A method, device and system for detecting color fastness of a children's textile product

Abstract

The present application relates to the technical field of textile detection, and particularly relates to a method, device and system for detecting color fastness of children's textile products, which comprises: obtaining hyperspectral images of children's textile products before and after color fastness detection; determining the performance completeness of printing and dyeing edges of dyeing abnormal areas at each frequency of the hyperspectral images before and after color fastness detection; determining color fastness loss factors of children's textile products before and after color fastness detection according to the performance completeness before and after color fastness detection and representative frequencies in the hyperspectral images before and after color fastness detection, wherein the representative frequency is the frequency with the most pixels in the hyperspectral images; and determining an evaluation value of color loss of the textile products in the color fastness test process of children's textile products based on the color fastness loss factors. Thus, the present application reduces the error of the detection result of the color fastness of children's textile products.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of textile detection, in particular to a child textile product color fastness detection method, device and system. BACKGROUND

[0002] Children's skin is delicate and sensitive, and its tolerance to external stimuli is much lower than that of adults, which makes children's textiles have more stringent requirements on safety and quality standards, and color fastness is a crucial indicator. In daily wear, children often have special behavior patterns such as biting clothes and frequent rubbing, and if the color fastness of textiles is poor, dyes are easily detached and attached to children's skin, and long-term contact may even have potential adverse effects on children's growth and development. Therefore, more stringent standards should be established for the color fastness detection of children's textiles. The traditional color fastness comparison method mainly relies on manual comparison with prior color cards after testing to determine the degree of pigment detachment. However, the evaluation result is highly dependent on the accuracy of human eye recognition, and is easily affected by factors such as subjective experience of the tester, visual fatigue, and environmental light, resulting in errors, and the standard number of prior color cards is too small to cover the various color change gradients that may occur in actual detection, further affecting the accuracy of the evaluation.

[0003] In some scenarios, to overcome the defects of traditional methods, high-spectral technology is introduced to detect the color distribution of the child textile product after abrasion and compare it with the color distribution before testing to determine the fault abnormal position. However, in actual application, due to differences in the weaving method of the fabric itself (such as warp and weft density, weave structure, etc.), insufficient dyeing uniformity, and other factors, the spectral curve of the textile itself may have some degree of separation; and the spectral curve profile of the sample changes after color fastness detection due to pigment abrasion, which often superimposes on the above-mentioned inherent differences. This superimposition effect makes the color fastness judgment result of the child textile product deviate, and it is difficult to accurately reflect the actual color fastness level of the child textile product. SUMMARY

[0004] In order to solve the technical problem of large error in the detection result of the color fastness of the child textile product, the purpose of the present application is to provide a child textile product color fastness detection method, device and system.

[0005] To solve the above technical problems, the technical solutions adopted are as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for detecting color fastness of a children's textile product, comprising: obtaining hyperspectral images of the children's textile product before and after color fastness detection, respectively; determining completeness of a printing and dyeing edge of a dyeing abnormal area at each frequency of the hyperspectral images before and after color fastness detection according to a distribution rule of pixel points at the frequency in the hyperspectral images before and after color fastness detection, respectively; determining a color fastness loss factor of the children's textile product before and after color fastness detection according to the completeness before and after color fastness detection and a representative frequency in the hyperspectral images before and after color fastness detection, respectively, wherein the representative frequency is a frequency with the most pixel points in the hyperspectral images; and determining an evaluation value of color loss of the children's textile product in a color fastness test process based on the color fastness loss factor.

[0007] Optionally, the determining of the completeness of the printing and dyeing edge of the dyeing abnormal area at each frequency of the hyperspectral images before and after color fastness detection according to the distribution rule of the pixel points at the frequency in the hyperspectral images before and after color fastness detection comprises: decomposing the hyperspectral images by fast Fourier transform to obtain a frequency spectrum of the hyperspectral images; performing inverse Fourier transform on the frequencies in the frequency spectrum to obtain pixel points at the frequency in the hyperspectral images; merging pixel points in a surrounding area of each pixel point at the frequency in the hyperspectral images to obtain a plurality of effective frequency edges at the frequency in the hyperspectral images, a length of the effective frequency edge being a printing and dyeing edge of a dyeing abnormal area corresponding to the pixel point at the frequency in the hyperspectral images; and determining the completeness according to the edge length of each effective frequency edge and the frequency value of each frequency.

[0008] Optionally, the determining of the completeness according to the edge length of each effective frequency edge and the frequency value of each frequency comprises: selecting a maximum edge length from the edge lengths of each effective frequency edge and determining an average edge length of the edge lengths of all effective frequency edges; selecting a reference frequency with the most pixel points from the frequency values of each frequency and calculating a first standard deviation of the frequency values of all frequencies; and determining the completeness according to the frequency values of each frequency, the maximum edge length, the average edge length, the reference frequency, and the first standard deviation.

