Multi-blade knife split-blade measurement method, device and equipment based on machine vision and medium

Abstract

The application provides a multi-blade tool split-blade measurement method, device, equipment and medium based on machine vision, which comprises the following steps: collecting multiple split-blade images of a measured tool with a known number of split blades in a rotating state; dividing the multiple split-blade images into a first number of split-blade image sets, wherein the first number is the same as the known number of split blades; synthesizing the images in each split-blade image set to obtain a first number of split-blade synthesis images; determining split-blade features according to the split-blade synthesis images; and determining split-blade structure parameters according to the split-blade features. The application can realize measurement in a high-speed rotating state of a tool, thereby improving measurement efficiency and accuracy.

Description

Technical Field

[0001] This invention relates to the fields of CNC machine tool processing and manufacturing technology and machine vision measurement technology, and particularly to a method, device, equipment and medium for measuring the blade division of a multi-bladed tool based on machine vision. Background Technology

[0002] Commonly used cutting tools for CNC machine tools include flat-end cutters, ball-end cutters, and bullnose cutters, and a large proportion of the tools used in the cutting process are multi-flute tools. Existing measurement methods for multi-flute tools are basically similar to those for ordinary tools, only measuring the overall geometric parameters of the tool such as length, radius, and fillet radius, without considering the geometric parameters of each cutting edge or the differences between them. Measuring each cutting edge of a multi-flute tool helps to better understand its shape, allowing for the evaluation of the uniformity and consistency of each edge, and also enabling the assessment and calculation of cutting runout using the radius differences between the edges.

[0003] Currently, there is no known method for measuring the blade runout of multi-edged tools. There are two main methods for measuring tool runout: contact static measurement and laser tool setter dynamic measurement. Contact measurement primarily uses a dial indicator for static runout measurement, but it cannot measure tool runout at high speeds. Laser tool setter dynamic measurement is based on the principle that the tool blocks the laser beam, triggering a signal. It can measure runout at high speeds, but its measurement mainly uses a step-by-step search method, which is relatively inefficient. Furthermore, due to its inherent limitations, the measurement results for small tools may not be very accurate. Summary of the Invention

[0004] To address the problems existing in the prior art, the present invention provides a method, apparatus, equipment, and medium for measuring the blade segmentation of a multi-blade knife based on machine vision.

[0005] This invention provides a machine vision-based method for measuring the blade segmentation of a multi-bladed knife, comprising: Collect multiple images of the cutting edges of the test tool with a known number of cutting edges in a rotating state; Multiple cutting edge images are divided to obtain a first number of cutting edge image sets, the first number being the same as the known number of cutting edges; The cutting edge images in each cutting edge image set are synthesized to obtain the first number of synthesized cutting edge images; The cutting edge features are determined based on the composite images of each cutting edge, and the cutting edge structural parameters are determined based on the cutting edge features.

[0006] According to the present invention, a machine vision-based method for measuring the cutting edge of a multi-blade knife includes dividing multiple cutting edge images into a first set of cutting edge images, comprising: In the first coordinate system, the contour line of each cutting edge image is identified, and the coordinates of a contour point are obtained from the contour line of each cutting edge image; In the second coordinate system, the coordinates of a contour point obtained on the contour line of each cutting edge image are mapped to the second coordinate system; wherein, the horizontal axis of the second coordinate system is the acquisition number of the cutting edge image corresponding to the contour point coordinates, and the vertical axis is the coordinate value of the contour point coordinates in the X direction. Based on the coordinate points in the second coordinate system, determine the starting image number of the cutting edge image group from the acquisition number of the cutting edge image; Based on the starting image number, the total number of cutting edge images, and the known number of cutting edges, the multiple cutting edge images are divided into a first set of cutting edge images.

[0007] According to the present invention, a machine vision-based method for measuring the cutting edge of a multi-blade knife includes identifying the contour line of each cutting edge image in a first coordinate system and obtaining the coordinates of a contour point from the contour line of each cutting edge image, comprising: Determine the target region in the cutting edge image and obtain the contour line within the target region; Determine the reference coordinates of the reference point in the target area in the first coordinate system; In the first coordinate system, a horizontal line is drawn using the coordinate values ​​of the reference coordinates in the Y direction, and the coordinates of the point where the horizontal line intersects with the contour line in the target area are used as the coordinates of the obtained contour point.

