A machine vision-based intelligent evaluation method for color fastness of textiles

Abstract

The application discloses a kind of textile color fastness intelligent evaluation method based on machine vision, after being wetted to textile, and before being detected to textile, the warp density adjustment of textile is carried out, so that the density of wetted textile is consistent with the density of textile before being not wetted, can guarantee that the color of textile will not be deviated due to warp density change in test process, improve the accuracy of textile in color fastness detection;Textile is detected by using the way of machine vision, and the illumination condition adjustment is carried out before image sampling, so that image sampling in detection process is under the same sampling condition, can guarantee the rapid detection in textile color fastness detection process, improve the efficiency and accuracy of textile color fastness;The rubbing direction of textile is parallel to the surface of textile, and the rubbing direction is consistent with the arrangement direction of yarn, can reduce the influence of warp density of textile, enhance textile color fastness detection effect.

Description

Technical Field

[0001] This invention relates to the field of textile testing technology, and more particularly to an intelligent evaluation method for color fastness of textiles based on machine vision. Background Technology

[0002] Machine vision is a technology that uses computers and image processing techniques to simulate and realize human vision. It acquires, processes, and analyzes image or video data to simulate human visual capabilities, thereby enabling the understanding and recognition of objects, scenes, and images.

[0003] Colorfastness (or simply colorfastness) refers to the degree of fading of dyed fabrics during use or processing, under the influence of external factors (squeezing, friction, washing, rain, sun exposure, light, seawater immersion, saliva immersion, water stains, perspiration, etc.). It is an important indicator of fabric quality. Because the conditions fabrics are subjected to during processing and use vary greatly, the requirements also differ.

[0004] Machine vision is used to assess the colorfastness of textiles, employing computer vision and image processing techniques. It analyzes and processes images of the textiles to determine their colorfastness grade. The advantages of machine vision in assessing textile colorfastness lie in its speed, automation, and non-destructive nature. It can significantly improve assessment efficiency and reduce human error. However, it is important to note that machine vision assessment methods still need to be combined with traditional laboratory testing to ensure the accuracy and reliability of the results. Therefore, the dry and wet rubbing colorfastness testing method, with its superior detection capabilities, is chosen for the basic testing of textile colorfastness.

[0005] The prior art CN113804619A discloses a method for testing the color fastness of textiles by wet and dry rubbing. This method involves treating two samples of the textiles by wet and dry methods, respectively, and then rubbing them with a rubbing head. The staining is then graded using a gray scale. This method can test the color fastness of textile samples. However, in the wet rubbing test, the textiles may deform after being immersed in warm water, which will cause changes in the warp and weft density of the textiles and lead to deviations in the color fastness of the textiles during the test.

[0006] Therefore, it is necessary to improve the existing methods for testing the color fastness of textiles in order to solve the above problems. Summary of the Invention

[0007] This invention overcomes the shortcomings of the prior art and provides a machine vision-based intelligent evaluation method for color fastness of textiles, aiming to solve the defects in the prior art that cause color deviation of textiles during the detection process.

[0008] To achieve the above objectives, the technical solution adopted by this invention is: an intelligent evaluation method for color fastness of textiles based on machine vision, comprising the following steps:

[0009] S1: Input the color fastness grade corresponding to the color in advance into the processor, and adjust the lighting conditions of the image input device.

[0010] S2: Cut two textile samples of the same size, record the warp width, weft width and warp and weft density of the samples, and place them in a constant temperature chamber for at least 18 hours;

[0011] S3: Soak one sample from S2 in warm water and stir;

[0012] S4: Rub the stirred sample from S3 with standard cotton cloth. Adjust the warp and weft density of the rubbed sample according to the fiber weaving sequence so that the warp and weft density of the sample is consistent with that of the sample in S2.

[0013] S5: Compare the color fastness of the sample obtained in S4 and the standard cotton at the image input device in S1.

[0014] S6: Rub the other sample from S2 with standard cotton cloth. Adjust the warp and weft density of the rubbed sample according to the fiber weaving sequence so that the warp and weft density of the sample is consistent with that of the sample in S2.

