A fluorescent staining system and method for fabric printing and dyeing

Abstract

The present invention discloses a fluorescence contamination system and method for fabric printing and dyeing, belonging to the technical field of textile printing and dyeing. The present invention solves the problem that the existing method is prone to cause detection personnel to inhale harmful substances. By using an area array camera to obtain the current fluorescence contamination image of the fabric printing and dyeing, the image is subjected to region division and noise reduction processing; the Sobel algorithm is used to extract the edge pixels of the fluorescence contamination area in the fluorescence contamination image of the fabric printing and dyeing, and the total area of the fluorescence contamination image of the fabric printing and dyeing and the actual area of the fluorescence contamination area are calculated; the proportion of the fluorescence contamination area occupying the total area of the fluorescence contamination image of the fabric printing and dyeing and its belonging level are judged, and a warning sound is issued when the contamination warning threshold is exceeded to remind the client to solve the problem in time, thereby avoiding the disadvantages of the detection personnel staying in the detection workshop for a long time, and optimizing the practicability and safety of the existing fluorescence contamination method.

Description

Technical Field

[0001] The invention relates to the technical field of textile printing and dyeing, and in particular to a fluorescent staining system and method for fabric printing and dyeing. Background Art

[0002] The textile process in the production chain is cumbersome and the additives are complex, especially for functional textiles. With the improvement of quality of life and the enhancement of health awareness, people's requirements for textile quality are constantly increasing, and the restriction and detection of harmful substances in textiles are particularly important. Fabric printing and dyeing fluorescent contamination is a common problem in the textile printing and dyeing process. It refers to the phenomenon that non-fluorescent fabrics (mainly white cloth and light-colored cloth) are stained with fluorescent substances during the processing process; this situation usually occurs when the relevant machines and equipment and the environment are not thoroughly cleaned during the processing, or the raw materials are not properly distinguished, resulting in fluorescent substances being stained on non-fluorescent fabrics; fluorescent brighteners are an important type of chemical additives that can effectively improve the whiteness of the product matrix.

[0003] The existing ultraviolet lamp irradiation observation method is one of the most commonly used methods. Its principle is based on the fact that fluorescent brighteners can absorb ultraviolet light and emit visible blue-purple fluorescence. The inspectors need to observe the fluorescence on the surface of the sample with the naked eye on site for identification. This method is simple and easy, but the inspectors need to stay in the inspection workshop for a long time, and the respiratory tract is prone to inhaling certain harmful substances from fabrics and printing and dyeing chemicals, which affects the physical fitness of the workers, thereby reducing the practicality of the existing fluorescent contamination method.

[0004] Therefore, the existing demand is not met, and we propose a fluorescent staining system and method for fabric printing and dyeing. Summary of the invention

[0005] The object of the present invention is to provide a fluorescent contamination system and method for fabric printing and dyeing, which obtains the current fabric printing and dyeing fluorescent contamination image picture through an area array camera, divides the picture into regions and performs noise reduction processing; adopts the Sobel algorithm to respectively extract the overall edge pixels of the fabric printing and dyeing fluorescent contamination image picture and the edge pixels of the fluorescent contamination area, and calculates the overall area of ​​the fabric printing and dyeing fluorescent contamination image picture and the actual area of ​​the fluorescent contamination area; judges the proportion of the fluorescent contamination area in the overall area of ​​the fabric printing and dyeing fluorescent contamination image picture and its grade, and sends a warning sound to remind the client to solve the problem in time when the contamination warning threshold is exceeded, thereby avoiding the disadvantage that the inspection personnel are in the inspection workshop for a long time, optimizing the practicality and safety of the existing fluorescent contamination method, and solving the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A fluorescence contamination system for fabric printing and dyeing, comprising:

[0008] An image acquisition unit for

[0009] Taking image data of the fabric to be detected through an area array camera, obtaining a fabric printing and dyeing fluorescence contamination image, and transmitting the fabric printing and dyeing fluorescence contamination image to the image analysis unit for analysis and processing in real time based on 5G communication technology;

[0010] An image processing unit for

[0011] Performing filtering and noise reduction processing on the fabric printing and dyeing fluorescence contamination image to obtain a fabric printing and dyeing fluorescence contamination image after noise reduction processing; and performing tone adjustment on the current fabric printing and dyeing fluorescence contamination image to clarify the fluorescence contamination area in the fabric printing and dyeing fluorescence contamination image;

[0012] A contamination calculation unit for

[0013] Segmenting and extracting the fluorescence contamination area in the fabric printing and dyeing fluorescence contamination image through an edge calculation method, and calculating the total area of the fabric printing and dyeing fluorescence contamination image and the area of the fluorescence contamination area map;

[0014] A contamination analysis unit for

[0015] Analyzing the proportion of the area of the fluorescence contamination area map in the total area of the fabric printing and dyeing fluorescence contamination image, and judging the severity of the fluorescence contamination after fabric printing and dyeing according to the current situation;

[0016] A human-computer interaction platform for

[0017] Displaying the operation interface of the fluorescence contamination system, and real-time showing the processing progress of the fabric printing and dyeing fluorescence contamination image and its fluorescence contamination processing result to the client.