[0009] Optionally, the color fastness loss factor of the children's textile product before and after the color fastness test is determined according to the performance integrity of the representative frequency in the hyperspectral image before and after the color fastness test, respectively, including: determining a second standard deviation of the performance integrity of the remaining frequencies except the representative frequency in each frequency, and a maximum difference value of the difference value of the performance integrity corresponding to each two frequencies in each frequency; determining the printing and dyeing quality of the children's textile product before and after the color fastness test according to the average performance integrity of the performance integrity of each frequency, the maximum difference value, the second standard deviation, and the performance integrity of the remaining frequencies except the representative frequency; and determining the color fastness loss factor of the children's textile product before and after the color fastness test according to the printing and dyeing quality of the children's textile product before and after the color fastness test and the representative frequency in the hyperspectral image before and after the color fastness test.

[0010] Optionally, the printing and dyeing quality of the children's textile product before and after the color fastness test is determined according to the average performance integrity of the performance integrity of each frequency, the maximum difference value, the second standard deviation, and the performance integrity of the remaining frequencies except the representative frequency, including: calculating a first ratio between the average performance integrity and the maximum difference value, and a first difference value between the performance integrity of the remaining frequencies except the representative frequency and the average performance integrity; determining a second ratio between each first difference value and the second standard deviation; and determining the printing and dyeing quality according to the first ratio and each second ratio.

[0011] Optionally, the color fastness loss factor of the children's textile product before and after the color fastness test is determined according to the printing and dyeing quality of the children's textile product before and after the color fastness test and the representative frequency in the hyperspectral image before and after the color fastness test, including: calculating a third ratio of the representative frequency in the hyperspectral image of the children's textile product before and after the color fastness test, and an absolute value of a second difference between the printing and dyeing quality of the children's textile product before and after the color fastness test; and determining the color fastness loss factor according to the third ratio and the absolute value of the second difference.

[0012] Optionally, the evaluation value of the color loss of the textile product of the children's textile product in the color fastness test process is determined based on the color fastness loss factor, including: weighting the color fastness loss factors of different detection types of color fastness to obtain a global loss factor; and taking the global loss factor as the evaluation value of the color loss of the textile product of the children's textile product in the color fastness test process.

[0013] Optionally, the weights of the color fastness loss factors of different detection types of color fastness are determined according to the preset emphasis needs of the children's textile product.

[0014] In a second aspect, an embodiment of the present application provides a child textile product color fastness detection system, comprising: an acquisition module configured to acquire hyperspectral images of a child textile product before and after color fastness detection; a determination module configured to determine, according to distribution rules of pixel points at each frequency in the hyperspectral images before and after color fastness detection, completeness of printing and dyeing edges of a dyeing abnormal area at each frequency in the hyperspectral images before and after color fastness detection; the determination module is further configured to determine, according to the completeness before and after color fastness detection and a representative frequency in the hyperspectral images before and after color fastness detection, a color fastness loss factor of the child textile product before and after color fastness detection, wherein the representative frequency is a frequency with the most pixel points in the hyperspectral images; and the determination module is further configured to determine, based on the color fastness loss factor, an evaluation value of color loss of the child textile product in a color fastness test process.

[0015] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory; wherein the memory is configured to store a computer program executable on the processor; and the processor is configured to execute the program stored in the memory to implement steps of the child textile product color fastness detection method mentioned in the first aspect.

[0016] The present application has the following beneficial effects:

[0017] The embodiment of the present application acquires hyperspectral images of a child textile product before and after detection, determines completeness of printing and dyeing edges of a dyeing abnormal area according to distribution rules of pixel points at each frequency, calculates a color fastness loss factor in combination with a representative frequency (a frequency with the most pixel points), and finally obtains an evaluation value of color loss. The embodiment of the present application gets rid of subjective limitations of traditional manual comparison of color cards, overcomes interference of mutual superposition of inherent differences of spectral curves in existing hyperspectral technology and abrasion changes before and after detection of a child textile product, can more accurately capture subtle changes before and after color fastness detection, and makes the color fastness evaluation result of a child textile product more consistent with an actual color fastness condition of the textile product. The embodiment of the present application focuses on completeness of printing and dyeing edges of a dyeing abnormal area at each frequency in a hyperspectral image, analyzes color fastness changes in edge areas in a targeted manner, can more sensitively capture color changes in edges caused by abrasion, and thus more accurately locates areas of color fastness abnormality. The calculation of the color fastness loss factor comprehensively considers completeness and a representative frequency, considers color distribution characteristics at different frequencies, and highlights influence of a frequency with the highest proportion, so that the evaluation value can comprehensively reflect color loss of a textile product in a color fastness test process, and helps to strictly control product quality of a child textile product. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, a brief introduction will be given to the drawings required in the description of the embodiments or the prior art. Obviously, the drawings in the following description only show some embodiments of the present application, and for those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0019] Figure 1 A flow chart of a child textile product color fastness detection method provided by an embodiment of the present application;

[0020] Figure 2 A structural schematic diagram of a child textile product color fastness detection system provided by an embodiment of the present application;

[0021] Figure 3 A structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined purposes, the following describes a child textile product color fastness detection method, device and system according to the present application, the specific implementation, structure, features and effects thereof in detail, as shown in the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0024] The following specifically describes a specific scheme of a child textile product color fastness detection method provided by the present application in combination with the accompanying drawings.

