A method and system for identifying cloth stripes

Abstract

The present invention belongs to the technical field of graphic cutting equipment, and provides a method and system for identifying stripes of cloth, including: an image acquisition module, which is used to acquire a real-time image of cloth; an initialization module, which is used to obtain real-time parameters of stripes in the real-time image according to a preset graphic drawn by a user on the real-time image; and a recognition module, which is used to segment the real-time image into corresponding areas according to the preset graphic drawn by the user on the real-time image and the real-time parameters, thereby forming corresponding grid lines. The advantage of the present invention is that the acquired real-time image of cloth is identified and segmented through the initialization module and the recognition module, and it is reproduced in the form of grid lines, and the grid lines generated when the image is deformed are corrected through a preset algorithm, which provides a basis for subsequent cutting of the cloth.

Description

Technical Field

[0001] The present invention relates to the technical field of graphic cutting equipment, and in particular to a cloth strip recognition method and system. Background Art

[0002] At present, during the cutting process of graphic cutting equipment, the cutting of patterns often needs to consider the alignment of strips, and the alignment process of strips is more complicated due to the different types of strips.

[0003] Especially in the processing of clothing fabrics, due to the inevitable lack of precision in the production process of the fabric, the fabric has problems with weft skew and large and small grids, resulting in the stripe pattern cycle not strictly following the theoretical cycle. Based on the above factors, the actual cut pieces cannot simultaneously meet the requirements of stripe alignment and strict size unchanged. Summary of the invention

[0004] The object of the present invention is to provide a cloth stripe recognition method and system to solve the above-mentioned problem.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is:

[0006] A cloth stripe recognition system, comprising:

[0007] An image acquisition module, which is used to acquire a real-time image of the fabric;

[0008] An initialization module, which is used to obtain real-time parameters of the bars in the real-time image according to a preset graphic drawn by a user on the real-time image;

[0009] The recognition module is used to divide the real-time image into corresponding areas according to the preset graphics drawn by the user on the real-time image and the real-time parameters, so as to form corresponding grid lines.

[0010] Furthermore, the type of fabric corresponding to the real-time image is stripes or grids.

[0011] Furthermore, if the type of cloth captured by the real-time image is stripes, the preset graphic drawn by the user includes a straight line representing the width of the stripes and a rectangle representing the size of the segmented area.

[0012] Furthermore, if the cloth type acquired by the real-time image is a grid, the preset graphic drawn by the user includes a point representing an initial segmentation position, a horizontal line representing a grid width, and a vertical line representing a grid height.

[0013] Furthermore, the real-time parameters obtained by the initialization module can be displayed on a preset interface and can be modified by the user on the preset interface.

[0014] Furthermore, the recognition module is also used to correct the generated grid lines into grid lines corresponding to the deformed cloth image through a preset correction algorithm when the cloth in the acquired real-time image is deformed.

[0015] Another aspect of the present invention provides a method for identifying cloth stripes, comprising the steps of:

[0016] S1, obtaining a real-time image of the cloth;

[0017] S2. obtaining real-time parameters of the bars in the real-time image according to a preset graphic drawn by a user on the real-time image;

[0018] S3. According to the preset graphics drawn by the user on the real-time image and the real-time parameters, the real-time image is divided into corresponding areas to form corresponding grid lines; when the cloth in the acquired real-time image is deformed, the generated grid lines are corrected into grid lines corresponding to the deformed cloth image by a preset correction algorithm.

[0019] Furthermore, the type of fabric corresponding to the real-time image is stripes or grids.

[0020] Furthermore, if the type of fabric captured by the real-time image is stripes, the preset graphic drawn by the user includes a straight line representing the width of the stripes and a rectangle representing the size of the segmented area;

[0021] If the cloth type acquired by the real-time image is a grid, the preset graphic drawn by the user includes a point representing an initial segmentation position, a horizontal line representing a grid width, and a vertical line representing a grid height.

[0022] Furthermore, the real-time parameters can be displayed on a preset interface and can be modified by the user on the preset interface.