[0015] S7: Compare the color fastness of the sample obtained in S6 and the standard cotton at the image input device in S1.

[0016] In a preferred embodiment of the present invention, the temperature inside the constant temperature chamber in step S2 is 25±2℃ and the humidity is 60±5%Rh.

[0017] In a preferred embodiment of the present invention, the textile in step S2 is a low moisture absorption textile.

[0018] In a preferred embodiment of the present invention, the warp width and weft width of the textile in step S2 are the same.

[0019] In a preferred embodiment of the present invention, the working direction of the image input device in S4 and S6 is perpendicular to the surface of the textile sample.

[0020] In a preferred embodiment of the present invention, the friction direction between the sample and the standard cotton cloth in S4 and S6 is horizontal.

[0021] In a preferred embodiment of the present invention, the samples in S4 and S6 are rubbed against the standard cotton cloth along the yarn direction.

[0022] A machine vision-based intelligent evaluation device for color fastness of textiles includes: a frame, and an image input device and a clamping structure respectively mounted on the frame;

[0023] The clamping structure includes: a plurality of clamps, a clamping unit disposed on each of the clamps, and a plurality of tensioning mechanisms disposed between adjacent clamps;

[0024] Each clamping unit includes: a clamping bracket, a clamping bar disposed on the clamping bracket, and a plurality of heddles disposed on one side of the clamping bracket; the clamping bracket is fixedly connected to the clamping device, the plurality of heddles are slidably connected to the clamping device, each heddle is vertically arranged, and each heddle is provided with a heddle eye for thread to pass through;

[0025] Each of the tensioning mechanisms includes: a cylinder, and a support rod fixedly connected to the cylinder; the cylinder is fixedly connected to the clamp, and the support rod is used to connect adjacent clamps; the plurality of support rods are arranged in parallel and located on the same horizontal plane.

[0026] In a preferred embodiment of the present invention, a plurality of heddles are disposed on opposite sides of adjacent clamps, and the axes of a plurality of heddle eyes on adjacent clamps are parallel and located on the same horizontal plane.

[0027] In a preferred embodiment of the present invention, the clamping rod is slidably connected to the clamping bracket, and a clamping block is fixedly connected to the lower end of each clamping rod, the clamping block being horizontally arranged.

[0028] This invention addresses the shortcomings of the prior art and has the following beneficial effects:

[0029] (1) The present invention adjusts the warp and weft density of textiles after wetting them and before testing them, so that the density of textiles after wetting is consistent with that of textiles before wetting. Compared with the existing textile color fastness testing methods, this invention can ensure that the color of textiles will not deviate due to changes in warp and weft density during the test, thereby improving the accuracy of textiles in color fastness testing.

[0030] (2) The present invention uses machine vision to test the color fastness of textiles and adjusts the lighting conditions before image sampling so that the image sampling is under the same sampling conditions during the detection process. Compared with the prior art, it can ensure the rapid detection of textile color fastness and improve the efficiency and accuracy of textile color fastness testing.

[0031] (3) When the present invention performs rubbing tests on the color fastness of textile samples, the rubbing direction is parallel to the surface of the textile and consistent with the yarn arrangement direction. Compared with the prior art, this invention can make the rubbing process of textile color fastness more uniform and reduce the influence on the warp and weft density of textiles, thereby enhancing the color fastness test effect of textiles. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in the embodiments of the present 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 only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 This is a process flow diagram of a preferred embodiment of the present invention;

[0034] Figure 2 This is a perspective view of the clamping structure according to a preferred embodiment of the present invention;

[0035] Figure 3 This is a side view of the clamping unit according to a preferred embodiment of the present invention;

[0036] In the diagram: 100, clamping device; 200, clamping unit; 210, clamping bracket; 220, clamping bar; 221, clamping block; 230, heddle wire; 240, eyelet; 300, tensioning mechanism; 310, cylinder; 320, support rod. Detailed Implementation

[0037] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0038] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein. Therefore, the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0039] In the description of this application, it should be understood that the terms "center," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as limiting the scope of protection of this application. Furthermore, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, features defined with "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0040] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art will understand the specific meaning of the above terms in this application based on the specific circumstances.

