Method and device for automatic planning of a cutting trajectory for false eyelashes

Abstract

The application discloses a kind of false eyelash cutting trajectory automatic planning method and device, by contour detection to the whole false eyelash image of horizontal arrangement, find out the contour where cutting point is, then according to the bottom point of contour, fit out the curve equation of cutting line in image, and select left, right end point on contour and substitute into curve equation, obtain a group of cutting points;Respectively obtain the right cutting point of left end contour of a section of false eyelash, the left cutting point of right end contour, obtain the width of each false eyelash and the distance between false eyelash, from the right cutting point of left end contour to right, from the left cutting point of right end contour to left, with the width of each false eyelash and the distance between false eyelash as radius alternately draw circle, until meet, based on the intersection of circle and curve equation, calculate the adjacent cutting point of a cutting point, obtain a group of reference cutting points, correct cutting point by reference cutting point, obtain final cutting point;Finally, the cutting trajectory of each false eyelash is planned.

Description

Technical Field

[0001] This invention belongs to the field of image processing and intelligent recognition and detection technology, and specifically relates to a method and apparatus for automatically planning the cutting trajectory of false eyelashes. Background Technology

[0002] The beauty market, including false eyelashes, is expanding rapidly, with strong demand for false eyelash products. Among them, low-puff products like the "lazy person's three-step" method are particularly popular due to their attractive appearance and ease of use. The existing cutting process for false eyelash products includes... Figures 1a to 1d As shown, it consists of two steps. The first step is as follows: Figure 1a Cut along the black line, keeping the upper half as shown. Figure 1b As shown; Step 2: As Figure 1c Cut longitudinally in segments, repeating the cuts at the positions indicated by the arrows, removing the black lines at both ends of the tuft of hair. Figure 1d As shown. However, due to the limitations of the aforementioned cluster-cutting process, the yield of clusters is low. As a crucial part of the false eyelash manufacturing process, the quality and speed of cutting directly determine the user experience and output of the product. Traditional cutting methods rely primarily on manual labor, which is slow, has unstable quality, and low production capacity. The difficulty with existing machine cutting lies in its poor cutting precision, resulting in a low yield rate. Summary of the Invention

[0003] To overcome the shortcomings of existing technologies and achieve the goal of obtaining the cutting points of false eyelashes and automatically planning the cutting point trajectory, this invention adopts the following technical solution:

[0004] A method for cutting false eyelashes includes the following steps:

[0005] Step S1: Obtain the image of the entire horizontally arranged false eyelashes;

[0006] Step S2: Perform contour detection on the entire false eyelash image to find the contour where the cutting point is located;

[0007] Step S3: Based on the bottom point of the contour, fit the curve equation of the cutting line in the image, and combine it with the layout structure of the entire false eyelash, select the left and right endpoints on the contour and substitute them into the curve equation to obtain a set of cutting points.

[0008] Step S4: Obtain the right cutting point of the left end contour and the left cutting point of the right end contour of each false eyelash segment. Calculate the width of each false eyelash and the distance between them. Starting from the right cutting point of the left end contour and moving rightwards, and from the left cutting point of the right end contour and moving leftwards, draw circles alternately with the width of each false eyelash and the distance between them as the radius, until they meet. Based on the intersection of the circle and the curve equation, calculate the adjacent cutting points of a cutting point to obtain a set of reference cutting points. Correct the cutting points using these reference points to obtain the final cutting points. During the cutting point detection process, it was found that the inconsistent specifications of the false eyelashes resulted in different contour sizes for the cutting points, which may lead to false detections and missed detections. Therefore, an iterative method was used to calculate a set of reference points to optimize the cutting points that were missed or falsely detected.

[0009] Furthermore, in step S1, placing the false eyelashes on a white cardboard facilitates image processing, but the background board is easily damaged during cutting. Therefore, this invention arranges each false eyelash and fixes it into a whole false eyelash with white tape. One side of the tape is placed in a metal tooling device, and the other side, the part to be cut, is placed on a light-transmitting base plate. To avoid the influence of the lighting environment on recognition, this invention uses a rectangular light source set below the light-transmitting base plate for supplementary lighting. The camera is fixed above the glass base plate to take pictures and obtain the image of the whole false eyelash from above the base plate.