[0018] Furthermore, the camera array module includes:

[0019] A static variable determination module for obtaining the fabric size, fabric thickness and light source position of the fabric to be detected, and establishing static scene variables based on the specific characteristics of the fabric size, fabric thickness and light source position;

[0020] A dynamic variable determination module for obtaining the activity characteristics within the camera range of the fabric to be detected, and establishing dynamic scene variables based on the activity characteristics;

[0021] A coordinate determination module for establishing a three-dimensional camera scene based on the static scene variables and dynamic scene variables, determining the coordinate positions of the static scene variables in the three-dimensional camera scene, and determining the coordinate activity range of the dynamic scene variables in the three-dimensional camera scene;

[0022] A set determination module, which is used to design an initial camera array set of area array cameras based on the imaging range characteristics of area array cameras and the coordinate positions of static scene variables in a three-dimensional imaging scene, in combination with the number of area array cameras.

[0023] A weight determination module, which is used to set the variable weight of static scene variables in a three-dimensional imaging scene based on the photography difficulty, and set the coordinate weight of the coordinate position of the fabric area based on the fabric visual characteristics.

[0024] A set processing module, which is used to determine the imaging weighted accuracy of the fabric to be detected by combining the variable weight and the coordinate weight when imaging according to each initial camera array in the initial camera array set, and select a target camera array set with an imaging weighted accuracy greater than the preset accuracy from the initial camera array set.

[0025] An array determination module, which is used to determine the dynamic area of fabric detection based on the coordinate activity range of dynamic scene variables in a three-dimensional imaging scene, determine the detection frequency and detection angle of each camera array in the target camera array set for the dynamic area, and select the camera array with the best comprehensive detection frequency and detection angle as the target camera array.

[0026] A shooting module, which is used to shoot the fabric to be detected by using the target camera array to obtain a fabric printing fluorescence contamination image.

[0027] Further, the image acquisition unit includes

[0028] An imaging layout module, which is used to ensure that a complete fabric printing fluorescence contamination image is obtained at one time in a short time through a camera array composed of multiple area array cameras horizontally.

[0029] A wireless transmission module, which is used to transmit the fabric printing fluorescence contamination image to the image processing unit in real time through 5G communication technology for image preprocessing to obtain a fabric printing fluorescence contamination image with clear pixels.

[0030] Further, the image processing unit includes

[0031] A region division module, which is used to mark the fabric fluorescence contamination region and the fabric non-fluorescence contamination region with different colors in the fabric printing fluorescence contamination image to be recognized by using Photoshop software, so as to distinguish different image components in the fabric printing fluorescence contamination image.

[0032] A filtering processing module, which is used to perform weighted average filtering processing on the fabric printing fluorescence contamination image by using the Gaussian filtering method to reduce the residual noise in the fabric printing fluorescence contamination image.

[0033] Further, the contamination calculation unit includes

[0034] An edge calculation module for performing edge detection on the fluorescent contamination area in the fabric printing fluorescent contamination image using the Sobel algorithm, finding the number of all pixel points within the edge of the fluorescent contamination area, and calculating the actual area of the fluorescent contamination area;

[0035] A proportion calculation module for calculating the proportion of the actual area of the fluorescent contamination area in the total area of the fabric printing fluorescent contamination image, and obtaining the pollution proportion of the fluorescent contamination area in the fabric printing fluorescent contamination image.

[0036] Further, the edge calculation module includes:

[0037] A pixel point analysis module for obtaining the suspicious edge area of the fluorescent contamination area and using the Sobel algorithm to calculate the image gray value and image gradient value of each pixel point in the suspicious edge area of the fabric printing fluorescent contamination image. The calculation formulas are as follows:

[0038]

[0039] Where, G represents the image gray value of the pixel point, θ represents the image gradient value of the pixel point, Gx represents the image gray value of the pixel point detected horizontally, and Gy represents the image gray value of the pixel point detected vertically;

[0040] A pixel point evaluation module for calculating the comprehensive score of each pixel point based on the image gray value and image gradient value of each pixel point according to the following formula;

[0041]

[0042] Where, K represents the comprehensive score of the pixel point, σ1 represents the proportion of the image gray value in the determination of the edge point, and σ2 represents the proportion of the image gradient value in the determination of the edge point;

[0043] An area calculation module for selecting the pixel points with a comprehensive score greater than the preset score as target pixel points and calculating the actual area of the fluorescent contamination area based on the number of target pixel points.

[0044] Further, before calculating the actual area of the fluorescent contamination area in the fabric printing fluorescent contamination image, the edge calculation module needs to determine the length and width of the fabric printing fluorescent contamination image and calculate the total area value of the fabric printing fluorescent contamination image.

[0045] Further, the contamination analysis unit includes

[0046] A level establishment module, which is used to establish a corresponding pollution proportion level mechanism according to the proportion of the actual area of the fluorescent contamination area in the total area of the fabric printing and dyeing fluorescent contamination image picture;

[0047] A level evaluation module, which is used to judge the level to which the area proportion of the fluorescent contamination area in the current fabric printing and dyeing fluorescent contamination image picture belongs based on the pollution proportion level mechanism, and obtain the severity of the fluorescent contamination in the current fabric printing and dyeing fluorescent contamination image picture based on this proportion level;

[0048] A result output module, which is used to display the severity of the fluorescent contamination in the current fabric printing and dyeing fluorescent contamination image picture on the human-computer interaction platform through 5G communication technology to assist the client in viewing.