[0041] Example 1

[0042] like Figure 1 As shown, a machine vision-based intelligent assessment method for color fastness of textiles includes the following steps:

[0043] S1: Input the color fastness grade corresponding to the color in advance into the processor, and adjust the lighting conditions of the image input device.

[0044] S2: Cut two textile samples of the same size, record the warp width, weft width and warp and weft density of the samples, and place them in a constant temperature chamber for at least 18 hours;

[0045] S3: Soak one sample from S2 in warm water and stir.

[0046] S4: Rub the stirred sample from S3 with standard cotton cloth. Adjust the warp and weft density of the rubbed sample according to the fiber weaving sequence so that the warp and weft density of the sample is consistent with that of the sample in S2.

[0047] S5: Compare the color fastness of the sample obtained in S4 with that of the standard cotton at the image input device in S1.

[0048] S6: Rub the other sample from S2 with the standard cotton cloth. Adjust the warp and weft density of the rubbed sample according to the fiber weaving sequence so that the warp and weft density of the sample is consistent with that of the sample in S2.

[0049] S7: Compare the color fastness of the sample obtained in S6 with that of the standard cotton placed in the image input device in S1.

[0050] After wetting the textile, the warp and weft density of the textile is adjusted before testing in S4 and S6 so that the density of the textile after wetting is consistent with that before wetting. This ensures that the color of the textile will not deviate due to changes in warp and weft density during the test, thus improving the accuracy of the textile in color fastness testing.

[0051] The temperature inside the S2 constant temperature chamber is 25±2℃, and the humidity is 60±5%Rh. Maintaining consistent temperature and humidity within the chamber ensures stable pigment adhesion on the textile samples, guaranteeing the accuracy of subsequent friction tests.

[0052] The textiles in S2 are low-moisture-absorbing textiles. If the moisture absorption rate of the textiles is too high, the yarn density will increase and the porosity of the textiles will decrease during the wetting process, resulting in an overall increase in the density of the textile fabric, which will affect the evaluation of color fastness in the test.

[0053] In S2, the warp and weft widths of the textile are the same. Using textiles with consistent warp and weft widths ensures that the yarns do not shift excessively due to friction during the friction test, effectively maintaining the warp and weft density of the textile.

[0054] like Figure 2 and Figure 3 As shown, a machine vision-based intelligent assessment device for color fastness of textiles includes: a frame, and an image input device and a clamping structure respectively mounted on the frame.

[0055] The clamping structure includes: a plurality of clamps 100, a clamping unit 200 disposed on each of the clamps 100, and a plurality of tensioning mechanisms 300 disposed between adjacent clamps 100.

[0056] Each clamping unit 200 includes: a clamping bracket 210, a clamping bar 220 disposed on the clamping bracket 210, and a plurality of heddles 230 disposed on one side of the clamping bracket 210; the clamping bracket 210 is fixedly connected to the clamping device, the plurality of heddles 230 are slidably connected to the clamping device, each heddle 230 is vertically arranged, and each heddle 230 is provided with a heddle eye 240 for the thread to pass through.

[0057] Each stretching mechanism 300 includes: a cylinder 310, and a support rod 320 fixedly connected to the cylinder 310; the cylinder 310 is fixedly connected to a clamping device, and the support rod 320 is used to connect adjacent clamping devices 100. Several support rods 320 are arranged parallel to each other and located on the same horizontal plane. The cylinder 310 is used to stretch adjacent clamping devices 100. After the wire is clamped, the stretching action of the cylinder 310 causes the wire to straighten.

[0058] Several heddles 230 are arranged on opposite sides of adjacent clamps, and several heddle eyes 240 on adjacent clamps have parallel axes and are located on the same horizontal plane. The heddle eyes 240 being located on the same horizontal plane ensures that all the threads of the textile fabric are located on the same horizontal plane, which allows for effective stretching of each thread and maintenance of the fabric structure during adjustment.

