;

[0123] (b) If points 8' and 8 are not old frontier points, then points 8' and 8 are retained, leaving 2 neighboring points;

[0124] (c) If the number of neighboring points exceeds 1, increase the number of reinforcement axes by 2-1=1 (the number of neighboring points is 2). The corresponding neighboring points 8' and 8' are stored as the leading edge points of reinforcement axis 1 and reinforcement axis 2, respectively. At this time, the number of reinforcement axes changes from 1 to 2, led by the leading edge points 8' and 8', respectively.

[0125] (d) Points 8' and 8 are not endpoints, and the front edge points of reinforcement axis 1 and reinforcement axis 2 still need to be found.

[0126] (5) By analogy, continue searching for the leading edge points of reinforcement axis 1 and reinforcement axis 2. When points 10' and 10 are leading edge points, the number of reinforcement axes increases by 1, from 2 to 3, namely reinforcement axis 1 led by leading edge point 11', reinforcement axis 2 led by leading edge point 11, and reinforcement axis 3 led by leading edge point 11'. Determine:

[0127] (a) Point 11' is the endpoint, so the reinforcement axis 1 led by this front point ends the search for and saves the front point;

[0128] (b) Neither point 11 nor point 11” is an endpoint, so new frontier points are searched for respectively.

[0129] (6) By analogy, when the reinforcement axis 2 finds the leading edge point 17, since the number of neighboring points that meet the conditions is 2, one reinforcement axis is added. At this time, the reinforcement axes that are still searching for the leading edge point are the reinforcement axis 3 led by the leading edge point 18", the reinforcement axis 4 led by the leading edge point 18' and the reinforcement axis 2 led by the leading edge point 18.

[0130] (7) Continue searching for the leading edge point. The leading edge points of reinforcement axis 3 and reinforcement axis 4 meet at point 20”. The nearest point of the leading edge point 20” of reinforcement axis 3 is the leading edge point 19’ of reinforcement axis 4. Therefore, delete the leading edge point 20”, the leading edge point 19’, as well as reinforcement axis 3 and reinforcement axis 4 at the same time.

[0131] (8) The reinforcement axis 2 continues to move forward to find the leading edge point until it reaches the endpoint 25. The calculation of the reinforcement axis 2 ends and the reinforcement axis 2 is saved.

[0132] (9) Repeat the above steps starting from other endpoints.

[0133] (10) Calculate the length of the found reinforcement axis and take the longest reinforcement axis as the main axis of the reinforcement;

[0134] (11) Calculate the shortest distance from the two endpoints of the main axis of the reinforcement to the outer contour of the reinforcement. Taking the axis 2 of the reinforcement as the main axis of the reinforcement as an example, calculate the length of the reinforcement according to the following formula:

[0135] Reinforcement length = Reinforcement main axis length + Shortest distance from reinforcement endpoint 1 to reinforcement outer contour + Shortest distance from reinforcement main axis endpoint 25 to reinforcement outer contour.

[0136] Specifically, the neighboring point cannot be an old front point. If it is an old front point, it is removed. Then, the front point is processed based on the number of remaining neighboring points and whether it is the front point or endpoint of another reinforcement axis. If the number of neighboring points of the front point exceeds two, a bifurcation is determined. A bifurcation indicates that there are more reinforcement axes, that is, the number of reinforcement axes is increased according to the number of neighboring points. It is determined whether the neighboring point is the front point of another reinforcement axis. If so, the front point and the axis led by the encountered front point are deleted. Otherwise, the neighboring point is set as the new front point, and the current front point is set as the old front point. It is determined whether the new front point is the new endpoint. If so, the reinforcement axis from the starting endpoint to the new endpoint is saved. Otherwise, the current front point is set as the old front point, and the next neighboring point is searched as the front point.

[0137] The image processing-based composite material reinforcement length calculation method proposed in the embodiments of this application is a mathematical morphology-based method for calculating the length of composite material reinforcements. It can be used to accurately and efficiently calculate the length of reinforcements during the automatic processing of composite material microstructure images. Practical application has proven that this invention can accurately and quickly measure the length of composite material reinforcements.

[0138] Further reference Figure 6 As an implementation of the methods shown in the above figures, this application provides an embodiment of a composite material reinforcement length calculation device based on image processing. This device embodiment is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0139] This application provides an image processing-based composite material reinforcement length calculation device, including:

[0140] Image acquisition module 1 is configured to acquire composite material tissue images and process the composite material tissue images to obtain reinforcement images with a single composite material reinforcement.

[0141] The thinning module 2 is configured to thin the augmented body image to obtain a first augmented body skeleton;

[0142] The point-by-point detection module 3 is configured to detect the first reinforcement skeleton point by point, remove the redundant points in the first reinforcement skeleton, and obtain the second reinforcement skeleton.