[0049] Further, the human-computer interaction platform includes

[0050] A contamination warning module, which is used to set a fluorescent contamination warning threshold. When the severity of the fluorescent contamination in the current fabric printing and dyeing fluorescent contamination image picture exceeds the warning threshold, a warning sound is emitted through a buzzer to remind the client to solve it in time;

[0051] A data storage module, which is used to save the processed fabric printing and dyeing fluorescent contamination image pictures and their fluorescent contamination calculation results in time series.

[0052] A fluorescent contamination method for fabric printing and dyeing, including the following steps:

[0053] S1. Obtain the current fabric printing and dyeing fluorescent contamination image picture by deploying a planar array camera array;

[0054] S2. Divide the area of the current fabric printing and dyeing fluorescent contamination image picture, and extract the fabric fluorescent contamination area and the fabric non-fluorescent contamination area through different hues;

[0055] S3. Perform filtering processing on the fabric printing and dyeing fluorescent contamination image picture after area division to eliminate the noise in the picture;

[0056] S4. First calculate the total area of the fabric printing and dyeing fluorescent contamination image picture using the Sobel algorithm, and then calculate the actual area of the fluorescent contamination area in the picture according to the same steps;

[0057] S5. Calculate the proportion of the actual area of the fluorescent contamination area in the total area of the fabric printing and dyeing fluorescent contamination image picture;

[0058] S6. Preset a proportion level mechanism and a contamination warning threshold. First, determine the level to which the current proportion of the fluorescent contamination area belongs, and transmit this signal to the human-machine interaction platform for display; the human-machine interaction platform compares the current proportion level of the fluorescent contamination with the contamination warning threshold, and emits a warning sound when the threshold is exceeded to remind the client to solve the problem in time.

[0059] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0060] In the present invention, a surface array camera is used to obtain the current fabric printing and dyeing fluorescent contamination image picture, and then the picture is subjected to region division and noise reduction processing to obtain a clearer fabric printing and dyeing fluorescent contamination image picture; the Sobel algorithm is used to extract the edge pixels of the fluorescent contamination area in the fabric printing and dyeing fluorescent contamination image picture, and the total area of the fabric printing and dyeing fluorescent contamination image picture and the actual area of the fluorescent contamination area are calculated; the proportion of the fluorescent contamination area occupying the total area of the fabric printing and dyeing fluorescent contamination image picture and its belonging level are judged, and a warning sound is emitted when the contamination warning threshold is exceeded, so as to remind the client to solve the fluorescent contamination problem in this fabric in time, thus avoiding the disadvantages of the long-term stay of the detection personnel in the detection workshop, and optimizing the practicability and safety of the existing fluorescent contamination method. Description of the Drawings

[0061] Figure 1 It is a composition diagram of the fluorescent contamination system for fabric printing and dyeing of the present invention;

[0062] Figure 2 It is a flow chart of the fluorescent contamination method for fabric printing and dyeing of the present invention. Detailed Embodiments

[0063] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0064] In order to solve the technical problem that the current ultraviolet lamp irradiation observation method is one of the most commonly used methods for judging fluorescent contamination in fabric printing and dyeing. Its principle is based on the fact that fluorescent whitening agents can absorb ultraviolet light and emit visible blue-violet fluorescence. Detection personnel need to observe the fluorescence on the surface of the sample with the naked eye on site for identification. This method is simple and easy to implement, but the detection personnel need to stay in the inspection workshop for a long time, and the respiratory tract is likely to inhale certain harmful substances in the fabric and printing and dyeing chemicals, which will affect the physical quality of the workers, thus reducing the practicability of the existing fluorescent contamination method. Please refer to Figure 1 - Figure 2 This embodiment provides the following technical solutions:

[0065] A fluorescence contamination system for fabric printing and dyeing, comprising:

[0066] An image acquisition unit, used for

[0067] Taking image data of the fabric to be detected through an area array camera, obtaining a fabric printing and dyeing fluorescence contamination image picture, and real-time transmitting the fabric printing and dyeing fluorescence contamination image picture to the image analysis unit for analysis and processing based on 5G communication technology; specifically, the area array camera mainly uses continuous, planar scanning light to realize the detection of the fabric, can obtain a complete fabric image at one time, and can collect images in time; it has the advantages of simple structure, easy use and maintenance, and the number of pixels and pixel size can be adjusted according to needs to adapt to different shooting requirements.

[0068] The image acquisition unit includes:

[0069] A camera array module, used to ensure obtaining a complete fabric printing and dyeing fluorescence contamination image picture at one time in a short time through a camera array composed of multiple area array cameras horizontally;

[0070] In this embodiment, for example: selecting a certain room in a certain printing and dyeing as a fluorescence contamination detection room after fabric printing and dyeing, and horizontally arranging multiple camera placement points in the room to form a camera array for taking fabric printing and dyeing fluorescence contamination image pictures.

[0071] A wireless transmission module, used to real-time transmit the fabric printing and dyeing fluorescence contamination image picture to the image processing unit for image preprocessing through 5G communication technology to obtain a fabric printing and dyeing fluorescence contamination image picture with clear pixels.