[0010] Further, in step S1, the acquired false eyelash image is preprocessed, the area to be cut is cropped as the source image, the source image is subjected to grayscale, inverse binarization and erosion operations in sequence, and the linear coordinates of the edge of the base plate are obtained based on the positional relationship between the tooling equipment and the base plate. The false eyelash image is further cropped using the linear coordinates to obtain the preprocessed false eyelash image.

[0011] Furthermore, step S2 also includes the following steps:

[0012] Step S2.1: Filter the detected contours by their area; set an area threshold, and discard all contours smaller than the area threshold.

[0013] Step S2.2: Filter contours based on their aspect ratio; set an aspect ratio threshold and calculate the minimum outer rectangle for each contour, with a size of [value missing]. The longer side is h, and the shorter side is w. If h / w is greater than the aspect ratio threshold, the contour is the desired contour; if it is less than the aspect ratio threshold, the contour is discarded.

[0014] Step S2.3: Filter by the shape of the smallest circumscribed triangle of the contour; fit the smallest circumscribed triangle to each contour to obtain the position of the three vertices of the smallest circumscribed triangle, determine the relative positional relationship between the three vertices, calculate the centroid of the triangle based on the position of the three vertices, and determine the vertical positional relationship between the three vertices and the centroid in the image. If one vertex is above the centroid, the contour is the desired contour; if two vertices are above the centroid, the contour is discarded.

[0015] Further, in step S3, the bottom point, left endpoint, and right endpoint of the contour are obtained, and an nth-degree polynomial model is constructed based on the bottom point:

[0016]

[0017] in, The coefficients of the polynomial to be solved are represented by x, the x-coordinate of the cutting point in the image coordinate system, and n, the order of the polynomial, which is determined by observing the extreme points of the glued line.

[0018] We construct a system of linear equations to calculate these coefficients, in matrix form as follows:

[0019]

[0020] Where X and Y are parameter matrices, with sizes respectively and The specific positions of the elements in the X and Y matrices are as follows: and A represents the coefficient matrix to be solved;

[0021]

[0022]

[0023]

[0024] Where i and j are the row and column indices of the matrix, and N is the number of input points. This represents the x-coordinate of the k-th cutting point in the pixel coordinate system. , They represent i, i+j powers, This represents the y-coordinate of the k-th cutting point in the pixel coordinate system, and T represents the transpose of the matrix;

[0025] Substitute the x-coordinates of the left and right endpoints of the contour into the polynomial model to obtain the cutting points.

[0026] Furthermore, in step S4, the curve equation is as follows:

[0027]

[0028] The equation of a circle is as follows:

[0029]

[0030] in, and Let the coordinates of the center of the circle be , then the function representing the intersection point of the circle and the curve equation is as follows:

[0031]

[0032] Using Newton's iteration method, the iterative formula for the intersection point is:

[0033]

[0034] Where iter is the number of iterations for calculation. yes The derivative;

[0035] The adjacent cutting points of a cutting point are calculated using the above method, resulting in a set of reference cutting points.

[0036] Further, in step S4, comparing the cutting point and the reference cutting point includes the following steps:

[0037] Step S4.1: Sort the cutting point set and the reference cutting point set in ascending order according to the x-coordinate;

[0038] Step S4.2: Calculate the absolute value of the x-coordinate distance between the points in the cutting point set and the points in the reference cutting point set. If the absolute value of the distance is less than the specified distance threshold, replace the x-coordinate of the corresponding point in the reference cutting point set with the x-coordinate of the point in the cutting point set.

[0039] A method for automatically planning the cutting trajectory of false eyelashes, based on the aforementioned false eyelash cutting method, further includes step S5: planning the cutting trajectory of each false eyelash according to the final cutting point obtained in step S4 and the requirements for cutting quality, so as to continuously cut along the trajectory by an automated cutting device.