[0008] According to the present invention, a machine vision-based method for measuring the cutting edge of a multi-blade cutting tool further includes: determining a starting image numbering strategy based on the structural type of the tool under test and the target area in the cutting edge image; correspondingly, determining the starting image number of the cutting edge image grouping from the acquisition number of the cutting edge images based on each coordinate point in the second coordinate system, including: Based on the initial image numbering strategy, determine the minimum value selection strategy or the maximum value selection strategy; According to the order of the acquisition numbers of the cutting edge images, the corresponding starting coordinate points are determined based on the minimum value selection strategy or the maximum value selection strategy, and the acquisition number corresponding to the starting coordinate point is used as the starting image number of the cutting edge image group.

[0009] According to the present invention, a machine vision-based method for measuring the blade division of a multi-blade knife includes dividing multiple blade images into a first set of blade images based on an initial image number, the total number of blade images, and the known number of blades. The number of cutting edge images corresponding to each cutting edge is determined based on the total number of cutting edge images and the known number of cutting edges. According to the acquisition number of the cutting edge images, and based on the starting image number and the number of cutting edge images corresponding to each cutting edge, the multiple cutting edge images are divided into the first number of cutting edge image sets.

[0010] According to the present invention, a multi-blade knife edge measurement method based on machine vision is provided. According to the acquisition order of multiple cutting edge images, cutting edge images are selected from multiple cutting edge images according to the interval selection rule. Correspondingly, in the first coordinate system, the contour line of each selected cutting edge image is identified, and the contour point coordinates are obtained from the contour line of each cutting edge image.

[0011] According to the present invention, a machine vision-based method for measuring the cutting edge of a multi-blade knife includes determining the cutting edge structural parameters based on the cutting edge features, comprising: The cutting radius of each cutting edge is determined based on the cutting edge characteristics. Extract the maximum and minimum values ​​from the cutting radius of each cutting edge; The radial runout value of the cutting edge is determined based on the maximum value and the minimum value.

[0012] The present invention also provides a multi-blade knife edge measurement device based on machine vision, comprising: The acquisition module is used to acquire multiple images of the cutting edges of a test tool with a known number of cutting edges in a rotating state; The segmentation module is used to segment multiple cutting edge images to obtain a first number of cutting edge image sets, the first number being the same as the known number of cutting edges; The compositing module is used to synthesize the cutting edge images in each cutting edge image set to obtain a first number of composite cutting edge images; The processing module is used to determine the cutting edge features based on the composite images of each cutting edge, and to determine the cutting edge structural parameters based on the cutting edge features.

[0013] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement any of the machine vision-based multi-blade knife edge measurement methods described above.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the machine vision-based multi-blade knife edge measurement methods described above.

[0015] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements any of the machine vision-based multi-blade knife edge measurement methods described above.

[0016] This invention provides a machine vision-based method, apparatus, device, and medium for measuring the number of cutting edges of a multi-bladed tool. It acquires multiple images of the cutting edges of a tool with a known number of cutting edges in a rotating state, divides these images into multiple image sets, and synthesizes the images from each image set to obtain multiple composite images of the cutting edges. Then, it determines the cutting edge features based on these composite images and the cutting edge structural parameters based on these features. This allows for measurement to be completed while the tool is rotating at high speed, improving measurement efficiency and accuracy. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the multi-blade blade segmentation measurement method based on machine vision provided by the present invention.

[0019] Figure 2 This is a structural diagram of the cutting edge image acquisition device provided by the present invention.

[0020] Figure 3 This is a trend diagram of the X-direction coordinate change of the contour point provided by the present invention.

[0021] Figure 4 This is a schematic diagram illustrating the relationship between the reference coordinates and the contour point coordinates provided by the present invention.

[0022] Figure 5 This is a flowchart illustrating the process of determining the starting image number provided by the present invention.

[0023] Figure 6 This is a schematic diagram of the image synthesis of the test tool provided by the present invention.

[0024] Figure 7 This is a flowchart of the cutting edge radial runout measurement provided by the present invention.

[0025] Figure 8 This is a schematic diagram of the multi-blade blade segmentation measurement device based on machine vision provided by the present invention.

[0026] Figure 9 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0028] The following is combined with Figures 1-9 This invention describes a machine vision-based method, apparatus, device, and storage medium for measuring the blade segmentation of a multi-blade knife.