[0025] Embodiment one:

[0026] Please refer to Figure 1 which shows a flow chart of a child textile product color fastness detection method provided by an embodiment of the present application, including:

[0027] Step S101, respectively acquiring hyperspectral images of the child textile product before and after color fastness detection.

[0028] Specifically, the embodiment of the present application first cuts the child textile product to obtain a sample of the child textile product. Since the child textile product has different color materials spliced or a single piece of material printed with different colors, the embodiment of the present application marks the samples of the textile product of each color by an operator. Then, the samples are placed on the bottom plate of the hyperspectral imaging system, the hyperspectral camera is started to shoot images, and the hyperspectral images of the child textile product before color fastness detection are obtained. Then, the samples after shooting are placed in the detection equipment corresponding to the color fastness detection item for color fastness detection. The color fastness detection includes but is not limited to sweat fastness, water fastness, soaping fastness, dry cleaning fastness, artificial light fastness, etc. After the samples after color fastness detection are taken out of the detection equipment, they are placed on the bottom plate of the hyperspectral imaging system again, the hyperspectral camera is started to shoot images, and the hyperspectral images of the child textile product after color fastness detection are obtained.

[0029] For example, as shown in Table 1 below, which shows the color fastness detection items, reagents and materials, detection equipment and preparation methods of the child textile product. As can be seen from Table 1, the color fastness detection items of the child textile product are various, and the reagents and materials, detection equipment and preparation methods used are different. It is worth noting that the color fastness detection items of the child textile product can also be other types, and the embodiment of the present application is not limited to the examples shown in Table 1.

[0030] Table 1 Color fastness detection item experiment

[0031] ;

[0032] In step S102, the performance completeness of the dyeing abnormal area printing edge in each frequency of the hyperspectral images before and after color fastness detection is determined according to the distribution rule of the pixel points in each frequency in the hyperspectral images before and after color fastness detection.

[0033] Specifically, each pixel point of the hyperspectral image has a complete and continuous spectrum, different pixel point positions represent a part of the dyeing area of the child textile sample, and the color of the fabric surface can reflect different wavelengths of light in the visible light band at different reflectivities, thereby forming special spectral data, and different colors can be distinguished by the combination of different reflectivities of different wavelengths. Therefore, the color reference of the current textile sample is judged by the spectral component deviation shown in the hyperspectral image, so as to screen out the influence of different wavelength color changes from the hyperspectral image, and further compare the changes of the spectral components with significant changes before and after color fastness detection, extract the color change metric, and achieve the purpose of accurately evaluating the color fastness.

[0034] Further, as an optional embodiment of the present application, the performance completeness of the printing and dyeing edge of the dyeing abnormal area at each frequency of the hyperspectral images before and after the color fastness detection is determined according to the distribution rules of the pixel points at each frequency of the hyperspectral images before and after the color fastness detection, respectively, including: the hyperspectral images are decomposed by fast Fourier transform to obtain the frequency spectrum of the hyperspectral images; the frequencies in the frequency spectrum are extracted and then inverse Fourier transform is performed to obtain the pixel points at the frequency in the hyperspectral images; the pixel points in the surrounding area of each pixel point at the frequency in the hyperspectral images are merged to obtain a plurality of effective frequency edges at the frequency in the hyperspectral images, and the length of the effective frequency edge is the printing and dyeing edge of the dyeing abnormal area corresponding to the pixel point at the frequency in the hyperspectral images; and the performance completeness is determined according to the edge length of each effective frequency edge and the frequency value of each frequency.

[0035] Specifically, the embodiment of the present application first decomposes the spectral images before and after the color fastness detection of the children's textiles by fast Fourier transform to obtain the frequency spectrum of the spectral lines. Further, the pigment dyeing characteristics shown between the frequency bands are analyzed, wherein the high-frequency characteristics indicate that there are significant difference positions between the pixel points in the high-frequency spectral images, which can represent the dyeing defects existing in the current children's textiles. The uneven dyeing causes the different distribution contents of the color on the surface, so that the extraction of the connected points of the high-frequency change positions is completed to extract the abnormal dyeing area.

[0036] More specifically, the frequencies in the frequency spectrum are sorted in descending order, and the frequencies are extracted in descending order. For any one high-frequency characteristic segment, the frequency band information is extracted and the original information in the high-frequency spectral image is maintained, then the remaining positions in the frequency spectrum are emptied to obtain an updated frequency spectrum graph, and the updated frequency spectrum graph is input into fast inverse Fourier transform to obtain the pixel points in the original hyperspectral image. Further, the distribution fitting and state continuity of the positions of these pixel points in the hyperspectral image are judged.