[0040] A false eyelash cutting device includes an image acquisition module, a contour acquisition module, a cutting point acquisition module, and a cutting point correction module;

[0041] The image acquisition module acquires an image of the entire horizontally arranged false eyelashes;

[0042] The contour acquisition module performs contour detection on the entire false eyelash image to find the contour where the cutting point is located.

[0043] The cutting point acquisition module fits the curve equation of the cutting line in the image based on the bottom point of the contour, and combines the layout structure of the entire false eyelash to select the left and right endpoints on the contour and substitute them into the curve equation to obtain a set of cutting points.

[0044] The cutting point correction module obtains the right cutting point of the left end contour and the left cutting point of the right end contour of a segment of false eyelashes, respectively, and obtains the width of each false eyelash and the distance between the false eyelashes. Starting from the right cutting point of the left end contour to the right and from the left cutting point of the right end contour to the left, circles are drawn alternately with the width of each false eyelash and the distance between the false eyelashes as the radius until they meet. Based on the intersection of the circle and the curve equation, the adjacent cutting points of a cutting point are calculated to obtain a set of reference cutting points. The cutting points are corrected by the reference cutting points to obtain the final cutting point.

[0045] An automatic planning device for the cutting trajectory of false eyelashes, based on the aforementioned false eyelash cutting device, further includes a trajectory planning module, which plans the cutting trajectory of each false eyelash according to the final cutting point and the requirements for cutting quality, so that the automatic cutting equipment can continuously cut along the trajectory.

[0046] The advantages and beneficial effects of this invention are as follows:

[0047] This invention provides a method and apparatus for intelligently planning the cutting trajectory of false eyelashes. It can quickly detect cutting points and plan trajectories for the eyelash cutting machine to automate the cutting process, significantly increasing output. Furthermore, this invention can accurately identify false eyelashes of different specifications processed by different manufacturers, solving the problem of needing to adjust tooling according to eyelash specifications in previous eyelash cutting machines, thus improving cutting accuracy and the stability of cutting quality. This invention uses an iterative method to calculate the intersection points of curves and circles one by one, calculating a set of cutting point positions. In case of missed or false detections, it automatically calibrates the cutting points, improving the cutting rate. Attached Figure Description

[0048] Figure 1a This is a schematic diagram of the horizontal cutting of eyelashes, the first step in the existing false eyelash cutting process.

[0049] Figure 1b This is an image showing the effect after the first step of the eyelash cutting process in the existing technology.

[0050] Figure 1c This is a schematic diagram of the longitudinal segmentation cutting in the second step of the existing false eyelash cutting process.

[0051] Figure 1d This is an image showing the effect after the second step of the eyelash cutting process in the existing technology.

[0052] Figure 2This is a flowchart of the automatic trajectory planning method in an embodiment of the present invention.

[0053] Figure 3 This is the original image of the false eyelash sample in the embodiment of the present invention.

[0054] Figure 4a This is a diagram showing the effect of a false eyelash sample above a light source in an embodiment of the present invention.

[0055] Figure 4b This is a diagram showing the effect of trimmed false eyelashes in an embodiment of the present invention.

[0056] Figure 5 This is a diagram showing the effect of image preprocessing on the source image in an embodiment of the present invention.

[0057] Figure 6 This is a diagram showing the effect of contour filtering in an embodiment of the present invention.

[0058] Figure 7 This is a diagram showing the effect after iterative optimization in an embodiment of the present invention.

[0059] Figure 8a This is a diagram showing the entire cutting trajectory in an embodiment of the present invention.

[0060] Figure 8b This is a magnified cutting trajectory planning diagram in an embodiment of the present invention.

[0061] Figure 9 This is a schematic diagram of the structure of the automatic trajectory planning device in an embodiment of the present invention. Detailed Implementation

[0062] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0063] like Figure 2 As shown, a method for automatically planning the cutting trajectory of false eyelashes involves taking a picture of the false eyelashes to obtain the original image, performing image processing operations on the original image, obtaining the cutting point positions based on cutting point features, iteratively calculating a set of cutting points for position optimization, and finally planning the cutting trajectory based on the cutting point positions. The method includes the following steps:

[0064] Step S1: Image acquisition, obtain the image of the entire false eyelash: as shown Figure 3As shown, placing the false eyelashes on a white cardboard facilitates image processing, but the background board is easily damaged during cutting. Therefore, this invention places the white tape and the part below the false eyelashes on a metal fixture, suspending the part to be cut, while the upper part is placed on a transparent glass plate. To avoid the influence of lighting conditions on recognition, this invention places a rectangular light source below the glass plate for supplemental lighting, and a camera is fixed above the glass plate for taking pictures. The captured image is shown below. Figure 4a , Figure 4b As shown.