[0072] An image processing unit, used for

[0073] Performing filtering and noise reduction processing on the fabric printing and dyeing fluorescence contamination image picture to obtain a fabric printing and dyeing fluorescence contamination image picture after noise reduction processing; and performing tone adjustment on the current fabric printing and dyeing fluorescence contamination image picture to clarify the fluorescence contamination area in the fabric printing and dyeing fluorescence contamination image picture; the image processing unit includes:

[0074] The region division module is used to use Photoshop software to mark the fabric fluorescence contamination area and the fabric non-fluorescence contamination area with different colors in the fabric printing fluorescence contamination image to be recognized, so as to distinguish different image components in the fabric printing fluorescence contamination image. Specifically, by loading Photoshop CS6 software in the human-computer interaction platform and opening the fabric printing fluorescence contamination image in this software, select a part of the fabric non-fluorescence contamination area by color, and click Select → Color Range; then open the Color Range setting window and default to use the Eyedropper tool; then click on the fabric fluorescence contamination area, and the fabric non-fluorescence contamination area will be shown as selected. At this time, the fabric non-fluorescence contamination area is shown as white; then click to use the Add to Sample tool and click on the fabric fluorescence contamination area to add it to the selection area; click OK, and it can be seen from the marching ants that both areas have become the selection areas; according to the above operations, the fabric non-fluorescence contamination area in the fabric printing fluorescence contamination image can be marked with the same color, so that the fabric fluorescence contamination area and the fabric non-fluorescence contamination area form different background colors, which is convenient to distinguish their area attributes.

[0075] The filtering processing module is used to perform weighted average filtering processing on the fabric printing fluorescence contamination image by using the Gaussian filtering method to reduce the remaining noise in the fabric printing fluorescence contamination image. Specifically, Gaussian filtering is a linear smoothing filtering technology, which is realized by the process of weighted averaging the entire image, and the value of each pixel point is obtained by weighted averaging its own and other pixel values in the neighborhood; this processing method can effectively smooth the image and reduce noise, especially when dealing with Gaussian noise, the effect is remarkable; and the calculation process is relatively simple and fast, so the Gaussian filtering method is very suitable for real-time image processing after fabric printing.

[0076] In one embodiment, the camera array module includes:

[0077] The static variable determination module is used to obtain the fabric size, fabric thickness and light source position of the fabric to be detected, and establish static scene variables based on the specific characteristics of the fabric size, fabric thickness and light source position;

[0078] The dynamic variable determination module is used to obtain the activity characteristics within the camera range of the fabric to be detected and establish dynamic scene variables based on the activity characteristics;

[0079] The coordinate determination module is used to establish a three-dimensional camera scene based on the static scene variables and dynamic scene variables, determine the coordinate position of the static scene variables in the three-dimensional camera scene, and determine the coordinate activity range of the dynamic scene variables in the three-dimensional camera scene;

[0080] A collection determination module, configured to design an initial camera array collection of area array cameras based on the imaging range characteristics of the area array cameras and the coordinate positions of static scene variables in a three-dimensional imaging scene, in combination with the number of area array cameras;

[0081] A weight determination module, configured to set the variable weight of static scene variables in a three-dimensional imaging scene based on the photography difficulty, and set the coordinate weight of the coordinate position of the fabric area based on the fabric visual characteristics;

[0082] A collection processing module, configured to determine the imaging weighted accuracy of the fabric to be detected by combining the variable weight and the coordinate weight when imaging according to each initial camera array in the initial camera array collection, and select a target camera array collection with an imaging weighted accuracy greater than a preset accuracy from the initial camera array collection;

[0083] An array determination module, configured to determine the dynamic area for fabric detection based on the coordinate activity range of dynamic scene variables in a three-dimensional imaging scene, determine the detection frequency and detection angle of each camera array in the target camera array collection for the dynamic area, and select the camera array with the best comprehensive detection frequency and detection angle as the target camera array;

[0084] A shooting module, configured to use the target camera array to shoot the fabric to be detected to obtain a fabric printing fluorescence contamination image.

[0085] In this embodiment, the activity characteristics within the imaging range of the fabric to be detected include flipping and moving the fabric, etc.

[0086] In this embodiment, determining the imaging weighted accuracy of the fabric to be detected means that the larger the coordinate weight, the more imaging captures are made at that position, and the higher the variable weight, the greater the impact on the imaging of the fabric area to be detected, and the higher the corresponding weighted accuracy.

[0087] In this embodiment, the lower the photography difficulty of the static scene variables, the higher the corresponding variable weight.

[0088] The beneficial effects of the above design are as follows: Obtain the fabric size, fabric thickness, and light source position of the fabric to be detected, and establish static scene variables based on the specific characteristics of the fabric size, fabric thickness, and light source position; obtain the activity characteristics within the camera range of the fabric to be detected, and establish dynamic scene variables based on the activity characteristics; establish a three-dimensional camera scene based on the static scene variables and dynamic scene variables, determine the coordinate position of the static scene variables in the three-dimensional camera scene, and determine the coordinate activity range of the dynamic scene variables in the three-dimensional camera scene; design the initial camera array set of the area array cameras based on the camera range characteristics of the area array cameras and the coordinate position of the static scene variables in the three-dimensional camera scene, in combination with the number of area array cameras; set the variable weight of the static scene variables in the three-dimensional camera scene based on the shooting difficulty, and set the coordinate weight of the coordinate position of the fabric area based on the fabric visual characteristics; determine the shooting weighted accuracy of the fabric to be detected by combining the variable weight and the coordinate weight when shooting according to each initial camera array in the initial camera array set, and select the target camera array set with a shooting weighted accuracy greater than the preset accuracy from the initial camera array set; determine the dynamic area of fabric detection based on the coordinate activity range of the dynamic scene variables in the three-dimensional camera scene, determine the detection frequency and detection angle of each camera array in the target camera array set for the dynamic area, and select the camera array with the best comprehensive detection frequency and detection angle as the target camera array; use the target camera array to shoot the fabric to be detected to obtain a fabric printing and dyeing fluorescence contamination image, realize the precise arrangement of the camera array, ensure the accuracy of the obtained fabric printing and dyeing fluorescence contamination image, and provide a basis for subsequent fluorescence contamination detection.