[0029] Figure 1 This diagram illustrates a flowchart of a machine vision-based multi-blade knife edge measurement method provided by the present invention. (See attached diagram.) Figure 1 The method includes the following steps: Step 11: Collect multiple images of the cutting edges of the test tool with a known number of cutting edges in a rotating state.

[0030] Step 12: Divide the multiple cutting edge images to obtain a first set of cutting edge images, which is the same as the known number of cutting edges.

[0031] Step 13: Combine the cutting edge images in each cutting edge image set to obtain the first number of combined cutting edge images.

[0032] Step 14: Determine the cutting edge features based on the composite images of each cutting edge, and determine the cutting edge structural parameters based on the cutting edge features.

[0033] Regarding steps 11 to 14, it should be noted that measuring the individual blades of multi-bladed tools (such as flat-end cutters, ball-end cutters, and bullnose cutters) helps to better understand the shape of the tool itself. It can be used to evaluate the uniformity and consistency of each blade, and the difference in radius between each blade can be used to evaluate and calculate the cutting runout.

[0034] This invention aims to measure the cutting edge runout of a cutting tool at high speeds. To achieve this, multiple images of the cutting edge of the tool under test while it is rotating at high speeds are required. For the acquisition of these cutting edge images, this invention employs... Figure 2 The cutting edge image acquisition device shown is described in the following document. Figure 2 The measuring position corresponding to the cutting edge of the tool under test is moved to the measuring area of ​​the vision measuring device, the camera trigger mode is turned on, and then the CNC system sends a trigger pulse to the camera to uniformly collect cutting edge images at different angles at high speed. The camera then transmits the collected images to the CNC system. Figure 2The numerical designations in the code represent the following: 1. Industrial camera; 2. Lens; 3. Light source; 4. Protective device; 5. Tool measuring area; 6. Machine tool worktable. It should be noted that the trigger pulses sent by the CNC system to the camera are calculated based on the machine tool's control of the tool's rotation speed. This is to control the industrial camera to capture images of the high-speed rotating tool, ensuring that the actual rotation angle of the tool in two adjacent cutting edge images is a fixed value. That is, every time the tool rotates a certain angle, a cutting edge image will be captured.

[0035] In this invention, due to the precise acquisition of the cutting edge image of the tested tool, the cutting edge data collected over a period of time can be evenly divided into multiple image sets according to the number of cutting edges. Specifically, multiple cutting edge images are divided into a first number of cutting edge image sets, the first number being the same as the known number of cutting edges. At this point, each image set corresponds to one cutting edge; that is, each cutting edge image in the image set is primarily acquired for one specific cutting edge.

[0036] In this invention, the images from each cutting edge image set are synthesized to obtain a first number of synthesized cutting edge images. In other words, through image synthesis, an overall image of each cutting edge can be obtained.

[0037] Next, the cutting edge features are determined based on the composite images of each cutting edge, and the cutting edge structural parameters are determined based on the cutting edge features. These cutting edge structural parameters can be the geometric parameters of the cutting edge (such as radius) and the radial runout value of the cutting edge.

[0038] The multi-blade cutting edge measurement method based on machine vision provided by this invention acquires multiple cutting edge images of a test tool with a known number of cutting edges in a rotating state, divides the multiple cutting edge images into multiple cutting edge image sets, synthesizes the images in each cutting edge image set to obtain multiple composite cutting edge images, determines the cutting edge features based on each composite cutting edge image, and determines the cutting edge structural parameters based on the cutting edge features, so as to complete the measurement in the high-speed rotation state of the tool, thereby improving the measurement efficiency and accuracy.

[0039] In a further method described above, the process of dividing multiple cutting edge images into a first set of cutting edge images is explained in detail below: In the first coordinate system, the contour line of each cutting edge image is identified, and the coordinates of a contour point are obtained from the contour line of each cutting edge image.

[0040] In the second coordinate system, the coordinates of a contour point obtained from the contour line of each cutting edge image are mapped to the second coordinate system; where the horizontal axis of the second coordinate system is the acquisition number of the cutting edge image corresponding to the contour point coordinates, and the vertical axis is the coordinate value of the contour point in the X direction.

[0041] Based on the coordinate points in the second coordinate system, determine the starting image number of the cutting edge image group from the acquisition number of the cutting edge image.