[0065] Image preprocessing, cropping the image of the area where the false eyelashes are located: Figure 4a As can be seen, the bright areas in the image are the parts to be cut, while the rest are black. Because the relative positions of the camera, the glass plate, and the fixture are fixed, the image can be cropped as follows: Figure 4b As shown, the source image src is obtained. The src image is then subjected to grayscale, inverse binarization, and erosion processes sequentially. Finally, the linear coordinates of the lower edge of the glass plate are obtained, using the following formula:

[0066] erode_img = erode(threshold(gray(src)))

[0067] Here, `gray` represents grayscale processing, `threshold` represents inverse binarization, and `erode` represents erosion. Based on this, the image contour is calculated, and the straight line along the lower edge of the glass plate is detected using Hough transform. The pixel coordinates of the two ends of the line, `lp` and `rp`, are obtained. The image is further cropped and grayscale and binarized based on the positions of `lp` and `rp`, resulting in the following: Figure 5 As shown.

[0068] Step S2: Contour Filtering: In Figure 5 Based on this, contour detection is performed on the false eyelash image to find the contour where the cutting point is located. Figure 5 As can be seen, not only are there outlines between two hairs, but there are also outlines inside each hair. To ensure that the correct outlines are selected, the rules for selecting outlines in this invention include the following steps:

[0069] Step S2.1: Pair the contour area Figure 5 The detected contours are filtered, and the area threshold is set to areaThreshold (specifically, based on the image resolution, this invention uses 400). All contours smaller than areaThreshold are discarded.

[0070] Step S2.2: Filter contours based on their aspect ratio, setting the aspect ratio threshold to `aspectRatio`, and calculate the minimum outer rectangle for each contour, with a size of [missing value]. The longer side is denoted as h, and the shorter side as w. If h / w is greater than the aspect ratio threshold, it means that the contour is the desired contour; if it is less than the aspect ratio threshold, the contour is discarded.

[0071] Step S2.3: Filter by the shape of the smallest circumscribed triangle of the contour. Fit the smallest circumscribed triangle to each contour to obtain the positions of the three vertices of the smallest circumscribed triangle, and determine the relative positional relationship between these three vertices. Calculate the centroid of the triangle based on the positions of the three vertices, and determine the vertical positional relationship between the three vertices and the centroid in the image. If one vertex is above the centroid, the contour is the desired contour; if two vertices are above the centroid, the contour is discarded.

[0072] The contours filtered according to the above three rules are used as candidate contours (candidateContours). The filtered result is as follows: Figure 6 As shown.

[0073] Step S3: Calculate the cutting point: Fit the equation of the cutting line in the image based on the bottom point of the contour, and combine it with the structural characteristics of the false eyelashes to select points on the contour and substitute them into the equation to obtain the coordinates of the cutting point.

[0074] Specifically, the contours in `candidateContours` are sorted in ascending order by pixels along both the x and y directions. The bottom point, leftmost endpoint, and rightmost endpoint of each contour are identified. Based on all the bottom points, an nth-degree polynomial model is constructed as follows:

[0075]

[0076] in, The coefficients of the polynomial to be solved are represented by x, the x-coordinate of the cutting point in the image coordinate system, and n, the order of the polynomial. Based on observation, the glue-coated line has at most two extreme points, so n is 3 in this invention.

[0077] We construct a system of linear equations to calculate these coefficients, in matrix form as follows:

[0078]

[0079] Where X and Y are parameter matrices, with sizes respectively and The specific positions of the elements in the X and Y matrices are as follows: and Let A represent the coefficient matrix to be solved, specifically as shown in the following formula A.