[0037] Further, the pixel points generated in the hyperspectral image after the inverse transform of the frequencies in the frequency spectrum are denoted as The more closely the distribution of the pixel points is combined, and the fewer the pixel points dispersed around, the more the pixel points at the positions obtained at the current frequency are the pixel points on the boundary of the color distribution abnormal area formed by the dyeing abnormality, and the position of these pixel points can be screened to evaluate the printing and dyeing boundary of the current children's textiles. The embodiment of the present application merges the pixel points in the surrounding 8-neighborhood of the pixel points generated in the hyperspectral image after the inverse transform, that is, each pixel point The pixels in the surrounding 8 neighborhoods at the same frequency are merged to obtain multiple effective frequency edges b, where the edge length of the effective frequency edge represents the length of the adjacent boundary of the coloring abnormal region of the pixel corresponding to each frequency.

[0038] Furthermore, as an optional embodiment of the present invention, determining the performance integrity based on the edge length of each effective frequency edge and the frequency value of each frequency includes: selecting the maximum edge length from the edge lengths of each effective frequency edge, and determining the average edge length of all effective frequency edges; selecting the reference frequency with the most pixels from the frequency values ​​of each frequency and calculating the first standard deviation of the frequency values ​​of all frequencies; and determining the performance integrity based on the frequency value of each frequency, the maximum edge length, the average edge length, the reference frequency, and the first standard deviation.

[0039] Specifically, the embodiments of the present invention use the following formula to calculate the representation completeness:

[0040] ;

[0041] In the above formula, This indicates the completeness of the performance at frequency f. The average edge length represents the edge length of all effective frequency edges. This indicates that the maximum edge length is selected from the edge lengths of each effective frequency edge. The edge length of the effective frequency edge. This indicates the frequency value of each frequency. This represents the frequency value of the reference frequency that corresponds to the most pixels after performing an inverse Fourier transform. This represents the first standard deviation of all frequency values. The maximum value of the edge length of the effective frequency edge corresponding to the current frequency f. With average edge length The larger the ratio between the two, the more complete the effective frequency edge exists in the current frequency, reflecting that the current effective frequency edge can better represent the complete edge of the staining abnormal region. The frequency value is the frequency of the reference frequency with the most corresponding pixels after performing an inverse Fourier transform on the current frequency value f. The difference The standard deviation of the frequency values ​​of all frequencies in the current hyperspectral image. The larger the ratio between them, the more significant the color change represented by the current frequency. This represents the most common color on the surface of current children's textile products. The higher the difference in the current frequency value, the greater the range of color variation represented by the current frequency.

[0042] By the above formula, the performance integrity of the children's textile before color fastness detection and the performance integrity of the children's textile after color fastness detection are calculated respectively.

[0043] In step S103, the color fastness loss factor of the children's textile product before and after color fastness detection is determined according to the performance integrity before and after color fastness detection and the representative frequency in the hyperspectral image before and after color fastness detection, wherein the representative frequency is the frequency with the most pixels in the hyperspectral image.

[0044] Specifically, the dyeing abnormal area existing on the surface of the children's textile product is more likely to appear in the area with uneven dyeing. Therefore, the present embodiment extracts the easy-wear frequency according to the dyeing error variation shown by the performance integrity of the split frequency value, evaluates the dyeing state of the easy-wear frequency before and after color fastness detection, avoids the color unevenness from causing the wear amount of the compensation of the missing color position from the overflow color position, and thus causes the error judgment condition that the surface of the children's textile product directly passes the spectral inspection without producing significant abnormality. Therefore, the present embodiment first judges the uniformity of the printing and dyeing color of the children's textile product by the distribution of the performance integrity, wherein the abnormal color variation in the dyeing area represented by the performance integrity of a single frequency. Therefore, for the current sample of children's textile product, the difference between the performance integrities is judged, the different areas of the color printing and dyeing quality in the current sample of children's textile product are divided, and then the color change shown by the color variation before and after wear is evaluated.

[0045] Further, the printing and dyeing product without defects does not have color change, i.e. the pixel points are completely the same, but there is no perfect quality in the conventional industrial production. The children's textile product often has more stringent requirements on the quality and addition amount of pigments to ensure that the children's textile product does not harm children. Therefore, the present embodiment distinguishes the contribution ratio of the current frequency to the performance integrity to determine the printing and dyeing quality of the children's textile product.

[0046] Further, as an optional embodiment of the present application, the color fastness loss factor of the child textile product before and after the color fastness detection is determined according to the performance completeness of each frequency before and after the color fastness detection and the representative frequency in the hyperspectral image before and after the color fastness detection, comprising: determining the second standard deviation of the performance completeness of the remaining frequencies except the representative frequency and the maximum difference of the difference of the performance completeness of each two frequencies; determining the printing and dyeing quality of the child textile product before and after the color fastness detection according to the average performance completeness of each frequency, the maximum difference, the second standard deviation and the performance completeness of the remaining frequencies except the representative frequency; and determining the color fastness loss factor of the child textile product before and after the color fastness detection according to the printing and dyeing quality of the child textile product before and after the color fastness detection and the representative frequency in the hyperspectral image before and after the color fastness detection.