[0143] The leading edge movement module 4 is configured to calculate the length of the composite reinforcement based on the second reinforcement skeleton using the leading edge movement method.

[0144] The following is for reference. Figure 7 It illustrates an electronic device suitable for implementing embodiments of this application (e.g., Figure 1 The diagram shows the structure of a computer device 700 (a server or terminal device). Figure 7 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0145] like Figure 7 As shown, the computer device 700 includes a central processing unit (CPU) 701 and a graphics processing unit (GPU) 702, which can perform various appropriate actions and processes according to programs stored in read-only memory (ROM) 703 or programs loaded from storage section 709 into random access memory (RAM) 704. The RAM 704 also stores various programs and data required for the operation of the device 700. The CPU 701, GPU 702, ROM 703, and RAM 704 are interconnected via a bus 705. An input / output (I / O) interface 706 is also connected to the bus 705.

[0146] The following components are connected to I / O interface 706: an input section 707 including a keyboard, mouse, etc.; an output section 708 including an LCD, speakers, etc.; a storage section 709 including a hard disk, etc.; and a communication section 710 including a network interface card, such as a LAN card or modem. The communication section 710 performs communication processing via a network such as the Internet. A drive 711 may also be connected to I / O interface 706 as needed. A removable medium 712, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 711 as needed so that computer programs read from it can be installed into storage section 709 as needed.

[0147] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 710, and / or installed from removable medium 712. When the computer program is executed by central processing unit (CPU) 701 and graphics processing unit (GPU) 702, the functions defined in the methods of this application are performed.

[0148] It should be noted that the computer-readable medium described in this application can be a computer-readable signal medium, a computer-readable medium, or any combination thereof. A computer-readable medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor device, or any combination thereof. More specific examples of a computer-readable medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution device, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than a computer-readable medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution device, apparatus, or apparatus. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0149] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0150] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using dedicated hardware-based means to perform the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0151] The modules described in the embodiments of this application can be implemented in software or hardware. These modules can also be located within a processor.

[0152] In another aspect, this application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: acquire a composite material microstructure image; process the composite material microstructure image to obtain a reinforcement image with a single composite material reinforcement; refine the reinforcement image to obtain a first reinforcement skeleton; detect the first reinforcement skeleton point by point, remove redundant points in the first reinforcement skeleton to obtain a second reinforcement skeleton; and calculate the length of the composite material reinforcement based on the second reinforcement skeleton using the leading edge movement method.

[0153] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for calculating the length of a composite material reinforcement based on image processing, characterized in that, Includes the following steps: S1, acquire a composite material microstructure image, process the composite material microstructure image to obtain a reinforcement image with a single composite material reinforcement; S2, refine the augmentation image to obtain the first augmentation skeleton; S3, perform point-by-point detection on the first reinforcement skeleton, remove redundant points in the first reinforcement skeleton, and obtain the second reinforcement skeleton, specifically including: Determine the number of neighboring points around the current point, and determine whether to retain the current point based on the number of neighboring points around the current point and the positional relationship of the neighboring points. The positions of the neighboring points include the centers of the four vertices and four sides of the quadrilateral centered on the current point. S4, Calculate the length of the composite reinforcement based on the second reinforcement skeleton using the leading edge movement method, specifically including: S41, Select an endpoint as the leading edge point of the reinforcing body axis, and determine the neighboring points around the leading edge point; S42, Processing the leading edge point or reinforcement axis according to the number and / or attributes of the neighboring points around the leading edge point, specifically including: Determine whether the neighboring point is the leading edge point through which the axis of the reinforcement passes. If so, remove the neighboring point; otherwise, retain the neighboring point. In response to determining that the number of remaining neighboring points exceeds 1, the number of reinforcing body axes is increased to n-1, where n is the number of neighboring points, and the corresponding neighboring points are stored as the leading edge points of the corresponding reinforcing body axes; In response to determining that the number of remaining neighboring points is 1, the neighboring point is stored as the leading edge point of the reinforcement axis led by the leading edge point; In response to determining that the remaining neighboring points are the leading edge points of another reinforcement axis, the reinforcement axis and the other reinforcement axis and their leading edge points are deleted. In response to determining that the remaining neighboring points are endpoints, the calculation of the axis led by the leading edge point is completed, and the calculation of other axes continues until the leading edge point is an endpoint. S43, using the other endpoints as leading edges, repeat steps S41-S42 to determine several reinforcing body axes; S44, calculate the length of all reinforcement axes, and take the longest reinforcement axis as the main reinforcement axis. The main reinforcement axis has a first end point and a second end point. S45, calculate the shortest distances from the first and second endpoints of the main axis of the augmentation body to the outer contour of the augmentation body in the image, and calculate the length of the augmentation body according to the following formula: The length of the reinforcement = the length of the main axis of the reinforcement + the shortest distance from the first endpoint of the main axis of the reinforcement to the outer contour of the reinforcement + the shortest distance from the second endpoint of the main axis of the reinforcement to the outer contour of the reinforcement.