[0089] The contamination calculation unit is used for

[0090] segment and extract the fluorescence contamination area in the fabric printing and dyeing fluorescence contamination image through an edge calculation method, and calculate the total area of the fabric printing and dyeing fluorescence contamination image and the area of its fluorescence contamination area map; the contamination calculation unit includes:

[0091] The edge calculation module is used to perform edge detection on the fluorescence contamination area in the fabric printing and dyeing fluorescence contamination image using the Sobel algorithm, find the number of all pixel points within the edge of the fluorescence contamination area, and calculate the actual area of the fluorescence contamination area; secondly, before calculating the actual area of the fluorescence contamination area in the fabric printing and dyeing fluorescence contamination image, the edge calculation module needs to determine the length and width of the fabric printing and dyeing fluorescence contamination image and calculate the total area value of the fabric printing and dyeing fluorescence contamination image;

[0092] In one embodiment, the edge calculation module includes:

[0093] The pixel point analysis module is used to obtain the suspicious edge area of the fluorescent contamination area, and uses the Sobel algorithm to calculate the image gray value and image gradient value of each pixel point in the suspicious edge area of the fabric printing and dyeing fluorescent contamination image. The calculation formulas are as follows:

[0094]

[0095] Among them, G represents the image gray value of the pixel point, θ represents the image gradient value of the pixel point, Gx represents the image gray value detected horizontally by the pixel point, and Gy represents the image gray value detected vertically by the pixel point;

[0096] The pixel point evaluation module is used to calculate the comprehensive score of each pixel point based on the image gray value and image gradient value of each pixel point according to the following formula;

[0097]

[0098] Among them, K represents the comprehensive score of the pixel point, σ1 represents the proportion of the image gray value in the determination of the edge point, and σ2 represents the proportion of the image gradient value in the determination of the edge point;

[0099] The area calculation module is used to select the pixel points with a comprehensive score greater than the preset score as the target pixel points, and calculate the actual area of the fluorescent contamination area based on the number of target pixel points.

[0100] In this embodiment, the sum of the proportion of the image gray value in the determination of the edge point and the proportion of the image gradient value in the determination of the edge point is 1, and σ1 > σ2.

[0101] In this embodiment, the suspicious edge area is an area that can be used as an edge and needs to be further determined.

[0102] In this embodiment, the comprehensive score of the pixel point is used to represent the probability that the pixel point can be used as an edge point. The higher the comprehensive score, the higher the probability.

[0103] In this embodiment, the preset score is set according to the actual situation.

[0104] The beneficial effects of the above design are as follows: By obtaining the suspicious edge area of the fluorescent contamination area and using the Sobel algorithm to calculate the image gray value and image gradient value of each pixel in the suspicious edge area of the fabric printing and dyeing fluorescent contamination image. Based on the image gray value and image gradient value of each pixel, calculate the comprehensive score of each pixel. Select the pixels with a comprehensive score greater than the preset score as target pixels, and calculate the actual area of the fluorescent contamination area based on the number of target pixels. Considering both the pixel gray value and the gradient value, and adding the proportion situation, ensure the accuracy of the target pixels as edge points, and finally ensure the accuracy of calculating the actual area of the fluorescent contamination area.

[0105] Continuing from the above embodiment, the Sobel algorithm is used for edge detection. Specifically: First, define the Sobel operator template: The Sobel operator has two 3x3 convolution kernels, one for detecting edges in the horizontal direction Gx, and the other for detecting edges in the vertical direction Gy; These convolution kernels are usually defined as: In the horizontal direction Gx: [-1, 0, 1; -2, 0, 2; -1, 0, 1], in the vertical direction Gy: [-1, -2, -1; 0, 0, 0; 1, 2, 1]; Secondly, convolution operation: Convolve the Sobel operator template with each pixel of the image. For each pixel, perform multiplication operations with its surrounding pixels, and then add the products to get a result; This process is carried out separately in the horizontal and vertical directions to calculate the gradients of the image in these two directions; Then, calculate the gradient magnitude and direction: After the gradient calculations in the horizontal and vertical directions are completed, the gradient magnitude G and gradient direction θ of each pixel in the image can be calculated through formulas. The gradient magnitude G is obtained by calculating the square root of the sum of Gx^2 and Gy^2, and the gradient direction θ is obtained by calculating the ratio of Gy to Gx through the atan2 function; Finally, edge detection: Edge detection can be performed based on the gradient magnitude. Pixels with a larger gradient magnitude are likely to be edge points in the image, thereby determining the edge information of each pixel, that is: Obtain the number of all pixels within the edge; Secondly, after obtaining the number of all pixels within the edge, calculate the actual area of the fluorescent contamination area according to the following steps. Specifically: First, determine the resolution of the image: Usually represented by the number of dots per inch DPI. The resolution of the image is crucial for converting the number of pixels into the actual area because it determines the actual size represented by each pixel in the image; Secondly, calculate the actual size represented by each pixel: By obtaining the DPI of the image, calculate the length and width represented by each pixel in the actual physical size, in inches; Finally, calculate the total area: Multiply the calculated actual size (length and width) represented by each pixel by the total number of pixels to obtain the area of the entire image area.