[0042] Based on the starting image number, the total number of cutting edge images, and the known number of cutting edges, the multiple cutting edge images are divided into a first set of cutting edge images.

[0043] It should be noted that in this invention, the cutting edge image contains a cutting edge contour. Therefore, the cutting edge image can be analyzed to extract the cutting edge contour features. Specifically, filtering, thresholding, morphological operations, and speckle removal operations can be performed on the cutting edge image to eliminate interfering factors and extract the cutting edge contour features.

[0044] In this invention, numerous cutting edge images are acquired for each cutting edge. Due to the high-speed rotation of the cutting edge, it is difficult to directly identify the corresponding cutting edge image from the large number of acquired images. Therefore, this invention selects a position point on the cutting edge contour from each cutting edge image. This position point needs to be represented by coordinate values. Thus, during image analysis, a coordinate system (i.e., the first coordinate system) can be constructed, and the analyzed cutting edge images can be mapped into this coordinate system. Then, using a unified position point selection rule, the coordinates of a contour point are obtained from the contour line of each cutting edge image.

[0045] In this invention, it is necessary to divide the acquired multiple cutting edge images into a set of cutting edge images corresponding to each cutting edge. If each cutting edge image is assigned an acquisition number, it is difficult to determine from which image to start and how many images to collect as a set. Therefore, this invention requires fitting the acquired contour point coordinates into a curve and observing the curve's pattern to represent each cutting edge. For this purpose, a coordinate system (i.e., a second coordinate system) needs to be constructed. In this coordinate system, the horizontal axis represents the acquisition number of the cutting edge image corresponding to the contour point coordinates, and the vertical axis represents the X-axis coordinate value of the contour point. Then, in the second coordinate system, the coordinates of a contour point obtained from the contour line of each cutting edge image are mapped to the second coordinate system. See also... Figure 3 The graph shows the trend of the X-axis coordinates of the contour points. That is, by plotting the image acquisition number on the horizontal axis and the X-axis coordinates of the contour points of the cut edge extracted from the image on the vertical axis, it can be found that the point series has a distribution of "high in the middle and low at both ends... high in the middle and low at both ends". A distribution of "high in the middle and low at both ends" reflects the shape of a cut edge.

[0046] Next, based on the coordinate points in the second coordinate system, the starting image number for grouping the cutting edge images is determined from the acquisition numbers of the cutting edge images. In other words, based on the number of images in the image set, starting from the starting image number, the number of consecutively counted "image counts" can be grouped into one image set. Specifically, based on the starting image number, the total number of cutting edge images, and the known number of cutting edges, multiple cutting edge images are divided into a first number of cutting edge image sets. Specifically: based on the total number of cutting edge images and the known number of cutting edges, the number of cutting edge images corresponding to each cutting edge is determined; according to the order of the acquisition numbers of the cutting edge images, and based on the starting image number and the number of cutting edge images corresponding to each cutting edge, multiple cutting edge images are divided into a first number of cutting edge image sets.

[0047] by Figure 3 Taking the trend of contour point coordinate change of the four-edged bullnose knife as an example, the starting image number of the cutting edge group is determined to be 21. First, based on the total number of cutting edge images N = 200 and the number of cutting edges of the knife itself C = 4, the number of images corresponding to each cutting edge is calculated to be A = N / C = 50.

[0048] Then, starting from the initial image number of the cutting edge group, every 50 images are grouped into an image set for each cutting edge. This results in an image set belonging to each cutting edge. Images belonging to cutting edge 1 are numbered 21-70, images belonging to cutting edge 2 are numbered 71-120, images belonging to cutting edge 3 are numbered 121-170, and images belonging to cutting edge 4 are numbered 171-200 and 1-20.

[0049] A further method of the present invention maps the contour points obtained from the cutting edge image to a coordinate system. Based on each coordinate point in the coordinate system, the starting image number of the cutting edge image group is determined from the acquisition number of the cutting edge image. Based on the starting image number, the total number of cutting edge images and the known number of cutting edges, multiple cutting edge images are divided into a cutting edge image set. This method can speed up and accurately divide multiple images, preparing for the subsequent image synthesis.