[0047] Specifically, the embodiment of the present application first takes the frequency with the preset value of performance completeness as the representative frequency , wherein the preset value can be 0. The representative frequency is the frequency with the most measured pixel points in the corresponding child textile product sample, that is, the most common printing and dyeing condition on the surface of the child textile product sample, so that the inclination between the performance completeness of each frequency is illustrated by comparing the performance completeness of the remaining frequencies except the representative frequency with the representative frequency, and the actual printing and dyeing quality of the child textile product sample is evaluated.

[0048] Further, as an optional embodiment of the present application, the printing and dyeing quality of the child textile product before and after the color fastness detection is determined according to the average performance completeness of each frequency, the maximum difference, the second standard deviation and the performance completeness of the remaining frequencies except the representative frequency, comprising: calculating the first ratio between the average performance completeness and the maximum difference and the first difference between the performance completeness of the remaining frequencies except the representative frequency and the average performance completeness; determining the second ratio between each first difference and the second standard deviation; and determining the printing and dyeing quality according to the first ratio and each second ratio.

[0049] Specifically, the embodiment of the present application calculates the printing and dyeing quality by the following formula:

[0050] ;

[0051] In the above formula, represents the printing and dyeing quality. represents the average performance completeness of each frequency. represents the performance completeness of the frequency f. represents the performance completeness of the frequency . represents the performance completeness of the remaining all frequencies except the representative frequency . . Indicates the frequency, except for the frequency. The completeness of the representation of the j-th frequency among all remaining frequencies other than those mentioned above. This represents the second standard deviation. This represents the maximum difference between the performance integrity of any two frequencies across all frequencies. The mean of the performance completeness of all frequencies f corresponding to the current children's textile product sample. The range of representational completeness present across all frequencies f The larger the ratio, the more likely it is that the frequency of the current children's textile product sample is not concentrated in the low-frequency region. In other words, the dyeing of the children's textile product sample is more uneven, with more subtle changes between colors. As a result, the color wear in the subsequent color fastness test is more likely to blur more of the current subtle color changes. Indicates the frequency other than the current frequency. All other frequencies The completeness of the representation by traversing all remaining frequencies Compared with the mean of completeness of expression difference The standard deviation of the completeness of the performance of the remaining frequencies cube of the ratio The larger the positive value of this formula, the greater the color difference between the current children's textile product samples, meaning the greater the range of color variation and the more obvious the differences between colors. When the formula is negative, it indicates that the differences between the surface colors of the children's textile product samples are less obvious, meaning that the printing and dyeing quality of the current children's textile product samples is better.

[0052] Thus, the dyeing and finishing quality of children's textile products before and after color fastness testing are calculated using the above method. For ease of distinction, in this embodiment of the invention, the dyeing and finishing quality of children's textile products before color fastness testing is denoted as z, and the dyeing and finishing quality of children's textile products after color fastness testing is denoted as z. Thus, a dynamic rating of the printing and dyeing quality of current children's textile product samples has been completed. This enables accurate evaluation of the printing and dyeing quality of children's textile product samples with different colors and dyeing qualities. By defining the current printing and dyeing status of textile products, it is easier to accurately judge the color fastness by measuring color changes before and after testing.

[0053] Further, the color variation process targeted in the actual detection is not obvious, and the direct comparison is not accurate. By comparing the printing quality of the sample before and after the detection scheme, the color loss intensity generated in the test process is evaluated, so as to optimize the micro abrasion variation (change of color frequency) of the dyeing pigment before and after the color fastness detection, and to provide a more accurate reference for the evaluation of color fastness. As an optional embodiment of the present application, according to the printing quality of the children's textile product before and after the color fastness detection and the representative frequency in the hyperspectral image before and after the color fastness detection, the color fastness loss factor of the children's textile product before and after the color fastness detection is determined, including: calculating the third ratio of the representative frequency in the hyperspectral image of the children's textile product before and after the color fastness detection, and the absolute value of the second difference between the printing quality of the children's textile product before and after the color fastness detection; determining the color fastness loss factor according to the third ratio and the absolute value of the second difference.

[0054] Specifically, the printing quality of the children's textile product before the color fastness detection and the printing quality of the children's textile product after the color fastness detection are obtained by the embodiment of the present application. After that, the absolute value of the difference between the printing quality of the children's textile product before the color fastness detection and the printing quality of the children's textile product after the color fastness detection is calculated. As the change of the color uniformity of the surface of the children's textile product after the color fastness detection, the representative frequency in the hyperspectral image of the children's textile product before the color fastness detection is recorded as , and the representative frequency in the hyperspectral image of the children's textile product after the color fastness detection is recorded as . As the most common pixel point existing on the surface of the children's textile product before and after the color fastness detection, the representative frequency represents the main dyeing characteristics of the surface of the current children's textile product, and since the performance completeness of all representative frequencies is a preset value, the problem of frequency default when directly judging the difference between the printing quality of the children's textile product before the color fastness detection and the printing quality of the children's textile product after the color fastness detection is avoided.