[0023] Compared with the prior art, the present invention has at least the following beneficial effects:

[0024] (1) The present invention recognizes and segments the acquired real-time image of the cloth through the initialization module and the recognition module, and reproduces it in the form of grid lines, which provides a basis for subsequent cutting of the cloth;

[0025] (2) During initialization, the present invention allows the user to define the segmentation area by simple graphics to determine the relevant parameters of the segmentation recognition area, and the parameters can be fine-tuned by the user to meet the user's segmentation accuracy;

[0026] (3) When the cloth is deformed, the present invention can find the most suitable point in the coordinates by combining the genetic algorithm with the triangular meshing algorithm according to the parameters obtained in the initialization module, thereby forming a pattern segmentation area closest to the acquired real-time image, so that the accuracy of the corrected grid line in reproducing the cloth pattern is greatly improved, and the accuracy of the subsequent cutting stage is further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a schematic diagram of the framework of the system provided by the embodiment of the present invention;

[0028] Figure 2 is a schematic diagram of initialization of the striped fabric in an embodiment of the present invention;

[0029] Figure 3 is a schematic diagram of initialization of a mesh cloth in an embodiment of the present invention;

[0030] Figure 4 is a schematic diagram of the recognition and segmentation results of the mesh cloth in an embodiment of the present invention;

[0031] Figure 5 It is a flow chart of a method for identifying cloth stripes provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0032] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0033] In addition, the technical solutions between the various embodiments of the present invention can be combined with each other, but it must be based on the fact that ordinary technicians in the field can implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0034] The following are specific embodiments of the present invention, and the technical solutions of the present invention are further described in conjunction with the accompanying drawings, but the present invention is not limited to these embodiments.

[0035] like Figure 1 As shown, the present invention provides a cloth stripe recognition system, comprising:

[0036] An image acquisition module, which is used to acquire a real-time image of the fabric;

[0037] An initialization module, which is used to obtain real-time parameters of the bars in the real-time image according to a preset graphic drawn by a user on the real-time image;

[0038] The recognition module is used to divide the real-time image into corresponding areas according to the preset graphics drawn by the user on the real-time image and the real-time parameters, so as to form corresponding grid lines.

[0039] This system is installed on a graphic cutting machine. When the cutting method of a certain fabric pattern is not stored in the system, the new fabric pattern will be identified through the initialization module and the recognition module, and the cutting method will be stored in the system according to the user's needs. After that, when the fabric pattern needs to be cut, when the fabric pattern information is identified through the image acquisition module, the fabric pattern will be cut in the corresponding way according to the cutting method stored in the system.

[0040] Among them, with regard to the image acquisition module, it takes pictures of the transmitted cloth through components such as a camera, thereby acquiring a real-time image of the cloth.

[0041] After the image acquisition module obtains the corresponding real-time image, the system will confirm whether the pattern is a pattern with a set segmentation method. If so, it will directly enter the next step of cutting according to the preset cutting method. When the system confirms that the acquired image is not a pattern with a segmentation method stored in the system, the user needs to set the segmentation method for the acquired pattern.

[0042] During the setting, the initialization module first obtains the user's data information on the size of the segmented area, and obtains the corresponding data information through the preset graphics drawn by the user on the real-time image.

[0043] The types of fabrics that this system can segment are mainly stripes and grids. Stripes can be but are not limited to being formed by arranging strips of different colors, while grids are formed by combining horizontal lines or stripes and vertical lines or stripes.

[0044] like Figure 2 As shown, if the type of fabric captured by the real-time image is stripes, the preset graphic drawn by the user includes a straight line representing the width of the stripes and a rectangle representing the size of the segmented area. The widths of the stripes of different colors can be distinguished by the straight line of the stripe width, and the length of each strip segmentation can be determined by the rectangular graphic. By measuring the straight line and the rectangle, the real-time parameters that the user wants to segment can be obtained, which can be displayed on the preset interface and can be changed by the user on the preset interface.

[0045] The user can fine-tune the real-time parameters for segmentation, and can also use the real-time parameters to determine whether there is an error in distinguishing different color bars, which can also lay the foundation for subsequent segmentation.

[0046] like Figure 3As shown, when the cloth type acquired by the real-time image is a grid, the preset graphic drawn by the user includes a point representing the initial segmentation position, a horizontal line representing the grid width, and a vertical line representing the grid height.

[0047] This point will be used as the coordinate origin for subsequent segmentation, and the size of the grid will be determined by horizontal and vertical lines. The real-time parameters of the grid obtained through the above graphics can be displayed on the preset interface and can be changed by the user on the preset interface. On the one hand, the user can obtain the data of the segmented area on the preset interface, and on the other hand, the boundary data of the segmented area, so as to fine-tune the size of the segmented area according to the boundary data information, thereby improving the accuracy of subsequent recognition and segmentation.

[0048] By setting the parameters of the initialization module, the system can then perform recognition and segmentation through the recognition module to form the corresponding grid lines. Taking stripe segmentation as an example, the recognition and segmentation results are as follows: Figure 4 shown.

[0049] When the fabric in the acquired real-time image is deformed, the recognition module will deviate from the area that the user wants to segment during recognition, so the generated grid lines need to be corrected.

[0050] The correction algorithm used in this system is to find the most suitable point in the coordinates by combining the genetic algorithm with the triangulated meshing algorithm according to the parameters obtained in the initialization module, so as to form the pattern segmentation area closest to the acquired real-time image.