[0050] A further method described above mainly explains the process of identifying the contour line of each cutting edge image in the first coordinate system and obtaining the coordinates of a contour point from the contour line of each cutting edge image, as follows: The target region in the cutting edge image is determined, and the contour line within the target region is obtained. It should be noted that when the machine tool is rotating, if the image of the tool is taken from the side, capturing the entire viewing angle will result in two cutting edges appearing in the image, one on the left and one on the right. This is not conducive to subsequent analysis of the image and the cutting edge contour. Therefore, it is necessary to determine a target region where only a single cutting edge contour can appear, which is beneficial for subsequent analysis of the image and the cutting edge contour. For example, the left side of the entire image can be used as the target region.

[0051] Next, determine the reference coordinates of the reference point within the target area in the first coordinate system. Then, in the first coordinate system, draw a horizontal line using the Y-coordinates of the reference coordinates. The coordinates of the point where this horizontal line intersects the contour line in the target area are used as the obtained contour point coordinates. See [link to documentation]. Figure 4 A schematic diagram showing the relationship between reference coordinates and contour point coordinates is presented. Figure 4 Point A is the reference coordinate point, point B is the contour point on the current cutting edge image, and point C is the contour point on the previous cutting edge image.

[0052] In a further step of the above method, a starting image numbering strategy is determined based on the structure type of the tool being tested and the target area in the cutting edge image; correspondingly, based on each coordinate point in the second coordinate system, the starting image number for the cutting edge image group is determined from the acquisition number of the cutting edge images, including: Based on the initial image numbering strategy, determine the minimum value selection strategy or the maximum value selection strategy; According to the order of the acquisition numbers of the cutting edge images, the corresponding starting coordinate points are determined based on the minimum value selection strategy or the maximum value selection strategy. The acquisition number corresponding to the starting coordinate point is used as the starting image number of the cutting edge image group.

[0053] It should be noted that different tool structures and different target regions in the selected images will lead to different initial image numbering strategies. In this invention, we continue to use... Figure 3 As shown, the starting number is determined primarily by the magnitude of the vertical values ​​of the coordinate points in the coordinate system, using either the minimum or maximum value. Therefore, given the known tool structure type and target area, a minimum or maximum value selection strategy can be determined. Then, following the order of the acquisition numbers of the cutting edge images, the corresponding starting coordinate points are determined based on the minimum or maximum value selection strategy. The acquisition number corresponding to the starting coordinate point is used as the starting image number for grouping the cutting edge images.

[0054] It should also be noted that, to reduce the complexity of the image analysis process, cutting edge images can be selected from multiple cutting edge images according to the acquisition order and an interval selection rule. Accordingly, in the first coordinate system, the contour line of each selected cutting edge image is identified, and the coordinates of a contour point are obtained from the contour line of each cutting edge image. For example, if there are 400 images acquired, one type of image can be acquired every 9 images, such as acquiring the 1st, 11th, 21st, and so on.

[0055] See Figure 5 A flowchart illustrating the process of determining the starting image number is shown. Figure 5 It mainly includes the following five steps: (1) The total number of images acquired is N = 200, the current image processing number is set to i = 1, and the number of image processing intervals is set to S = 10; (2) Perform image processing on the i-th image; (3) Extract the coordinates of the contour points in the processed image and add the coordinates and the corresponding image number to the storage list; (4) Set i = i+S. If i<= N, go to (2), otherwise go to (5); (5) If the currently acquired image is the left side image of the cutting edge (i.e. the target area), then the image number corresponding to the element with the largest X-direction image coordinate in the storage list is taken as the starting image number (i.e., the maximum value selection strategy); if the currently acquired image is the right side image of the cutting edge, then the image number corresponding to the element with the smallest X-direction image coordinate in the storage list is taken as the starting image number.

[0056] See Figure 6 A schematic diagram of image synthesis for the tested cutting tool is shown. In this invention, based on the principle of minimum grayscale, the cutting edge images belonging to each cutting edge image set can be synthesized into a single composite cutting edge image, preserving the maximum outer contour features of each cutting edge of the tool to the greatest extent.

[0057] Then, the cutting edge features are determined based on the composite image of each cutting edge, the cutting edge radius of each cutting edge is determined based on the cutting edge features, the maximum and minimum values ​​are extracted from the cutting edge radius of each cutting edge, and the radial runout value of the cutting edge is determined based on the maximum and minimum values.