[0106] The proportion calculation module is used to calculate the proportion of the actual area of the fluorescent contamination area in the total area of the fabric printing and dyeing fluorescent contamination image, and obtain the pollution proportion of the fluorescent contamination area in the fabric printing and dyeing fluorescent contamination image;

[0107] Continuing with the above embodiment, for example: the length of the fabric printing and dyeing fluorescent contamination image is 54 mm, and the width is 39 mm. According to the area calculation formula: length * width, the total area of the fabric printing and dyeing fluorescent contamination image is 2120 mm 2 ; If the actual area of the fluorescent contamination area obtained according to the above steps is: 150 mm 2 ; Then calculate according to the proportion formula: quantity ÷ total number × 100 = percentage, that is: 150 ÷ 2120 × 100 = 2.3584. Rounding to two decimal places, it indicates that the actual area of the fluorescent contamination area accounts for 2.35% of the total area of the fabric printing and dyeing fluorescent contamination image. By analogy, obtain the proportion of the fluorescent contamination area in each fabric image in the total area of the fabric printing and dyeing fluorescent contamination image.

[0108] The contamination analysis unit is used to

[0109] Analyze the proportion of the area of the fluorescent contamination area map in the total area of the fabric printing and dyeing fluorescent contamination image, and judge the severity of the fluorescent contamination after fabric printing and dyeing according to the current situation; The contamination analysis unit includes:

[0110] The level establishment module is used to establish a corresponding pollution proportion level mechanism according to the proportion of the actual area of the fluorescent contamination area in the total area of the fabric printing and dyeing fluorescent contamination image;

[0111] Continuing with the above embodiment, for example: according to the actual proportion of the fluorescent contamination area, the actual area of the fluorescent contamination area accounting for 1% - 10% of the total area of the fabric printing and dyeing fluorescent contamination image can be regarded as primary, 10% - 20% as intermediate, and more than 20% as high level, thus establishing a pollution proportion level mechanism.

[0112] The level evaluation module is used to judge the level to which the area proportion of the fluorescent contamination area in the current fabric printing and dyeing fluorescent contamination image belongs based on the pollution proportion level mechanism, and obtain the severity of the fluorescent contamination in the current fabric printing and dyeing fluorescent contamination image based on this proportion level;

[0113] Continuing from the above embodiments, for example: Through the above calculations, it is shown that the actual area of the fluorescent contamination area accounts for 2.35% of the total area of the fabric printing and dyeing fluorescent contamination image picture. Referring to the established pollution ratio grading mechanism, it is concluded that the current ratio of 2.35% conforms to the primary mechanism in the pollution ratio grading mechanism. Thus, it is concluded that the severity of the fluorescent contamination in the current fabric printing and dyeing fluorescent contamination image picture is at the primary level. Then, the current result is transmitted and displayed on the human-computer interaction platform through 5G communication technology.

[0114] The result output module is used to display the severity of the fluorescent contamination in the current fabric printing and dyeing fluorescent contamination image picture on the human-computer interaction platform to assist the client in viewing.

[0115] The human-computer interaction platform is used for

[0116] displaying the operation interface of the fluorescent contamination system, and real-time showing the processing progress of the fabric printing and dyeing fluorescent contamination image picture and its fluorescent contamination processing result to the client; The human-computer interaction platform includes:

[0117] The contamination warning module is used to set the fluorescent contamination warning threshold. When the severity of the fluorescent contamination in the current fabric printing and dyeing fluorescent contamination image picture exceeds the warning threshold, it emits a warning sound through the buzzer to remind the client to solve it in time;

[0118] Continuing from the above embodiments, for example: Considering the fluorescent contamination area ratio of 1%-10% as primary, the contamination warning threshold in the primary level can be set to 1%, and the buzzer can be set to beep - beep - beep, with at least a 5S interval between every two beeps. At this time, the warning sound is in a slow rhythm; Considering the fluorescent contamination area ratio of 10%-20% as intermediate, the contamination warning threshold in the intermediate level can be set to 10%, and the buzzer can be set to beep - beep - beep, with at least a 3S interval between every two beeps. At this time, the warning sound is in a relatively rapid rhythm; Considering the fluorescent contamination area ratio of more than 20% as high level, the contamination warning threshold in the high level can be set to 20%, and the buzzer can be set to beep - beep - beep, with at least a 1S interval between every two beeps. At this time, the warning sound is in an extremely rapid rhythm; The client judges the severity of the fluorescent contamination after fabric printing and dyeing through the rhythm of the warning sound emitted by the buzzer, so as to urge the client to check the problem of the fabric in time.

[0119] The data storage module is used to save the processed fabric printing and dyeing fluorescent contamination image pictures and their fluorescent contamination calculation results in time series; Specifically, by storing each detected picture and its detection result in correspondence, it is convenient for the client to view and refer to later to obtain historical data.