[0055] Further, the embodiment of the present application specifically calculates the color fastness loss factor of the children's textile product before and after the color fastness detection by the following formula:

[0056] ;

[0057] In the above formula, represents the first ratio of the representative frequency in the hyperspectral image of the children's textile product before and after the color fastness detection, and the absolute value of the second difference between the printing quality of the children's textile product before and after the color fastness detection. a color fastness loss factor under a color fastness detection item. For different color fastness test methods under the color fastness detection item, if the color change is not large, s is close to 1. represents a color fastness test method under a different color fastness detection item. represents a representative frequency of a hyperspectral image of the children's textile product before color fastness detection, represents a representative frequency of a hyperspectral image of the children's textile product after color fastness detection. represents a printing quality of the children's textile product before color fastness detection. represents a printing quality of the children's textile product after color fastness detection.

[0058] In this way, the color fastness loss factor under different color fastness detection items is obtained according to the above formula.

[0059] In step S104, an evaluation value of textile color loss of the children's textile product in the color fastness test process is determined based on the color fastness loss factor.

[0060] Specifically, after the color fastness loss factor under different color fastness detection items is obtained through the above embodiments of the present application, the color fastness loss factors under different color fastness detection items are weighted. As an optional embodiment of the present application, determining the evaluation value of textile color loss of the children's textile product in the color fastness test process based on the color fastness loss factor includes: weighting the color fastness loss factors of different color fastnesses of different detection types to obtain a global loss factor; and taking the global loss factor as the evaluation value of textile color loss of the children's textile product in the color fastness test process. The weights of the color fastness loss factors of different color fastnesses of different detection types are determined according to the preset emphasis requirements of the children's textile product.

[0061] For example, the detection items of the color fastness of the children's textile product in the embodiments of the present application include: sweat fastness u1, water fastness u2, soaping fastness u3, dry cleaning fastness u4, and artificial light fastness u5. According to the preset emphasis requirements, the weights of the sweat fastness u1, the water fastness u2, the soaping fastness u3, the dry cleaning fastness u4, and the artificial light fastness u5 are 0.2, 0.3, 0.1, 0.1, and 0.3, respectively. The global loss factor can be calculated by the following formula:

[0062] ;

[0063] In the above formula, represents the global loss factor. represents the color fastness loss factor of the sweat fastness u1. represents the color fastness loss factor of the water fastness u2. Color fastness loss factor representing color fastness to soaping u3. Color fastness loss factor representing color fastness to dry cleaning u4. Color fastness loss factor representing color fastness to artificial light u5.

[0064] So far, the embodiment of the present application completes the global variation of the color fastness of the children's textile product, and takes the global loss factor as the evaluation value of the color loss of the textile product during the color fastness test process. After obtaining the evaluation value of the color loss of the textile product, the color loss evaluation value can be combined with the relevant standards of the color fastness of the children's textile product (such as the color fastness grade division threshold value specified in the national standard and the industry standard) to be included in the preset grade determination system. For example, if the evaluation value is lower than a certain threshold value, it corresponds to the highest color fastness grade, indicating that the color loss of the textile product during the test process is extremely small, and it can effectively resist the wear under the special behavior mode of children; if the evaluation value is in a certain interval, it corresponds to the medium color fastness grade, indicating that the textile product has a certain degree of color loss risk; if the evaluation value exceeds the upper threshold value, it is determined as the low color fastness grade, indicating that the textile product cannot meet the safety requirements for children's use.

[0065] The embodiment of the present application obtains the hyperspectral images before and after the detection of the children's textile product respectively, determines the printing and dyeing edge performance completeness based on the distribution rule of the pixel points at each frequency, combines the representative frequency (the frequency with the most pixel points) to calculate the color fastness loss factor, and finally obtains the color loss evaluation value. It gets rid of the subjective limitations of traditional manual comparison of color cards, and overcomes the interference of the mutual superposition of the inherent differences of the spectral curve in the existing hyperspectral technology and the wear variation before and after the detection of the children's textile product. It can more accurately capture the subtle changes before and after the color fastness detection, so that the color fastness evaluation result of the children's textile product is more in line with the actual color fastness condition of the textile product. Moreover, the embodiment of the present application focuses on the printing and dyeing edge performance completeness of the dyeing abnormal area at each frequency in the hyperspectral image, analyzes the color fastness change in the edge area, and can more sensitively capture the color change of the edge caused by wear, so as to more accurately locate the area of color fastness abnormality. The calculation of the color fastness loss factor comprehensively considers the color distribution characteristics at different frequencies and highlights the influence of the frequency with the highest proportion, so that the evaluation value can fully reflect the color loss of the textile product during the color fastness test process, which helps to strictly control the product quality of the children's textile product.