[0058] See Figure 7 A flowchart for measuring the radial runout of the cutting edge is shown. Figure 7 Includes the following steps: (1) Set the current cutting edge number i=1, and the current number of cutting edges C = 4; (2) Perform image processing on the composite image corresponding to the i-th cutting edge; (3) Perform feature extraction on the processed image and calculate the geometric parameters (such as the cutting radius) of the i-th cutting edge. (4) Set i = i+1. If i <= C, go to (2), otherwise go to (5); (5) Based on all the calculated cutting radii, extract the maximum and minimum values. The difference between the maximum and minimum values ​​is the radial runout.

[0059] The following describes the machine vision-based multi-blade blade segmentation measurement device provided by the present invention. The machine vision-based multi-blade blade segmentation measurement device described below and the machine vision-based multi-blade blade segmentation measurement method described above can be referred to in correspondence with each other.

[0060] Figure 8 This diagram illustrates the structure of a machine vision-based multi-blade blade segmentation measurement device provided by the present invention. (See attached diagram.) Figure 8 The device includes an acquisition module 81, a division module 82, a synthesis module 83, and a processing module 84, wherein: The acquisition module is used to acquire multiple images of the cutting edges of a test tool with a known number of cutting edges in a rotating state; The segmentation module is used to segment multiple cutting edge images to obtain a first number of cutting edge image sets, the first number being the same as the known number of cutting edges; The compositing module is used to synthesize the cutting edge images in each cutting edge image set to obtain a first number of composite cutting edge images; The processing module is used to determine the cutting edge features based on the composite images of each cutting edge, and to determine the cutting edge structural parameters based on the cutting edge features.

[0061] Since the apparatus of this embodiment is based on the same principle as the method of the above embodiment, more detailed explanations will not be repeated here.

[0062] It should be noted that, in the embodiments of the present invention, the relevant functional modules can be implemented by a hardware processor.

[0063] The multi-blade cutting edge measurement device based on machine vision provided by this invention acquires multiple cutting edge images of a test tool with a known number of cutting edges in a rotating state, divides the multiple cutting edge images into multiple cutting edge image sets, synthesizes the images in each cutting edge image set to obtain multiple composite cutting edge images, determines the cutting edge features based on each composite cutting edge image, and determines the cutting edge structural parameters based on the cutting edge features, thereby realizing measurement while the tool is rotating at high speed, improving measurement efficiency and accuracy.

[0064] Figure 9 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 9As shown, the electronic device may include a processor 91, a communication interface 92, a memory 93, and a communication bus 94. The processor 91, communication interface 92, and memory 93 communicate with each other via the communication bus 94. The processor 91 can call logical instructions in the memory 93 to execute a machine vision-based multi-blade cutting edge measurement method. This method includes: acquiring multiple cutting edge images of a test tool with a known number of cutting edges in a rotating state; dividing the multiple cutting edge images to obtain a first set of cutting edge images, the first set being the same as the known number of cutting edges; synthesizing the cutting edge images in each set to obtain a first set of synthesized cutting edge images; determining cutting edge features based on each synthesized cutting edge image; and determining cutting edge structural parameters based on the cutting edge features.

[0065] Furthermore, the logical instructions in the aforementioned memory 93 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, 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 (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0066] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the machine vision-based multi-blade cutting edge measurement method provided by the above methods. The method includes: acquiring multiple cutting edge images of a test tool with a known number of cutting edges in a rotating state; dividing the multiple cutting edge images to obtain a first number of cutting edge image sets, the first number being the same as the known number of cutting edges; synthesizing the cutting edge images in each cutting edge image set to obtain a first number of synthesized cutting edge images; determining cutting edge features based on each synthesized cutting edge image; and determining cutting edge structural parameters based on the cutting edge features.

[0067] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the machine vision-based multi-blade cutting edge measurement method provided by the above methods. The method includes: acquiring multiple cutting edge images of a test tool with a known number of cutting edges in a rotating state; dividing the multiple cutting edge images to obtain a first number of cutting edge image sets, the first number being the same as the known number of cutting edges; synthesizing the cutting edge images in each cutting edge image set to obtain a first number of synthesized cutting edge images; determining cutting edge features based on each synthesized cutting edge image; and determining cutting edge structural parameters based on the cutting edge features.