[0120] The present invention provides a fluorescent contamination method for fabric printing and dyeing, including the following steps:

[0121] S1. Obtain the current fabric printing and dyeing fluorescence contamination image by deploying an area array camera array;

[0122] S2. Divide the area of the current fabric printing and dyeing fluorescence contamination image, and extract the fabric fluorescence contamination area and the fabric non-fluorescence contamination area through different color tones;

[0123] S3. Filter the fabric printing and dyeing fluorescence contamination image after area division to eliminate the noise in the image;

[0124] S4. First calculate the total area of the fabric printing and dyeing fluorescence contamination image using the Sobel algorithm, and then calculate the actual area of the fluorescence contamination area in the image according to the same steps;

[0125] S5. Calculate the proportion of the actual area of the fluorescence contamination area in the total area of the fabric printing and dyeing fluorescence contamination image;

[0126] S6. Preset a proportion level mechanism and a contamination warning threshold. First, determine the level to which the current fluorescence contamination area proportion belongs, and transmit this signal to the human-computer interaction platform for display; the human-computer interaction platform compares the current fluorescence contamination proportion level with the contamination warning threshold, and emits a warning sound when it exceeds the contamination warning threshold to remind the client to solve it in time.

[0127] The beneficial effects achieved by the above content: Through the above method, the existing fluorescence contamination detection method can avoid the disadvantages of long-term presence of detection personnel in the detection workshop, and optimize the practicability and safety of the existing fluorescence contamination method.

[0128] Working principle: Obtain the current fabric printing and dyeing fluorescence contamination image through an area array camera, perform area division and noise reduction processing on the image; use the Sobel algorithm to extract the edge pixels of the fluorescence contamination area in the fabric printing and dyeing fluorescence contamination image, and calculate the total area of the fabric printing and dyeing fluorescence contamination image and the actual area of the fluorescence contamination area; judge the proportion of the fluorescence contamination area in the total area of the fabric printing and dyeing fluorescence contamination image and its belonging level, and emit a warning sound to remind the client to solve the problem in time when it exceeds the contamination warning threshold.

[0129] It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device.

[0130] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention.

Claims

1. A fluorescent staining system for fabric printing and dyeing, comprising: The image acquisition unit uses an area array camera to capture image data of the fabric to be tested, obtains the fabric printing and dyeing fluorescent stain image picture, and transmits the fabric printing and dyeing fluorescent stain image picture to the image processing unit in real time for analysis and processing based on 5G communication technology; the image acquisition unit includes: The camera array module uses a camera array composed of multiple area array cameras to ensure that the complete fabric printing and dyeing fluorescent staining image is obtained at one time in a short time; Camera array module, including: The static variable determination module obtains the fabric size, fabric thickness and light source position of the fabric to be detected, and establishes static scene variables based on the specific characteristics of the fabric size, fabric thickness and light source position; A dynamic variable determination module obtains the activity features within the camera range of the fabric to be detected and establishes dynamic scene variables based on the activity features; A coordinate determination module, which establishes a three-dimensional camera scene based on the static scene variables and the dynamic scene variables, determines the coordinate position of the static scene variables in the three-dimensional camera scene, and determines the coordinate activity range of the dynamic scene variables in the three-dimensional camera scene; The collection determination module designs the initial camera array collection of the area array camera based on the camera range characteristics of the area array camera and the coordinate positions of the static scene variables in the three-dimensional camera scene, combined with the number of area array cameras; A weight determination module sets the variable weights of static scene variables in the three-dimensional camera scene based on the difficulty of photography, and sets the coordinate weights of the coordinate positions of the fabric area based on the visual characteristics of the fabric; The collection processing module determines the weighted accuracy of the image of the fabric to be inspected by combining the variable weights and the coordinate weights when each initial camera array in the initial camera array collection is used for image capture, and selects a target camera array collection whose weighted accuracy is greater than a preset accuracy from the initial camera array collection.

2. A fluorescent staining system for fabric printing and dyeing according to claim 1, characterized in that: The image acquisition unit further includes: A wireless transmission module is used to transmit the fabric printing and dyeing fluorescent staining image picture to the image processing unit in real time through 5G communication technology for image preprocessing to obtain a pixel-clear fabric printing and dyeing fluorescent staining image picture; The system also includes a human-computer interaction platform for displaying the operation interface of the fluorescent staining system and showing the processing progress of the fabric printing and dyeing fluorescent staining image pictures and the fluorescent staining processing results to the client in real time.

3. A fluorescent staining system for fabric printing and dyeing according to claim 1, characterized in that: The camera array module also includes: An array determination module is used to determine the dynamic area of ​​fabric detection based on the coordinate activity range of the dynamic scene variables in the three-dimensional camera scene, determine the detection frequency and detection angle of each camera array in the target camera array collection for the dynamic area, and select the camera array with the best detection frequency and detection angle as the target camera array; A shooting module is used to shoot the fabric to be inspected using a target camera array to obtain an image of the fabric printed and dyed fluorescent stains; The system also includes an image processing unit, which is used to filter and reduce noise on the fabric printing and dyeing fluorescent stain image picture to obtain the fabric printing and dyeing fluorescent stain image picture after noise reduction processing; and adjust the color tone of the current fabric printing and dyeing fluorescent stain image picture to clarify the fluorescent stain area in the fabric printing and dyeing fluorescent stain image picture; A contamination calculation unit is used to segment and extract the fluorescent contamination area in the fabric printing and dyeing fluorescent contamination image picture by an edge calculation method, and calculate the overall area of ​​the fabric printing and dyeing fluorescent contamination image picture and the area of ​​the fluorescent contamination area map; The contamination analysis unit is used to analyze the proportion of the area of ​​the fluorescent contamination area map to the overall area of ​​the fabric printing and dyeing fluorescent contamination image picture, and judge the severity of the fluorescent contamination of the fabric after printing and dyeing based on the current situation.