[0051] When this system determines whether the cloth in the real-time image is deformed, it uses the recognition module to identify and segment according to the real-time parameters, and continuously finds multiple actual points that meet the intervals based on the stripes or grid intervals. Whether it meets the requirements is determined by the real-time parameters near the point. These points are used as a benchmark to calculate all other points. If no points are found within a certain range, a virtual point is created and regarded as a simulation point. The corresponding score is obtained by calculating the number of simulation points and actual points. Users can set the corresponding threshold based on experience. A score exceeding the threshold is considered to be that the cloth in the real-time image has not been deformed.

[0052] Through the initialization module and the recognition module, the system recognizes and segments the real-time image of the cloth, reproduces it in the form of grid lines, and corrects the grid lines generated when the image is deformed through a preset algorithm, providing a basis for subsequent cutting of the cloth.

[0053] like Figure 5 As shown, the present invention also provides a method for identifying cloth stripes, comprising the steps of:

[0054] S1, obtaining a real-time image of the cloth;

[0055] S2. obtaining real-time parameters of the bars in the real-time image according to a preset graphic drawn by a user on the real-time image;

[0056] S3. According to the preset graphics drawn by the user on the real-time image and the real-time parameters, the real-time image is divided into corresponding areas to form corresponding grid lines; when the cloth in the acquired real-time image is deformed, the generated grid lines are corrected into grid lines corresponding to the deformed cloth image by a preset correction algorithm.

[0057] Wherein, the type of fabric corresponding to the real-time image is stripes or grids. If the fabric type acquired by the real-time image is stripes, the preset graphic drawn by the user includes a straight line representing the width of the stripes and a rectangle representing the size of the segmented area. If the fabric type acquired by the real-time image is a grid, the preset graphic drawn by the user includes a point representing the initial segmentation position, a horizontal line representing the grid width, and a vertical line representing the grid height.

[0058] And the obtained real-time parameters can be displayed on a preset interface and can be modified by the user on the preset interface.

[0059] This method can identify and segment the acquired real-time cloth image, reproduce it in the form of grid lines, and correct the grid lines generated when the image is deformed through a preset algorithm, providing a basis for subsequent cutting of the cloth.

[0060] The specific embodiments described herein are merely examples of the spirit of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in similar ways, but they will not deviate from the spirit of the present invention or exceed the scope defined by the appended claims.

Claims

1. A cloth stripe recognition system, characterized in that: include: An image acquisition module, which is used to acquire a real-time image of the fabric; An initialization module, which is used to obtain real-time parameters of the bars in the real-time image according to a preset graphic drawn by a user on the real-time image; A recognition module, which is used to divide the real-time image into corresponding areas according to a preset graphic drawn by a user on the real-time image and the real-time parameters, thereby forming corresponding grid lines; The type of fabric corresponding to the real-time image is stripes or grids; If the fabric type captured by the real-time image is stripes, the preset graphic drawn by the user includes a straight line representing the width of the stripes and a rectangle representing the size of the segmented area; if the fabric type captured by the real-time image is a grid, the preset graphic drawn by the user includes a point representing the initial segmentation position, a horizontal line representing the grid width, and a vertical line representing the grid height.

2. A cloth stripe recognition system according to claim 1, characterized in that: The real-time parameters obtained by the initialization module can be displayed on a preset interface and can be modified by the user on the preset interface.

3. A cloth stripe recognition system according to claim 1, characterized in that: The recognition module is also used to correct the generated grid lines into grid lines corresponding to the deformed cloth image through a preset correction algorithm when the cloth in the acquired real-time image is deformed.

4. A method for identifying cloth stripes, characterized in that: Includes steps: S1, obtaining a real-time image of the cloth; S2, obtaining real-time parameters of the bars in the real-time image according to a preset graphic drawn by a user on the real-time image; S3, dividing the real-time image into corresponding areas according to the preset graphics drawn by the user on the real-time image and the real-time parameters, thereby forming corresponding grid lines; when the cloth in the acquired real-time image is deformed, correcting the generated grid lines into grid lines corresponding to the deformed cloth image by a preset correction algorithm; The type of fabric corresponding to the real-time image is stripes or grids; If the type of fabric captured by the real-time image is stripes, the preset graphic drawn by the user includes a straight line representing the width of the stripes and a rectangle representing the size of the segmented area; If the cloth type acquired by the real-time image is a grid, the preset graphic drawn by the user includes a point representing an initial segmentation position, a horizontal line representing a grid width, and a vertical line representing a grid height.

5. A method for identifying cloth stripes according to claim 4, characterized in that: The real-time parameters can be displayed on a preset interface and can be modified by a user on the preset interface.

Images