[0068] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0069] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0070] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for measuring the blade segmentation of a multi-bladed knife based on machine vision, characterized in that, include: Collect multiple images of the cutting edges of the test tool with a known number of cutting edges in a rotating state; Multiple cutting edge images are divided to obtain a first number of cutting edge image sets, the first number being the same as the known number of cutting edges; The cutting edge images in each cutting edge image set are synthesized to obtain the first number of synthesized cutting edge images; The cutting edge features are determined based on the composite images of each cutting edge, and the cutting edge structural parameters are determined based on the cutting edge features; The step of dividing multiple cutting edge images into a first number of cutting edge image sets includes: In the first coordinate system, the contour line of each cutting edge image is identified, and the coordinates of a contour point are obtained from the contour line of each cutting edge image; In the second coordinate system, the coordinates of a contour point obtained on the contour line of each cutting edge image are mapped to the second coordinate system; wherein, the horizontal axis of the second coordinate system is the acquisition number of the cutting edge image corresponding to the contour point coordinates, and the vertical axis is the coordinate value of the contour point coordinates in the X direction. Based on the coordinate points in the second coordinate system, determine the starting image number of the cutting edge image group from the acquisition number of the cutting edge image; Based on the starting image number, the total number of cutting edge images, and the known number of cutting edges, the multiple cutting edge images are divided into a first set of cutting edge images; In the first coordinate system, identifying the contour line of each cutting edge image and obtaining the coordinates of a contour point from the contour line of each cutting edge image includes: Determine the target region in the cutting edge image and obtain the contour line within the target region; Determine the reference coordinates of the reference point in the target area in the first coordinate system; In the first coordinate system, a horizontal line is drawn using the coordinate values ​​of the reference coordinates in the Y direction, and the coordinates of the point where the horizontal line intersects with the contour line in the target area are used as the coordinates of the obtained contour point. The method further includes: determining a starting image numbering strategy based on the structure type of the tested tool and the target area in the cutting edge image; correspondingly, determining the starting image number of the cutting edge image grouping from the acquisition number of the cutting edge images based on each coordinate point in the second coordinate system, including: Based on the initial image numbering strategy, determine the minimum value selection strategy or the maximum value selection strategy; According to the order of the acquisition numbers of the cutting edge images, the corresponding starting coordinate points are determined based on the minimum value selection strategy or the maximum value selection strategy, and the acquisition number corresponding to the starting coordinate point is used as the starting image number of the cutting edge image group.

2. The multi-blade knife edge measurement method based on machine vision according to claim 1, characterized in that, The step of dividing multiple cutting edge images into a first set of cutting edge images based on the starting image number, the total number of cutting edge images, and the known number of cutting edges includes: The number of cutting edge images corresponding to each cutting edge is determined based on the total number of cutting edge images and the known number of cutting edges. According to the acquisition number of the cutting edge images, and based on the starting image number and the number of cutting edge images corresponding to each cutting edge, the multiple cutting edge images are divided into the first number of cutting edge image sets.

3. The multi-blade knife edge measurement method based on machine vision according to claim 1, characterized in that, Based on the acquisition order of multiple cutting edge images, a cutting edge image is selected from the multiple cutting edge images according to the interval selection rule. Correspondingly, in the first coordinate system, the contour line of each selected cutting edge image is identified, and the coordinates of a contour point are obtained from the contour line of each cutting edge image.

4. The multi-blade knife edge measurement method based on machine vision according to claim 1, characterized in that, Determining the cutting edge structural parameters based on the cutting edge characteristics includes: The cutting radius of each cutting edge is determined based on the cutting edge characteristics. Extract the maximum and minimum values ​​from the cutting radius of each cutting edge; The radial runout value of the cutting edge is determined based on the maximum value and the minimum value.

5. A machine vision-based multi-blade blade segmentation measurement device based on the machine vision-based multi-blade blade segmentation measurement method according to any one of claims 1-4, characterized in that, include: The acquisition module is used to acquire multiple images of the cutting edges of a test tool with a known number of cutting edges in a rotating state; The segmentation module is used to segment multiple cutting edge images to obtain a first number of cutting edge image sets, the first number being the same as the known number of cutting edges; The compositing module is used to synthesize the cutting edge images in each cutting edge image set to obtain a first number of composite cutting edge images; The processing module is used to determine the cutting edge features based on the composite images of each cutting edge, and to determine the cutting edge structural parameters based on the cutting edge features.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements any one of the machine vision-based multi-blade knife blade measurement methods as described in claims 1-4.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements any one of the machine vision-based multi-blade knife blade measurement methods as described in claims 1-4.

Images