[0080]

[0081]

[0082]

[0083] Where i and j are the row and column indices of the matrix, and N is the number of input points. This represents the x-coordinate of the k-th cutting point in the pixel coordinate system. , They represent i, i+j powers, Let represent the y-coordinate of the k-th cutting point in the pixel coordinate system, and T represent the transpose of the matrix.

[0084] After obtaining the curve equation, substituting the x-coordinates of the left and right endpoints of each contour (left.x and right.x) into the curve equation yields the cutting points. Figure 5 The leftmost and rightmost contours are composed of image edges, so only the rightmost and leftmost endpoints are taken, respectively. Therefore, ideally, 40 cutting points should be detected for 20 hairs, and the point set is Points_1.

[0085] Step S4: Iterative Optimization: Obtain the right cutting point of the left contour and the left cutting point of the right contour of a segment of false eyelashes. Obtain the width of each false eyelash and the distance between them. Starting from the right cutting point of the left contour and moving to the right, and from the left cutting point of the right contour and moving to the left, draw circles alternately with the width of each false eyelash and the distance between them as the radius until they meet. Based on the intersection of the circle and the curve equation, calculate the adjacent cutting points of a cutting point to obtain a set of reference cutting points. Correct the cutting points using the reference cutting points to obtain the final cutting points. During the cutting point detection process, it was found that the inconsistent specifications of the false eyelashes resulted in different contour sizes at the cutting points, which may lead to false detections and missed detections. Therefore, this invention proposes to use an iterative method to calculate a set of reference points and use this set of reference points to optimize the cutting points that are missed or falsely detected.

[0086] Specifically, by Figure 5 It can be seen that the largest contour is the middle contour. In step S3, the left cutting point centerContourLeft and the right cutting point centerContourRight of the middle contour can be calculated. Furthermore, the right cutting point leftContourRight of the leftmost contour and the left cutting point rightContourLeft of the rightmost contour can also be obtained in step S3. From the eyelash image, it can be seen that the width of each eyelash and the distance between eyelashes (except for the two middle eyelashes) are approximately the same. From the image, it is easy to determine that the width of one eyelash is w, and the straight-line distance between two eyelashes is s.

[0087] Starting from centerContourLeft and leftContourRight, draw circles to the left and right with radii w and s respectively until they meet, and calculate the intersection point of the circle with the curve in step S3. Similarly, starting from centerContourRight and rightContourLeft, draw circles to the right and left with radii w and s respectively until they meet, and calculate the intersection point of the circle with the curve in step S3.

[0088] Assume the curve equation is as follows:

[0089]

[0090] The equation of a circle is as follows:

[0091]

[0092] a~d are the known parameters in step S3. and Let be the coordinates of the center of the circle, and in this example, a known tangent point, such as centerContourLeft and centerContourRight. Then, the function representing the intersection of the circle and the curve equation is as follows:

[0093]

[0094] Using Newton's iteration method, the iterative formula for the intersection point can be obtained as follows:

[0095]

[0096] Where iter is the number of iterations for calculation. yes The derivative of .

[0097] The above method can be used to calculate the adjacent cutting points of a cutting point, thus obtaining an iterative calculation version of 40 cutting points, with the point set being Points_2.

[0098] Note that due to false positives and false negatives, the number of cutting points detected visually in step S3 may not be exactly 40. Therefore, the point set Points_1 is compared with Points_2. The specific steps are as follows:

[0099] Step S4.1: Sort Points_1 and Points_2 in ascending order based on their x-coordinates.

[0100] Step S4.2: Calculate the absolute distance d between the x-coordinates of the points in Points_1 and the points in Points_2. If the value of d is less than the specified threshold t, replace the x-coordinate of the point in Points_2 with the x-coordinate of the point in Points_1.

[0101] The resulting cut point set Points_2 has the following characteristics: (1) It must contain 40 points; (2) All 40 points are calculated in step S3 and lie on the cut line; (3) If visual detection is possible, the visual detection result is used; otherwise, the result calculated iteratively is used. Figure 7 As shown, the black dots are the points calculated in step S4, and the white dots are the final results after replacement according to step S3.