[0066] Embodiment two:

[0067] Corresponding to the color fastness detection method of the children's textile product provided by the above embodiment, based on the same technical concept, the embodiment of the present application also provides a color fastness detection system for children's textile products, which is used to execute the color fastness detection method of the children's textile product,Figure 2 A structural schematic diagram of a child textile product color fastness detection system provided by an embodiment of the present application is shown in FIG. 2. Figure 2 The child textile product color fastness detection system 200 includes an acquisition module 201 configured to acquire hyperspectral images of a child textile product before and after color fastness detection, respectively; a determination module 202 configured to determine, according to distribution rules of pixel points at each frequency in the hyperspectral images before and after color fastness detection, respectively, the performance completeness of printing and dyeing edges of a dyeing abnormal area at each frequency in the hyperspectral images before and after color fastness detection; the determination module 202 is further configured to determine, according to the performance completeness before and after color fastness detection and a representative frequency in the hyperspectral images before and after color fastness detection, respectively, a color fastness loss factor of the child textile product before and after color fastness detection, wherein the representative frequency is a frequency with the most pixel points in the hyperspectral images; and the determination module 202 is further configured to determine, based on the color fastness loss factor, an evaluation value of color loss of the child textile product in a color fastness test process.

[0068] The embodiment of the present application acquires the hyperspectral images of the child textile product before and after detection, respectively, determines the performance completeness of the printing and dyeing edges based on the distribution rules of the pixel points at each frequency, calculates the color fastness loss factor in combination with the representative frequency (the frequency with the most pixel points), and finally obtains the evaluation value of the color loss. The embodiment of the present application gets rid of the subjective limitations of the traditional manual comparison of color cards, overcomes the interference of the mutual superposition of the inherent differences of the spectral curves and the wear changes before and after the detection of the child textile product in the existing hyperspectral technology, can more accurately capture the subtle changes before and after the color fastness detection, and makes the evaluation result of the color fastness of the child textile product more consistent with the actual color fastness condition of the textile product. The embodiment of the present application focuses on the performance completeness of the printing and dyeing edges of the dyeing abnormal area at each frequency in the hyperspectral images, analyzes the embodiment of the color fastness changes in the edge area, can more sensitively capture the color changes of the edge caused by wear, and thus more accurately locates the area of the color fastness abnormality. The calculation of the color fastness loss factor comprehensively considers the performance completeness and the representative frequency, considers the color distribution characteristics at different frequencies, highlights the influence of the frequency with the highest proportion, and makes the evaluation value fully reflect the color loss of the textile product in the color fastness test process, which is helpful to strictly control the product quality of the child textile product.

[0069] Embodiment three

[0070] Corresponding to the child textile product color fastness detection method provided by the above embodiment, based on the same technical concept, the embodiment of the present application further provides an electronic device for executing the child textile product color fastness detection method, Figure 3 A structural schematic diagram of another electronic device provided by an embodiment of the present application is shown in FIG. 3. Figure 3The electronic device can have a large difference due to different configurations or performances, and can include one or more processors 301 and memories 302 for storing computer programs executable on the processors 301 and the processors 301 for executing the programs stored on the memories 302 to implement the above Figure 1 each step in the method embodiments. The memories 302 can be temporary or persistent memories. The application programs stored in the memories 302 can include one or more modules (not shown in the figure), each of which can include a series of computer executable instructions in the electronic device.

[0071] Further, the processors 301 can be configured to communicate with the memories 302 to execute a series of computer executable instructions in the memories 302 on the electronic device. The electronic device can further include one or more power supplies 303, one or more wired or wireless network interfaces 304, one or more input / output interfaces 305, and one or more keyboards 306.

[0072] In particular, in the embodiment, the electronic device includes a processor, a communication interface, a memory, and a communication bus; the processor, the communication interface, and the memory communicate with each other through the bus; the memory is used to store computer programs; the processor is used to execute the programs stored on the memory to implement the above Figure 1 each step in the method embodiments, and has the beneficial effects of the above method embodiments. To avoid repetition, the embodiments of the present application will not be described here.

[0073] It should be noted that the electronic device provided by the embodiments of the present application is based on the same application concept as the child textile product color fastness detection method provided by the embodiments of the present application, so the specific implementation of this embodiment can be referred to the implementation of the aforementioned child textile product color fastness detection method, and has the same or similar beneficial effects, and the repeated parts will not be described here.

[0074] It should be noted that the above sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0075] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0076] The embodiment of the present application further provides a computer readable storage medium, the computer readable medium stores one or more programs, and the one or more programs, when executed by an electronic device comprising a plurality of application programs, cause the electronic device to perform the method as shown in the embodiment of the present application. Figure 1 The method disclosed in the embodiment and the functions and advantages of each method in the foregoing method embodiments are not repeated here.

[0077] The computer readable storage medium includes a read-only memory (ROM), a random access memory (RAM), a magnetic disc or an optical disc, etc.

Claims

1. A method for testing the color fastness of children's textile products, characterized in that, include: Hyperspectral images of children's textile products before and after color fastness testing were obtained. Based on the distribution pattern of pixels at each frequency in the hyperspectral images before and after the color fastness test, the integrity of the printing edge of the dyeing abnormal area at each frequency in the hyperspectral images before and after the color fastness test is determined. The color fastness loss factor of the children's textile product before and after the color fastness test is determined based on the performance integrity before and after the color fastness test and the representative frequency in the hyperspectral image before and after the color fastness test. The representative frequency is the frequency with the most pixels in the hyperspectral image. The evaluation value of the color loss of the children's textile products during the color fastness test is determined based on the color fastness loss factor.