[0059] The clamping rod 220 is slidably connected to the clamping bracket 210, and a clamping block 221 is fixedly connected to the lower end of each clamping rod 220. The clamping block 221 is horizontally set. The function of the clamping block 221 is to squeeze and clamp the wire. When placed, the wire is located below the clamping block 221, so that several wires between the clamping block 221 and the clamper 100 are clamped.

[0060] Example 2

[0061] In S4 and S6, the image input devices operate perpendicular to the surface of the textile sample. This provides the most intuitive viewing during the testing process, is least affected by changes in the warp and weft density of the textile fabric, and avoids cumbersome alignment procedures when changing samples for repeated tests, thus speeding up sample changes and improving the overall efficiency of the experiment.

[0062] Using machine vision to test the color fastness of textiles, and adjusting the lighting conditions before image sampling, ensures that all image samples are under the same sampling conditions during the testing process. This guarantees rapid detection of color fastness of textiles and improves the efficiency and accuracy of color fastness testing.

[0063] The samples in S4 and S6 rubbed against the standard cotton fabric in a horizontal direction. The associated friction mode is vertical friction. However, the friction force of vertical compression is relatively small, and compared with horizontal friction, it is insufficient in terms of friction against the pigments on the textile surface. Horizontal friction is closer to the way people rub against clothing in real life.

[0064] The samples in S4 and S6 were rubbed against standard cotton fabric along the yarn direction. When rubbing along the yarn direction, the yarn's oscillation amplitude is reduced, and the frictional force mainly acts on the pigment on the yarn surface. However, when rubbing at a certain angle to the yarn direction, the frictional force causes the yarn to oscillate, and the frictional force does no work on the yarn, increasing the energy consumption during yarn friction. The frictional force received by the pigment in the textile fabric is also reduced.

[0065] The friction direction is parallel to the textile surface and consistent with the yarn arrangement direction. Compared with existing technologies, this makes the color fastness testing process of textiles more uniform and reduces the impact on the warp and weft density of textiles, thereby enhancing the color fastness testing effect of textiles.

[0066] During the process of adjusting the warp and weft density of the textile sample, the warp and weft density recorded in S1 is first adjusted so that the arrangement density of several heddles 230 on adjacent clamps 100 is consistent with the recorded warp and weft density.

[0067] After adjusting the density of the heddle 230 to match the density of the warp yarns of the textile, the warp yarns of the textile are each threaded into the heddle eye 240 on the heddle 230. The clamping bar 220 is then used to move downwards. As the clamping block 221 gradually descends, the warp yarns are squeezed under the clamping block 221. Finally, the warp yarns are pressed between the clamping block 221 and the clamping device 100.

[0068] Once the warp yarns on adjacent clamps 100 have been fully compressed, cylinder 310 is activated, causing support rod 320 to extend. During the extension of support rod 320, the warp yarns are stretched and gradually arranged at a pre-set warp density. Under the premise of ensuring that the warp yarns are not stretched and broken, the warp density is eventually adjusted to the state in S1.

[0069] After adjusting the density of several heddles 230 to match the density of the weft yarn of the textile, several weft yarns of the textile are threaded into the heddle eye 240 on several heddles 230, and the clamping bar 220 is used to move downward. During the process of the clamping block 221 gradually descending, several weft yarns are squeezed under the clamping block 221, and finally the weft yarns are pressed between the clamping block 221 and the clamping device 100.

[0070] Once the weft yarns on adjacent clamps 100 have been fully compressed, cylinder 310 is activated, causing support rod 320 to extend. During the extension of support rod 320, the weft yarns are stretched and gradually arranged at a pre-set weft yarn density. Under the premise of ensuring that the weft yarns are not stretched and broken, the weft yarn density is eventually adjusted to the state in S1.