2. The method for calculating the length of a composite material reinforcement based on image processing according to claim 1, characterized in that, The processing of the composite material tissue image in step S1 specifically includes: cropping and enlarging the composite material tissue image, wherein the cropped image contains a complete single composite material reinforcement.

3. The method for calculating the length of a composite material reinforcement based on image processing according to claim 1, characterized in that, Step S2 specifically includes: Extract the outer contour of the augmented body image; The outer contour of the augmented body image is skeletonized to obtain the first augmented body skeleton.

4. The method for calculating the length of a composite material reinforcement based on image processing according to claim 1, characterized in that, The step of determining whether to retain the current point based on the number of neighboring points and the positional relationship between the neighboring points specifically includes: In response to determining that there is one neighboring point around the current point, the current point is retained and marked as an endpoint; In response to determining that there are two adjacent points around the current point, it is determined whether the positions of the two adjacent points at the four vertices and the center of the four sides of the quadrilateral are adjacent. If so, the current point is deleted; otherwise, the current point is retained. In response to determining that there are 3 neighboring points around the current point, it is determined whether the positions of the 3 neighboring points on the four vertices and the center of the four sides of the quadrilateral are continuous. If so, the current point is deleted; otherwise, the current point is retained. In response to determining that there are 4 neighboring points around the current point, it is determined whether the positions of the 4 neighboring points on the four vertices and the center of the four sides of the quadrilateral are continuous. If so, the current point is deleted; otherwise, the current point is retained. In response to determining that there are 5 neighboring points around the current point, it is determined whether the positions of the 5 neighboring points on the four vertices and the center of the four sides of the quadrilateral are continuous. If so, the current point is deleted; otherwise, the current point is retained. In response to determining that there are 6 neighboring points around the current point, it is determined whether the positions of the 6 neighboring points on the four vertices and the center of the four sides of the quadrilateral are continuous. If so, the current point is deleted; otherwise, the current point is retained. In response to determining that the current point has 7 or more neighboring points, the current point is deleted.

5. A composite material reinforcement length calculation device based on image processing, characterized in that, include: The image acquisition module is configured to acquire composite material tissue images and process the composite material tissue images to obtain reinforcement images with a single composite material reinforcement. The thinning module is configured to thin the augmented body image to obtain a first augmented body skeleton; The point-by-point detection module is configured to detect the first reinforcement skeleton point by point, remove redundant points in the first reinforcement skeleton, and obtain the second reinforcement skeleton, specifically including: Determine the number of neighboring points around the current point, and determine whether to retain the current point based on the number of neighboring points around the current point and the positional relationship of the neighboring points. The positions of the neighboring points include the centers of the four vertices and four sides of the quadrilateral centered on the current point. The leading-edge movement module is configured to calculate the length of the composite reinforcement based on the second reinforcement skeleton using the leading-edge movement method, specifically including: The first submodule is configured to select an endpoint as the leading edge point of the reinforcement axis and determine the neighboring points around the leading edge point; The second submodule is configured to process the leading edge point or reinforcement axis based on the number and / or attributes of neighboring points around the leading edge point. Specifically, the second submodule includes: Determine whether the neighboring point is the leading edge point through which the axis of the reinforcement passes. If so, remove the neighboring point; otherwise, retain the neighboring point. In response to determining that the number of remaining neighboring points exceeds 1, the number of reinforcing body axes is increased to n-1, where n is the number of neighboring points, and the corresponding neighboring points are stored as the leading edge points of the corresponding reinforcing body axes; In response to determining that the number of remaining neighboring points is 1, the neighboring point is stored as the leading edge point of the reinforcement axis led by the leading edge point; In response to determining that the remaining neighboring points are the leading edge points of another reinforcement axis, the reinforcement axis and the other reinforcement axis and their leading edge points are deleted. In response to determining that the remaining neighboring points are endpoints, the calculation of the axis led by the leading edge point is completed, and the calculation of other axes continues until the leading edge point is an endpoint. The third submodule is configured to repeatedly execute the first and second submodules with other endpoints as leading edges to determine several reinforcement axes. The fourth submodule is configured to calculate the length of all reinforcement axes, and take the longest reinforcement axis as the main reinforcement axis, wherein the main reinforcement axis has a first endpoint and a second endpoint; The fifth submodule is configured to calculate the shortest distances from the first and second endpoints of the augmentation's main axis to the outer contour of the augmentation in the augmentation image, and to calculate the augmentation length according to the following formula: The length of the reinforcement = the length of the main axis of the reinforcement + the shortest distance from the first endpoint of the main axis of the reinforcement to the outer contour of the reinforcement + the shortest distance from the second endpoint of the main axis of the reinforcement to the outer contour of the reinforcement.

6. An electronic device, comprising: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-4.

Images