[0102] Step S5: Trajectory Planning: Based on the cutting points calculated in Step S4 and the requirements for cutting quality, the trajectory for cutting the hair is planned. (Combined with...) Figures 1a to 1d To cut eyelashes that meet the required specifications, each eyelash needs to be cut two to three times. Because automated cutting uses equipment such as lasers, a continuous cutting trajectory is required. Therefore, this invention designs a method as follows: Figure 8a and Figure 8b The cutting path.

[0103] like Figure 9 As shown, a device for automatically planning the cutting trajectory of false eyelashes includes an image acquisition module, a contour acquisition module, a cutting point acquisition module, a cutting point correction module, and a trajectory planning module.

[0104] The image acquisition module acquires the image of the entire horizontally arranged false eyelashes;

[0105] The contour acquisition module performs contour detection on the entire false eyelash image to find the contour where the cutting point is located.

[0106] The cutting point acquisition module fits the curve equation of the cutting line in the image based on the bottom point of the contour, and combines the layout structure of the entire false eyelash to select the left and right endpoints on the contour and substitute them into the curve equation to obtain a set of cutting points.

[0107] The cutting point correction module obtains the right cutting point of the left end contour and the left cutting point of the right end contour of a segment of false eyelashes. It also obtains the width of each false eyelash and the distance between the false eyelashes. Starting from the right cutting point of the left end contour to the right and from the left cutting point of the right end contour to the left, it alternately draws circles with the width of each false eyelash and the distance between the false eyelashes as the radius until they meet. Based on the intersection of the circle and the curve equation, it calculates the adjacent cutting points of a cutting point to obtain a set of reference cutting points. The cutting points are then corrected using the reference cutting points to obtain the final cutting point.

[0108] The trajectory planning module plans the cutting trajectory for each false eyelash based on the final cutting point and the requirements for cutting quality, so that it can be continuously cut along the trajectory by automated cutting equipment.

[0109] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. 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 or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for cutting false eyelashes, characterized in that... Includes the following steps: Step S1: Obtain the image of the entire horizontally arranged false eyelashes; Step S2: Perform contour detection on the entire false eyelash image to find the contour where the cutting point is located; Step S3: Based on the bottom point of the contour, fit the curve equation of the cutting line in the image, and select the left and right endpoints on the contour to substitute into the curve equation to obtain a set of cutting points. Step S4: Obtain the right cutting point of the left end contour and the left cutting point of the right end contour of a segment of false eyelashes. Obtain the width of each false eyelash and the distance between the false eyelashes. Starting from the right cutting point of the left end contour to the right and from the left cutting point of the right end contour to the left, draw circles alternately with the width of each false eyelash and the distance between the false eyelashes as the radius until they meet. Based on the intersection of the circle and the curve equation, calculate the adjacent cutting points of a cutting point to obtain a set of reference cutting points. Correct the cutting points using the reference cutting points to obtain the final cutting points.

2. The method for cutting false eyelashes according to claim 1, characterized in that: In step S1, each false eyelash is arranged and fixed into a whole false eyelash with tape. One side of the tape is placed in the tooling equipment, and the other side is placed on the light-transmitting base plate. The light source set below the light-transmitting base plate is used for supplementary lighting, and the image of the whole false eyelash is obtained from above the base plate.

3. The method for cutting false eyelashes according to claim 2, characterized in that: In step S1, the acquired false eyelash image is preprocessed, the area to be cut is cropped as the source image, and grayscale, inverse binarization and erosion operations are performed on the source image in sequence. Based on the positional relationship between the tooling equipment and the base plate, the linear coordinates of the edge of the base plate are obtained. The false eyelash image is further cropped using the linear coordinates to obtain the preprocessed false eyelash image.