[0071] After adjusting the warp and weft densities, colorfastness tests were performed on both textile fabrics sequentially. The reason for conducting both wet and dry colorfastness tests simultaneously is to simulate textiles under different environmental conditions. The wet textile sample is analogous to clothing worn by a person after sweating, while the dry textile sample is analogous to clothing worn by a person in a dry state. Testing under multiple conditions allows for an assessment of the textile's adaptability to colorfastness, resulting in a more comprehensive evaluation of its colorfastness.

[0072] Based on the preferred embodiments of the present invention described above, those skilled in the art can make various changes and modifications without departing from the inventive concept. The technical scope of this invention is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. A machine vision-based intelligent evaluation method for color fastness of textiles, characterized in that, Includes the following steps: S1: Input the color fastness grade corresponding to the color in advance into the processor, and adjust the lighting conditions of the image input device. S2: Cut two textile samples of the same size, record the warp width, weft width and warp and weft density of the samples, and place them in a constant temperature chamber for at least 18 hours; S3: Soak one sample from S2 in warm water and stir; S4: Rub the stirred sample from S3 with standard cotton cloth. Adjust the warp and weft density of the rubbed sample according to the fiber weaving sequence so that the warp and weft density of the sample is consistent with that of the sample in S2. S5: Compare the color fastness of the sample obtained in S4 and the standard cotton at the image input device in S1. S6: Rub the other sample from S2 with standard cotton cloth. Adjust the warp and weft density of the rubbed sample according to the fiber weaving sequence so that the warp and weft density of the sample is consistent with that of the sample in S2. S7: Compare the color fastness of the sample obtained in S6 and the standard cotton at the image input device in S1.

2. The intelligent evaluation method for color fastness of textiles based on machine vision according to claim 1, characterized in that: The temperature inside the constant temperature chamber in S2 is 25±2℃, and the humidity is 60±5%Rh.

3. The intelligent evaluation method for color fastness of textiles based on machine vision according to claim 1, characterized in that: The textile in S2 is a low moisture absorption textile.

4. The intelligent evaluation method for color fastness of textiles based on machine vision according to claim 1, characterized in that: The warp width and weft width of the textile in S2 are the same.

5. The intelligent evaluation method for color fastness of textiles based on machine vision according to claim 1, characterized in that: In S4 and S6, the working direction of the image input device is perpendicular to the surface of the textile sample.

6. The intelligent evaluation method for color fastness of textiles based on machine vision according to claim 1, characterized in that: The samples in S4 and S6 are rubbed against the standard cotton cloth in a horizontal direction.

7. The intelligent evaluation method for color fastness of textiles based on machine vision according to claim 1, characterized in that: The samples in S4 and S6 are rubbed against the standard cotton cloth along the yarn direction.

8. A machine vision-based intelligent assessment device for colorfastness of textiles, based on any one of claims 1-7, comprising: A frame, and an image input device and a clamping structure respectively fixedly mounted on the frame; The clamping structure includes: a plurality of clamps, a clamping unit disposed on each of the clamps, and a plurality of tensioning mechanisms disposed between adjacent clamps; Each clamping unit includes: a clamping bracket, a clamping bar disposed on the clamping bracket, and a plurality of heddles disposed on one side of the clamping bracket; the clamping bracket is fixedly connected to the clamping device, the plurality of heddles are slidably connected to the clamping device, each heddle is vertically arranged, and each heddle is provided with a heddle eye for thread to pass through; Each of the tensioning mechanisms includes: a cylinder, and a support rod fixedly connected to the cylinder; the cylinder is fixedly connected to the clamp, and the support rod is used to connect adjacent clamps; the plurality of support rods are arranged in parallel and located on the same horizontal plane.

9. The intelligent assessment device for color fastness of textiles based on machine vision according to claim 8, characterized in that: Several heddles are arranged on opposite sides of adjacent clamps, and the axes of several heddle eyes on adjacent clamps are parallel and located on the same horizontal plane.

10. The intelligent assessment device for color fastness of textiles based on machine vision according to claim 8, characterized in that: The clamping rod is slidably connected to the clamping bracket, and a clamping block is fixedly connected to the lower end of each clamping rod, with the clamping block being horizontally positioned.

Images