2. The method for testing color fastness of children's textile products according to claim 1, characterized in that, The determination of the integrity of the printing edge representation of the abnormal dyeing area at each frequency in the hyperspectral images before and after the color fastness test, based on the pixel distribution patterns at each frequency in the hyperspectral images before and after the color fastness test, includes: The hyperspectral image is decomposed by Fast Fourier Transform to obtain the spectrum of the hyperspectral image; After extracting the frequencies from the spectrum, an inverse Fourier transform is performed to obtain the pixels at the specified frequencies in the hyperspectral image. The pixels surrounding each pixel at a given frequency in the hyperspectral image are merged to obtain multiple effective frequency edges at that frequency in the hyperspectral image. The length of each effective frequency edge is the staining edge of the staining abnormal region corresponding to the pixel at that frequency in the hyperspectral image. The performance integrity is determined based on the edge length of each effective frequency edge and the frequency value of each frequency.

3. The method for testing color fastness of children's textile products according to claim 2, characterized in that, Determining the performance integrity based on the edge length of each effective frequency edge and the frequency value of each frequency includes: Select the maximum edge length from the edge lengths of each effective frequency edge, and determine the average edge length of all effective frequency edges; Select the reference frequency with the largest number of pixels from the frequency values ​​of each frequency and calculate the first standard deviation of the frequency values ​​of all frequencies; The performance integrity is determined based on the frequency values ​​of each frequency, the maximum edge length, the average edge length, the reference frequency, and the first standard deviation.

4. The method for testing the color fastness of children's textile products according to claim 1, characterized in that, The determination of the colorfastness loss factor of the children's textile products before and after colorfastness testing, based on the integrity of the product's appearance before and after colorfastness testing and the representative frequencies in the hyperspectral images before and after colorfastness testing, includes: Determine the second standard deviation of the performance integrity of the remaining frequencies other than the representative frequency in each frequency range, and the maximum difference between the performance integrity of each pair of frequencies in each frequency range. The printing and dyeing quality of the children's textile products before and after color fastness testing is determined based on the average performance integrity of each frequency, the maximum difference, the second standard deviation, and the performance integrity of the remaining frequencies other than the representative frequency. Based on the printing and dyeing quality of the children's textile products before and after the color fastness test, and the representative frequencies in the hyperspectral images before and after the color fastness test, the color fastness loss factor of the children's textile products before and after the color fastness test is determined respectively.

5. The method for testing color fastness of children's textile products according to claim 4, characterized in that, The determination of the printing and dyeing quality of the children's textile products before and after colorfastness testing, based on the average performance integrity of each frequency, the maximum difference, the second standard deviation, and the performance integrity of the remaining frequencies other than the representative frequency, includes: Calculate a first ratio between the average performance completeness and the maximum difference, and a first difference between the performance completeness of the frequencies other than the representative frequency and the average performance completeness; Determine a second ratio between each of the first differences and the second standard deviation; The dyeing quality is determined based on the first ratio and each of the second ratios.

6. The method for testing color fastness of children's textile products according to claim 4, characterized in that, The determination of the colorfastness loss factor of the children's textile products before and after colorfastness testing, based on the dyeing quality of the products before and after colorfastness testing and the representative frequencies in the hyperspectral images before and after colorfastness testing, includes: Calculate the third ratio of the representative frequencies in the hyperspectral images of the children's textile products before and after the color fastness test, and the absolute value of the second difference between the printing and dyeing quality of the children's textile products before and after the color fastness test. The color fastness loss factor is determined based on the absolute value of the third ratio and the second difference.

7. The method for testing color fastness of children's textile products according to claim 1, characterized in that, The assessment value for determining the color loss of the children's textile products during the color fastness test based on the color fastness loss factor includes: The color fastness loss factors for different test types are weighted to obtain the global loss factor; The global loss factor is used as an evaluation value for the color loss of the children's textile products during the color fastness test.

8. The method for testing color fastness of children's textile products according to claim 7, characterized in that, The weights of the color fastness loss factors for different types of color fastness testing are determined based on the preset emphasis requirements of the children's textile products.

9. A color fastness testing system for children's textile products, characterized in that, include: The acquisition module is used to acquire hyperspectral images of children's textile products before and after color fastness testing. The determination module is used to determine the integrity of the printing edge of the dyeing abnormal area at each frequency of the hyperspectral images before and after the color fastness test, based on the distribution pattern of pixels at each frequency in the hyperspectral images before and after the color fastness test. The determining module is further configured to determine the color fastness loss factor of the children's textile product before and after the color fastness test based on the performance integrity before and after the color fastness test and the representative frequency in the hyperspectral image before and after the color fastness test, wherein the representative frequency is the frequency with the most pixels in the hyperspectral image. The determining module is also used to determine the evaluation value of the color loss of the children's textile products during the color fastness test based on the color fastness loss factor.

10. An electronic device, characterized in that, include: Processor and memory; wherein the memory is used to store computer programs that can run on the processor; A processor is used to execute a program stored in memory to implement the steps of the color fastness testing method for children's textile products as described in any one of claims 1-8.

Images