4. The method for cutting false eyelashes according to claim 1, characterized in that: Step S2 further includes the following steps: Step S2.1: Filter the detected contours by their area; set an area threshold, and discard all contours smaller than the area threshold. Step S2.2: Filter contours based on their aspect ratio; set an aspect ratio threshold and calculate the minimum outer rectangle for each contour, with a size of [value missing]. The longer side is h, and the shorter side is w. If h / w is less than the aspect ratio threshold, the contour is discarded. Step S2.3: Filter by the shape of the smallest circumscribed triangle of the contour; fit the smallest circumscribed triangle to each contour to obtain the position of the three vertices of the smallest circumscribed triangle, determine the relative positional relationship between the three vertices, calculate the centroid of the triangle based on the position of the three vertices, determine the vertical positional relationship between the three vertices and the centroid in the image, if two vertices are above the centroid, the contour is discarded.

5. The method for cutting false eyelashes according to claim 1, characterized in that: In step S3, the bottom point, left endpoint, and right endpoint of the contour are obtained, and an nth-degree polynomial model is constructed based on the bottom point: in, The coefficients of the polynomial to be solved are represented by x, the x-coordinate of the cutting point in the image coordinate system, and n, the order of the polynomial, which is determined by observing the extreme points of the glued line. We construct a system of linear equations to calculate these coefficients, in matrix form as follows: Where X and Y are parameter matrices, with sizes respectively and The specific positions of the elements in the X and Y matrices are as follows: and A represents the coefficient matrix to be solved; Where i and j are the row and column indices of the matrix, and N is the number of input points. This represents the x-coordinate of the k-th cutting point in the pixel coordinate system. , They represent i, i+j powers, This represents the y-coordinate of the k-th cutting point in the pixel coordinate system, and T represents the transpose of the matrix; Substitute the x-coordinates of the left and right endpoints of the contour into the polynomial model to obtain the cutting points.

6. The method for cutting false eyelashes according to claim 5, characterized in that: In step S4, the curve equation is as follows: The equation of a circle is as follows: in, and Let the coordinates of the center of the circle be , then the function representing the intersection point of the circle and the curve equation is as follows: Using Newton's iteration method, the iterative formula for the intersection point is: Where iter is the number of iterations for calculation. yes The derivative; The adjacent cutting points of a cutting point are calculated using the above method, resulting in a set of reference cutting points.

7. The method for cutting false eyelashes according to claim 1, characterized in that: In step S4, comparing the cutting point and the reference cutting point includes the following steps: Step S4.1: Sort the cutting point set and the reference cutting point set in ascending order according to the x-coordinate; Step S4.2: Calculate the absolute value of the x-coordinate distance between the points in the cutting point set and the points in the reference cutting point set. If the absolute value of the distance is less than the specified distance threshold, replace the x-coordinate of the corresponding point in the reference cutting point set with the x-coordinate of the point in the cutting point set.

8. A method for automatically planning the cutting trajectory of false eyelashes, characterized in that: The method for cutting false eyelashes according to claim 1 further includes step S5: planning the cutting trajectory of the false eyelashes based on the final cutting point obtained in step S4 and the requirements for cutting quality.

9. A false eyelash cutting device, comprising an image acquisition module, a contour acquisition module, a cutting point acquisition module, and a cutting point correction module, characterized in that: The image acquisition module acquires an image of the entire horizontally arranged false eyelashes; The contour acquisition module performs contour detection on the entire false eyelash image to find the contour where the cutting point is located. The cutting point acquisition module fits the curve equation of the cutting line in the image based on the bottom point of the contour, and selects the left and right endpoints on the contour to substitute into the curve equation to obtain a set of cutting points. The cutting point correction module obtains the right cutting point of the left end contour and the left cutting point of the right end contour of a segment of false eyelashes, respectively, and obtains the width of each false eyelash and the distance between the false eyelashes. Starting from the right cutting point of the left end contour to the right and from the left cutting point of the right end contour to the left, circles are drawn alternately with the width of each false eyelash and the distance between the false eyelashes as the radius until they meet. Based on the intersection of the circle and the curve equation, the adjacent cutting points of a cutting point are calculated to obtain a set of reference cutting points. The cutting points are corrected by the reference cutting points to obtain the final cutting point.

10. A device for automatically planning the cutting trajectory of false eyelashes, characterized in that: The false eyelash cutting device according to claim 9 further includes a trajectory planning module, which plans the cutting trajectory of the false eyelashes according to the final cutting point and the requirements for cutting quality.

Images