4. A fluorescent staining system for fabric printing and dyeing according to claim 3, characterized in that: The image processing unit comprises: The area division module is used to mark the fabric fluorescent stain area and the fabric fluorescent unstained area in the fabric printing and dyeing fluorescent stain image to be identified by different colors using Photoshop software, so as to distinguish different image components in the fabric printing and dyeing fluorescent stain image; The filtering processing module is used to perform weighted average filtering processing on the fabric printing and dyeing fluorescent stain image picture by using Gaussian filtering method, so as to reduce the residual noise in the fabric printing and dyeing fluorescent stain image picture.

5. A fluorescent staining system for fabric printing and dyeing according to claim 3, characterized in that: The contamination calculation unit comprises: The edge computing module is used to use the Sobel algorithm to perform edge detection on the fluorescent stain area in the fabric printing and dyeing fluorescent stain image, find out the number of all pixels within the edge of the fluorescent stain area, and calculate the actual area of ​​the fluorescent stain area; The proportion calculation module is used to calculate the proportion of the actual area of ​​the fluorescent stain area to the total area of ​​the fabric printing and dyeing fluorescent stain image picture, and obtain the pollution proportion of the fluorescent stain area in the fabric printing and dyeing fluorescent stain image picture.

6. A fluorescent staining system for fabric printing and dyeing according to claim 5, characterized in that: The edge computing module includes: The pixel point analysis module is used to obtain the suspicious edge area of ​​the fluorescent stain area, and use the Sobel algorithm to calculate the image gray value and image gradient value of each pixel in the suspicious edge area of ​​the fabric printing and dyeing fluorescent stain image. The calculation formula is as follows: in, Represents the grayscale value of the pixel. Represents the image gradient value of the pixel point, Represents the image grayscale value of the horizontal detection of the pixel point, Represents the image grayscale value of the vertical detection of the pixel; The pixel evaluation module is used to calculate the comprehensive score of each pixel based on the image grayscale value and image gradient value of each pixel according to the following formula; in, Represents the comprehensive score of the pixel, Represents the gray value of the image The proportion of edge points in the determination of Represents the image gradient value The proportion in edge point determination; The area calculation module is used to select pixels whose comprehensive scores are greater than a preset score as target pixels, and calculate the actual area of ​​the fluorescent contamination area based on the number of target pixels.

7. A fluorescent staining system for fabric printing and dyeing according to claim 5, characterized in that: Before calculating the actual area of ​​the fluorescent stain area in the fabric printing and dyeing fluorescent stain image picture, the edge computing module needs to determine the length and width of the fabric printing and dyeing fluorescent stain image picture and calculate the overall area value of the fabric printing and dyeing fluorescent stain image picture.

8. A fluorescent staining system for fabric printing and dyeing according to claim 3, characterized in that: The contamination analysis unit comprises: A level establishment module is used to establish a corresponding pollution proportion level mechanism according to the ratio of the actual area of ​​the fluorescent contamination area to the total area of ​​the fabric printing and dyeing fluorescent contamination image picture; The grade assessment module is used to determine the grade of the fluorescent stain area ratio in the current fabric printing and dyeing fluorescent stain image according to the pollution ratio grade mechanism, and determine the severity of the fluorescent stain in the current fabric printing and dyeing fluorescent stain image based on the ratio grade; The result output module is used to display the severity of fluorescent stains in the current fabric printing and dyeing fluorescent stain image on the human-computer interaction platform through 5G communication technology to assist the client in viewing.

9. A fluorescent staining system for fabric printing and dyeing according to claim 2, characterized in that: The human-computer interaction platform comprises: The contamination warning module is used to set the fluorescent contamination warning threshold. When the severity of the fluorescent contamination in the current fabric printing and dyeing fluorescent contamination image exceeds the warning threshold, a warning sound is issued through the buzzer to remind the client to solve it in time; The data storage module is used to store the processed fabric printing and dyeing fluorescent stain image pictures and the fluorescent stain calculation results according to time series.

10. A method for fluorescent staining for fabric printing and dyeing, implemented based on the fluorescent staining system for fabric printing and dyeing according to any one of claims 1 to 9, characterized in that: The following steps are involved: S1. Obtain the current fabric printing and dyeing fluorescent stain image by deploying an array camera array; S2, dividing the current fabric printing and dyeing fluorescent stain image into regions, and extracting the fabric fluorescent stain area and the fabric fluorescent unstained area through different tones; S3, filtering the fabric printing and dyeing fluorescent stain image after the area division to eliminate the noise in the image; S4, using the Sobel algorithm to first calculate the total area of ​​the fabric printing and dyeing fluorescent stain image, and then calculating the actual area of ​​the fluorescent stain area in the image according to the same steps; S5, calculating the ratio of the actual area of ​​the fluorescent stain area to the total area of ​​the fabric printing and dyeing fluorescent stain image; S6. Preset the proportion level mechanism and contamination warning threshold. First, determine the level of the current fluorescent contamination area proportion, and transmit the result to the human-computer interaction platform for display; the human-computer interaction platform compares the current fluorescent contamination proportion level with the contamination warning threshold, and emits a warning sound when it exceeds the contamination warning threshold, reminding the client to solve it in time.

Images